{"meta":{"query_hash":"98f632c1f71b","filters":{"topic":"Data Quality and Management"},"cohort_total":867,"direct_labels_cover":10,"predictions_cover":867,"exported":867,"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/98f632c1f71b","api":"https://metacan.xera.ac/api/v1/cohort?topic=Data+Quality+and+Management"},"results":[{"id":"W10093320","doi":"","title":"Data warehousing model for integrating fragmented electronic health records from disparate and heterogeneous clinical data stores","year":2013,"lang":"en","type":"dissertation","venue":"School of Electrical Engineering & Computer Science; Science & Engineering Faculty","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data warehouse; Health records; Logical data model; Data science; Conceptual model; Computer science; Data integration; Data modeling; Health care; Data mining; Database; Political science","score_opus":0.198103558537665,"score_gpt":0.45206952459394517,"score_spread":0.2539659660562802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W10093320","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":[0.17550763,0.0007849071,0.81944156,0.000121813435,0.0018602937,0.00092783006,0.0011558307,0.00019325898,0.000006867095],"genre_scores_gemma":[0.575865,0.0003635989,0.41842154,0.00022956707,0.0006458847,0.00007489399,0.004053196,0.00011176502,0.00023460946],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98831946,0.00008810624,0.0024944856,0.0038339095,0.0034135017,0.0018505468],"domain_scores_gemma":[0.99191535,0.0011059415,0.0010148584,0.0041276896,0.0008569432,0.0009792404],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0153707005,0.0007254569,0.0013984381,0.0014659064,0.000597928,0.001988595,0.012684689,0.00023478302,0.000013163431],"category_scores_gemma":[0.010332296,0.0006159541,0.000159892,0.003881403,0.000414773,0.0038020445,0.0030563239,0.0011573968,0.000016583035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096323325,0.00030926708,0.00024320792,0.0002242541,0.00020826732,0.0000067132205,0.0008278157,0.7549435,0.0059728506,0.0029883515,0.010017899,0.22416158],"study_design_scores_gemma":[0.000361147,0.0002916466,0.0028858786,0.00024904442,0.00004423271,0.0000046415153,0.00003911805,0.9923983,0.00023518341,0.00033407361,0.002533289,0.00062339526],"about_ca_topic_score_codex":0.00043762656,"about_ca_topic_score_gemma":0.00016197657,"teacher_disagreement_score":0.40102002,"about_ca_system_score_codex":0.0005332712,"about_ca_system_score_gemma":0.0029344072,"threshold_uncertainty_score":0.9996292},"labels":[],"label_agreement":null},{"id":"W103306089","doi":"","title":"Comparing the Predictive Ability of PLS and Covariance Models","year":2012,"lang":"en","type":"article","venue":"International Conference on Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Covariance; Computer science; Artificial intelligence; Statistics; Econometrics; Mathematics","score_opus":0.34153558244347226,"score_gpt":0.40697868604926923,"score_spread":0.06544310360579697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W103306089","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":[0.095505826,0.00004474591,0.5043876,0.0013216734,0.0023292864,0.0006816956,0.0003380048,0.000037794885,0.39535338],"genre_scores_gemma":[0.9995296,0.000010826706,0.000061916806,0.00015935166,0.000048749494,0.000031562053,0.000022556584,0.0000012066288,0.00013422454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99780226,0.00015404337,0.0007151451,0.00009311792,0.0011320078,0.00010340678],"domain_scores_gemma":[0.9981605,0.0004109011,0.00048308528,0.0003081786,0.0005892567,0.00004811545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038159546,0.00007251377,0.00014933513,0.00012221708,0.00007411257,0.00034608698,0.00057688984,0.00003067308,0.00005651602],"category_scores_gemma":[0.0004444001,0.000045151388,0.000027961696,0.00011832372,0.00010280216,0.0032312968,0.00016788825,0.00007784796,0.000114942755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004078697,0.000019098323,0.0040033464,0.000011109027,0.000022384032,2.0591525e-8,0.003057064,0.0038217963,0.0000067540354,0.985613,0.0013262805,0.0020783632],"study_design_scores_gemma":[0.0005571454,0.000061142266,0.07422487,0.00011458658,0.000010286976,0.0000064885144,0.016304007,0.8196285,0.000050544106,0.03536702,0.053514536,0.00016091141],"about_ca_topic_score_codex":0.00012855415,"about_ca_topic_score_gemma":0.00000343979,"teacher_disagreement_score":0.950246,"about_ca_system_score_codex":0.000038112554,"about_ca_system_score_gemma":0.000025806605,"threshold_uncertainty_score":0.3337325},"labels":[],"label_agreement":null},{"id":"W10845949","doi":"","title":"An Effective and Efficient Data Cleaning Technique in Large Databases.","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Database; Computer science","score_opus":0.17543865131859368,"score_gpt":0.4672611410951992,"score_spread":0.2918224897766055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W10845949","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":[0.13830079,0.0000394325,0.85457236,0.00044430073,0.000084313666,0.0008079723,0.000400745,0.00007443019,0.005275641],"genre_scores_gemma":[0.9840086,0.000007134078,0.01516305,0.00056900905,0.000015918906,0.000022595188,0.00015633497,0.000005077845,0.00005227358],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980008,0.00020848018,0.00031544722,0.0007125457,0.0005459243,0.00021679656],"domain_scores_gemma":[0.9977437,0.0003542941,0.00006217228,0.0017277044,0.00003068943,0.00008142945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009343783,0.000090715155,0.00015880233,0.00022761685,0.00008960273,0.00018503526,0.0010446506,0.00002501992,0.00011544901],"category_scores_gemma":[0.0011284838,0.000066108136,0.000011050098,0.0005007648,0.000057549307,0.000816547,0.0015334775,0.000105703686,0.000091199734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011328527,0.0019287054,0.008760975,0.000041251085,0.000023221864,0.00015892218,0.0019474457,0.0023688984,0.0019320729,0.7152196,0.007644174,0.2598614],"study_design_scores_gemma":[0.009884334,0.0009816596,0.35865912,0.00040430727,0.00006729423,0.000059714483,0.032477587,0.071199514,0.0154434815,0.09477736,0.41396067,0.0020849663],"about_ca_topic_score_codex":0.0006649242,"about_ca_topic_score_gemma":0.0025447793,"teacher_disagreement_score":0.84570783,"about_ca_system_score_codex":0.000030217314,"about_ca_system_score_gemma":0.000019142868,"threshold_uncertainty_score":0.32383874},"labels":[],"label_agreement":null},{"id":"W1103151178","doi":"10.1007/978-3-319-21542-6_18","title":"Ontology-Based Multidimensional Contexts with Applications to Quality Data Specification and Extraction","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Datalog; Dimension (graph theory); Context (archaeology); Ontology; Data quality; Quality (philosophy); Information retrieval; Data mining; Database; Data extraction; Online analytical processing; Data warehouse","score_opus":0.3076732723549056,"score_gpt":0.4521949623316024,"score_spread":0.1445216899766968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1103151178","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":[0.00009803077,0.00016114436,0.99321073,0.0036178138,0.0003061093,0.00081282866,0.00017491638,0.00003867662,0.0015797757],"genre_scores_gemma":[0.13664694,0.000015341971,0.8564056,0.0045876913,0.0004325083,0.00005879065,0.00044470193,0.000029758616,0.0013786277],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.995108,0.00010905841,0.0006682864,0.001876829,0.0019755028,0.0002623035],"domain_scores_gemma":[0.9943712,0.0016609615,0.00042516357,0.0027174999,0.00060666696,0.00021851936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067875492,0.0002628618,0.00039889346,0.00060706376,0.00022094477,0.00036230893,0.0021074505,0.00014594274,0.000053332966],"category_scores_gemma":[0.0007423807,0.00019658823,0.000024913486,0.00048212826,0.0007267475,0.0005826572,0.0010719931,0.00031752524,0.00013826984],"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":[0.00007344937,0.00006261807,0.00013109444,0.000013215953,0.000007592824,0.000006840663,0.00017792278,0.0075468617,0.00007849381,0.04395644,0.0010111949,0.9469343],"study_design_scores_gemma":[0.001024644,0.00032542914,0.008052986,0.00020850233,0.000035349996,0.000032124062,0.000008790725,0.08317952,0.00017398925,0.24319193,0.6627165,0.0010502201],"about_ca_topic_score_codex":0.000083270876,"about_ca_topic_score_gemma":0.0019754642,"teacher_disagreement_score":0.94588405,"about_ca_system_score_codex":0.00014956146,"about_ca_system_score_gemma":0.00040021504,"threshold_uncertainty_score":0.8016635},"labels":[],"label_agreement":null},{"id":"W113155598","doi":"","title":"Using an information ecology approach to identify research areas: Findings from Lithuania","year":2009,"lang":"en","type":"article","venue":"ResearchWorks at the University of Washington (University of Washington)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; University of Washington; Bill and Melinda Gates Foundation","keywords":"Ecology; Geography; Environmental resource management; Environmental planning; Environmental science; Biology","score_opus":0.2254375186368085,"score_gpt":0.403475608388509,"score_spread":0.1780380897517005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W113155598","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":[0.95733225,0.000028335615,0.027997078,0.004838221,0.00010669415,0.00070407585,0.00020703916,0.000056556928,0.008729765],"genre_scores_gemma":[0.9872219,0.00008093222,0.008624971,0.00017141952,0.000037056503,7.7041705e-8,0.00015621056,0.000011075831,0.0036963641],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99219024,0.00211985,0.00048246377,0.0008008976,0.003592553,0.00081400434],"domain_scores_gemma":[0.9942475,0.0017534798,0.0004124345,0.0017759339,0.0013217289,0.0004889138],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01465949,0.0002331692,0.0005823764,0.0015578169,0.0023161576,0.00036081148,0.006221526,0.00030132677,0.00095766655],"category_scores_gemma":[0.0018816006,0.00023528095,0.0002579135,0.0026935693,0.0011218113,0.004385389,0.00346053,0.00088707404,0.0004723473],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0087367315,0.003543296,0.012992725,0.00026610593,0.00084562285,0.00019420087,0.30448946,0.04054961,0.014013987,0.06576746,0.39669457,0.15190625],"study_design_scores_gemma":[0.0034952282,0.0012894344,0.28236762,0.00037336937,0.00019917655,0.000011568554,0.4918069,0.04511116,0.00077989255,0.024591668,0.14894767,0.0010263115],"about_ca_topic_score_codex":0.008395531,"about_ca_topic_score_gemma":0.002622076,"teacher_disagreement_score":0.2693749,"about_ca_system_score_codex":0.0006607557,"about_ca_system_score_gemma":0.00024513068,"threshold_uncertainty_score":0.9999556},"labels":[],"label_agreement":null},{"id":"W125535106","doi":"10.1007/978-0-387-35503-0_28","title":"Environmental Decision Support Systems: Exactly What Are They?","year":2000,"lang":"en","type":"book-chapter","venue":"IFIP advances in information and communication technology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Decision support system; Geography; Environmental planning; Environmental resource management; Psychology; Operations research; Management science; Computer science; Engineering; Environmental science; Artificial intelligence","score_opus":0.032767156516840985,"score_gpt":0.3210601548778049,"score_spread":0.28829299836096395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W125535106","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081052305,0.06808295,0.007530541,0.003868616,0.0009890215,0.0020159164,0.00045050654,0.00042082136,0.9158311],"genre_scores_gemma":[0.17476563,0.78712034,0.0023503802,0.0017536929,0.000030928273,0.00022464352,0.0010014217,0.000037871938,0.032715093],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969424,0.00008189607,0.0016386559,0.00032475576,0.0008091318,0.00020314404],"domain_scores_gemma":[0.9959447,0.00050850544,0.0012227851,0.0021975958,0.00007053886,0.00005592231],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016163602,0.00027856132,0.00048680074,0.0014384072,0.00021041029,0.0005885684,0.001890179,0.00048517258,0.00074951025],"category_scores_gemma":[0.00019985897,0.00024639958,0.00006212107,0.00014940763,0.00041101637,0.0065342826,0.0008570522,0.00052740984,0.0015534818],"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":[0.000023454191,0.00001340977,0.000039098988,0.00001222001,0.000005891825,0.000001013541,0.00023917791,0.00009354214,1.1403714e-7,0.27239645,0.00063397334,0.72654164],"study_design_scores_gemma":[0.00024355488,0.000035089924,0.00005578539,0.00019864812,0.0000061816486,0.000013201746,0.005147452,0.00013532623,0.0000019555546,0.29791,0.69607365,0.0001791557],"about_ca_topic_score_codex":0.000007059762,"about_ca_topic_score_gemma":0.00012625425,"teacher_disagreement_score":0.883116,"about_ca_system_score_codex":0.00013268497,"about_ca_system_score_gemma":0.000027277873,"threshold_uncertainty_score":0.9999988},"labels":[],"label_agreement":null},{"id":"W1416634528","doi":"","title":"Automating Data Capture from the Ontario Laboratories Information System (OLIS) for Secondary Data Uses","year":2011,"lang":"en","type":"article","venue":"ElectronicHealthcare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Automatic identification and data capture; Computer science; Information system; Data science; Engineering; Operating system","score_opus":0.4134392341345837,"score_gpt":0.4101554214904161,"score_spread":0.003283812644167605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1416634528","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":[0.48505777,0.018377023,0.15995723,0.057759844,0.012505398,0.01444674,0.22229186,0.0026636287,0.026940504],"genre_scores_gemma":[0.97069514,0.000024324554,0.0063570677,0.0042822226,0.0003416581,0.00008264778,0.017864197,0.000021682321,0.00033103654],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99681616,0.00035190023,0.00087502267,0.00063235575,0.0008456872,0.00047885373],"domain_scores_gemma":[0.9932228,0.0008391103,0.0005503359,0.004912654,0.00037821542,0.00009688445],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0047763907,0.00018074547,0.00030062397,0.00006735851,0.00054734515,0.00067529234,0.0055982145,0.00010773417,0.00019651529],"category_scores_gemma":[0.0018751182,0.00011845714,0.00003172661,0.00041761663,0.000058683876,0.0045632403,0.0017234018,0.00039883464,0.00012295437],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031733603,0.000070503804,0.013984363,0.00046236077,0.00030619415,0.000007970357,0.074322864,0.000005597422,0.000007150112,0.1477531,0.55573684,0.20702569],"study_design_scores_gemma":[0.00041783412,0.000075610056,0.017573578,0.00006069582,0.000054801025,0.0000040505856,0.028796315,0.0020200645,0.000050250834,0.003782062,0.94694066,0.00022407593],"about_ca_topic_score_codex":0.08296509,"about_ca_topic_score_gemma":0.4214528,"teacher_disagreement_score":0.4856374,"about_ca_system_score_codex":0.00031972863,"about_ca_system_score_gemma":0.0017252208,"threshold_uncertainty_score":0.99978197},"labels":[],"label_agreement":null},{"id":"W145435252","doi":"10.1007/978-3-642-19041-4_15","title":"Rule Testing with JRules","year":2011,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Consistency (knowledge bases); Key (lock); Set (abstract data type); Suite; Business rule; Software engineering; Operator (biology); Isolation (microbiology); Software; Service (business); Data mining; Business process; Artificial intelligence; Programming language; Operating system; Engineering; Work in process","score_opus":0.46040201778689865,"score_gpt":0.3754587824837807,"score_spread":0.08494323530311798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W145435252","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007061732,0.000049927952,0.007703834,0.00020110267,0.00013479141,0.00015168285,0.0000484848,0.00008833253,0.99161476],"genre_scores_gemma":[0.00027300813,0.000011151776,0.012184562,0.00070835295,0.0000827082,0.000003532681,0.000019037096,0.000021145754,0.9866965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975317,0.00002175986,0.00047973148,0.0005914047,0.0011977018,0.00017766395],"domain_scores_gemma":[0.99767923,0.0006195845,0.00031489652,0.0010624332,0.00023309498,0.00009077367],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001665764,0.00021907389,0.00032672085,0.00021505683,0.00009803033,0.0002580112,0.0010175713,0.00010664476,0.012819223],"category_scores_gemma":[0.00044738123,0.00012716991,0.00006576785,0.000060156046,0.00014241804,0.00023247527,0.00048797613,0.0001573773,0.010005744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070007454,0.000007752838,0.000023704022,0.000005821638,0.00002438984,0.000021961603,0.000041183514,6.421246e-7,3.646697e-7,0.77552706,0.07131238,0.1530277],"study_design_scores_gemma":[0.000051041534,0.000041916835,0.000075221724,0.00003671121,0.000016924825,0.0000030977608,0.000038352333,0.0000043010723,0.0000036291635,0.38306612,0.61650866,0.00015399515],"about_ca_topic_score_codex":0.0001240003,"about_ca_topic_score_gemma":0.0002273767,"teacher_disagreement_score":0.5451963,"about_ca_system_score_codex":0.000014300828,"about_ca_system_score_gemma":0.00004921151,"threshold_uncertainty_score":0.9907651},"labels":[],"label_agreement":null},{"id":"W146486917","doi":"10.1007/978-3-642-31537-4_2","title":"Transductive Relational Classification in the Co-training Paradigm","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"","keywords":"Computer science; Schema (genetic algorithms); Relational database; Artificial intelligence; Machine learning; Construct (python library); Training set; Statistical relational learning; Independence (probability theory); Labeled data; Data mining","score_opus":0.28507347646492137,"score_gpt":0.3941394393181918,"score_spread":0.10906596285327042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W146486917","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":[0.00014881797,0.00020848855,0.97293305,0.0053942595,0.0007398062,0.00040280083,0.000027080905,0.000018663573,0.020127028],"genre_scores_gemma":[0.9664494,0.000042801843,0.028505819,0.0036967883,0.0006912946,0.000022760685,0.000060256116,0.00001752954,0.00051338377],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953842,0.000194631,0.0007050096,0.00092743174,0.002399404,0.00038932],"domain_scores_gemma":[0.9956037,0.0029003702,0.00031920004,0.0010149581,0.00009479129,0.00006701089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010178292,0.00024263172,0.0003116698,0.0007514699,0.00023166716,0.0004324826,0.0024556778,0.00017542785,0.00016321513],"category_scores_gemma":[0.0005118093,0.00016098295,0.00008757902,0.00069915364,0.0008927087,0.0008005446,0.00017358392,0.00066077505,0.00019270772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073813007,0.000024742287,0.000122053374,0.0000040300743,0.00000403528,0.000008647075,0.009909997,0.0039834976,0.000007880768,0.35221398,0.00014872674,0.633565],"study_design_scores_gemma":[0.00018714149,0.0000448946,0.012860625,0.00008176928,0.000008723852,0.000022845776,0.00002925773,0.021866884,0.000013590742,0.88762844,0.07692584,0.00033001578],"about_ca_topic_score_codex":0.000013491701,"about_ca_topic_score_gemma":0.00015831648,"teacher_disagreement_score":0.96630055,"about_ca_system_score_codex":0.00015059755,"about_ca_system_score_gemma":0.00022611876,"threshold_uncertainty_score":0.65646946},"labels":[],"label_agreement":null},{"id":"W1469477946","doi":"10.1007/978-3-642-39872-8_3","title":"The Vivification Problem in Real-Time Business Intelligence: A Vision","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in business information processing","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Correctness; Business intelligence; Business rule; Schema (genetic algorithms); Data warehouse; Business information; Artifact-centric business process model; Data science; Business process modeling; Knowledge management; Business process; Database; Information retrieval; Business; Algorithm; Work in process; Marketing","score_opus":0.05337242464430064,"score_gpt":0.3409791299198733,"score_spread":0.28760670527557264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1469477946","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":[0.00014176777,0.0005862799,0.6956014,0.01042622,0.00067670224,0.0023991978,0.000041165426,0.0001962917,0.289931],"genre_scores_gemma":[0.5440053,0.028898848,0.14287592,0.016709605,0.0033750366,0.0032495544,0.012090969,0.001032452,0.24776232],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994352,0.000106918145,0.0026198875,0.00056355563,0.0019116764,0.00044596242],"domain_scores_gemma":[0.99368966,0.001159076,0.0018495315,0.0010019995,0.0022380464,0.000061709936],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004506887,0.0004984957,0.0005833107,0.0013386298,0.000433937,0.0029304852,0.0015691799,0.0005262484,0.0004574294],"category_scores_gemma":[0.0036927022,0.00032873725,0.00007024536,0.0020176966,0.0002813931,0.0053084427,0.0004620421,0.0005678838,0.0016959076],"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":[0.000048501315,0.00002076918,0.000013876611,0.00028014023,0.00000568752,0.000001627908,0.0011851599,0.010734632,0.000010370461,0.015354923,0.00078225514,0.971562],"study_design_scores_gemma":[0.00037016268,0.00002549463,0.003120934,0.0022723486,0.00002642216,0.000009069841,0.00020155538,0.03866058,0.00006141243,0.5485922,0.40574095,0.0009188233],"about_ca_topic_score_codex":0.00019958107,"about_ca_topic_score_gemma":0.00033710196,"teacher_disagreement_score":0.9706432,"about_ca_system_score_codex":0.0002867365,"about_ca_system_score_gemma":0.00037684268,"threshold_uncertainty_score":0.9999165},"labels":[],"label_agreement":null},{"id":"W147952491","doi":"10.3233/978-1-61499-203-5-37","title":"Challenges in data quality assurance for electronic health records","year":2013,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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 Victoria","funders":"","keywords":"Quality assurance; Computer science; Dimension (graph theory); Data quality; Health records; Scale (ratio); Data science; Quality (philosophy); Electronic health record; Risk analysis (engineering); Data mining; Health care; Medicine; Engineering; Operations management","score_opus":0.5625995491724509,"score_gpt":0.5567803044172939,"score_spread":0.005819244755157049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W147952491","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05434439,0.14876352,0.015347868,0.77026504,0.001433101,0.0059382697,0.00030238723,0.00029026062,0.0033151654],"genre_scores_gemma":[0.6010889,0.3638985,0.024165532,0.009731066,0.000043645734,0.0006860875,0.00006548292,0.000013640909,0.00030718077],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963255,0.00022567932,0.0021250313,0.00033261292,0.00030958152,0.0006816165],"domain_scores_gemma":[0.99638146,0.0015100732,0.00069833593,0.0012372676,0.00012319289,0.000049645223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017845018,0.00013750757,0.0006639162,0.0007045852,0.00022034337,0.00003382297,0.0010729381,0.00010909887,0.0000052813657],"category_scores_gemma":[0.006874692,0.00010755692,0.000016211634,0.0008446377,0.00032082802,0.0008950237,0.0010554899,0.00032913827,0.000025561954],"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":[0.000011635426,0.000048871916,0.0031950977,0.0010746537,0.000018387991,1.1456445e-7,0.0041931067,0.000006701221,2.2784523e-8,0.19725631,0.03187949,0.76231563],"study_design_scores_gemma":[0.0007474915,0.0004085207,0.015563192,0.00020397591,0.0000012687332,0.0000029368898,0.109346226,0.0023700928,6.7938765e-7,0.4011607,0.47002408,0.00017084726],"about_ca_topic_score_codex":0.00020030582,"about_ca_topic_score_gemma":0.0123367375,"teacher_disagreement_score":0.76214474,"about_ca_system_score_codex":0.00015910789,"about_ca_system_score_gemma":0.00020418258,"threshold_uncertainty_score":0.8230145},"labels":[],"label_agreement":null},{"id":"W1505573608","doi":"10.1007/978-3-642-13094-6_6","title":"Dependency Discovery in Data Quality","year":2010,"lang":"en","type":"book-chapter","venue":"Notes on numerical fluid mechanics and multidisciplinary design","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Dependency (UML); Computer science; Bayesian network; Data mining; Data quality; Consistency (knowledge bases); Completeness (order theory); Functional dependency; Dependency theory (database theory); Quality (philosophy); Knowledge extraction; Artificial intelligence; Relational database; Mathematics; Engineering","score_opus":0.3158537684515106,"score_gpt":0.42526183407947443,"score_spread":0.10940806562796385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1505573608","genre_codex":"methods","genre_gemma":"other","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":[0.00015939123,0.00060218544,0.97311723,0.0031129606,0.0015775713,0.0015450821,0.0021503905,0.00010260857,0.01763257],"genre_scores_gemma":[0.29897308,0.00901204,0.18362993,0.0046664625,0.002065184,0.0002892779,0.004344964,0.00086992135,0.49614915],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9914943,0.00047535257,0.0018313406,0.0026594605,0.0029444392,0.0005951009],"domain_scores_gemma":[0.98869574,0.0059234044,0.0006078148,0.004218454,0.00020059288,0.00035397816],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012176303,0.0007670897,0.0013239752,0.0005359663,0.00033063392,0.00060139474,0.0031369652,0.00076347194,0.00044877004],"category_scores_gemma":[0.0048968084,0.0005821541,0.0002115914,0.0002106939,0.000115423354,0.00097192207,0.0044997684,0.001359658,0.00059130974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073444407,0.00050752406,0.000013137308,0.000066928296,0.00008611687,0.00023710013,0.0002639317,0.00021643376,0.0010720986,0.8821126,0.003057854,0.11163179],"study_design_scores_gemma":[0.00093210634,0.00053069356,0.00015827383,0.00019840988,0.000085890824,0.000011755766,0.00013623876,0.04099702,0.00014795261,0.8803881,0.07516992,0.0012436247],"about_ca_topic_score_codex":0.000094772004,"about_ca_topic_score_gemma":0.0002847611,"teacher_disagreement_score":0.7894873,"about_ca_system_score_codex":0.000109350156,"about_ca_system_score_gemma":0.00023467772,"threshold_uncertainty_score":0.999663},"labels":[],"label_agreement":null},{"id":"W1512943107","doi":"10.1007/11546849_25","title":"A Machine Learning Approach to Identifying Database Sessions Using Unlabeled Data","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Session (web analytics); Database design; Data mining; Artificial intelligence; Machine learning; Database; World Wide Web","score_opus":0.31826524345177737,"score_gpt":0.4276292084454128,"score_spread":0.10936396499363543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512943107","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":[0.00006435049,0.00043455145,0.9912115,0.00060966326,0.0010141658,0.00053797395,0.00028811986,0.00008409402,0.0057556354],"genre_scores_gemma":[0.022678081,0.00007092687,0.9683414,0.0035153402,0.0008489066,0.0000066819607,0.00056121114,0.00006191249,0.0039155087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9913861,0.00020312963,0.0011137951,0.0031088758,0.0034549346,0.00073313416],"domain_scores_gemma":[0.993105,0.0012405083,0.00051492266,0.004552375,0.00025643138,0.00033078945],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.010424136,0.00051499996,0.0007136028,0.0018092161,0.0007474361,0.0018909348,0.009543776,0.00018582522,0.00019311834],"category_scores_gemma":[0.0028082223,0.00041360757,0.000091202724,0.0016319042,0.00048040727,0.0018417782,0.014524094,0.001129119,0.00024649725],"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":[0.000014841134,0.00008252753,0.00006264113,0.000039264964,0.000019457362,0.000046416702,0.00074841717,0.21848345,0.00018175211,0.005923103,0.0004967313,0.7739014],"study_design_scores_gemma":[0.00022199204,0.00003193005,0.000022504011,0.00035574014,0.00002836923,0.000031227457,0.000004254966,0.8939723,0.000042856118,0.016952284,0.08774236,0.0005942215],"about_ca_topic_score_codex":0.00016632096,"about_ca_topic_score_gemma":0.00036634255,"teacher_disagreement_score":0.7733072,"about_ca_system_score_codex":0.00023173135,"about_ca_system_score_gemma":0.0003869041,"threshold_uncertainty_score":0.99983156},"labels":[],"label_agreement":null},{"id":"W1514828683","doi":"10.1186/1472-6963-6-48","title":"Assessing record linkage between health care and Vital Statistics databases using deterministic methods","year":2006,"lang":"en","type":"article","venue":"BMC Health Services Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute of Health Economics; University of Calgary","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale; University of Calgary","keywords":"Linkage (software); Record linkage; Medicine; Database; Population; Identifier; Demography; Statistics; Computer science; Genetics; Biology; Environmental health; Mathematics","score_opus":0.5803401570006748,"score_gpt":0.6702429424110904,"score_spread":0.08990278541041563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1514828683","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":[0.15392682,0.0032388472,0.8375663,0.00050149043,0.00035782624,0.0011703576,0.0024788026,0.00007523243,0.0006842989],"genre_scores_gemma":[0.17877656,0.00019180609,0.8186132,0.0009779938,0.000448179,0.000019532345,0.0007755491,0.000036003225,0.00016122586],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9863939,0.007163932,0.001600293,0.0010758773,0.0025579191,0.0012080466],"domain_scores_gemma":[0.9878415,0.0093031125,0.00054764136,0.0011742397,0.0005837851,0.0005497501],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.02907761,0.00022289148,0.0006724646,0.00073740224,0.0016171745,0.0017369569,0.0010159278,0.00007112267,0.00006711682],"category_scores_gemma":[0.00075062714,0.00019365433,0.000044745804,0.0013197409,0.00023225586,0.0010907059,0.0013859391,0.00048677914,0.000058497382],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003159494,0.000085235595,0.06656787,0.004511392,0.000011928668,0.000017957114,0.0027078243,0.00003174611,0.000020551184,0.0024257917,0.0014810266,0.9221071],"study_design_scores_gemma":[0.001469416,0.0011628873,0.49323106,0.0014596073,0.00003501636,0.000017128865,0.10993217,0.036483023,0.00007450288,0.019588687,0.33562717,0.00091933616],"about_ca_topic_score_codex":0.022897812,"about_ca_topic_score_gemma":0.011549312,"teacher_disagreement_score":0.92118776,"about_ca_system_score_codex":0.00034309865,"about_ca_system_score_gemma":0.0014591725,"threshold_uncertainty_score":0.9997689},"labels":[],"label_agreement":null},{"id":"W151902604","doi":"","title":"Proceedings of the second international workshop on MapReduce and its applications","year":2011,"lang":"en","type":"article","venue":"","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":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Variety (cybernetics); Cover (algebra); Data science; Pleasure; Software engineering; Engineering; Artificial intelligence","score_opus":0.23526634734999,"score_gpt":0.3886907317663773,"score_spread":0.1534243844163873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W151902604","genre_codex":"other","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":[0.18178412,0.00001099389,0.0008678185,0.0023305877,0.00013450411,0.00026949396,0.00002996747,0.000012319849,0.8145602],"genre_scores_gemma":[0.9357032,0.0000044343224,0.00044614475,0.0006512182,0.000018405435,0.000022714152,5.824143e-7,0.0000015276771,0.06315175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992759,0.00000621132,0.000173546,0.00015915523,0.00033897473,0.000046185312],"domain_scores_gemma":[0.99953234,0.00011352236,0.00008641353,0.00013371774,0.000112193724,0.0000217884],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006260285,0.0000336607,0.00004687517,0.000052035914,0.000040314193,0.000053120933,0.00061971723,0.000015055076,0.002115883],"category_scores_gemma":[0.0002158518,0.000018505547,0.000019351857,0.00016933493,0.00003939609,0.00018984918,0.00026220243,0.00003482062,0.0000930396],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008990226,0.00006858143,0.00046548713,0.00000438116,0.000010247613,2.7448944e-8,0.00066616543,1.7796245e-7,0.0003696653,0.9337899,0.04056541,0.024050945],"study_design_scores_gemma":[0.00017099433,0.000018125165,0.04499258,0.000014710835,0.000006117059,0.0000012815528,0.0038163583,0.00015075093,0.015976759,0.12347449,0.81129235,0.000085504515],"about_ca_topic_score_codex":0.0000029887804,"about_ca_topic_score_gemma":0.000015190979,"teacher_disagreement_score":0.81031543,"about_ca_system_score_codex":0.0000038944245,"about_ca_system_score_gemma":0.000004586791,"threshold_uncertainty_score":0.99879634},"labels":[],"label_agreement":null},{"id":"W1530008852","doi":"10.71781/23019","title":"Schémas de classification et repérage des documents administratifs électroniques dans un contexte de gestion décentralisée des ressources informationnelles","year":2007,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.03626827190118999,"score_gpt":0.2923677993185969,"score_spread":0.25609952741740694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530008852","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":[0.8909465,0.0065623266,0.04890013,0.0006861531,0.0005210961,0.0006893827,0.00020660597,0.00019554289,0.051292256],"genre_scores_gemma":[0.94613034,0.0049144006,0.00899285,0.00031203454,0.000103931605,0.000052187497,0.0015968371,0.000034159108,0.037863236],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9939282,0.0012351838,0.0013261967,0.00089308835,0.0016625525,0.0009548017],"domain_scores_gemma":[0.99578464,0.0007690906,0.001285838,0.00078100624,0.0007888744,0.000590534],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00426702,0.0006084519,0.0005153112,0.00058155204,0.01137831,0.0008220682,0.001216454,0.0006926441,0.00012878352],"category_scores_gemma":[0.0012737418,0.0006675521,0.0003631809,0.000796835,0.0014056441,0.0030449,0.00022831722,0.00068643386,0.00010317905],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025616041,0.0008915406,0.044903032,0.0005866006,0.00071931933,0.0009942194,0.58769494,0.0060942746,0.017404942,0.24346948,0.00137571,0.093304366],"study_design_scores_gemma":[0.0015569585,0.00036800295,0.51173484,0.0011945949,0.0006164482,0.0006312451,0.3285152,0.0072694267,0.031799674,0.022764454,0.092426114,0.0011230544],"about_ca_topic_score_codex":0.06366968,"about_ca_topic_score_gemma":0.054395314,"teacher_disagreement_score":0.4668318,"about_ca_system_score_codex":0.010196988,"about_ca_system_score_gemma":0.002156664,"threshold_uncertainty_score":0.9995776},"labels":[],"label_agreement":null},{"id":"W1534641784","doi":"10.1609/aimag.v36i1.2575","title":"Reports of the AAAI 2014 Conference Workshops","year":2015,"lang":"en","type":"article","venue":"AI Magazine","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan; Université du Québec à Chicoutimi; University of Toronto; University of British Columbia; McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Analytics; Applications of artificial intelligence; Data science; Intelligence analysis; Robotics; Big data; Robot","score_opus":0.20037606968535615,"score_gpt":0.4032725950413384,"score_spread":0.20289652535598224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1534641784","genre_codex":"other","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":[0.09014332,0.0005769493,0.0485995,0.11928226,0.0068389457,0.0011130895,0.00009442873,0.00014468051,0.7332068],"genre_scores_gemma":[0.94429713,0.0000074612026,0.00044965863,0.0023650448,0.00005037618,0.0000046627993,0.000005702206,0.000004140977,0.052815825],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977452,0.00017057749,0.00054243294,0.00027568193,0.0011280256,0.00013808724],"domain_scores_gemma":[0.9976734,0.00018616625,0.00030777857,0.0013648327,0.00038352635,0.00008432114],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004263216,0.000074946045,0.0001777856,0.000057341047,0.00003853254,0.00011369127,0.0007513818,0.000033637483,0.00091786205],"category_scores_gemma":[0.0029105498,0.000041699208,0.00006145466,0.00040101548,0.00014731075,0.00027229474,0.00058310525,0.0000889288,0.0013657516],"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":[0.000008067941,0.00003460316,0.002151241,0.000002297636,0.0000059664208,0.000010710438,0.00020307451,0.000028572109,0.000056394045,0.012591196,0.9679715,0.016936386],"study_design_scores_gemma":[0.00013489286,0.000024245568,0.014993811,0.000012856604,0.000009180522,0.000009768714,0.00019502883,0.00017160474,0.0001910268,0.07886327,0.9053268,0.00006754004],"about_ca_topic_score_codex":0.00003858987,"about_ca_topic_score_gemma":0.00013083589,"teacher_disagreement_score":0.8541538,"about_ca_system_score_codex":0.0000109758985,"about_ca_system_score_gemma":0.000082705796,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W1538933717","doi":"10.1007/978-3-540-74780-2_10","title":"Private Data Management in Collaborative Environments","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Workflow; Personally identifiable information; Personal information management; World Wide Web; Collaborative software; Personal information manager; Software; Knowledge management; Data science; Information system; Management information systems; Computer security; Database; Engineering","score_opus":0.143453871508199,"score_gpt":0.38611388243082495,"score_spread":0.24266001092262596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538933717","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":[0.0000571849,0.00023299553,0.965532,0.00064743974,0.001115153,0.00081836956,0.000120444565,0.000022441853,0.03145395],"genre_scores_gemma":[0.049017373,0.0012941376,0.9114175,0.014715884,0.00087939244,0.000039933282,0.00052063307,0.00012844008,0.021986742],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99207896,0.00010066518,0.0011291303,0.0025603373,0.003487298,0.000643628],"domain_scores_gemma":[0.9943151,0.00091895286,0.00045900344,0.00410074,0.00006261876,0.00014360604],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.010061226,0.0004368567,0.00056536414,0.0017779323,0.0001580642,0.00067963044,0.008479815,0.00019961412,0.00020419972],"category_scores_gemma":[0.00038450566,0.0003631418,0.000049622045,0.0014444257,0.00094193226,0.00096982374,0.008723586,0.0005455105,0.0004968034],"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":[0.000020720143,0.000060464863,0.000092649534,0.000013713401,0.000018472609,0.00029009467,0.00038556164,0.006073211,0.0000047790486,0.026365615,0.00049784983,0.96617687],"study_design_scores_gemma":[0.00062866404,0.000097669355,0.0017440692,0.00025874766,0.000017908485,0.0000053018707,0.0000072935713,0.032089837,0.00009579449,0.4043665,0.5598968,0.00079140626],"about_ca_topic_score_codex":0.000018654575,"about_ca_topic_score_gemma":0.0005303887,"teacher_disagreement_score":0.96538544,"about_ca_system_score_codex":0.00033981533,"about_ca_system_score_gemma":0.00011313364,"threshold_uncertainty_score":0.99988204},"labels":[],"label_agreement":null},{"id":"W1556370583","doi":"10.1109/bigdataservice.2015.13","title":"Towards a 'Big' Health Data Analytics Platform","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Standardization; Computer science; Data science; Data integration; Big data; Terminology; Analytics; Pipeline (software); Data analysis; Data sharing; Data transformation; Data visualization; Health care; Data mining; Data warehouse; Visualization","score_opus":0.8491534457873675,"score_gpt":0.5524366211064039,"score_spread":0.2967168246809636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556370583","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":[0.0014433997,0.0001985212,0.5047413,0.050046645,0.0014775603,0.0003441169,0.00061315583,0.0001535828,0.4409817],"genre_scores_gemma":[0.7060354,0.00020759506,0.09208856,0.06999105,0.00093582226,0.000010799857,0.0016524643,0.000036539477,0.1290418],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969502,0.00008072717,0.00056358724,0.0004661651,0.0016933597,0.00024595862],"domain_scores_gemma":[0.9966881,0.00016080974,0.00015020401,0.0025421414,0.00013370025,0.0003250316],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.012557652,0.00008234589,0.00022169903,0.00014967128,0.00006968242,0.00038444932,0.0025610055,0.00002613701,0.00037135516],"category_scores_gemma":[0.0027129478,0.00005308752,0.000028186,0.00060790067,0.000050246123,0.0007595442,0.0020743317,0.0000685021,0.0020058863],"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":[0.000005549011,0.00003053477,0.00007406202,0.0000017484692,0.0000071711165,0.000001941108,0.000194579,0.000011462874,6.016802e-8,0.04020541,0.67813414,0.28133333],"study_design_scores_gemma":[0.00023136786,0.00006024534,0.0005408294,0.000002443215,0.000003843536,0.000001618632,0.0040549394,0.0073006055,0.0000025371764,0.05737734,0.9303461,0.00007816299],"about_ca_topic_score_codex":0.0012009457,"about_ca_topic_score_gemma":0.0023278988,"teacher_disagreement_score":0.70459193,"about_ca_system_score_codex":0.00005169635,"about_ca_system_score_gemma":0.00037126505,"threshold_uncertainty_score":0.9987712},"labels":[],"label_agreement":null},{"id":"W1564399566","doi":"","title":"Accuracy of Approximate String Joins Using Grams","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"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 Toronto","funders":"","keywords":"Substring; Joins; Similarity (geometry); Computer science; Data mining; String (physics); String metric; Matching (statistics); Join (topology); String searching algorithm; Algorithm; Pattern matching; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics; Data structure","score_opus":0.3939898281848053,"score_gpt":0.48855991414726413,"score_spread":0.0945700859624588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1564399566","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":[0.33699924,0.00002054095,0.6332073,0.00011533903,0.00017904637,0.00011949791,0.000007742892,0.00002842949,0.029322825],"genre_scores_gemma":[0.97692406,0.0000052604646,0.021765385,0.00020885175,0.00002698378,3.8223018e-7,0.0000025803074,0.0000035368164,0.001062968],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981083,0.000045566,0.0005904283,0.00022536666,0.00082925207,0.00020106058],"domain_scores_gemma":[0.99840796,0.0006764733,0.00022790648,0.00053397444,0.000093444185,0.00006023102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006383631,0.00006389373,0.00015458267,0.00018247419,0.00006525265,0.00011597972,0.0005327268,0.000025459833,0.00036613707],"category_scores_gemma":[0.0013499057,0.00004476779,0.00005885524,0.0005374992,0.000053074258,0.00046575652,0.00032985033,0.000045986842,0.000072822375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034891225,0.00017446425,0.0042764377,0.000028566581,0.000027280665,0.000011852414,0.0006629005,0.00028425222,0.0050451984,0.39483026,0.0042445734,0.5903793],"study_design_scores_gemma":[0.002207171,0.00021602353,0.042629827,0.00012848566,0.00008401508,0.000019146368,0.03972926,0.036766287,0.143361,0.3241499,0.409598,0.001110901],"about_ca_topic_score_codex":0.00026543156,"about_ca_topic_score_gemma":0.00012081223,"teacher_disagreement_score":0.6399248,"about_ca_system_score_codex":0.000014966882,"about_ca_system_score_gemma":0.000016462052,"threshold_uncertainty_score":0.40089443},"labels":[],"label_agreement":null},{"id":"W1569990199","doi":"10.1109/icdm.2002.1184040","title":"FD/spl I.bar/Mine: discovering functional dependencies in a database using equivalences","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":49,"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 Regina","funders":"","keywords":"Computer science; Bar (unit); Database; Functional dependency; Data mining; Programming language; Relational database; Geology","score_opus":0.4113009556627037,"score_gpt":0.4381036786068579,"score_spread":0.0268027229441542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569990199","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":[0.6586753,0.00019090995,0.29052648,0.00030926164,0.0007789141,0.00022910791,0.00007789118,0.00004522634,0.0491669],"genre_scores_gemma":[0.9779756,0.000025089068,0.014302035,0.00050858257,0.0000466045,0.000008896121,0.00001764741,0.0000065722566,0.007108978],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99696624,0.00023544271,0.0005611561,0.0005330233,0.001394795,0.00030934348],"domain_scores_gemma":[0.9986981,0.0004762142,0.000110943314,0.0005716243,0.000060923077,0.00008219609],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004610201,0.00013105324,0.00019093954,0.00029411667,0.00014337245,0.0003960967,0.0005181144,0.00003301042,0.004472158],"category_scores_gemma":[0.0019270473,0.000095474985,0.00006065599,0.00070623297,0.00009456172,0.0017829537,0.00038157415,0.00010266,0.00035061903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008250662,0.0004549223,0.07584103,0.00006683428,0.00004592491,0.00012351334,0.00093433395,0.010507161,0.003406023,0.87845045,0.019223437,0.010863874],"study_design_scores_gemma":[0.0043697683,0.0002710855,0.10680956,0.00046503244,0.00011271491,0.0001548442,0.11145778,0.055561766,0.009375393,0.17919658,0.5294333,0.0027921733],"about_ca_topic_score_codex":0.00077943545,"about_ca_topic_score_gemma":0.0020449741,"teacher_disagreement_score":0.69925386,"about_ca_system_score_codex":0.000055890498,"about_ca_system_score_gemma":0.0000949889,"threshold_uncertainty_score":0.9964379},"labels":[],"label_agreement":null},{"id":"W1572842536","doi":"10.1016/b978-012088469-8.50109-1","title":"Trends in Data Warehousing","year":2004,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Data warehouse; Computer science; Intranet; Consolidation (business); Metadata; Business intelligence; Database; Concurrency; Data science; World Wide Web; Business; The Internet; Distributed computing","score_opus":0.26254447991093344,"score_gpt":0.410674666130839,"score_spread":0.14813018621990554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1572842536","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000040180157,0.00042230886,0.000060435257,0.0006264316,0.0006084825,0.00021346747,0.00050486624,0.000053368247,0.9975066],"genre_scores_gemma":[0.0005243229,0.000047734055,0.00076563057,0.00095987174,0.00022118313,0.000005470409,0.00045483,0.00004782828,0.99697316],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99517,0.000088214896,0.0012257678,0.0013796155,0.0017725143,0.00036389215],"domain_scores_gemma":[0.99468356,0.0002560992,0.0004562152,0.0044046184,0.00007371001,0.0001257998],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004304816,0.00038570017,0.0007159969,0.0011810608,0.00010287692,0.00040610202,0.0037939944,0.0002550018,0.0031247921],"category_scores_gemma":[0.00025573108,0.0003200715,0.00016514573,0.00009255398,0.00018474356,0.00032322228,0.0028290786,0.0004913276,0.0016240659],"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":[0.000007713055,0.000009910882,0.0000018123292,0.0000112038515,0.000022803197,0.000097793185,0.0001844945,0.0000055545675,3.169556e-7,0.042936448,0.0058343033,0.9508876],"study_design_scores_gemma":[0.00023129424,0.000013599206,0.00003439657,0.000204982,0.00002986216,0.0000031231089,0.000028899763,0.000014312633,8.172037e-7,0.19137548,0.8077643,0.0002989171],"about_ca_topic_score_codex":0.000007818343,"about_ca_topic_score_gemma":0.0012919463,"teacher_disagreement_score":0.9505887,"about_ca_system_score_codex":0.00015115312,"about_ca_system_score_gemma":0.00013870001,"threshold_uncertainty_score":0.99992514},"labels":[],"label_agreement":null},{"id":"W1573082841","doi":"10.1007/11424918_24","title":"Probability and Equality: A Probabilistic Model of Identity Uncertainty","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Identity (music); Computer science; Probabilistic logic; Task (project management); Context (archaeology); Similarity (geometry); Representation (politics); Object (grammar); Artificial intelligence; Theoretical computer science; Image (mathematics)","score_opus":0.1747452922368207,"score_gpt":0.36920874559150796,"score_spread":0.19446345335468726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1573082841","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":[0.0021904754,0.00014855455,0.99149334,0.0009285329,0.0003338993,0.0007430449,0.00010412032,0.00003545903,0.0040225936],"genre_scores_gemma":[0.7391197,0.00006609412,0.2566634,0.0018922535,0.00027429164,0.000022090022,0.000017205002,0.00003087258,0.0019140502],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933568,0.00013915623,0.0013382782,0.0018005348,0.0029261408,0.0004390842],"domain_scores_gemma":[0.9952023,0.0014970857,0.0006376804,0.0019334138,0.00056332676,0.00016621411],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011668473,0.00038220276,0.00080298126,0.0006313561,0.0001690987,0.00054624345,0.0027730947,0.00022598461,0.00007919589],"category_scores_gemma":[0.0027711818,0.00029670377,0.00013703294,0.00059774844,0.002402944,0.0009971566,0.0025657506,0.0004629581,0.000022629885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019387446,0.00006458906,0.000074849835,0.000115785144,0.000008871124,0.000002688999,0.00073889585,0.29010558,0.000018897643,0.22879344,0.000028770015,0.48002824],"study_design_scores_gemma":[0.000111768684,0.000048771366,0.000096323936,0.00008814232,0.000010801332,0.0000021878625,6.3218056e-7,0.35785663,0.000018440525,0.6408778,0.00067722413,0.00021132018],"about_ca_topic_score_codex":0.00012310795,"about_ca_topic_score_gemma":0.0023310776,"teacher_disagreement_score":0.73692924,"about_ca_system_score_codex":0.00024141614,"about_ca_system_score_gemma":0.0004845001,"threshold_uncertainty_score":0.9999485},"labels":[],"label_agreement":null},{"id":"W1577547142","doi":"10.1007/11430919_86","title":"The TIMERS II Algorithm for the Discovery of Causality","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Causality (physics); Computer science; Algorithm; Artificial intelligence; Data mining; Theoretical computer science","score_opus":0.08055751605725435,"score_gpt":0.3605419344042727,"score_spread":0.2799844183470183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577547142","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":[0.000009548019,0.00063892,0.9892521,0.0055174762,0.0017900574,0.0006157188,0.00012910574,0.000013822497,0.0020332336],"genre_scores_gemma":[0.093946464,0.0017188612,0.74985135,0.02370234,0.006763624,0.00019554477,0.00009066045,0.00016895465,0.12356221],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957047,0.00006964752,0.0008091686,0.00090251863,0.0021079967,0.00040598467],"domain_scores_gemma":[0.98951197,0.00771038,0.0005200766,0.0019101399,0.00029425495,0.000053161617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009555518,0.00026547865,0.00038518192,0.00022483729,0.0008758458,0.0007816733,0.0048366194,0.00011824974,0.00003151305],"category_scores_gemma":[0.00095110905,0.0001269588,0.00020920396,0.00042521147,0.0021148198,0.0005003261,0.001997638,0.0003354231,0.00002242836],"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":[0.000006741015,0.000012622724,0.0000017145999,0.0000038137987,0.000015152451,0.0000010209276,0.0002612905,0.003545868,0.0000029446915,0.019614344,0.0013067336,0.9752278],"study_design_scores_gemma":[0.00019730821,0.00014311034,0.0001240064,0.000067368084,0.00002816582,0.000003881177,0.0000059427352,0.20619698,0.00023612328,0.38650343,0.40619478,0.00029889614],"about_ca_topic_score_codex":0.00005677484,"about_ca_topic_score_gemma":0.00045439164,"teacher_disagreement_score":0.97492886,"about_ca_system_score_codex":0.000094169576,"about_ca_system_score_gemma":0.00026473327,"threshold_uncertainty_score":0.89877224},"labels":[],"label_agreement":null},{"id":"W1578664299","doi":"","title":"Extending q-grams to estimate selectivity of string matching with low edit distance","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":50,"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 British Columbia","funders":"","keywords":"Edit distance; Approximate string matching; String searching algorithm; String metric; Computer science; String (physics); Algorithm; Boyer–Moore string search algorithm; Matching (statistics); Similarity (geometry); Theoretical computer science; Data mining; Pattern matching; Mathematics; Artificial intelligence; Statistics; Image (mathematics)","score_opus":0.062628898205617,"score_gpt":0.42885606747204424,"score_spread":0.36622716926642723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578664299","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":[0.29792315,0.0000045068864,0.6935752,0.00016039553,0.00012431432,0.00011979436,0.0000066348293,0.000036673206,0.008049347],"genre_scores_gemma":[0.9654484,6.900525e-7,0.032768752,0.00013275506,0.000040562983,0.0000024531453,0.0000018500783,0.0000060434995,0.001598504],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9977478,0.000046042882,0.00041844515,0.0003888694,0.001098398,0.00030045304],"domain_scores_gemma":[0.9985049,0.0006437191,0.00015279301,0.00047521593,0.00010773848,0.00011567983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060373372,0.0001015222,0.00021114695,0.0001706591,0.00011496657,0.00017936561,0.000517865,0.000021221551,0.00009778157],"category_scores_gemma":[0.00050140684,0.00006827854,0.00003341303,0.00089336815,0.00004183703,0.00051261677,0.00023663274,0.00007826512,0.000058000875],"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":[0.00034835064,0.00032717115,0.022109507,0.00008902882,0.000054472024,0.00005668218,0.0019739969,0.00794528,0.0030544584,0.34178987,0.006643932,0.61560726],"study_design_scores_gemma":[0.0027141124,0.0012814017,0.49213094,0.0010567259,0.00010000315,0.000035029356,0.020876048,0.008962478,0.10712474,0.2239794,0.13935253,0.0023865926],"about_ca_topic_score_codex":0.00023537682,"about_ca_topic_score_gemma":0.0024573593,"teacher_disagreement_score":0.66752523,"about_ca_system_score_codex":0.000040336483,"about_ca_system_score_gemma":0.000016419988,"threshold_uncertainty_score":0.2784318},"labels":[],"label_agreement":null},{"id":"W1586049858","doi":"10.1007/bf03405034","title":"Development of a computer linkage system for a blood recipient notification program in Nova Scotia.","year":2002,"lang":"en","type":"article","venue":"PubMed","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Canada","funders":"","keywords":"Nova scotia; Record linkage; Medical record; Data file; Medicine; Computer science; Medical emergency; Database; Geography; Surgery; Environmental health; Population","score_opus":0.26855825142610584,"score_gpt":0.35374264056325516,"score_spread":0.08518438913714932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586049858","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":[0.8244772,0.00015629923,0.15246539,0.0017481106,0.002223621,0.012265403,0.000083563544,0.00021316166,0.006367248],"genre_scores_gemma":[0.93551993,9.446034e-7,0.062319156,0.00006473977,0.000048397174,0.0015272028,0.000019175777,0.0000060927027,0.00049433165],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976612,0.000089079935,0.000916849,0.00039545228,0.0006600409,0.00027738977],"domain_scores_gemma":[0.99881315,0.00023285422,0.00027946368,0.00046627916,0.00013842693,0.000069799746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043057417,0.00009012404,0.00022707178,0.00027341663,0.000039266884,0.00013209858,0.00052934466,0.000045182507,0.000020512964],"category_scores_gemma":[0.00031575124,0.000072281204,0.00005495232,0.0005959786,0.00003330891,0.00016556843,0.0001498269,0.00004597772,0.00008477004],"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":[0.000012089095,0.0005912545,0.00060077367,0.00009094086,0.000020917083,0.0000013066813,0.000986705,0.00002423395,0.0000064884703,0.0017545284,0.0025512304,0.9933595],"study_design_scores_gemma":[0.004825791,0.00016303708,0.47625637,0.00022535406,0.000081084414,0.000005091271,0.002083646,0.018604897,0.005415087,0.00055401004,0.49108192,0.00070372835],"about_ca_topic_score_codex":0.000018915738,"about_ca_topic_score_gemma":0.00027760194,"teacher_disagreement_score":0.9926558,"about_ca_system_score_codex":0.00006042364,"about_ca_system_score_gemma":0.000011230942,"threshold_uncertainty_score":0.2947542},"labels":[],"label_agreement":null},{"id":"W1586702196","doi":"10.19173/irrodl.v13i3.1176","title":"Identification of conflicting questions in the PARES system","year":2012,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cheating; Test (biology); Computer science; Vocabulary; Similarity (geometry); Mathematics education; Identification (biology); Space (punctuation); Artificial intelligence; Mathematics; Psychology; Linguistics; Image (mathematics); Social psychology","score_opus":0.37724406529817267,"score_gpt":0.587940438919133,"score_spread":0.21069637362096028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586702196","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":[0.6910791,0.082940884,0.01409854,0.119955175,0.00092967536,0.006941481,0.0007360696,0.00003311091,0.08328598],"genre_scores_gemma":[0.99648815,0.0031666453,0.000019484243,0.00006804313,0.000020012298,0.000052475487,0.00004561009,0.0000015108158,0.00013804158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954325,0.002206964,0.0007419711,0.00013199932,0.001344364,0.00014219021],"domain_scores_gemma":[0.9951702,0.0038385468,0.00031060821,0.0003061965,0.00034922248,0.000025273623],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06530426,0.0000405578,0.00015550407,0.0001430647,0.00010990384,0.00020756743,0.0017543694,0.000014554041,0.000047869788],"category_scores_gemma":[0.015744183,0.000021600297,0.000026355821,0.0007397895,0.00013516558,0.0003873082,0.0006477086,0.00025237066,0.00001842989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005590668,0.00023149181,0.12424161,0.0013697846,0.00003086938,0.000003043827,0.00224922,0.0002248503,0.00014999487,0.8094092,0.006586129,0.055447925],"study_design_scores_gemma":[0.00077501126,0.00007554979,0.3743298,0.015813865,0.00002260162,0.000022089687,0.15836212,0.006154497,0.000220591,0.009056085,0.43499786,0.00016992749],"about_ca_topic_score_codex":0.00073087256,"about_ca_topic_score_gemma":0.000043406875,"teacher_disagreement_score":0.8003531,"about_ca_system_score_codex":0.000043318658,"about_ca_system_score_gemma":0.00003966594,"threshold_uncertainty_score":0.9925466},"labels":[],"label_agreement":null},{"id":"W1593995188","doi":"10.1007/11533962_24","title":"Lineage Tracing in Mediator-Based Information Integration Systems","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Tracing; Metadata; Context (archaeology); Schema (genetic algorithms); Lineage (genetic); Information retrieval; Theoretical computer science; Distributed computing; Programming language; World Wide Web","score_opus":0.06659882761350404,"score_gpt":0.334403244244845,"score_spread":0.26780441663134097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1593995188","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":[0.00022628017,0.0001129629,0.991438,0.00079916173,0.0018819942,0.00049497565,0.000029123297,0.000047332644,0.004970182],"genre_scores_gemma":[0.93356395,0.000035074198,0.060734525,0.0039202007,0.0009292894,0.000029188755,0.00014508837,0.000023385204,0.0006193154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950008,0.00009901111,0.0013615323,0.000736442,0.0024444347,0.00035781402],"domain_scores_gemma":[0.99671364,0.0013388445,0.0005854989,0.0009643491,0.0002984045,0.000099258825],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007487278,0.00030799935,0.0004669549,0.0021784098,0.00012279423,0.0013470707,0.0019217212,0.00025500514,0.00006485833],"category_scores_gemma":[0.0013453887,0.00024067725,0.00008280713,0.0008833184,0.00030257943,0.0020746642,0.00035852732,0.0005753278,0.00024378514],"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":[0.000009051222,0.000015959491,0.00004490697,0.00002579004,0.0000018140887,0.000008794171,0.00092486496,0.25589126,0.000006142041,0.0073831403,0.00014313827,0.73554516],"study_design_scores_gemma":[0.00035475587,0.000074415984,0.00022710601,0.0005080871,0.0000052495056,0.0000039197093,0.000009414974,0.95553136,0.00026574556,0.014975707,0.027633045,0.00041118465],"about_ca_topic_score_codex":0.000086192566,"about_ca_topic_score_gemma":0.000875713,"teacher_disagreement_score":0.9333376,"about_ca_system_score_codex":0.00037353174,"about_ca_system_score_gemma":0.00032527887,"threshold_uncertainty_score":0.99968964},"labels":[],"label_agreement":null},{"id":"W1599163950","doi":"10.18438/b81596","title":"Name Authority Challenges for Indexing and Abstracting Databases","year":2006,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Authority control; Metadata; Search engine indexing; Database; Information retrieval; Control (management); World Wide Web; Bibliographic database; Artificial intelligence","score_opus":0.17201754704839065,"score_gpt":0.39698351337865123,"score_spread":0.22496596633026059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599163950","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":[0.020947875,0.010824061,0.25864586,0.64321744,0.00083177834,0.0019336244,0.0005253574,0.00048192657,0.06259208],"genre_scores_gemma":[0.8296511,0.007042521,0.10608924,0.054692496,0.00049218367,0.00012782376,0.0004463755,0.00002002978,0.0014382368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99818313,0.00024516735,0.0006401557,0.00024686722,0.0005203118,0.00016438901],"domain_scores_gemma":[0.98659074,0.012339861,0.0005750753,0.00033391768,0.00008493013,0.00007548138],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.004769719,0.00011225654,0.00014240853,0.00020115697,0.00033385906,0.001234524,0.000248727,0.00004440659,0.00010251887],"category_scores_gemma":[0.012004413,0.00009401505,0.00002723095,0.00021091192,0.000066424414,0.30007744,0.00022673416,0.00013169729,0.00003598605],"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":[0.00021296622,0.000036363363,0.00036159682,0.00016108034,0.0000067491774,0.0000016217003,0.00021895966,0.000093357754,0.000007856816,0.7868765,0.009042805,0.20298016],"study_design_scores_gemma":[0.00023950363,0.000058837744,0.012869471,0.00011467541,0.000018093688,0.000007335837,0.0046678176,0.0054203398,0.00023300402,0.004777634,0.9714571,0.0001361464],"about_ca_topic_score_codex":0.000029700668,"about_ca_topic_score_gemma":5.97146e-7,"teacher_disagreement_score":0.9624143,"about_ca_system_score_codex":0.0000047656235,"about_ca_system_score_gemma":0.000060682298,"threshold_uncertainty_score":0.9998023},"labels":[],"label_agreement":null},{"id":"W161959767","doi":"10.1007/978-3-642-14619-0_20","title":"Towards a Unified Data Management and Decision Support System for Health Care","year":2010,"lang":"en","type":"book-chapter","venue":"Smart innovation, systems and technologies","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Health care; Decision support system; Computer science; Data management; Data science; Knowledge management; Process management; Psychology; Business; Data mining; Political science","score_opus":0.16804501472805397,"score_gpt":0.39154810809541796,"score_spread":0.223503093367364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W161959767","genre_codex":"methods","genre_gemma":"other","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":[0.0010357109,0.021671604,0.53936297,0.021194762,0.015160457,0.021441627,0.02399347,0.005237186,0.3509022],"genre_scores_gemma":[0.2970547,0.0087208925,0.24055387,0.0022146204,0.0012690859,0.0020891593,0.024122152,0.00058216107,0.42339334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952196,0.00002764972,0.0018613451,0.0014241406,0.0011295968,0.00033769512],"domain_scores_gemma":[0.99447703,0.00027896368,0.0012155116,0.003118255,0.00086399604,0.000046249887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0056684124,0.0004222613,0.0009044628,0.0015657777,0.0004847576,0.00082012743,0.0018173301,0.0005809254,0.000009204503],"category_scores_gemma":[0.00053758064,0.00032177358,0.00004518543,0.00047663195,0.0003069506,0.00041102298,0.002823126,0.000333159,0.000024946483],"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":[0.000018281715,0.0000048683337,0.000018421704,0.0009025508,0.000064325475,0.0000050145095,0.0000889416,2.046918e-7,9.649053e-7,0.6666158,0.04576159,0.28651905],"study_design_scores_gemma":[0.00042865318,0.00013896967,0.000066276654,0.00046692658,0.000040949235,0.000020402276,0.012772414,0.00004259049,0.000006975725,0.072610125,0.91308606,0.00031965444],"about_ca_topic_score_codex":0.00008216108,"about_ca_topic_score_gemma":0.00024322448,"teacher_disagreement_score":0.8673245,"about_ca_system_score_codex":0.00010765297,"about_ca_system_score_gemma":0.00013991813,"threshold_uncertainty_score":0.9999234},"labels":[],"label_agreement":null},{"id":"W1620933693","doi":"10.1002/047148296x.tie082","title":"Information Quality in Internet and E‐business Environments","year":2004,"lang":"en","type":"other","venue":"The Internet Encyclopedia","topic":"Data Quality and Management","field":"Decision Sciences","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":"Impact","funders":"","keywords":"The Internet; Computer science; Information quality; Quality (philosophy); Business information; Knowledge management; World Wide Web; Information system; Business; Marketing; Engineering","score_opus":0.05312032767530156,"score_gpt":0.343006711105528,"score_spread":0.28988638343022644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1620933693","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018257443,0.0003759879,0.009003146,0.00077348616,0.0010299659,0.00060060766,0.000109162,0.000053437874,0.98622847],"genre_scores_gemma":[0.016723162,0.0011932177,0.0001999382,0.0011488777,0.00014366365,0.000044739394,0.00015997842,0.000067130735,0.9803193],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972495,0.0003112927,0.00089834345,0.00033513992,0.00096660183,0.00023914422],"domain_scores_gemma":[0.9982461,0.0002534825,0.00056828256,0.0008522678,0.000017680717,0.00006223742],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026251904,0.0002654506,0.00038186013,0.00040838175,0.000016241034,0.00030256467,0.0014115699,0.00017724546,0.0034621635],"category_scores_gemma":[0.00078256824,0.00016821946,0.000049876595,0.00030447586,0.00021227497,0.0004856733,0.0009761099,0.00026207566,0.0030601511],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003651491,0.00006800547,0.0013491715,0.000056197117,0.000041946303,0.000006194585,0.0034479857,0.000009830838,2.9908549e-7,0.014765347,0.8704353,0.109783195],"study_design_scores_gemma":[0.00034528744,0.000014361112,0.018782476,0.0001294535,0.000011356409,0.0000020717189,0.00042516386,0.000020930369,0.0000012898382,0.006492086,0.9735696,0.00020594354],"about_ca_topic_score_codex":0.00893643,"about_ca_topic_score_gemma":0.004093671,"teacher_disagreement_score":0.109577246,"about_ca_system_score_codex":0.00008774105,"about_ca_system_score_gemma":0.00003374615,"threshold_uncertainty_score":0.99771607},"labels":[],"label_agreement":null},{"id":"W1626378195","doi":"10.1145/1938551.1938585","title":"Data cleaning and query answering with matching dependencies and matching functions","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Tuple; Matching (statistics); Computer science; Monotone polygon; Conjunctive query; Dependency (UML); Functional dependency; Semantics (computer science); Dependency theory (database theory); Query optimization; Upper and lower bounds; Theoretical computer science; Mathematics; Information retrieval; Discrete mathematics; Relational database; Artificial intelligence; Programming language","score_opus":0.3569999851508519,"score_gpt":0.37439216888693916,"score_spread":0.017392183736087252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1626378195","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":[0.5379349,0.00007501179,0.4228636,0.00027194663,0.0001229343,0.000114725684,0.00006275924,0.00009173376,0.03846241],"genre_scores_gemma":[0.9638334,0.00002617346,0.03369413,0.00044259595,0.00002422445,0.0000026299874,0.000015441467,0.000008539111,0.001952876],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9984892,0.00007155665,0.0002743815,0.0005203014,0.0004671768,0.0001774018],"domain_scores_gemma":[0.99868757,0.00031486343,0.000085820626,0.00079156976,0.000033690423,0.000086462365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026822218,0.00010400166,0.00014772399,0.00012874969,0.0003290744,0.0005082656,0.00053409894,0.000024661145,0.00024894407],"category_scores_gemma":[0.0001559216,0.000069005124,0.000009542385,0.00017297635,0.00008762223,0.0020712677,0.0013725954,0.000102410304,0.00004250402],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003021333,0.00023860188,0.060388498,0.00017281361,0.0003339726,0.00017130461,0.043550976,0.0001608553,0.00094893604,0.40153417,0.025870804,0.46632692],"study_design_scores_gemma":[0.0014120963,0.000342186,0.19971883,0.0002598643,0.00020076198,0.00031770466,0.45431635,0.0048846984,0.00022745306,0.21169029,0.12522115,0.0014086053],"about_ca_topic_score_codex":0.0017928156,"about_ca_topic_score_gemma":0.005569226,"teacher_disagreement_score":0.46491832,"about_ca_system_score_codex":0.0000055682344,"about_ca_system_score_gemma":0.000014165317,"threshold_uncertainty_score":0.4901217},"labels":[],"label_agreement":null},{"id":"W1691660836","doi":"10.1002/pds.2205","title":"Record linkage for pharmacoepidemiological studies in cancer patients","year":2011,"lang":"en","type":"review","venue":"Pharmacoepidemiology and Drug Safety","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pharmacoepidemiology; Medicine; Cancer registry; Record linkage; Database; Epidemiology; Generalizability theory; Population; Linkage (software); Cancer; Family medicine; MEDLINE; Environmental health; Medical prescription; Internal medicine; Pharmacology","score_opus":0.7226817690093758,"score_gpt":0.6243594865246453,"score_spread":0.0983222824847304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1691660836","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002968775,0.989839,0.000907681,0.0010880465,0.0037109856,0.0024324253,0.0013049858,0.00006537736,0.00062178576],"genre_scores_gemma":[0.000028420369,0.99108183,0.0010959145,0.0041029328,0.0004937113,0.0014170739,0.00029350925,0.000038964165,0.0014476643],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9801731,0.01163793,0.0047623543,0.0020973692,0.00031008627,0.0010191671],"domain_scores_gemma":[0.93879366,0.057778683,0.0021363776,0.0006862203,0.00029318975,0.00031190075],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04645655,0.00086916814,0.0060047894,0.00062456005,0.00031658955,0.000027546283,0.0016321139,0.000507937,0.00052671344],"category_scores_gemma":[0.030703539,0.00054598984,0.00083802635,0.0006576108,0.00073404424,0.0003745672,0.0012917364,0.0010846326,0.00018160038],"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":[0.0001389135,0.00016436356,0.0013703266,0.0029824064,0.00032220242,0.0000051745233,0.00019234934,0.000002260768,1.3150261e-8,0.0030430434,0.1650893,0.82668966],"study_design_scores_gemma":[0.0010323694,0.000067028246,0.00022541765,0.0015946615,0.0006887137,0.0000023747666,0.00009174338,0.000066969034,1.557408e-7,0.015779793,0.97986996,0.00058082247],"about_ca_topic_score_codex":0.0002041886,"about_ca_topic_score_gemma":0.00019798006,"teacher_disagreement_score":0.8261088,"about_ca_system_score_codex":0.0002021395,"about_ca_system_score_gemma":0.00012554818,"threshold_uncertainty_score":0.9996992},"labels":[],"label_agreement":null},{"id":"W1748398123","doi":"10.5555/359640.359930","title":"Data quality in internet time, space, and communities (panel session)","year":2000,"lang":"en","type":"article","venue":"International Conference on Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Session (web analytics); The Internet; Quality (philosophy); Computer network; World Wide Web; Physics","score_opus":0.4236509632793228,"score_gpt":0.4455404448422119,"score_spread":0.021889481562889113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1748398123","genre_codex":"other","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":[0.15661715,0.000023710809,0.0060143466,0.0046160426,0.0010489443,0.00052745343,0.0019680501,0.00008862987,0.82909566],"genre_scores_gemma":[0.9860069,0.00006246171,0.00009391154,0.0006550338,0.000035751393,0.000019860921,0.00118361,0.0000030099302,0.011939428],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99675965,0.00042869212,0.001154118,0.00019613704,0.0013223988,0.0001390189],"domain_scores_gemma":[0.99789494,0.0005059474,0.00034946637,0.00089487777,0.0002896004,0.00006514502],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0045239874,0.00012999742,0.00023672682,0.00040612687,0.000066506924,0.0014685377,0.0018850234,0.000062217594,0.0037667907],"category_scores_gemma":[0.00042734007,0.00010329203,0.000021226691,0.00019640724,0.000094365125,0.0052547674,0.000495234,0.00016817752,0.0039529307],"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":[0.0001950538,0.00008772655,0.0029706662,0.000033689426,0.000039815484,0.000002242232,0.005194639,0.00041190744,0.000006018274,0.81622225,0.06016235,0.11467366],"study_design_scores_gemma":[0.0006558324,0.00003889446,0.012071235,0.000202173,0.0000026041107,0.000008875955,0.012871218,0.20089203,0.0000039516704,0.0038679135,0.7691749,0.00021038401],"about_ca_topic_score_codex":0.0021476827,"about_ca_topic_score_gemma":0.00023230526,"teacher_disagreement_score":0.8293898,"about_ca_system_score_codex":0.000051371306,"about_ca_system_score_gemma":0.00004476552,"threshold_uncertainty_score":0.99956805},"labels":[],"label_agreement":null},{"id":"W1852280707","doi":"10.1609/aaai.v29i1.9404","title":"Existential Rule Languages with Finite Chase: Complexity and Expressiveness","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"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 Alberta","funders":"","keywords":"Decidability; Computer science; Chase; Ontology language; Existentialism; Regular language; Property (philosophy); Mathematics; Discrete mathematics; Theoretical computer science; Artificial intelligence","score_opus":0.45711114531969094,"score_gpt":0.42983730638237017,"score_spread":0.02727383893732077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1852280707","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":[0.90096664,0.000070492446,0.013277434,0.007518486,0.00042904948,0.0007622552,0.00011517889,0.000083122875,0.07677735],"genre_scores_gemma":[0.99787545,0.000013516476,0.0009494438,0.00021685762,0.000053893666,0.000016235905,0.0000019633123,0.000007389234,0.0008652543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975843,0.000046680427,0.0004988018,0.00047036834,0.0011681359,0.00023174669],"domain_scores_gemma":[0.99802244,0.00022853618,0.0004242162,0.000332282,0.00085516897,0.00013738616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018743392,0.00016815175,0.0002817152,0.00013265223,0.00016049865,0.00046271435,0.0012996703,0.000048771464,0.00017223497],"category_scores_gemma":[0.0020012625,0.00009918596,0.00005060352,0.00048582174,0.0007548985,0.0004287893,0.0005550282,0.00015493442,0.000102367536],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046982898,0.00019166006,0.00078672916,0.000034893692,0.000021919242,0.0000022012498,0.0031050837,0.000060119586,0.0025536066,0.92548126,0.0013388599,0.06595384],"study_design_scores_gemma":[0.00018971077,0.0005591566,0.0015343652,0.00038238286,0.00004711056,0.000009379831,0.038586352,0.007898056,0.19614449,0.7490517,0.005123938,0.00047335261],"about_ca_topic_score_codex":0.0001581009,"about_ca_topic_score_gemma":0.00007016795,"teacher_disagreement_score":0.19359088,"about_ca_system_score_codex":0.000016774153,"about_ca_system_score_gemma":0.00005959601,"threshold_uncertainty_score":0.44619653},"labels":[],"label_agreement":null},{"id":"W1852537914","doi":"10.1109/nafips.1999.781771","title":"A characterization of information quality using fuzzy logic","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Fuzzy logic; Computer science; Information quality; Quality (philosophy); Perspective (graphical); Information system; Fuzzy set; Characterization (materials science); Data mining; Artificial intelligence; Engineering","score_opus":0.3191743449327472,"score_gpt":0.44823633327241463,"score_spread":0.12906198833966742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1852537914","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":[0.42764875,0.0000012324073,0.5158227,0.000164507,0.00015045528,0.00012035994,0.000023200708,0.000015545009,0.05605323],"genre_scores_gemma":[0.99249446,0.0000029664357,0.0059129773,0.00094960566,0.000006132415,0.0000015431274,0.00003730823,0.0000011369453,0.0005938396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983656,0.0002389482,0.0006294858,0.000093891314,0.00059424725,0.00007784034],"domain_scores_gemma":[0.9990682,0.00010144309,0.00031872085,0.00031596955,0.00016975182,0.000025920759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042919116,0.000043887285,0.00011548086,0.00013679288,0.000043854598,0.000107917826,0.00019160568,0.000025728932,0.0005874976],"category_scores_gemma":[0.0017556917,0.00003136968,0.000033075958,0.00042826234,0.00002779608,0.0014529751,0.000052668693,0.000021773078,0.00018414934],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007801947,0.00003575513,0.00096120016,0.000012091505,0.0000045606203,8.113959e-8,0.0004041196,0.00004279259,0.010145502,0.97273016,0.00022221929,0.015433733],"study_design_scores_gemma":[0.0010335421,0.00009942393,0.11626956,0.00002062366,0.00002408383,0.0000034689322,0.0076770727,0.0028511754,0.034895375,0.44066745,0.39599144,0.0004667736],"about_ca_topic_score_codex":0.000052557167,"about_ca_topic_score_gemma":0.000008308671,"teacher_disagreement_score":0.56484574,"about_ca_system_score_codex":0.000012593525,"about_ca_system_score_gemma":0.000022609449,"threshold_uncertainty_score":0.64326864},"labels":[],"label_agreement":null},{"id":"W1860275762","doi":"10.1109/nafips.1999.781722","title":"Fuzzy measures for data quality","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"York University","funders":"","keywords":"Computer science; Fuzzy logic; Quality (philosophy); Data mining; Representation (politics); Data quality; Fuzzy set; External Data Representation; Information retrieval; Artificial intelligence; Engineering","score_opus":0.757558786964487,"score_gpt":0.5624620966962995,"score_spread":0.19509669026818743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1860275762","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":[0.0007994203,0.00007196268,0.574892,0.0034473285,0.00051382,0.00034512675,0.00029891575,0.00005598075,0.41957545],"genre_scores_gemma":[0.70521104,0.00003557299,0.13480714,0.011427317,0.00016580749,0.000059851718,0.00035562043,0.000021000827,0.14791664],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974339,0.00037119602,0.00049649144,0.0005347237,0.0009824014,0.0001813046],"domain_scores_gemma":[0.9957959,0.0013949,0.00010308554,0.0024838941,0.00014878642,0.00007343196],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021499682,0.000069731774,0.00016198635,0.00006293795,0.000118334574,0.0002922202,0.001710534,0.00002768086,0.0005813592],"category_scores_gemma":[0.01757596,0.00004597835,0.000046391968,0.00024095725,0.000046028552,0.0005717244,0.0003406824,0.00003231611,0.0005780561],"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":[0.0000060983375,0.000031107116,0.00018651412,0.0000023930734,0.0000071304735,1.4994399e-7,0.000026955988,0.0000015018849,0.00001346967,0.54857504,0.40347838,0.047671266],"study_design_scores_gemma":[0.00015949848,0.000009678479,0.00049459893,6.4849905e-7,0.0000041100966,2.0038102e-7,0.0006507069,0.000041472114,0.000107595755,0.26935694,0.7291113,0.00006325692],"about_ca_topic_score_codex":0.00010987507,"about_ca_topic_score_gemma":0.00063236273,"teacher_disagreement_score":0.7044116,"about_ca_system_score_codex":0.0000080192885,"about_ca_system_score_gemma":0.000037894064,"threshold_uncertainty_score":0.9906994},"labels":[],"label_agreement":null},{"id":"W1863738141","doi":"10.32920/ryerson.14660694","title":"Identity matching in social media platforms","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Matching (statistics); Social media; Identity (music); Set (abstract data type); Task (project management); Information retrieval; World Wide Web; Similarity (geometry); Process (computing); Social Semantic Web; Semantic Web; Artificial intelligence; Mathematics; Engineering","score_opus":0.2828132511239933,"score_gpt":0.4597413444349298,"score_spread":0.1769280933109365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1863738141","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":[0.8214923,0.000029272673,0.042289123,0.0034150078,0.000878103,0.00006557851,0.000023077799,0.000044423858,0.13176309],"genre_scores_gemma":[0.9918983,0.000008140632,0.0014571059,0.001407441,0.00011037442,0.0000025427662,0.000018561794,0.0000028577454,0.0050946604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982593,0.000049237715,0.00034749866,0.00023820024,0.00096503494,0.00014071328],"domain_scores_gemma":[0.99914527,0.00048555864,0.000049219816,0.00023489879,0.000051912546,0.000033161497],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0031694593,0.00004641269,0.00012870374,0.00010173556,0.000088167166,0.00037269876,0.0004426286,0.000030542134,0.0033709304],"category_scores_gemma":[0.0014055435,0.000034016542,0.000047052738,0.0006090997,0.000024737874,0.0011819361,0.00049957674,0.00007522484,0.0011074825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003916791,0.000053508367,0.0010650005,0.0000032834112,0.000004470124,0.000054608863,0.0029625061,0.000007145393,0.00005264707,0.9191076,0.037817307,0.038868014],"study_design_scores_gemma":[0.00017306066,0.0000013269506,0.044047814,0.0000025230624,0.000001510569,9.448265e-7,0.013726301,0.000036652928,0.00013025681,0.91906345,0.02275173,0.000064433836],"about_ca_topic_score_codex":0.0000869819,"about_ca_topic_score_gemma":0.011957301,"teacher_disagreement_score":0.170406,"about_ca_system_score_codex":0.000020781456,"about_ca_system_score_gemma":0.000029775294,"threshold_uncertainty_score":0.99967027},"labels":[],"label_agreement":null},{"id":"W1869211391","doi":"","title":"An XML Based Document Management Framework to Prevent Data Leakage (情報セキュリティ)","year":2014,"lang":"en","type":"article","venue":"India Software Engineering Conference","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; XML; Leakage (economics); Database; World Wide Web","score_opus":0.08554686642750002,"score_gpt":0.37492078300027526,"score_spread":0.2893739165727752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1869211391","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":[0.0077904053,0.000019294137,0.9890839,0.0006654394,0.00089390186,0.0005798124,0.00015528958,0.00038296636,0.0004290012],"genre_scores_gemma":[0.737594,0.0000067522915,0.2601435,0.0013947969,0.00013199101,0.00008426303,0.00018499003,0.00003078645,0.0004289671],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99554294,0.0002196731,0.0007232692,0.0012883425,0.0016435456,0.00058220414],"domain_scores_gemma":[0.9934279,0.0012257992,0.00015574158,0.004613129,0.00013438278,0.0004430739],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044989116,0.00033677026,0.00038971793,0.00044090408,0.00013725601,0.000958822,0.0048253615,0.000110689936,0.0006849638],"category_scores_gemma":[0.004007907,0.00030746727,0.000064932705,0.00072470115,0.000039030496,0.0008119668,0.0014528553,0.00027920684,0.0009837248],"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":[0.000066364286,0.000775082,0.0026040436,0.00034607065,0.00020773386,0.00010770547,0.0017731853,0.09433852,0.00009635009,0.27247804,0.033464924,0.59374195],"study_design_scores_gemma":[0.0005695092,0.0003802922,0.03580509,0.00052263826,0.000082748345,0.0000027008537,0.00038463608,0.06469256,0.00046867048,0.019051068,0.87672526,0.0013148163],"about_ca_topic_score_codex":0.000039659048,"about_ca_topic_score_gemma":0.000024453791,"teacher_disagreement_score":0.84326035,"about_ca_system_score_codex":0.000075267766,"about_ca_system_score_gemma":0.00005430464,"threshold_uncertainty_score":0.9999377},"labels":[],"label_agreement":null},{"id":"W1924314351","doi":"10.1007/978-3-319-22849-5_11","title":"Quality Metrics for Linked Open Data","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Quality (philosophy); Data mining","score_opus":0.6007819523488969,"score_gpt":0.5116201951511121,"score_spread":0.08916175719778474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1924314351","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":[0.0000035925154,0.00033685114,0.97417754,0.0026392154,0.0025090796,0.0012712484,0.0007927013,0.00004208029,0.018227695],"genre_scores_gemma":[0.010146649,0.000063582454,0.95799196,0.009153862,0.0013884671,0.00003753314,0.0007690584,0.00006863129,0.020380262],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9912403,0.00016353975,0.0013912134,0.0028762545,0.003762404,0.0005662731],"domain_scores_gemma":[0.9859997,0.0055693127,0.0007937733,0.0063679884,0.0010071163,0.00026212673],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.041879978,0.0004068017,0.00092416134,0.0011564812,0.00029311536,0.0032071252,0.028361501,0.00028551288,0.00013248215],"category_scores_gemma":[0.01394007,0.00031031988,0.00010483585,0.0013691812,0.00077680603,0.0022784679,0.023964936,0.00048670886,0.00020246778],"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":[0.00002608148,0.00003377781,0.000014528239,0.000018800574,0.00001228765,0.000007485213,0.00018278926,0.0014377098,0.0000018479807,0.057943087,0.014264075,0.9260575],"study_design_scores_gemma":[0.0002982383,0.00007327861,0.00003513769,0.00004023535,0.000008877632,0.0000019073586,0.0000011457291,0.03994881,0.000006244927,0.53899777,0.42027405,0.00031428598],"about_ca_topic_score_codex":0.00015327914,"about_ca_topic_score_gemma":0.0009203215,"teacher_disagreement_score":0.9257432,"about_ca_system_score_codex":0.00023301234,"about_ca_system_score_gemma":0.000958945,"threshold_uncertainty_score":0.9999349},"labels":[],"label_agreement":null},{"id":"W1946996879","doi":"10.2196/mhealth.4183","title":"Effectiveness of Using Mobile Phone Image Capture for Collecting Secondary Data: A Case Study on Immunization History Data Among Children in Remote Areas of Thailand","year":2015,"lang":"en","type":"article","venue":"JMIR mhealth and uhealth","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Faculty of Tropical Medicine, Mahidol University; Mahidol University; Bill and Melinda Gates Foundation","keywords":"Logbook; Data quality; Data collection; Computer science; Mobile phone; Medicine; Multimedia; Engineering; Telecommunications; Operations management; Statistics","score_opus":0.3159661544709465,"score_gpt":0.48658033966033715,"score_spread":0.17061418518939064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1946996879","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":[0.9923277,0.0007833842,0.002722622,0.000029404731,0.0002211816,0.002783928,0.0010206182,0.0000110267865,0.00010016228],"genre_scores_gemma":[0.9983076,0.000029778352,0.0009539436,0.000065033724,0.00003201768,0.000017821558,0.0005496672,0.000013452545,0.000030722476],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963991,0.0012421083,0.00087126205,0.00069579674,0.0005338815,0.0002578726],"domain_scores_gemma":[0.9960959,0.0010839704,0.0007435163,0.0016941018,0.00019882759,0.00018368926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016334815,0.00014423401,0.0005500683,0.00037240845,0.00014050795,0.000034968758,0.00071216066,0.00006572371,0.000005677003],"category_scores_gemma":[0.0011980294,0.00012107616,0.000018132514,0.0005416462,0.000108672844,0.0007055125,0.00064308586,0.00019675719,5.965779e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009741428,0.0075858333,0.6984574,0.011912355,0.00027391032,0.00037636107,0.09156361,0.0013749526,0.00015176125,0.00022650223,0.0525442,0.12579165],"study_design_scores_gemma":[0.015652057,0.0024588082,0.83928674,0.00074936746,0.00022075372,0.0001936892,0.093495,0.04476364,0.000036768346,0.0008746,0.0016820341,0.00058653584],"about_ca_topic_score_codex":0.023361918,"about_ca_topic_score_gemma":0.004155902,"teacher_disagreement_score":0.14082932,"about_ca_system_score_codex":0.00022424871,"about_ca_system_score_gemma":0.00082376896,"threshold_uncertainty_score":0.9831416},"labels":[],"label_agreement":null},{"id":"W1964327907","doi":"10.1145/1370256.1370264","title":"Design and development of a prototype system for detecting abnormal weather observations","year":2008,"lang":"en","type":"article","venue":"","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 Manitoba","funders":"","keywords":"Consistency (knowledge bases); Computer science; Weather forecasting; Weather patterns; Weather satellite; Data quality; Automatic weather station; Set (abstract data type); Model output statistics; Data mining; Meteorology; Satellite; Artificial intelligence; Engineering; Geography; Climate change","score_opus":0.4395776018191143,"score_gpt":0.38437826037872513,"score_spread":0.05519934144038918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964327907","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":[0.07790048,0.000010183557,0.92011154,0.00006279973,0.00004256449,0.0010087615,0.0000025022398,0.0000265233,0.000834639],"genre_scores_gemma":[0.538254,6.7917443e-7,0.46041536,0.000042303316,0.000007653257,0.00017809476,0.0000012756566,0.0000033311587,0.0010973068],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889827,0.00006513848,0.0004253263,0.00017452205,0.0003339735,0.000102798585],"domain_scores_gemma":[0.99900997,0.00050555234,0.0001180072,0.00018910966,0.00014586418,0.000031479758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027555444,0.00005294427,0.00012092509,0.00007593451,0.00022601565,0.00003449616,0.00019463387,0.000020563019,0.000024662431],"category_scores_gemma":[0.00034815643,0.000036564154,0.000017008782,0.00016703564,0.000029167853,0.00020135984,0.00008530549,0.000017994762,0.000017137212],"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":[0.0011562011,0.00063774857,0.026958238,0.0010986633,0.00039640904,0.000016671767,0.05660293,0.002018953,0.009343208,0.12753828,0.016943615,0.7572891],"study_design_scores_gemma":[0.0061921175,0.0015009434,0.1328447,0.00034747747,0.00008217202,0.000092126895,0.065520175,0.071914144,0.16905014,0.008488769,0.54236186,0.0016053484],"about_ca_topic_score_codex":0.000012821726,"about_ca_topic_score_gemma":0.000020321077,"teacher_disagreement_score":0.7556837,"about_ca_system_score_codex":0.000014055382,"about_ca_system_score_gemma":0.00006599845,"threshold_uncertainty_score":0.17383525},"labels":[],"label_agreement":null},{"id":"W1966277682","doi":"10.12927/hcpap.2012.22706","title":"\"In God We Trust; All Others Must Bring Data\"","year":2012,"lang":"en","type":"article","venue":"A Nudge Too Far? A Nudge at All? On Paying People to Be Healthy","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Internet privacy; Business; Environmental ethics; Social psychology; Computer science; Philosophy","score_opus":0.38685212466784186,"score_gpt":0.4682621043301587,"score_spread":0.08140997966231683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966277682","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2596622,0.0004735389,0.00150662,0.7281287,0.0018328552,0.001233493,0.00047658262,0.00020154688,0.0064844717],"genre_scores_gemma":[0.06846077,0.00029720162,0.0019983714,0.9216686,0.000111093366,0.000120048644,0.00020611934,0.00009197884,0.007045815],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910715,0.00093484984,0.0018334778,0.0018545445,0.002249256,0.0020563672],"domain_scores_gemma":[0.9921509,0.0020951787,0.00054473116,0.003889178,0.000106536405,0.0012134837],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.012336129,0.00059759925,0.0009832657,0.00077655725,0.00041812853,0.00046657235,0.0033763791,0.00023262638,0.0017267644],"category_scores_gemma":[0.0022370468,0.0005197833,0.00019823208,0.0017195607,0.00007729572,0.002068735,0.0025519892,0.00054838037,0.00824692],"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":[0.00041190055,0.0005485238,0.00400149,0.000049805392,0.00005115942,0.000028097482,0.011264859,0.00003644639,0.00008307552,0.005261405,0.9561025,0.022160744],"study_design_scores_gemma":[0.0013126209,0.00028422166,0.01005241,0.0000017127114,0.000034171564,0.000018874358,0.003465433,0.0009982537,0.0000417144,0.00040887302,0.98275185,0.00062987313],"about_ca_topic_score_codex":0.0030270454,"about_ca_topic_score_gemma":0.007276407,"teacher_disagreement_score":0.19353992,"about_ca_system_score_codex":0.0007440993,"about_ca_system_score_gemma":0.00018647133,"threshold_uncertainty_score":0.9997254},"labels":[],"label_agreement":null},{"id":"W1967167578","doi":"10.14778/1453856.1453980","title":"Discovering data quality rules","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":268,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data quality; Consistency (knowledge bases); Context (archaeology); Quality (philosophy); Data mining; Data integrity; Set (abstract data type); Data consistency; Process (computing); Database; Artificial intelligence; Programming language; Engineering","score_opus":0.49777141101266814,"score_gpt":0.451736219472416,"score_spread":0.04603519154025215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967167578","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":[0.9511541,0.00012862953,0.00045843213,0.005143543,0.0004836817,0.00046454006,0.00031224947,0.00004861448,0.041806225],"genre_scores_gemma":[0.99422973,0.00008732842,0.0019098001,0.00033891847,0.00007437031,0.000012659445,0.000009695446,0.000007553263,0.003329965],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99658775,0.000030389752,0.00075386645,0.0005427183,0.0018482468,0.00023703698],"domain_scores_gemma":[0.9979997,0.00023210481,0.00051173725,0.0010212205,0.0001685729,0.00006665223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043975953,0.00013047698,0.0002713974,0.000084786334,0.00025556717,0.00014410127,0.0043056463,0.000028199831,0.000102604106],"category_scores_gemma":[0.0025366838,0.00007487221,0.00009972433,0.0003850528,0.00022391541,0.0010271574,0.0042868266,0.000101986094,0.00010806411],"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":[0.00017594465,0.0008405626,0.074812256,0.00021315133,0.00021673864,0.0000030715871,0.0062539536,0.00005269947,0.014850645,0.40627158,0.4563141,0.039995335],"study_design_scores_gemma":[0.0012760415,0.000097619464,0.19340204,0.00012766459,0.0000712369,0.000025424612,0.007961334,0.0005190978,0.03693907,0.11903248,0.6399669,0.000581099],"about_ca_topic_score_codex":0.00029214527,"about_ca_topic_score_gemma":0.00002114362,"teacher_disagreement_score":0.28723907,"about_ca_system_score_codex":0.000036563437,"about_ca_system_score_gemma":0.000028474376,"threshold_uncertainty_score":0.80010337},"labels":[],"label_agreement":null},{"id":"W197224835","doi":"","title":"Automatic Message Triage: Decision Support from Patient-Provider Messages","year":2013,"lang":"en","type":"article","venue":"Americas Conference on Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Popularity; Triage; Health care; Computer science; Internet privacy; Decision support system; Work (physics); Medical emergency; Medicine; Data mining; Psychology","score_opus":0.10443091422551239,"score_gpt":0.36029266413013505,"score_spread":0.2558617499046227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W197224835","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":[0.29446617,0.00010616512,0.34968692,0.005238329,0.006311199,0.006002037,0.00096264936,0.0009479058,0.33627862],"genre_scores_gemma":[0.99468493,0.00002799585,0.0013985676,0.002303141,0.000046298046,0.0003371359,0.00023519437,0.000010782118,0.0009559459],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935351,0.0005075643,0.0022986338,0.00043929627,0.0028225505,0.00039682424],"domain_scores_gemma":[0.99425143,0.0017212289,0.0014940336,0.0015166772,0.0007683204,0.00024829232],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001938088,0.00031005597,0.0006407167,0.0005126681,0.00023566873,0.0031461404,0.0012255305,0.000118120195,0.009026136],"category_scores_gemma":[0.0022712718,0.00021863656,0.0001337592,0.0007625856,0.00013960477,0.00619855,0.00032831825,0.00019367505,0.04141823],"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":[0.000022847526,0.000045950423,0.00016229184,0.00001717755,0.000034199522,0.0000025095005,0.002759851,0.00012137506,0.00001666898,0.011717448,0.19572239,0.7893773],"study_design_scores_gemma":[0.002035745,0.00070655264,0.010678292,0.00029953054,0.00004645563,0.000010723031,0.08583025,0.1359024,0.0001512503,0.014488589,0.7488156,0.0010345948],"about_ca_topic_score_codex":0.0017123583,"about_ca_topic_score_gemma":0.000009488121,"teacher_disagreement_score":0.7883427,"about_ca_system_score_codex":0.0000819631,"about_ca_system_score_gemma":0.0001210071,"threshold_uncertainty_score":0.9978887},"labels":[],"label_agreement":null},{"id":"W1974097983","doi":"10.1109/sose.2014.25","title":"Towards Knowledge Discovery in Big Data","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":56,"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 Saskatchewan","funders":"","keywords":"NoSQL; Computer science; Unstructured data; Big data; Knowledge extraction; Data warehouse; Data science; Semi-structured data; Schema (genetic algorithms); SQL; Analytics; Database; Data mining; Information retrieval; Relational database","score_opus":0.5125727714900005,"score_gpt":0.47666404228785153,"score_spread":0.03590872920214894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974097983","genre_codex":"other","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":[0.010092354,0.000053764586,0.2976686,0.0036300512,0.0012726748,0.000119679295,0.0000810179,0.000036750313,0.6870451],"genre_scores_gemma":[0.9506948,0.000014948226,0.0010818418,0.0011780331,0.00019580031,0.0000033853992,0.000066265304,0.0000041855196,0.046760764],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99821764,0.00023705297,0.0003705556,0.00048183394,0.00053193176,0.00016098192],"domain_scores_gemma":[0.9972219,0.000522542,0.000049003913,0.002128677,0.0000299092,0.000047997335],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0077451286,0.00006674994,0.00015160491,0.0001772488,0.00003355881,0.00042691524,0.002363645,0.000024957995,0.00030280766],"category_scores_gemma":[0.0031358222,0.000042591557,0.000022331304,0.000509378,0.000048910682,0.001049535,0.0023290038,0.00005528142,0.0021574367],"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":[0.0000041920666,0.000069678244,0.0006160629,0.0000028112584,0.0000022222657,8.205916e-7,0.00010266833,0.0000027940034,0.0000054339544,0.10877981,0.21735755,0.67305595],"study_design_scores_gemma":[0.0001814767,0.000014001039,0.013269048,0.000004757859,0.0000019160134,2.1749116e-7,0.00043564805,0.0025050968,0.00003127346,0.044136677,0.9393415,0.0000783835],"about_ca_topic_score_codex":0.0003795861,"about_ca_topic_score_gemma":0.0055051134,"teacher_disagreement_score":0.9406024,"about_ca_system_score_codex":0.000011707175,"about_ca_system_score_gemma":0.000035592035,"threshold_uncertainty_score":0.9986195},"labels":[],"label_agreement":null},{"id":"W1975236650","doi":"10.1007/s10664-008-9101-9","title":"A subject-based empirical evaluation of SSUCD’s performance in reducing inconsistencies in use case models","year":2008,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Subject (documents); Empirical research; Statistics; Mathematics; World Wide Web","score_opus":0.4411743086357212,"score_gpt":0.4184957454988292,"score_spread":0.022678563136892038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975236650","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":[0.9595954,0.000097536,0.03960092,0.00016467895,0.00013247886,0.0002834544,0.0000137467,0.00006190276,0.00004988566],"genre_scores_gemma":[0.990956,0.000007691159,0.008783903,0.00013443007,0.000020383797,0.000044632507,0.000008936475,0.000013576553,0.000030452802],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99626523,0.000297752,0.0010059993,0.0004952896,0.0015888251,0.00034692904],"domain_scores_gemma":[0.99684197,0.0021196643,0.00013193836,0.00056885334,0.00023619483,0.00010136779],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054510557,0.00018426434,0.00040780843,0.0007623269,0.00006795343,0.00005551094,0.00034529486,0.00010371626,0.00004820182],"category_scores_gemma":[0.010492348,0.00016437264,0.00008969029,0.0016790298,0.00007475567,0.00093052397,0.00017143998,0.0002596431,0.000014071563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022451099,0.00010849999,0.23521264,0.000027580456,0.0000048058755,0.00018463978,0.0015901679,0.7592541,0.000009636747,0.000012535744,0.00035455296,0.0032183772],"study_design_scores_gemma":[0.00066521455,0.000047364938,0.2587697,0.0000832254,0.000010366755,0.000070832684,0.00019593397,0.73913395,0.00014735738,0.0001514614,0.0005274688,0.0001971343],"about_ca_topic_score_codex":0.00038918082,"about_ca_topic_score_gemma":0.00028440292,"teacher_disagreement_score":0.031360596,"about_ca_system_score_codex":0.0002724915,"about_ca_system_score_gemma":0.00022191186,"threshold_uncertainty_score":0.99784267},"labels":[],"label_agreement":null},{"id":"W1976355580","doi":"10.1007/s10115-011-0439-8","title":"Finding best evidence for evidence-based best practice recommendations in health care: the initial decision support system design","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Best practice; Medical prescription; Clinical decision support system; Decision support system; Harm; Health care; Quality (philosophy); eHealth; Evidence-based practice; Medicine; Risk analysis (engineering); Computer science; Data mining; Nursing; Psychology; Alternative medicine","score_opus":0.539744659034669,"score_gpt":0.4976609918738763,"score_spread":0.04208366716079265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976355580","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":[0.00045683808,0.004046795,0.9736748,0.0026020787,0.002696932,0.0037808493,0.00011380267,0.000060661983,0.0125672715],"genre_scores_gemma":[0.9879296,0.000609986,0.009169791,0.0010180823,0.00017237136,0.0007149783,0.00006680217,0.000011298208,0.00030710443],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99551815,0.0011935574,0.0019788905,0.0002883934,0.000723738,0.0002972798],"domain_scores_gemma":[0.9866272,0.010610133,0.001032666,0.0006218566,0.0009825462,0.00012559367],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021306742,0.00016788527,0.00032426917,0.0005301597,0.0006133903,0.00084466866,0.00068921724,0.00008535634,0.000029806963],"category_scores_gemma":[0.010161366,0.0001137103,0.00006559705,0.0008075533,0.00006141597,0.010797429,0.00016445635,0.00013567123,0.00077147345],"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":[0.0010049428,0.0002513301,0.0004499779,0.0021624637,0.000042759355,0.0000031010252,0.09895134,0.0006792665,0.000001981751,0.067830525,0.15898974,0.66963255],"study_design_scores_gemma":[0.00086473516,0.00083361927,0.00018328597,0.0036075711,0.00003859261,0.00002038893,0.13100518,0.018965557,0.000035843026,0.000088143555,0.8441218,0.00023527854],"about_ca_topic_score_codex":0.00055333367,"about_ca_topic_score_gemma":0.00015655845,"teacher_disagreement_score":0.9874728,"about_ca_system_score_codex":0.00029106246,"about_ca_system_score_gemma":0.0005215887,"threshold_uncertainty_score":0.99817646},"labels":[],"label_agreement":null},{"id":"W1977341443","doi":"10.1177/1460458205055685","title":"Managing hospital databases: can large hospitals really protect patient data?","year":2005,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Legislation; Directive; Compliance (psychology); Data Protection Act 1998; Business; Internet privacy; Database; Medicine; Computer security; Computer science; Political science; Law","score_opus":0.1516301388436691,"score_gpt":0.43200304840649456,"score_spread":0.28037290956282546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977341443","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":[0.04529782,0.0011879256,0.752306,0.16700715,0.004035919,0.0038812605,0.0064704246,0.0002668461,0.019546665],"genre_scores_gemma":[0.46353397,0.005596781,0.41837847,0.10602887,0.002338903,0.00009369665,0.0023564934,0.000110984394,0.0015618263],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99236864,0.00032066499,0.0033667595,0.00028879303,0.002728841,0.0009263091],"domain_scores_gemma":[0.9944811,0.00023648149,0.0022868041,0.0020525956,0.0003027021,0.0006403456],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.018060919,0.00023767856,0.00044713265,0.00047767546,0.0009665701,0.0011442291,0.0023823758,0.00004275145,0.00035372179],"category_scores_gemma":[0.0021177207,0.00017784904,0.00008404417,0.00054836,0.00006197156,0.004367833,0.0017037177,0.00062963937,0.00062198524],"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":[0.000014625819,0.0001491659,0.00031131483,0.00008675287,0.000032142383,0.000013718397,0.010083208,0.00026549998,8.829122e-8,0.0037648857,0.40857252,0.5767061],"study_design_scores_gemma":[0.0006309208,0.00034323457,0.0007869502,0.00013138032,0.000009521997,0.00008175224,0.015321452,0.01572694,0.0000036431584,0.0022261958,0.96448356,0.00025443354],"about_ca_topic_score_codex":0.000101523154,"about_ca_topic_score_gemma":0.00037776702,"teacher_disagreement_score":0.57645166,"about_ca_system_score_codex":0.00025801768,"about_ca_system_score_gemma":0.00056761334,"threshold_uncertainty_score":0.99989265},"labels":[],"label_agreement":null},{"id":"W1977628174","doi":"10.1071/ah080766","title":"A decade of data linkage in Western Australia: strategic design, applications and benefits of the WA data linkage system","year":2008,"lang":"en","type":"article","venue":"Australian Health Review","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":514,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Linkage (software); Population health; Health economics; Record linkage; Data quality; Public health; Population; Data science; Linked data; Medicine; Business; Computer science; Environmental health; Marketing; World Wide Web; Biology; Genetics","score_opus":0.7754379927253564,"score_gpt":0.5261300498695192,"score_spread":0.24930794285583724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977628174","genre_codex":"review","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":[0.14833617,0.5653355,0.028761944,0.15327628,0.0015888789,0.055192366,0.04566558,0.0003379705,0.0015052565],"genre_scores_gemma":[0.78720134,0.1968265,0.009770202,0.0024175635,0.0001339199,0.00019117931,0.0010006574,0.00003712253,0.0024215032],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99419856,0.001194782,0.0023350858,0.0009144199,0.0009827545,0.00037437337],"domain_scores_gemma":[0.992178,0.00062042265,0.0012367843,0.0056484845,0.0001216479,0.00019460854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011191545,0.00020675192,0.00091685745,0.0001305149,0.00014567921,0.00004676117,0.00485499,0.000092599155,0.00004618614],"category_scores_gemma":[0.00035201167,0.00013742552,0.000054808108,0.0013337658,0.00023089048,0.0006705398,0.0014930214,0.00028109155,0.00007047682],"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":[0.00008091778,0.0018526441,0.061815783,0.15092306,0.00033003138,0.000068994945,0.0022981598,0.00041833642,0.000041999392,0.07545147,0.35376018,0.35295844],"study_design_scores_gemma":[0.0017625975,0.00039019328,0.21387021,0.0371948,0.0003752561,0.00023970898,0.002161981,0.00041434047,0.00007773512,0.0017676137,0.7407639,0.0009816573],"about_ca_topic_score_codex":0.001089047,"about_ca_topic_score_gemma":0.0007821236,"teacher_disagreement_score":0.6388652,"about_ca_system_score_codex":0.000041072843,"about_ca_system_score_gemma":0.000277287,"threshold_uncertainty_score":0.90218604},"labels":[],"label_agreement":null},{"id":"W1980720057","doi":"10.1007/s00500-015-1632-6","title":"Feature-driven linguistic-based entity matching in linked data with application in pharmacy","year":2015,"lang":"en","type":"article","venue":"Soft Computing","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"SPARQL; Computer science; RDF; Process (computing); Linked data; Feature (linguistics); Information retrieval; Natural language; Hyperlink; Semantic Web; Natural language processing; World Wide Web; Web page; Linguistics; Programming language","score_opus":0.22022291767357507,"score_gpt":0.4482172416113033,"score_spread":0.2279943239377282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980720057","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":[0.23804845,0.000050869858,0.7575906,0.0019896482,0.0002952596,0.0004424506,0.00003132058,0.0000875313,0.0014638894],"genre_scores_gemma":[0.97152406,6.1752604e-7,0.027637275,0.00050583936,0.00012472695,0.0000036040396,0.00015216395,0.000008078481,0.000043655367],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977182,0.00025318403,0.00039466564,0.0006126977,0.00078279845,0.00023841215],"domain_scores_gemma":[0.9978746,0.0007168363,0.00022601344,0.00097011484,0.00012654284,0.00008586026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005968488,0.00011164254,0.00021213274,0.00024307554,0.0000709676,0.00026851395,0.0014271445,0.000029564086,0.0000044805347],"category_scores_gemma":[0.0021153186,0.00009297091,0.000016341417,0.0008113353,0.000042594067,0.0002885417,0.0007959922,0.00024530548,0.00008099962],"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":[0.00028270643,0.0006285178,0.44540486,0.0000983462,0.000027830616,0.00012446016,0.0069159064,0.1865946,0.00013092082,0.0065741013,0.01188755,0.3413302],"study_design_scores_gemma":[0.0017113672,0.000020051351,0.015328277,0.00009295221,0.000008677741,0.0000013152047,0.00078574684,0.90578735,0.00001934479,0.006132036,0.06990552,0.00020735047],"about_ca_topic_score_codex":0.0011927477,"about_ca_topic_score_gemma":0.0025721265,"teacher_disagreement_score":0.73347557,"about_ca_system_score_codex":0.00006997302,"about_ca_system_score_gemma":0.00012702399,"threshold_uncertainty_score":0.37912437},"labels":[],"label_agreement":null},{"id":"W1981001739","doi":"10.14778/1454159.1454200","title":"Semandaq","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Relational database; SQL; Quality (philosophy); Database; Data mining; User interface; Interface (matter); Data quality; Programming language; Engineering; Operating system; Metric (unit)","score_opus":0.19753170774097992,"score_gpt":0.36462387965471404,"score_spread":0.16709217191373413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981001739","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":[0.80068356,0.000118321805,0.00017972747,0.008735856,0.00062021887,0.0005853546,0.000023982971,0.000056114586,0.18899688],"genre_scores_gemma":[0.98654854,0.000048459333,0.0005943238,0.00061057153,0.00005098256,0.000018157654,4.494238e-7,0.0000051787465,0.012123348],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99758977,0.000012106426,0.00046608812,0.0002824942,0.001462681,0.00018688786],"domain_scores_gemma":[0.9990459,0.000106558204,0.0003029659,0.00027634916,0.00021190692,0.000056326575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017533688,0.00009620295,0.00018751732,0.000098011194,0.00019713928,0.000065729495,0.0014223708,0.000025135536,0.00020311882],"category_scores_gemma":[0.00086513394,0.000052640884,0.00013033643,0.0004938522,0.00016242663,0.0003044075,0.000753782,0.000075279604,0.00016661463],"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":[0.00006856683,0.00036302433,0.023082986,0.000051659805,0.00007718274,0.0000022745867,0.0046289642,0.000022125005,0.010050088,0.19339785,0.7510016,0.017253686],"study_design_scores_gemma":[0.0008672022,0.0001264121,0.032872606,0.000052078558,0.00003461584,0.000035094992,0.003185166,0.0001226683,0.09423654,0.11127891,0.756931,0.00025773153],"about_ca_topic_score_codex":0.000039089464,"about_ca_topic_score_gemma":0.0000035280275,"teacher_disagreement_score":0.18586498,"about_ca_system_score_codex":0.000028662422,"about_ca_system_score_gemma":0.000017523329,"threshold_uncertainty_score":0.26431423},"labels":[],"label_agreement":null},{"id":"W1981314985","doi":"10.1016/j.im.2010.04.001","title":"Governing the data commons: Policy, practice, and the advancement of science","year":2010,"lang":"en","type":"article","venue":"Information & Management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Space Agency; NASA Headquarters; Australian Government; Agência Espacial Brasileira; University of California Berkeley; National Aeronautics and Space Administration","keywords":"Data sharing; Commons; Intellectual property; Shared resource; Common-pool resource; Natural resource; Global commons; Political science; Knowledge management; Data science; Business; Computer science; Law; Economics; Computer security; Ecology","score_opus":0.08970413318049758,"score_gpt":0.43075133922144787,"score_spread":0.3410472060409503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981314985","genre_codex":"other","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":[0.0049502887,0.00012845265,0.21805203,0.23931247,0.0017251826,0.0030460123,0.00031764444,0.00007309528,0.5323948],"genre_scores_gemma":[0.96757764,0.0007443005,0.01344069,0.01593252,0.00010511924,0.0000898644,0.00009124499,0.000006331207,0.0020122875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965949,0.0001303776,0.0007425785,0.00020021663,0.0021385087,0.00019344165],"domain_scores_gemma":[0.99555516,0.0010472497,0.00072837685,0.0023709973,0.00025146097,0.000046769594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021404136,0.00008896119,0.00012529086,0.00025050066,0.0005854513,0.00088734244,0.0033870135,0.000014500077,0.00005693461],"category_scores_gemma":[0.005547191,0.00004390222,0.000023082433,0.0010658904,0.0014861374,0.0063956995,0.004368827,0.00013585534,0.00018626383],"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":[0.00003113966,0.000014489596,0.000011613517,0.000010285364,0.00001555993,1.6046556e-7,0.0012167281,0.00008035578,0.0000020423163,0.64736664,0.008298015,0.34295297],"study_design_scores_gemma":[0.00057988137,0.000009930513,0.0028832904,0.0000069590233,0.000024888994,0.0000022792847,0.013658107,0.005456223,0.000010121242,0.008337206,0.9689741,0.000057009445],"about_ca_topic_score_codex":0.00027433105,"about_ca_topic_score_gemma":0.00010517654,"teacher_disagreement_score":0.96262735,"about_ca_system_score_codex":0.000022845978,"about_ca_system_score_gemma":0.000056092304,"threshold_uncertainty_score":0.85566634},"labels":[],"label_agreement":null},{"id":"W1981578383","doi":"10.14778/2536336.2536345","title":"Discovering linkage points over web data","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":41,"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 Toronto","funders":"","keywords":"Computer science; Schema matching; Schema (genetic algorithms); Data integration; Information retrieval; Data mining; Linked data; Linkage (software); Star schema; Database schema; Semi-structured model; Semantic Web; Database design","score_opus":0.1633565029719125,"score_gpt":0.3784563459656941,"score_spread":0.2150998429937816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981578383","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":[0.9129798,0.00011415341,0.00022802861,0.016537564,0.0009450997,0.0013378053,0.00024175725,0.00006987094,0.06754591],"genre_scores_gemma":[0.99342567,0.000044397417,0.0012500599,0.00085167494,0.000091476584,0.000033784854,0.000006921232,0.000010999965,0.004285006],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969058,0.000018836261,0.0006434542,0.000578454,0.0015704246,0.00028303842],"domain_scores_gemma":[0.99807376,0.00017455778,0.00043601185,0.0010589286,0.0001717631,0.00008495867],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028414004,0.00014930883,0.00024101562,0.00011189501,0.00012964274,0.0005334381,0.0043639434,0.00003589757,0.0010719707],"category_scores_gemma":[0.0016988288,0.000083659,0.0000911408,0.000453439,0.00011373502,0.0018153233,0.0054029427,0.00013048263,0.00046066876],"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":[0.000027637863,0.00034791208,0.017461369,0.00012628308,0.00012641019,6.487209e-7,0.0012085491,0.000013935286,0.028694225,0.07321998,0.84908104,0.029692033],"study_design_scores_gemma":[0.0017917813,0.00013344384,0.08077819,0.0003077345,0.000113078524,0.0000070881465,0.0062133013,0.006896957,0.033514403,0.21411501,0.6554526,0.0006764249],"about_ca_topic_score_codex":0.0002499803,"about_ca_topic_score_gemma":0.000018090554,"teacher_disagreement_score":0.19362843,"about_ca_system_score_codex":0.00003873338,"about_ca_system_score_gemma":0.000021513402,"threshold_uncertainty_score":0.9998412},"labels":[],"label_agreement":null},{"id":"W1983388548","doi":"10.1007/s10844-012-0229-0","title":"Reducing the size of databases for multirelational classification: a subgraph-based approach","year":2012,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"Computer science; Database; Preprocessor; Tuple; Data mining; Relational database; Data pre-processing; Schema (genetic algorithms); Machine learning; Artificial intelligence","score_opus":0.34538316626348664,"score_gpt":0.421210654523675,"score_spread":0.07582748826018837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983388548","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":[0.0047327443,0.00030647553,0.98887,0.00052447786,0.0013137079,0.0005585077,0.0001499434,0.000006727926,0.0035374186],"genre_scores_gemma":[0.9915719,0.000017450931,0.007707572,0.0001888686,0.00023011566,0.000025640824,0.00005932944,0.000003561495,0.00019558503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956981,0.00024151847,0.00234426,0.00006725924,0.0014978255,0.00015102919],"domain_scores_gemma":[0.992221,0.0030663568,0.002870416,0.00041780266,0.0013395748,0.000084873194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013156024,0.000094640134,0.0002560618,0.0003467634,0.00013948398,0.0001988294,0.0006326823,0.00003812372,0.000042195927],"category_scores_gemma":[0.0046564457,0.000053007632,0.00020094537,0.00047308308,0.000074880314,0.0028021247,0.000045583394,0.000107734144,0.00003717053],"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":[0.000794917,0.0008729892,0.010609151,0.0007332234,0.0004101403,2.2888443e-7,0.014401121,0.12661026,0.00026216588,0.5515664,0.19968154,0.09405785],"study_design_scores_gemma":[0.00056976423,0.00009542419,0.0051645995,0.00013321367,0.000059611986,0.000029083407,0.035247166,0.09476523,0.00078980013,0.00018846306,0.86281705,0.00014060496],"about_ca_topic_score_codex":0.000017612634,"about_ca_topic_score_gemma":5.469178e-7,"teacher_disagreement_score":0.9868391,"about_ca_system_score_codex":0.00005522048,"about_ca_system_score_gemma":0.00010039443,"threshold_uncertainty_score":0.55745363},"labels":[],"label_agreement":null},{"id":"W1983762395","doi":"10.2196/medinform.3463","title":"A Fuzzy-Match Search Engine for Physician Directories","year":2014,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Information retrieval; Fuzzy logic; Search engine; World Wide Web; MEDLINE; Medicine; Data mining; Artificial intelligence","score_opus":0.09893618723598034,"score_gpt":0.43024273842163446,"score_spread":0.3313065511856541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983762395","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":[0.065153815,0.00003556772,0.7266001,0.0135717895,0.0019714287,0.0017690423,0.00020820556,0.0003763071,0.19031376],"genre_scores_gemma":[0.914926,0.000054121105,0.03773922,0.03503064,0.002072518,0.00051896524,0.00036399296,0.000045699235,0.009248845],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958769,0.000095890326,0.00087351684,0.00013533545,0.0026654368,0.0003528971],"domain_scores_gemma":[0.99693197,0.0018081525,0.00015205173,0.00061440165,0.00020599259,0.0002874276],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061332667,0.00012393369,0.00031000155,0.00013866683,0.00014364818,0.00027926537,0.0010885935,0.00009735837,0.00019937484],"category_scores_gemma":[0.003308474,0.00008356714,0.00010103038,0.00045373852,0.00016733188,0.0006008944,0.00035941633,0.00017791755,0.00079715264],"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":[0.000019174904,0.00009027945,0.000041041745,0.00013830906,0.000020766329,5.613589e-7,0.0059533482,0.000021193915,0.0000017223018,0.09019348,0.23651801,0.66700214],"study_design_scores_gemma":[0.00049109093,0.0001042042,0.00019677705,0.000036375015,0.0000063320845,8.8358894e-7,0.0044184076,0.03526323,0.00007952768,0.027646583,0.9316184,0.00013818957],"about_ca_topic_score_codex":0.0000089666855,"about_ca_topic_score_gemma":0.000016731254,"teacher_disagreement_score":0.8497722,"about_ca_system_score_codex":0.000022285867,"about_ca_system_score_gemma":0.00006910286,"threshold_uncertainty_score":0.99998087},"labels":[],"label_agreement":null},{"id":"W1983996307","doi":"10.1109/cscwd.2014.6846921","title":"A study of intents resolving for service discovery","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Computer science; Matching (statistics); Service discovery; Service (business); Similarity (geometry); Information retrieval; Order (exchange); Data science; Empirical research; World Wide Web; Web service; Data mining; Artificial intelligence","score_opus":0.3462392937357613,"score_gpt":0.4645175144537989,"score_spread":0.11827822071803762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983996307","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":[0.81974846,0.000002615025,0.15837972,0.0010434041,0.00026632403,0.0005070897,0.000015041705,0.000018096582,0.020019231],"genre_scores_gemma":[0.99276096,2.8686276e-7,0.0010168555,0.0010706699,0.000019650295,0.000015096079,0.0000024439253,0.0000026739838,0.00511136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986141,0.00011593874,0.0003780634,0.00023421767,0.00056176295,0.00009592442],"domain_scores_gemma":[0.99822414,0.0008925064,0.00011570491,0.0005765266,0.00016562833,0.000025519425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036451505,0.000047298752,0.0001461986,0.00008755907,0.000048295413,0.00015166478,0.0006622177,0.000011576621,0.00003795523],"category_scores_gemma":[0.0019684813,0.000030107245,0.00003295972,0.00026663978,0.000010961928,0.00045367514,0.00040290237,0.000020015907,0.00005629373],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044672829,0.0046564196,0.045142453,0.00017430897,0.00023159447,0.0000024794533,0.01876217,0.0004612927,0.00084543444,0.47641775,0.24903572,0.20382364],"study_design_scores_gemma":[0.005109062,0.002146114,0.18960053,0.00006720512,0.00009687089,8.3422384e-7,0.2516675,0.011807788,0.00086410047,0.20494917,0.3331741,0.0005167101],"about_ca_topic_score_codex":0.00033960034,"about_ca_topic_score_gemma":0.002166057,"teacher_disagreement_score":0.2714686,"about_ca_system_score_codex":0.0000048018323,"about_ca_system_score_gemma":0.0000052273863,"threshold_uncertainty_score":0.23565984},"labels":[],"label_agreement":null},{"id":"W1985538849","doi":"10.1109/memea.2008.4543004","title":"Discrimination of Inconsistencies in Medical Data","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Children's Hospital of Eastern Ontario; University of Ottawa; Carleton University","funders":"Philips Research Americas","keywords":"Missing data; Computer science; Outlier; Data mining; Data quality; Data cleansing; Process (computing); Information retrieval; Artificial intelligence; Machine learning","score_opus":0.6116560649423984,"score_gpt":0.49962681511967716,"score_spread":0.11202924982272128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985538849","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":[0.62915444,0.00013625232,0.05546907,0.023859315,0.00047036106,0.00026912364,0.00013793272,0.000041569117,0.2904619],"genre_scores_gemma":[0.9958519,0.000047471385,0.0014037482,0.0004632483,0.000009027663,9.926677e-7,0.000035790326,9.338423e-7,0.0021868865],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99781877,0.00011052615,0.00042033003,0.00020162751,0.0013831861,0.00006555542],"domain_scores_gemma":[0.99849427,0.0005567271,0.00006411552,0.000801966,0.00004827828,0.000034653178],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004196137,0.000030365341,0.00010923638,0.00014071332,0.000024354418,0.000013568662,0.0012231037,0.000022878312,0.0012484536],"category_scores_gemma":[0.006709791,0.000019492634,0.00001252693,0.00033413785,0.00015717914,0.00046800842,0.00087965885,0.00003464988,0.00009214336],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024166404,0.0004891369,0.045826763,0.000023654855,0.000012067745,0.00008374666,0.0027765082,0.000008566329,0.00003807342,0.2610331,0.39163947,0.29804474],"study_design_scores_gemma":[0.0009186105,0.00006955918,0.6609612,0.00005071244,0.000008618238,0.000025230787,0.016549809,0.014453065,0.00035107983,0.05908579,0.2473063,0.00022002697],"about_ca_topic_score_codex":0.0004191354,"about_ca_topic_score_gemma":0.0035869111,"teacher_disagreement_score":0.6151344,"about_ca_system_score_codex":0.0000053787376,"about_ca_system_score_gemma":0.000054923465,"threshold_uncertainty_score":0.99966455},"labels":[],"label_agreement":null},{"id":"W1990694685","doi":"10.1145/1297797.1297800","title":"Does data warehouse end-user metadata add value?","year":2007,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Data warehouse; Metadata; Computer science; Database; End user; Value (mathematics); World Wide Web; Information retrieval","score_opus":0.4898806212217548,"score_gpt":0.5030314624550921,"score_spread":0.013150841233337318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990694685","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02064089,0.0042183422,0.044079244,0.8524115,0.003032072,0.002296597,0.009884409,0.00034322296,0.06309373],"genre_scores_gemma":[0.57289827,0.0006698898,0.40759763,0.0030237888,0.00006787528,0.000013532171,0.0006333737,0.00002323521,0.015072401],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973907,0.0005527745,0.000691496,0.00032063687,0.0008739588,0.0001704609],"domain_scores_gemma":[0.8104434,0.0045685107,0.0003973545,0.1843593,0.00017400974,0.000057430763],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.012372264,0.00008931744,0.00018385539,0.00012112264,0.00036319566,0.00019830499,0.16723262,0.000036103367,0.00019253684],"category_scores_gemma":[0.076019704,0.000042164756,0.00007643873,0.0006967728,0.00046727233,0.0011725761,0.16919145,0.00017131213,0.00016789668],"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":[0.000012208527,0.00022374201,0.0017086348,0.0000052522746,0.00007176839,2.4701384e-7,0.00038968786,0.00001360265,0.000116506235,0.13565423,0.83581156,0.025992585],"study_design_scores_gemma":[0.0001020118,0.000004825934,0.010104536,0.000011096884,0.00003950725,4.625304e-7,0.001032366,0.00008278502,0.00047207554,0.16760802,0.82047707,0.00006526078],"about_ca_topic_score_codex":0.00042502227,"about_ca_topic_score_gemma":0.0029680184,"teacher_disagreement_score":0.8493877,"about_ca_system_score_codex":0.000016549231,"about_ca_system_score_gemma":0.00004566884,"threshold_uncertainty_score":0.93176335},"labels":[],"label_agreement":null},{"id":"W1991083901","doi":"10.1007/s10606-008-9084-5","title":"alt.metadata.health: Ontological Context for Data Use and Integration","year":2008,"lang":"en","type":"article","venue":"Computer Supported Cooperative Work (CSCW)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Metadata; Computer science; Ontology; Context (archaeology); Data science; Data mapping; Data element; Set (abstract data type); Information retrieval; Data integration; Metadata modeling; Data integrity; World Wide Web; Data mining; Database","score_opus":0.5920331447390127,"score_gpt":0.4446306491918988,"score_spread":0.14740249554711388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991083901","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":[0.022920368,0.00030642233,0.96851206,0.005447398,0.00069085235,0.0011067479,0.00080023945,0.00008815899,0.00012775365],"genre_scores_gemma":[0.86204374,0.0003414114,0.10599232,0.018221464,0.000392591,0.00010463415,0.0065050456,0.000030919462,0.006367881],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959172,0.0007214309,0.0010227043,0.0012588653,0.00066018093,0.00041962546],"domain_scores_gemma":[0.9950802,0.0020873684,0.00032250173,0.0017063686,0.0005455146,0.00025810022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028738745,0.0002831766,0.0006507941,0.00017822666,0.0006194716,0.0010112209,0.0014944794,0.000082171755,0.0002436421],"category_scores_gemma":[0.0016959287,0.00019967431,0.000060443916,0.0006392428,0.0003596776,0.0028598236,0.0011886869,0.00022324255,0.000115865754],"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":[0.00014996855,0.00018723258,0.0014995688,0.0000050757963,0.00006385181,0.000025814594,0.00085153594,0.000019589033,0.00000515825,0.012990098,0.71445686,0.26974526],"study_design_scores_gemma":[0.0016342761,0.0010226348,0.026337499,0.000054755707,0.00002863861,0.000042911714,0.0005904135,0.031906314,0.000040400286,0.0010302142,0.93686223,0.00044972147],"about_ca_topic_score_codex":0.00016432238,"about_ca_topic_score_gemma":0.00077347714,"teacher_disagreement_score":0.86251974,"about_ca_system_score_codex":0.00004051493,"about_ca_system_score_gemma":0.00018240043,"threshold_uncertainty_score":0.9751226},"labels":[],"label_agreement":null},{"id":"W1993783004","doi":"10.1145/1645953.1646084","title":"A framework for semantic link discovery over relational data","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":56,"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 Toronto","funders":"","keywords":"Computer science; Linked data; Semantic Web; Relational database management system; Relational database; RDF; Information retrieval; Data quality; World Wide Web; Data science; Service (business)","score_opus":0.3959281110422866,"score_gpt":0.4899961649284179,"score_spread":0.09406805388613132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993783004","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":[0.0011472433,0.000031753483,0.9637723,0.025486607,0.00029275796,0.00021477543,0.00025665923,0.000032383854,0.008765528],"genre_scores_gemma":[0.5874631,0.000027369113,0.3261697,0.025066439,0.0008687258,0.00001155691,0.0009340988,0.000011257951,0.059447765],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99808097,0.00005121288,0.0003901205,0.00048944,0.0008276506,0.00016060389],"domain_scores_gemma":[0.9963285,0.0018902947,0.000100647056,0.0015827509,0.000050123548,0.000047728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027415322,0.00007459992,0.00013459957,0.0000864745,0.00011016177,0.00048226354,0.0012305198,0.000055521603,0.00071862416],"category_scores_gemma":[0.0045542857,0.00005076234,0.000053632513,0.00027971048,0.000030322935,0.0017723747,0.00038352102,0.0000779505,0.0003748024],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015324784,0.00003250711,0.00016118005,0.0000014219925,0.00000653385,6.9747176e-7,0.000028449651,0.000022094468,0.0000024401293,0.75916904,0.20261098,0.03794933],"study_design_scores_gemma":[0.000111536974,0.000026077927,0.014492789,0.000007683417,0.0000074988757,3.0047119e-7,0.000068326095,0.0049453834,0.000003702738,0.62439877,0.35587308,0.000064852655],"about_ca_topic_score_codex":0.000010873232,"about_ca_topic_score_gemma":0.000025814667,"teacher_disagreement_score":0.63760257,"about_ca_system_score_codex":0.000009560903,"about_ca_system_score_gemma":0.00002995115,"threshold_uncertainty_score":0.786843},"labels":[],"label_agreement":null},{"id":"W1994031640","doi":"10.4018/jdm.2014070102","title":"Improving Business Intelligence Traceability and Accountability","year":2014,"lang":"en","type":"article","venue":"Journal of Database Management","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 Ottawa","funders":"","keywords":"Traceability; Computer science; Metadata; Business intelligence; Process management; Data warehouse; Workflow; Accountability; Product (mathematics); Quality (philosophy); Knowledge management; Business process; Database; Software engineering; World Wide Web; Business; Work in process","score_opus":0.10957770867008844,"score_gpt":0.3884190335479261,"score_spread":0.2788413248778377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994031640","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":[0.14667988,0.00015486096,0.84568185,0.0025000314,0.00094538135,0.00037603805,0.000070730326,0.000029126822,0.0035621254],"genre_scores_gemma":[0.95544636,0.00018430119,0.04303103,0.0007860169,0.00019220937,0.0000052175237,0.0000111148065,0.000010709807,0.0003330544],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99603903,0.00041104128,0.0013093776,0.00045477672,0.0015498786,0.0002358861],"domain_scores_gemma":[0.9965592,0.0008032754,0.00079912896,0.001176413,0.00049864844,0.00016335999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021552838,0.00016107711,0.00037153045,0.000340422,0.00013245156,0.00044555758,0.0011720627,0.000029414168,0.00022116472],"category_scores_gemma":[0.0033965898,0.00011405692,0.000085382955,0.00065591704,0.00016420096,0.001557543,0.0011652249,0.0001818435,0.000051075964],"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":[0.00014509678,0.00021172657,0.0027087869,0.00027555117,0.00006446382,0.000027206419,0.00021466753,0.00014058506,0.000091929294,0.02040938,0.009962345,0.96574825],"study_design_scores_gemma":[0.001811005,0.0004320727,0.20322688,0.0002780348,0.00040910018,0.000083384024,0.011990298,0.016655035,0.00048554398,0.07750356,0.68626165,0.00086344715],"about_ca_topic_score_codex":0.00009011503,"about_ca_topic_score_gemma":0.00006709343,"teacher_disagreement_score":0.9648848,"about_ca_system_score_codex":0.000057773632,"about_ca_system_score_gemma":0.000022154543,"threshold_uncertainty_score":0.7469827},"labels":[],"label_agreement":null},{"id":"W1994820452","doi":"10.1109/i2ct.2014.7092302","title":"An effective way of mining knowledge from heterogeneous data sources","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Trinity College","funders":"","keywords":"Computer science; Data science; Association rule learning; Medical knowledge; Medical information; Knowledge extraction; Knowledge management; Big data; Data mining; Medicine","score_opus":0.19365702921052286,"score_gpt":0.43583604375056156,"score_spread":0.2421790145400387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994820452","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":[0.9011099,0.00008597158,0.08063776,0.000081389895,0.00025940474,0.00014429867,0.00020137226,0.000041377276,0.01743856],"genre_scores_gemma":[0.99551237,0.0000020511357,0.0034802984,0.0001742886,0.00009029166,0.000003544358,0.00010697046,0.0000053480217,0.0006248327],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977864,0.0005952082,0.0003915261,0.0005818107,0.00050449144,0.00014057501],"domain_scores_gemma":[0.994916,0.0025357325,0.00014878734,0.0022332259,0.00008173584,0.000084483894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004176054,0.000092555274,0.0002461142,0.00010220829,0.0000709965,0.00016541309,0.0023009137,0.000035680387,0.0006969022],"category_scores_gemma":[0.0015873715,0.00006242502,0.000036801925,0.00019142314,0.00008966673,0.0004974459,0.0010486642,0.000036998772,0.00047033836],"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":[0.00003105271,0.00021967299,0.0033937872,0.000007616899,0.000053682867,0.0000014883278,0.0028888835,0.00011556358,0.00067095313,0.0029428331,0.01708718,0.9725873],"study_design_scores_gemma":[0.0014641532,0.0009399201,0.0759043,0.00006415442,0.00011991911,0.0000024557391,0.011668872,0.13160539,0.028697334,0.03432557,0.714486,0.00072195265],"about_ca_topic_score_codex":0.00036030423,"about_ca_topic_score_gemma":0.0014790087,"teacher_disagreement_score":0.97186536,"about_ca_system_score_codex":0.0000061744613,"about_ca_system_score_gemma":0.0000068465924,"threshold_uncertainty_score":0.7630591},"labels":[],"label_agreement":null},{"id":"W1995541812","doi":"10.1007/s00778-009-0161-2","title":"Creating probabilistic databases from duplicated data","year":2009,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Probabilistic logic; Data mining; Scalability; Data deduplication; Task (project management); Cluster analysis; Database; String (physics); Probabilistic database; Information retrieval; Machine learning; Artificial intelligence; Database theory; Relational database","score_opus":0.47988074415434634,"score_gpt":0.47707972753851563,"score_spread":0.0028010166158307093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995541812","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":[0.5293232,0.0024235547,0.29970905,0.11263835,0.0023009914,0.0012078404,0.0038811231,0.000291307,0.048224542],"genre_scores_gemma":[0.9837586,0.00013517753,0.008627635,0.0044257157,0.0009578771,0.0000020623975,0.00033766124,0.00001003771,0.0017452181],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972023,0.000427707,0.00063121796,0.00036957616,0.0011368819,0.00023231217],"domain_scores_gemma":[0.99543417,0.0015396734,0.00036138826,0.0024319235,0.000117250085,0.00011561006],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0078893,0.00010474284,0.00018366906,0.00008003911,0.00054754975,0.0008991892,0.003927862,0.000017288223,0.0011956808],"category_scores_gemma":[0.0072119026,0.000053632048,0.000042746473,0.00040196124,0.000089754525,0.0009507232,0.0007711769,0.0002714593,0.0005578696],"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":[0.0000921679,0.00023965357,0.0005343524,0.0000019410327,0.00006524661,0.000058830145,0.0007895941,0.00035886202,0.00069943623,0.0189341,0.53608024,0.44214556],"study_design_scores_gemma":[0.000629178,0.00009594285,0.03953699,0.00007246639,0.000114039925,0.0001060638,0.002344685,0.013276628,0.00012037296,0.34037748,0.6030555,0.0002706689],"about_ca_topic_score_codex":0.00014816517,"about_ca_topic_score_gemma":0.000065203116,"teacher_disagreement_score":0.45443538,"about_ca_system_score_codex":0.000020064817,"about_ca_system_score_gemma":0.000058346992,"threshold_uncertainty_score":0.99971735},"labels":[],"label_agreement":null},{"id":"W2001097309","doi":"10.1007/s11306-014-0679-1","title":"The New Data Quality Task Group (DQTG): ensuring high quality data today and in the future","year":2014,"lang":"en","type":"article","venue":"Metabolomics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Quality (philosophy); Data quality; Task group; Computer science; Data science; Engineering; Engineering management; Operations management; Systems engineering","score_opus":0.2365783400962979,"score_gpt":0.4281732937617395,"score_spread":0.1915949536654416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001097309","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":[0.63389516,0.010479287,0.14895874,0.1854521,0.0074459077,0.002118344,0.006430616,0.0001859827,0.0050338698],"genre_scores_gemma":[0.96639556,0.0031889116,0.013116358,0.010693426,0.002392593,0.000018368304,0.0021503516,0.00003552944,0.0020088782],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912782,0.0042125513,0.0012671462,0.0012472,0.001557089,0.00043782245],"domain_scores_gemma":[0.9820487,0.0063760746,0.0005140736,0.010871205,0.000061825274,0.00012814364],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.074203104,0.0002161104,0.000472101,0.00007174359,0.00047125632,0.0012338388,0.009708341,0.00009414936,0.000036870082],"category_scores_gemma":[0.008234529,0.00011010796,0.000043888882,0.0005210606,0.00023125617,0.001241699,0.005670693,0.00037455812,0.00008611348],"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":[0.000109493754,0.00009573157,0.0024087639,0.000015253264,0.00004519248,0.000001828419,0.00088512735,0.000012620139,0.00007372749,0.4029745,0.16544876,0.42792904],"study_design_scores_gemma":[0.0003990231,0.000008890173,0.13190933,0.0000031322186,0.000025779715,0.0000012438453,0.0027042744,0.0005595759,0.0000067373717,0.053727083,0.8105027,0.00015224646],"about_ca_topic_score_codex":0.0016678575,"about_ca_topic_score_gemma":0.011089764,"teacher_disagreement_score":0.6450539,"about_ca_system_score_codex":0.00001386651,"about_ca_system_score_gemma":0.000050033465,"threshold_uncertainty_score":0.99980295},"labels":[],"label_agreement":null},{"id":"W2004002671","doi":"10.4018/jhdri.2010070104","title":"Record Linkage in Healthcare","year":2010,"lang":"en","type":"article","venue":"International Journal of Healthcare Delivery Reform Initiatives","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Record linkage; Confidentiality; Linkage (software); Computer science; Medical record; Health care; Probabilistic logic; Data science; Key (lock); Computer security; Medicine; Artificial intelligence","score_opus":0.12382062607717054,"score_gpt":0.44941090360488933,"score_spread":0.3255902775277188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004002671","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":[0.85242635,0.00029949928,0.0006625613,0.13131446,0.008129831,0.00023342199,0.00024015065,0.000021869522,0.0066718766],"genre_scores_gemma":[0.99138653,0.000999028,0.0021216788,0.004705441,0.0006462964,0.000005012659,0.00002039731,0.000011785102,0.00010381253],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9946568,0.00044709205,0.0020163555,0.0003125813,0.0022609953,0.00030615897],"domain_scores_gemma":[0.9946729,0.00073604606,0.0013309901,0.00037310275,0.0026477275,0.00023922662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005409049,0.00017157907,0.00042217236,0.0013363918,0.00008981009,0.00022720956,0.0019021963,0.00013904921,0.0002557885],"category_scores_gemma":[0.0019592184,0.00012467062,0.00019881397,0.0004921084,0.00012088867,0.0021101744,0.0002985102,0.0010734411,0.00010743982],"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":[0.0010115693,0.0004808132,0.06908372,0.000056298213,0.00017227819,0.0013615189,0.0045801685,0.000017065127,0.0002929822,0.14306138,0.002500637,0.77738154],"study_design_scores_gemma":[0.0035732305,0.0013863398,0.4489692,0.0005932699,0.000016822833,0.0007560139,0.019114053,0.00041285128,0.0008328885,0.18384007,0.3398072,0.000698068],"about_ca_topic_score_codex":0.0027398383,"about_ca_topic_score_gemma":0.010034726,"teacher_disagreement_score":0.7766835,"about_ca_system_score_codex":0.00033673336,"about_ca_system_score_gemma":0.00041810833,"threshold_uncertainty_score":0.55996126},"labels":[],"label_agreement":null},{"id":"W2008481019","doi":"10.1145/1107499.1107509","title":"In memoriam Alberto Oscar Mendelzon","year":2005,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","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":"TD Bank Group","funders":"","keywords":"Tribute; Battle; Friendship; Computer science; Intellect; Art history; Art; History; Ancient history; Theology; Philosophy; Sociology","score_opus":0.16446583863983466,"score_gpt":0.4286982494735129,"score_spread":0.26423241083367827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008481019","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":[0.5237374,0.0004581445,0.013273696,0.15876247,0.016922496,0.0015316092,0.00008343689,0.0002719222,0.28495887],"genre_scores_gemma":[0.8595002,0.00019660035,0.027527913,0.011340105,0.0024609314,0.00008043199,0.000027038945,0.00003744171,0.09882929],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972386,0.00023834435,0.00068518944,0.0005895479,0.00091052207,0.0003378247],"domain_scores_gemma":[0.9969689,0.0010784346,0.00014816877,0.0016385588,0.00006128623,0.00010459941],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0032842155,0.00014297321,0.00027783867,0.00030521664,0.000070037386,0.00017470265,0.001866507,0.00007488275,0.002879581],"category_scores_gemma":[0.003424542,0.00011259849,0.00008851728,0.00065866724,0.00004482466,0.0009826097,0.0007641051,0.00014754558,0.003971934],"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":[0.000035687724,0.00010968984,0.0008977993,0.0000028553186,0.000010210921,0.0000117112,0.00046291156,0.0000607022,0.000076066346,0.005448979,0.5537364,0.43914703],"study_design_scores_gemma":[0.00039308664,0.00004822501,0.001051275,0.000006660832,0.0000053719505,0.0000017678811,0.00039772035,0.0005730619,0.00025355245,0.05977349,0.9373393,0.00015650145],"about_ca_topic_score_codex":0.0005045992,"about_ca_topic_score_gemma":0.0047735707,"teacher_disagreement_score":0.4389905,"about_ca_system_score_codex":0.000072871364,"about_ca_system_score_gemma":0.000029102654,"threshold_uncertainty_score":0.9980319},"labels":[],"label_agreement":null},{"id":"W2008641248","doi":"10.1109/icde.2010.5447744","title":"ProbClean: A probabilistic duplicate detection system","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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; Probabilistic logic; Data mining; Set (abstract data type); Space (punctuation); Relational database; Quality (philosophy); Artificial intelligence","score_opus":0.10251911695511381,"score_gpt":0.372236251015045,"score_spread":0.26971713405993114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008641248","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":[0.39513916,0.000006061144,0.32507938,0.0025697276,0.0028219768,0.0016544308,0.0000221602,0.0008303019,0.27187678],"genre_scores_gemma":[0.99091446,2.0083422e-7,0.0018327124,0.00015374107,0.000074751966,0.000053837866,0.0000017605382,0.0000048800043,0.006963645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982737,0.00008247811,0.00039535048,0.00040569092,0.00068004924,0.00016276326],"domain_scores_gemma":[0.9985832,0.00019627472,0.00011075744,0.0008894062,0.0001370471,0.00008333563],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0034800228,0.000077357945,0.00012665345,0.00011357803,0.00012896949,0.00033474565,0.0006113428,0.000046315374,0.00041532365],"category_scores_gemma":[0.0012140111,0.000050030198,0.00005080325,0.0004038777,0.00006207287,0.0002814915,0.00019762808,0.00012337453,0.0037309579],"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":[0.000028799406,0.00011255759,0.00019282318,0.000060533548,0.000013477452,0.0000055916244,0.000195773,0.000034908255,0.012707148,0.7522672,0.012514991,0.2218662],"study_design_scores_gemma":[0.0006028905,0.0001581756,0.010080044,0.00001787881,0.00003403493,0.00004669331,0.0029731344,0.03889312,0.010122979,0.08181336,0.85478705,0.0004706466],"about_ca_topic_score_codex":0.00008791895,"about_ca_topic_score_gemma":0.0010439538,"teacher_disagreement_score":0.84227204,"about_ca_system_score_codex":0.000018261318,"about_ca_system_score_gemma":0.000014964021,"threshold_uncertainty_score":0.99704474},"labels":[],"label_agreement":null},{"id":"W2009189347","doi":"10.1002/bult.2006.1720320605","title":"The IA of potentiality: Toward a grounded theory of information architecture philosophy, theory and research","year":2006,"lang":"en","type":"article","venue":"Bulletin of the American Society for Information Science and Technology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Conversation; Grounded theory; Sociology; Epistemology; Participant observation; Architecture; Qualitative research; Philosophy; Social science; Communication","score_opus":0.05059845871226172,"score_gpt":0.3659003217522842,"score_spread":0.3153018630400225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009189347","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":[0.69467276,0.00035437875,0.12620297,0.15631634,0.00030703822,0.0027933493,0.000392073,0.000092030685,0.01886904],"genre_scores_gemma":[0.9967711,0.00008803549,0.002424525,0.0006061521,0.000008917599,0.00002541899,0.000003369372,0.0000017738404,0.000070694034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972818,0.00018603182,0.0007559904,0.00013576826,0.0014072484,0.00023316315],"domain_scores_gemma":[0.9954308,0.0016250567,0.0010172694,0.00059083884,0.001312225,0.000023778437],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0242948,0.00008029295,0.00022081613,0.0003539414,0.0005775709,0.00013997371,0.0013986977,0.000051715313,0.00000514669],"category_scores_gemma":[0.0050451756,0.000043647306,0.00011088152,0.002328279,0.011858113,0.00048302222,0.0009078297,0.00015205824,0.000003076944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008257401,0.000011710853,0.000064260304,0.00003587827,0.000013075119,5.2303695e-9,0.0011572503,0.000008930818,0.00022362806,0.8068772,0.0042835777,0.18724191],"study_design_scores_gemma":[0.0002547705,0.0001601761,0.0029326535,0.000016063397,0.000012015882,0.000002877173,0.03385049,0.000079681195,0.0020491688,0.782415,0.17816664,0.000060505827],"about_ca_topic_score_codex":0.00015268022,"about_ca_topic_score_gemma":0.000003352772,"teacher_disagreement_score":0.30209833,"about_ca_system_score_codex":0.000023698356,"about_ca_system_score_gemma":0.000120405835,"threshold_uncertainty_score":0.990831},"labels":[],"label_agreement":null},{"id":"W2009382242","doi":"10.1109/cloud.2013.131","title":"Toward an Ecosystem for Precision Sharing of Segmented Big Data","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Big data; Analytics; Raw data; Data science; Data analysis; Data sharing; Set (abstract data type); Data mining","score_opus":0.6475747092139017,"score_gpt":0.4630136464326516,"score_spread":0.18456106278125012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009382242","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":[0.16989669,0.000026701546,0.8134658,0.0013781369,0.0010492986,0.0016633571,0.0008824405,0.00008301462,0.011554589],"genre_scores_gemma":[0.97775656,0.0000065929585,0.016084883,0.00024393777,0.00009789532,0.00004155552,0.00029374516,0.00000837237,0.0054664733],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976634,0.00008271272,0.00070234295,0.0006129495,0.0007690372,0.00016958185],"domain_scores_gemma":[0.9965521,0.00050907145,0.0002012971,0.0024176198,0.00022983,0.000090042726],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004984676,0.000083240826,0.00022089179,0.00015383383,0.00005705225,0.0003430873,0.0029188453,0.00003482476,0.00091784436],"category_scores_gemma":[0.0011864211,0.00005434474,0.000041321186,0.00025450677,0.000016871028,0.0014234675,0.0016929966,0.000028490527,0.00038630638],"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":[0.00003488833,0.00018262802,0.0005591132,0.0000634983,0.00003497561,4.3232802e-7,0.00037826027,0.00003868332,0.00083271234,0.0125814425,0.2080717,0.7772217],"study_design_scores_gemma":[0.0016420402,0.00045871557,0.004731274,0.0000979585,0.00004367683,0.0000022822912,0.013811735,0.26700848,0.004538349,0.08165314,0.6255627,0.00044960514],"about_ca_topic_score_codex":0.00031997263,"about_ca_topic_score_gemma":0.00047300378,"teacher_disagreement_score":0.80785984,"about_ca_system_score_codex":0.000011852313,"about_ca_system_score_gemma":0.000016345577,"threshold_uncertainty_score":0.99999547},"labels":[],"label_agreement":null},{"id":"W2011133830","doi":"10.1145/1871437.1871786","title":"Exploring and visualizing academic social networks","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Alberta","funders":"","keywords":"Computer science; Visibility; Visualization; World Wide Web; Set (abstract data type); Citation; Social network (sociolinguistics); Social network analysis; Data science; Data visualization; Information retrieval; Data mining; Social media","score_opus":0.6616171706478876,"score_gpt":0.501443923905629,"score_spread":0.16017324674225863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011133830","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":[0.92103773,0.000027949336,0.04932717,0.003493411,0.0013030674,0.00011067166,0.000002658218,0.00009971573,0.024597641],"genre_scores_gemma":[0.9967341,0.000043971544,0.00060568843,0.0009830304,0.00036565267,0.000008373555,0.000001572767,0.0000040904574,0.0012535288],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99878615,0.000058192843,0.00027148647,0.00025835345,0.00045419435,0.00017161873],"domain_scores_gemma":[0.9993021,0.00035580902,0.00006190025,0.00018471255,0.000031386367,0.00006410292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032946393,0.00005748492,0.00010638871,0.000083688494,0.00020589589,0.00022141454,0.00037050294,0.000051910203,0.00029842247],"category_scores_gemma":[0.00050731486,0.00004452716,0.000026324933,0.00022708157,0.00007219282,0.00083647616,0.00040151377,0.00027698514,0.00012333841],"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":[0.000005805662,0.000008849179,0.0011724797,0.00000178565,0.000005606091,0.0000015806778,0.0008716846,0.0000064518276,0.0004688299,0.37339744,0.021171745,0.60288775],"study_design_scores_gemma":[0.00034504288,0.00002183166,0.062085666,0.000005366893,0.000011991174,0.000003356792,0.006576077,0.0074646072,0.0002980824,0.045976233,0.87691754,0.0002942195],"about_ca_topic_score_codex":0.00003024585,"about_ca_topic_score_gemma":0.00008014908,"teacher_disagreement_score":0.8557458,"about_ca_system_score_codex":0.0000030749836,"about_ca_system_score_gemma":0.000005269253,"threshold_uncertainty_score":0.32675168},"labels":[],"label_agreement":null},{"id":"W2012837162","doi":"10.1109/icde.2012.105","title":"Discovering Conservation Rules","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"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":"Intersection (aeronautics); Computer science; Class (philosophy); Data mining; Conservation law; Semantics (computer science); Process (computing); Quality (philosophy); Theoretical computer science; Artificial intelligence; Mathematics; Programming language","score_opus":0.3414115313259976,"score_gpt":0.4537697560876122,"score_spread":0.11235822476161461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012837162","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":[0.5865699,0.000047309717,0.15462448,0.0051302384,0.00061904953,0.00009100068,0.000014271888,0.00005500708,0.25284877],"genre_scores_gemma":[0.98104066,0.000003275052,0.0029723726,0.0019820945,0.00006541291,0.0000027371573,0.000007677089,0.0000016404581,0.013924162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991579,0.000048265167,0.00017316082,0.00008965639,0.00041690347,0.00011408045],"domain_scores_gemma":[0.99938434,0.00024825791,0.00004057178,0.00026098517,0.0000227089,0.00004311451],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002154581,0.000031452786,0.000052633728,0.000045434048,0.000049604725,0.00014472495,0.00021575823,0.000010436287,0.001300917],"category_scores_gemma":[0.0006255246,0.00002022979,0.000020651683,0.00011521634,0.000020538555,0.0010579195,0.00014815052,0.0000174282,0.0028695893],"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":[0.0000029836444,0.00003543079,0.033696376,0.0000016877441,0.000004121704,1.7750439e-7,0.0003533746,0.0000043880286,0.00007506909,0.7630816,0.16441979,0.038324997],"study_design_scores_gemma":[0.000055167857,0.000004019498,0.113770366,0.0000013830675,0.0000020177254,3.7035653e-7,0.0013071211,0.00019892644,0.00026192717,0.020899605,0.8634484,0.00005069317],"about_ca_topic_score_codex":0.000114501534,"about_ca_topic_score_gemma":0.000047563226,"teacher_disagreement_score":0.742182,"about_ca_system_score_codex":0.000006728778,"about_ca_system_score_gemma":0.0000039164347,"threshold_uncertainty_score":0.99961203},"labels":[],"label_agreement":null},{"id":"W2013003292","doi":"10.1590/s0034-89102003000100014","title":"Probabilistic linkage in household survey on hospital care usage","year":2003,"lang":"en","type":"article","venue":"Revista de Saúde Pública","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Record linkage; Database; Concordance; Medical record; Medicine; Hospital admission; Hospital care; Probabilistic logic; Linkage (software); Health care; Medical emergency; Environmental health; Computer science; Population","score_opus":0.1401548010313884,"score_gpt":0.3720897732461387,"score_spread":0.2319349722147503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013003292","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":[0.91627693,0.0011340551,0.002487873,0.0018558505,0.0005441604,0.0020111003,0.0012294386,0.00020436897,0.074256234],"genre_scores_gemma":[0.9974131,0.00006317125,0.00042547728,0.0007527034,0.000039860504,0.000034613,0.00007180496,0.000021592114,0.001177692],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953391,0.0015989674,0.00075778255,0.0007826076,0.0010382828,0.00048325196],"domain_scores_gemma":[0.9964379,0.0015912058,0.00019922853,0.0014483937,0.00013846428,0.00018478377],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008289467,0.00021687675,0.00041346505,0.00032080797,0.00011363963,0.0006988159,0.0010222107,0.000101861035,0.00028343473],"category_scores_gemma":[0.01580713,0.00017673304,0.00011832173,0.0012624725,0.00010155711,0.00022456337,0.00018052518,0.00028220413,0.0005375841],"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":[0.00013125986,0.0015430962,0.13098054,0.00034191462,0.000055783956,0.0002875018,0.0037423794,0.0008078396,0.000043416876,0.581089,0.21681403,0.06416322],"study_design_scores_gemma":[0.00043423337,0.00017540649,0.22555175,0.00007852004,0.00000957724,0.0000014445997,0.0003968404,0.00003755087,0.000028367025,0.0032151416,0.7697567,0.00031445705],"about_ca_topic_score_codex":0.0001990831,"about_ca_topic_score_gemma":0.00028564924,"teacher_disagreement_score":0.5778739,"about_ca_system_score_codex":0.0002046524,"about_ca_system_score_gemma":0.00012577558,"threshold_uncertainty_score":0.99248314},"labels":[],"label_agreement":null},{"id":"W2016901333","doi":"10.1145/2479440.2482677","title":"Issues in big data testing and benchmarking","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Institute of Innovation and Technology; University of Toronto; Deutsche Forschungsgemeinschaft; International Business Machines Corporation","keywords":"Benchmarking; Computer science; Big data; Scalability; Data science; Relational database; Data modeling; Data management; Database; Massively parallel; Volume (thermodynamics); Data mining; Parallel computing","score_opus":0.6107454406852676,"score_gpt":0.4649125596602122,"score_spread":0.14583288102505537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016901333","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":[0.6598023,0.00052243646,0.015774773,0.0216204,0.0010115396,0.00078319514,0.000046809782,0.0001267301,0.30031177],"genre_scores_gemma":[0.9498727,0.00003197428,0.041193046,0.0014898034,0.00016359956,0.0000068334575,0.000017226424,0.0000038855533,0.007220962],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99880284,0.00007428546,0.00027567794,0.0003498731,0.0003736639,0.0001236881],"domain_scores_gemma":[0.99789536,0.0011703444,0.000047822792,0.0008078864,0.000039850653,0.000038749808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031941237,0.00004695758,0.00009509349,0.00011853122,0.00004558514,0.00050879794,0.0007695333,0.000015078151,0.0006588392],"category_scores_gemma":[0.0042341314,0.00003154753,0.000004367981,0.00037624157,0.000036328933,0.0008166657,0.0014880081,0.000039762082,0.0003838026],"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":[3.5281533e-7,0.0000111151685,0.031668562,0.0000023105115,0.0000012388667,0.0000015455092,0.00009276077,0.0000018674374,0.000031486972,0.0014768596,0.07933876,0.88737315],"study_design_scores_gemma":[0.0002582163,0.000036020592,0.4342675,0.000034063487,0.000003501518,0.0000023492892,0.0038574864,0.037570506,0.000032372274,0.11654043,0.4071856,0.00021194712],"about_ca_topic_score_codex":0.005389053,"about_ca_topic_score_gemma":0.0013037607,"teacher_disagreement_score":0.8871612,"about_ca_system_score_codex":0.0000035282496,"about_ca_system_score_gemma":0.000006883172,"threshold_uncertainty_score":0.8146672},"labels":[],"label_agreement":null},{"id":"W2017217509","doi":"10.1007/s10115-011-0397-1","title":"Scalable clustering methods for the name disambiguation problem","year":2011,"lang":"en","type":"article","venue":"Knowledge and Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Illinois at Urbana-Champaign; University of British Columbia; Advanced Digital Sciences Center; Pennsylvania State University; National Science Foundation","keywords":"Cluster analysis; Computer science; Scalability; Artificial intelligence; Natural language processing; Entity linking; Data mining; Database","score_opus":0.22575786155557567,"score_gpt":0.43212848195334813,"score_spread":0.20637062039777246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017217509","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":[0.00012937761,0.000703313,0.90046537,0.00013182373,0.0007820256,0.00079595624,0.00001585072,0.00003346075,0.09694281],"genre_scores_gemma":[0.9021753,0.0004080944,0.0719536,0.0008394708,0.00045901418,0.0016313,0.00013387321,0.000024234669,0.022375083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986074,0.0001951491,0.0007045777,0.00012115891,0.00023139805,0.00014029424],"domain_scores_gemma":[0.9983549,0.00066864403,0.00026701315,0.00034204163,0.0003204006,0.000047007983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008740007,0.00008212918,0.00014915277,0.00013020082,0.00030244596,0.000546005,0.00035219773,0.000043261236,0.000042697156],"category_scores_gemma":[0.00058292464,0.00004699517,0.000042760585,0.00025244823,0.000042807915,0.0032755341,0.00017210074,0.000041907344,0.00037130123],"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":[0.000020388208,0.00001623201,0.00008231983,0.00013298626,0.000021040254,1.5692297e-8,0.015726142,0.000055867484,0.0000044098892,0.097619966,0.02069665,0.865624],"study_design_scores_gemma":[0.00021545541,0.000033797,0.00068207143,0.000021841912,0.000011635265,0.0000018658945,0.005581904,0.12435448,0.000035411224,0.0022609758,0.8667283,0.00007222288],"about_ca_topic_score_codex":0.00008203866,"about_ca_topic_score_gemma":0.000021590738,"teacher_disagreement_score":0.90204597,"about_ca_system_score_codex":0.000019809855,"about_ca_system_score_gemma":0.000019895027,"threshold_uncertainty_score":0.5265139},"labels":[],"label_agreement":null},{"id":"W2020414220","doi":"10.1016/j.hcmf.2011.03.003","title":"Client Satisfaction in Support of Service Planning within a Regulatory Framework: Experience of a Research Hospital","year":2011,"lang":"en","type":"article","venue":"Healthcare Management Forum","topic":"Data Quality and Management","field":"Decision Sciences","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":"University Health Network","funders":"","keywords":"Process management; Business; Stakeholder; Knowledge management; Service (business); Service quality; Key (lock); Process (computing); Computer science; Marketing; Public relations","score_opus":0.3511880478145705,"score_gpt":0.49749740769748396,"score_spread":0.14630935988291344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020414220","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":[0.9777408,0.00011338148,0.003903004,0.007385983,0.0008958958,0.0014617649,0.000042805736,0.000047245852,0.008409075],"genre_scores_gemma":[0.9930823,0.00003046061,0.005235229,0.0012514844,0.000013643472,0.00010220726,0.000008536372,0.000012593771,0.00026358047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99427366,0.00051014783,0.0014560551,0.0006731932,0.0024866625,0.0006002833],"domain_scores_gemma":[0.9973171,0.0002785683,0.0005573167,0.001316299,0.00039653617,0.00013421898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008407628,0.00015199809,0.00037306285,0.0010417026,0.00013465529,0.0000421536,0.00096463354,0.000112596186,0.00026006234],"category_scores_gemma":[0.00039945618,0.00013799542,0.00006809125,0.0020784177,0.00019853878,0.0004887325,0.0010853633,0.0003168127,0.000058257614],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003181236,0.00041582782,0.37356,0.00085881795,0.00004172765,0.00007410387,0.07820514,0.000090359776,0.000009009448,0.50275445,0.010764734,0.03290771],"study_design_scores_gemma":[0.00048309175,0.0006696148,0.6718845,0.00049745187,0.000008461051,0.0000014115835,0.21357009,0.00019322816,0.0004093271,0.10415972,0.0078886105,0.00023450793],"about_ca_topic_score_codex":0.0049929465,"about_ca_topic_score_gemma":0.0023324077,"teacher_disagreement_score":0.3985947,"about_ca_system_score_codex":0.000111866895,"about_ca_system_score_gemma":0.000062642095,"threshold_uncertainty_score":0.75478745},"labels":[],"label_agreement":null},{"id":"W2021255304","doi":"10.1007/s00778-013-0316-z","title":"Sampling from repairs of conditional functional dependency violations","year":2013,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Dependency (UML); Functional dependency; Data mining; Sampling (signal processing); Class (philosophy); Space (punctuation); Variety (cybernetics); Semantics (computer science); Artificial intelligence; Relational database; Programming language","score_opus":0.30258014556785606,"score_gpt":0.4077661213846789,"score_spread":0.10518597581682282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021255304","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":[0.5255728,0.00014875627,0.45826215,0.008137734,0.0011281417,0.00018448102,0.00020223566,0.000023685832,0.0063400534],"genre_scores_gemma":[0.9938018,0.000017909788,0.0042364188,0.00052212935,0.00035565748,0.000005609836,0.000034731307,0.0000040329514,0.0010217244],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976121,0.00023751272,0.0006314425,0.00014891579,0.0012398835,0.00013014345],"domain_scores_gemma":[0.9973035,0.001510576,0.00038332923,0.00035796437,0.0003674103,0.00007721853],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002777442,0.00006720267,0.00012663219,0.00013036036,0.0004084485,0.00027681302,0.0006001603,0.000028753566,0.019987103],"category_scores_gemma":[0.0011682183,0.00003846421,0.00012279763,0.00023071459,0.00010497769,0.0006429749,0.00014097407,0.00020341852,0.0010577996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010342408,0.00038714407,0.027957793,0.000005219534,0.00046604552,0.00000876316,0.0019606177,0.010501975,0.005718399,0.19865547,0.65474266,0.09949247],"study_design_scores_gemma":[0.00019170891,0.000018501014,0.24179137,0.000009104972,0.000017470886,0.00002413864,0.0014654264,0.001197145,0.00005459741,0.7391202,0.016055167,0.0000551596],"about_ca_topic_score_codex":0.00013953717,"about_ca_topic_score_gemma":0.000030045974,"teacher_disagreement_score":0.6386875,"about_ca_system_score_codex":0.000021683234,"about_ca_system_score_gemma":0.00006853491,"threshold_uncertainty_score":0.99972},"labels":[],"label_agreement":null},{"id":"W2022686325","doi":"10.1016/j.procs.2014.08.023","title":"A Model for Privacy Compromisation Value","year":2014,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 Calgary; University of Ottawa","funders":"","keywords":"Computer science; Incentive; Compromise; Information privacy; Internet privacy; Population; Value (mathematics); Computer security; Private information retrieval; Data science; Machine learning","score_opus":0.22143880321785245,"score_gpt":0.4101181923389419,"score_spread":0.18867938912108947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022686325","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":[0.019053826,0.0000038730054,0.9767417,0.0024661345,0.0005376428,0.00040767825,0.0000062691806,0.00007143765,0.00071149424],"genre_scores_gemma":[0.69924325,7.78058e-7,0.29829413,0.0019047777,0.00016130866,0.000038251645,0.0000031765906,0.0000044107655,0.00034991748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703306,0.00004750047,0.00040427138,0.0007714827,0.0014109687,0.00033274267],"domain_scores_gemma":[0.997974,0.000530107,0.0001740159,0.0007303382,0.0004474795,0.00014409474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008460421,0.000106448424,0.00016758303,0.00025163594,0.0003691959,0.0008117093,0.002381926,0.000024432464,0.000005794628],"category_scores_gemma":[0.0021124766,0.00008158852,0.000054379554,0.00084100786,0.0002804192,0.0012096327,0.0007489479,0.000051967214,0.000117559255],"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":[0.000017021252,0.0001036274,0.00030590483,0.000030737487,0.0000034598752,1.5420581e-7,0.0029271105,0.032913145,0.00047977408,0.5491084,0.022697574,0.39141312],"study_design_scores_gemma":[0.00020002286,0.00004993537,0.00090195844,0.0000054625557,0.0000024717572,8.350967e-7,0.000009940074,0.7973325,0.00018875385,0.18490057,0.016309798,0.000097712036],"about_ca_topic_score_codex":0.0000040851196,"about_ca_topic_score_gemma":0.0000034478217,"teacher_disagreement_score":0.7644194,"about_ca_system_score_codex":0.000035801422,"about_ca_system_score_gemma":0.0001575163,"threshold_uncertainty_score":0.7827332},"labels":[],"label_agreement":null},{"id":"W2024895566","doi":"10.1007/s11704-012-2007-0","title":"Matching dependencies: semantics and query answering","year":2012,"lang":"en","type":"article","venue":"Frontiers of Computer Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Tuple; Matching (statistics); Enforcement; Semantics (computer science); Invariant (physics); Generalization; Similarity (geometry); Theoretical computer science; Data mining; Information retrieval; Artificial intelligence; Programming language; Mathematics; Discrete mathematics","score_opus":0.07187203828515723,"score_gpt":0.34902872659215306,"score_spread":0.2771566883069958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024895566","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":[0.2919268,0.0002459003,0.7055417,0.00023546466,0.0015642216,0.0000588976,0.0000030961753,0.000016919714,0.00040700342],"genre_scores_gemma":[0.7942444,0.000013722075,0.20535985,0.00022857352,0.00006921591,7.371461e-7,3.2429355e-7,0.0000025759812,0.000080627586],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99754375,0.00006174669,0.0003671115,0.00033281927,0.0013362089,0.00035835628],"domain_scores_gemma":[0.9988367,0.00015282257,0.00017257773,0.00054427964,0.00012092328,0.00017269474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063816346,0.000091131136,0.0002035295,0.00033035717,0.00021075607,0.00033082737,0.0012441068,0.000023260392,0.000006664223],"category_scores_gemma":[0.00017963647,0.000072319286,0.000036303132,0.00068000995,0.00054260227,0.0023518235,0.001023608,0.00006744971,0.000016195916],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029581975,0.00028819987,0.16137588,0.000086113105,0.00005499959,0.000010752713,0.030376127,0.0017934985,0.0023943828,0.16305457,0.09733484,0.543201],"study_design_scores_gemma":[0.0011764314,0.00034998875,0.45228928,0.00018264,0.00007217751,0.00008403595,0.020613609,0.15711424,0.0100000715,0.16065781,0.19581966,0.0016400698],"about_ca_topic_score_codex":0.000047290323,"about_ca_topic_score_gemma":0.0000059787376,"teacher_disagreement_score":0.541561,"about_ca_system_score_codex":0.000020751228,"about_ca_system_score_gemma":0.000044285058,"threshold_uncertainty_score":0.31901762},"labels":[],"label_agreement":null},{"id":"W2025146961","doi":"10.1177/1460458207086333","title":"A method to map heterogeneity between near but non-equivalent semantic attributes in multiple health data registries","year":2008,"lang":"en","type":"article","venue":"Health Informatics Journal","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; Ontology; Metadata; Web Ontology Language; Information retrieval; Semantics (computer science); Semantic integration; Context (archaeology); Semantic heterogeneity; XML; Semantic Web; RDF; OWL-S; Data mapping; Ontology-based data integration; World Wide Web; Database; Semantic Web Stack; Geography; Programming language","score_opus":0.5805209750176058,"score_gpt":0.517028038760856,"score_spread":0.06349293625674979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025146961","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":[0.08260667,0.00027368887,0.8782081,0.036044218,0.0004999718,0.00091255124,0.0013231805,0.000037770733,0.00009383233],"genre_scores_gemma":[0.1537776,0.0011514793,0.8190784,0.024566013,0.00044828965,0.000018140214,0.0005600941,0.000032368214,0.00036762047],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904206,0.0009918628,0.0046832445,0.0003690876,0.0024490654,0.0010861384],"domain_scores_gemma":[0.993178,0.0015898201,0.0020668556,0.0018301917,0.00025441105,0.0010806986],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.037072223,0.00026283984,0.0009744582,0.00058778416,0.0013949805,0.0006745294,0.0027071116,0.00007901942,0.00004571578],"category_scores_gemma":[0.0033388953,0.00021024642,0.00010342487,0.00096720987,0.00012814824,0.0018651803,0.0016908922,0.00066337164,0.00052089104],"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":[0.00010933552,0.00023060678,0.07973348,0.0006543227,0.00008067769,0.000051285086,0.022380168,0.0028975294,7.896894e-7,0.00019595007,0.6621439,0.23152196],"study_design_scores_gemma":[0.0017856307,0.0006484824,0.07454975,0.0004570854,0.000010748083,0.00033327888,0.007995414,0.03273613,0.00002560164,0.0012587947,0.8797702,0.00042885396],"about_ca_topic_score_codex":0.0008243402,"about_ca_topic_score_gemma":0.0006816855,"teacher_disagreement_score":0.23109311,"about_ca_system_score_codex":0.0003891742,"about_ca_system_score_gemma":0.0015153292,"threshold_uncertainty_score":0.99990505},"labels":[],"label_agreement":null},{"id":"W20259189","doi":"10.3233/978-1-61499-488-6-170","title":"Using Business Intelligence for Efficient Inter-Facility Patient Transfer","year":2015,"lang":"en","type":"article","venue":"Studies in health technology and informatics","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":"University of Northern British Columbia","funders":"","keywords":"Online analytical processing; Computer science; Data warehouse; Visualization; Context (archaeology); Data cube; Business intelligence; Consistency (knowledge bases); Transfer (computing); Web application; Database; Data science; Data mining; World Wide Web; Artificial intelligence","score_opus":0.501093311015246,"score_gpt":0.5101973292725414,"score_spread":0.009104018257295343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W20259189","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":[0.28618082,0.0016957195,0.7053315,0.0044663004,0.0009506572,0.0009702321,0.000091491005,0.00006691241,0.00024638773],"genre_scores_gemma":[0.9818923,0.00042765803,0.016419014,0.0011610469,0.0000081191765,0.00006332644,0.00000558681,0.00000312442,0.000019843454],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99762315,0.00006928434,0.0014817887,0.0001808587,0.00032504124,0.00031989568],"domain_scores_gemma":[0.9985152,0.0003700681,0.00018431421,0.00039086342,0.0004756738,0.00006391911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048858686,0.00012446953,0.00039561288,0.00061109994,0.00019620126,0.000033213153,0.00035293875,0.00008820406,0.0000024078408],"category_scores_gemma":[0.0044604153,0.00009107799,0.000022887441,0.001255816,0.000584794,0.00021858783,0.00045868728,0.00014909037,0.000011049014],"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":[0.00013578605,0.00018959594,0.0026803687,0.0011474164,0.00004724727,0.0000019382653,0.054959238,0.0075135734,4.3100547e-7,0.093826704,0.0037416962,0.835756],"study_design_scores_gemma":[0.0009811522,0.0009200427,0.00032643267,0.0003444581,0.000012910993,0.000020635143,0.5212037,0.08546568,0.000106949425,0.1558239,0.23437591,0.00041824082],"about_ca_topic_score_codex":0.00002502717,"about_ca_topic_score_gemma":0.00007189474,"teacher_disagreement_score":0.83533776,"about_ca_system_score_codex":0.00013539377,"about_ca_system_score_gemma":0.00009809172,"threshold_uncertainty_score":0.53398556},"labels":[],"label_agreement":null},{"id":"W2031616148","doi":"10.1109/oceans.2012.6404783","title":"Beyond data management: How to foster data exploitation and better science?","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ocean Networks Canada Society","funders":"Canarie; Consortium for Ocean Leadership","keywords":"Computer science; Sampling (signal processing); Data logger; Scientific instrument; Remote sensing; Data management; Bandwidth (computing); Data science; Data mining; Telecommunications; Geology","score_opus":0.42389306397412346,"score_gpt":0.4529110742181073,"score_spread":0.029018010243983816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2031616148","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":[0.06350266,0.00025088512,0.4227424,0.19364811,0.003115506,0.0019164796,0.001524642,0.00018307165,0.31311622],"genre_scores_gemma":[0.7792154,0.00004011339,0.15101339,0.044493478,0.00040775933,0.00002495329,0.00080553256,0.000019167615,0.023980223],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99662846,0.000084560954,0.00028491887,0.00096194894,0.001635678,0.00040442435],"domain_scores_gemma":[0.9945679,0.00023368452,0.000077226796,0.0047940593,0.00007155934,0.00025562363],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011908376,0.00010957152,0.000131805,0.00040507843,0.00023616744,0.001553161,0.0050088377,0.000019732248,0.00045424222],"category_scores_gemma":[0.0009583456,0.000077310826,0.000009143654,0.0009118578,0.00018200852,0.011180082,0.014935163,0.00004562614,0.0009992453],"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":[0.000004587705,0.000034163873,0.0010935215,0.0000058561536,0.000009323274,0.0000011166412,0.00046598676,1.7880758e-7,0.000044470547,0.018534632,0.6927195,0.28708664],"study_design_scores_gemma":[0.00019571664,0.000017689958,0.016677804,0.0000057313005,0.000024504167,0.0000016951752,0.006345693,0.00057312654,0.00007329212,0.009858892,0.96604973,0.0001761217],"about_ca_topic_score_codex":0.000010875644,"about_ca_topic_score_gemma":0.000059816724,"teacher_disagreement_score":0.7157127,"about_ca_system_score_codex":0.000013611281,"about_ca_system_score_gemma":0.000010500516,"threshold_uncertainty_score":0.99977857},"labels":[],"label_agreement":null},{"id":"W2032024758","doi":"10.1007/s10994-013-5421-0","title":"Tracking people over time in 19th century Canada for longitudinal analysis","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; University of Guelph","funders":"Ontario Ministry of Research and Innovation; Research and Innovation Foundation","keywords":"Tracking (education); Late 19th century; Longitudinal data; Artificial intelligence; Computer science; Psychology; Data mining; Period (music); Art","score_opus":0.04624489143412698,"score_gpt":0.3420139273379866,"score_spread":0.2957690359038596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032024758","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":[0.9798911,0.00016074124,0.014231311,0.002454866,0.00019215788,0.00040874394,0.000058833815,0.0000412942,0.0025609056],"genre_scores_gemma":[0.9935564,0.0000046891023,0.00044448717,0.0003050841,0.00003867074,0.000010280273,0.0001176236,0.00000844991,0.005514347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978137,0.00020658325,0.00046430784,0.0004415689,0.0007535646,0.0003202565],"domain_scores_gemma":[0.9984389,0.00087399624,0.00018037113,0.00034214812,0.00008274517,0.000081842496],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0022162306,0.00012141717,0.00033537994,0.0003631206,0.00017290622,0.00034815786,0.00047123374,0.000030243293,0.0046446114],"category_scores_gemma":[0.0015959325,0.00009785692,0.00011637765,0.0012873982,0.00001427187,0.00038792545,0.00018682974,0.00017098815,0.00013464951],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017683387,0.000046343856,0.8881738,0.000012691732,0.00013640751,0.00000740321,0.0007724999,0.031050388,0.000038726354,0.00045263657,0.018180063,0.061111312],"study_design_scores_gemma":[0.000270056,0.00001981184,0.6950224,0.0000049249843,0.000053914286,4.3515456e-7,0.00048290123,0.21019818,0.0000045463894,0.00044050007,0.09335497,0.00014734015],"about_ca_topic_score_codex":0.6159591,"about_ca_topic_score_gemma":0.87547034,"teacher_disagreement_score":0.25951126,"about_ca_system_score_codex":0.0000889328,"about_ca_system_score_gemma":0.00005553258,"threshold_uncertainty_score":0.9962653},"labels":[],"label_agreement":null},{"id":"W2032227143","doi":"10.4018/jissc.2010092905","title":"Managing Demographic Data Inconsistencies in Healthcare Information Systems","year":2010,"lang":"en","type":"article","venue":"International Journal of Information Systems and Social Change","topic":"Data Quality and Management","field":"Decision Sciences","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":"Agfa-Gevaert (Canada); Athabasca University","funders":"","keywords":"Computer science; Workflow; XML; Disparate system; Information system; Data exchange; RDF; DICOM; Data science; Database; Health informatics; Information retrieval; Health care; Data mining; World Wide Web; Semantic Web","score_opus":0.20577542931885426,"score_gpt":0.40513484979588366,"score_spread":0.1993594204770294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032227143","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":[0.7677383,0.0019555364,0.0430753,0.105558425,0.061599318,0.003029677,0.0036515296,0.0001335345,0.013258378],"genre_scores_gemma":[0.9980678,0.00014245605,0.00009651431,0.0009879932,0.000527184,0.000010449241,0.00014764938,0.000002442307,0.000017519105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99623066,0.000155003,0.0016711266,0.00008619592,0.0017167157,0.00014028321],"domain_scores_gemma":[0.9967255,0.0001884063,0.0015168501,0.0002293798,0.0012715764,0.00006830882],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0070648515,0.0000997614,0.0002654,0.0012481656,0.00013319864,0.0014989256,0.0011641213,0.000096949225,0.0000064546884],"category_scores_gemma":[0.00057497656,0.00007916032,0.00005091328,0.00032156656,0.00006172548,0.012263563,0.00035002927,0.00027810907,0.000029545075],"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":[0.00018925357,0.00006790308,0.04393106,0.0003918777,0.00021334899,0.000025565176,0.055967975,0.00012028603,0.00001103409,0.5679294,0.015939169,0.31521314],"study_design_scores_gemma":[0.0013345141,0.00006426538,0.072722316,0.00020066273,0.000016381833,0.0002133487,0.06235934,0.0113290595,0.0000011410363,0.0028172862,0.8486859,0.000255768],"about_ca_topic_score_codex":0.0020436947,"about_ca_topic_score_gemma":0.000549312,"teacher_disagreement_score":0.83274674,"about_ca_system_score_codex":0.000053970303,"about_ca_system_score_gemma":0.00006513627,"threshold_uncertainty_score":0.9995376},"labels":[],"label_agreement":null},{"id":"W2035477134","doi":"10.1109/icdew.2014.6818333","title":"Extending contexts with ontologies for multidimensional data quality assessment","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Datalog; Context (archaeology); Quality (philosophy); Data quality; Information retrieval; Quality assessment; Database; Data mining; Data science; Evaluation methods","score_opus":0.5683286373405844,"score_gpt":0.5618813134575109,"score_spread":0.0064473238830734525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035477134","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":[0.008955861,0.000019576913,0.9712498,0.004178452,0.00027913667,0.00040852424,0.00021723153,0.000080952384,0.014610419],"genre_scores_gemma":[0.65363675,0.0000031340894,0.33737832,0.001920053,0.00006326204,0.000037575523,0.00027229934,0.000007887712,0.006680711],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967972,0.00039208453,0.000578275,0.00079223706,0.0011822266,0.00025798762],"domain_scores_gemma":[0.9921551,0.0052242777,0.0002445107,0.002073246,0.00021774248,0.000085130036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014341266,0.00012879411,0.00031574082,0.00008727279,0.00022116007,0.00021406179,0.0013017083,0.00003582987,0.00031068223],"category_scores_gemma":[0.0042593013,0.000073242976,0.00004308298,0.00014576955,0.00012354522,0.00076732406,0.00093837664,0.0000651654,0.00008536131],"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":[0.00007262002,0.00010629249,0.0023837944,0.000010059508,0.000031239924,8.0994755e-7,0.000042469095,0.000037931197,0.00006813222,0.743808,0.083280265,0.17015845],"study_design_scores_gemma":[0.0013051345,0.00020308289,0.07789071,0.000015296073,0.000020836254,0.0000017357523,0.0019349316,0.016142847,0.00009358924,0.031437807,0.87069243,0.00026162385],"about_ca_topic_score_codex":0.00019058002,"about_ca_topic_score_gemma":0.0015217831,"teacher_disagreement_score":0.78741217,"about_ca_system_score_codex":0.000023947356,"about_ca_system_score_gemma":0.000049295802,"threshold_uncertainty_score":0.5099089},"labels":[],"label_agreement":null},{"id":"W2037754936","doi":"10.1353/cja.2005.0055","title":"Data Quality in an Information-Rich Environment: Canada as an Example","year":2005,"lang":"en","type":"review","venue":"Canadian Journal on Aging / La Revue canadienne du vieillissement","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":195,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University of Manitoba; Health Sciences Centre; Manitoba Health","funders":"","keywords":"Quality (philosophy); Information quality; Data quality; Computer science; Data science; Business; Information system; Political science; Marketing; Epistemology","score_opus":0.1882385821084955,"score_gpt":0.3704396366493099,"score_spread":0.1822010545408144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037754936","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005239685,0.95378023,0.0004687307,0.0074152336,0.005406608,0.00340063,0.015964264,0.00005747528,0.008267138],"genre_scores_gemma":[0.0022166036,0.97696596,0.0006304301,0.008181433,0.0014503783,0.00012283798,0.008630581,0.00014715518,0.0016545998],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898202,0.00243897,0.003597216,0.0013837384,0.0011631586,0.0015967523],"domain_scores_gemma":[0.98817307,0.00091551093,0.0018077714,0.004450489,0.00022054826,0.0044325935],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016862826,0.0008124957,0.001879552,0.002020986,0.00078105653,0.0022975171,0.006939394,0.00026907836,0.0030217587],"category_scores_gemma":[0.0019050231,0.00073153095,0.00019732471,0.0010776577,0.00013118531,0.0033163254,0.00036723504,0.0013388416,0.0003185508],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0000033581503,0.000046411555,0.00010346428,0.00036244144,0.00007482643,0.000738115,0.001608482,0.0003500085,8.648719e-9,0.0058150156,0.03073278,0.9601651],"study_design_scores_gemma":[0.00029175857,0.00009220463,0.00042033827,0.0014978967,0.000115585826,0.00020270911,0.0026213375,0.000090617126,2.5429049e-8,0.0003440287,0.9934805,0.00084300264],"about_ca_topic_score_codex":0.95322365,"about_ca_topic_score_gemma":0.9995926,"teacher_disagreement_score":0.9627477,"about_ca_system_score_codex":0.006449316,"about_ca_system_score_gemma":0.009417726,"threshold_uncertainty_score":0.99951357},"labels":[],"label_agreement":null},{"id":"W2039548475","doi":"10.1145/2588555.2610520","title":"Descriptive and prescriptive data cleaning","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":53,"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; Tuple; Scalability; Data mining; Transformation (genetics); Decoupling (probability); Quality (philosophy); Benchmark (surveying); Data quality; Data source; Database; Engineering","score_opus":0.48782631250696074,"score_gpt":0.44451026631315627,"score_spread":0.04331604619380447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039548475","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":[0.025750106,0.000062655454,0.59661716,0.0029013874,0.00047748565,0.00025238527,0.00009862877,0.00010409964,0.37373608],"genre_scores_gemma":[0.970157,0.000012175939,0.013312605,0.0019754155,0.00007141922,0.0000026991927,0.000028258224,0.0000055191676,0.014434887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982441,0.0002332444,0.00026021298,0.00054647727,0.00056829397,0.00014764942],"domain_scores_gemma":[0.99788094,0.0005983422,0.00007419627,0.0012967032,0.00006885793,0.000080962505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050642896,0.000072383365,0.00013421524,0.00008169478,0.00011316085,0.00043216234,0.0012000958,0.000022296137,0.00037004222],"category_scores_gemma":[0.0035812773,0.00004908242,0.000012849099,0.00017502137,0.000099919074,0.0011308639,0.0019396138,0.000058281883,0.00042782875],"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":[0.000017087876,0.000027148355,0.0011674558,0.0000028751758,0.000016595062,0.0000013798937,0.0011308597,0.0000034141117,0.000057011814,0.33975932,0.3353731,0.32244375],"study_design_scores_gemma":[0.00022589634,0.000057015273,0.011962341,0.0000062521194,0.000011411484,0.0000015041003,0.00785686,0.01489346,0.00006660177,0.077600114,0.88719326,0.0001253045],"about_ca_topic_score_codex":0.00017859778,"about_ca_topic_score_gemma":0.0002546033,"teacher_disagreement_score":0.9444069,"about_ca_system_score_codex":0.000006613563,"about_ca_system_score_gemma":0.000007984123,"threshold_uncertainty_score":0.5499016},"labels":[],"label_agreement":null},{"id":"W2041442195","doi":"10.1109/icde.2013.6544854","title":"On the relative trust between inconsistent data and inaccurate constraints","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"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; Semantics (computer science); Consistency (knowledge bases); Data integrity; Data consistency; Data mining; Functional dependency; Data modeling; Theoretical computer science; Database; Programming language; Artificial intelligence; Relational database","score_opus":0.41102298245739677,"score_gpt":0.42876737936645853,"score_spread":0.017744396909061766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041442195","genre_codex":"other","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":[0.37033617,0.00003133401,0.021294449,0.0872106,0.00032632911,0.0012679859,0.00070860924,0.00006511479,0.51875937],"genre_scores_gemma":[0.99067056,0.000008278439,0.0004928459,0.0028417285,0.00002640052,0.000008821187,0.000032242227,0.000002691012,0.0059164427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982358,0.00029558293,0.00036007678,0.0004068262,0.0005658981,0.0001358039],"domain_scores_gemma":[0.9937946,0.004523485,0.00012686464,0.0014027864,0.00007544386,0.000076805634],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003202428,0.00008457326,0.00014311589,0.000061514664,0.00016862828,0.00048877293,0.0011516713,0.000029094706,0.0034160549],"category_scores_gemma":[0.0031290886,0.0000397813,0.00001892605,0.00019454295,0.00042863382,0.0008309379,0.0012727018,0.000107018815,0.0026968676],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032731587,0.000020788328,0.0030202905,0.0000014494298,0.00004311758,0.0000014404052,0.0002877473,3.0303522e-7,0.0000028156835,0.51154184,0.3085378,0.17653914],"study_design_scores_gemma":[0.000358107,0.00008288413,0.06435929,0.000016896942,0.00002704591,0.0000016187655,0.009354157,0.0012535224,0.00003238638,0.7332143,0.19110982,0.00018993812],"about_ca_topic_score_codex":0.00015056125,"about_ca_topic_score_gemma":0.00004703719,"teacher_disagreement_score":0.6203344,"about_ca_system_score_codex":0.000008878427,"about_ca_system_score_gemma":0.000018243642,"threshold_uncertainty_score":0.99807966},"labels":[],"label_agreement":null},{"id":"W2044469685","doi":"10.1109/icde.2013.6544847","title":"Holistic data cleaning: Putting violations into context","year":2013,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":319,"is_retracted":false,"has_abstract":true,"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; Rotation formalisms in three dimensions; Hypergraph; Context (archaeology); Pipeline (software); Exploit; Reachability; Quality (philosophy); Functional dependency; Theoretical computer science; Isolation (microbiology); Data mining; Machine learning; Programming language; Relational database; Computer security","score_opus":0.5895766416565716,"score_gpt":0.5011305017614565,"score_spread":0.08844613989511518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044469685","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":[0.024255488,0.00006405136,0.74378914,0.019468587,0.0008219974,0.00061235845,0.00007711017,0.00021522821,0.21069606],"genre_scores_gemma":[0.97231287,0.0000026972987,0.014648952,0.0025472308,0.00006755761,0.000008029888,0.00008594676,0.000004720801,0.010321983],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981281,0.00012485689,0.00047242505,0.0004605473,0.00064560527,0.0001684577],"domain_scores_gemma":[0.9967242,0.0010971337,0.000119814635,0.0018075348,0.00015551149,0.0000958197],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027580853,0.000074192576,0.0001302318,0.00011380095,0.0002115692,0.00086851366,0.0019041302,0.000025479385,0.0060995575],"category_scores_gemma":[0.005692525,0.000052104973,0.000024224977,0.00035331998,0.000063557694,0.0016467297,0.0015513559,0.00006790922,0.012388321],"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":[6.514601e-7,0.000021960826,0.0006453118,0.000001839727,0.0000067688825,6.5631366e-7,0.00027472846,0.000007747453,0.000027293097,0.11011197,0.44084525,0.44805583],"study_design_scores_gemma":[0.00016971598,0.000017352888,0.011811235,0.000008414145,0.000010141529,9.834822e-7,0.011063917,0.038463257,0.000017266744,0.23456918,0.70373523,0.0001333141],"about_ca_topic_score_codex":0.0019714735,"about_ca_topic_score_gemma":0.0007005745,"teacher_disagreement_score":0.9480574,"about_ca_system_score_codex":0.000012786765,"about_ca_system_score_gemma":0.000019996034,"threshold_uncertainty_score":0.99480903},"labels":[],"label_agreement":null},{"id":"W2045966259","doi":"10.1007/bf02287353","title":"Current evaluation and future needs of a mental health data linkage system in a remote region: A canadian experience","year":2002,"lang":"en","type":"article","venue":"The Journal of Behavioral Health Services & Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead Psychiatric Hospital","funders":"","keywords":"Linkage (software); Health informatics; Health psychology; Mental health; Data collection; Public health; Business; Medicine; Nursing; Psychology; Psychiatry","score_opus":0.5089985575688837,"score_gpt":0.578344012495853,"score_spread":0.06934545492696931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045966259","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":[0.94511664,0.029643098,0.000053201722,0.022885868,0.0006355653,0.0014024642,0.00015250962,0.0000054315597,0.00010520267],"genre_scores_gemma":[0.99238753,0.00691406,0.00012147942,0.00034842367,0.0001744329,0.0000031574723,0.000018123616,0.0000071866407,0.00002557346],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.990104,0.0038409496,0.0015281324,0.00024605592,0.0036988542,0.00058198173],"domain_scores_gemma":[0.99643975,0.00023786968,0.0008871251,0.0011819158,0.00069806224,0.00055529224],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04738733,0.00011638092,0.00041787635,0.0011830918,0.0004873936,0.00015783357,0.0024153145,0.000050342576,0.00006980592],"category_scores_gemma":[0.000014125065,0.00007490369,0.00003451351,0.0019559527,0.00014661305,0.0008273044,0.00059098226,0.0006308458,0.000011032161],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106398824,0.00014367522,0.0010022287,0.0003392839,0.0000041880335,0.000009647241,0.23826577,0.000005067972,0.0000028218458,0.00014066827,0.0045667305,0.75541353],"study_design_scores_gemma":[0.0011178582,0.00092910975,0.010955791,0.001614788,0.000013533058,0.00015391294,0.89162326,0.019508436,0.0000025680117,0.00020999051,0.0737565,0.00011422839],"about_ca_topic_score_codex":0.33385128,"about_ca_topic_score_gemma":0.37564123,"teacher_disagreement_score":0.75529927,"about_ca_system_score_codex":0.0006582789,"about_ca_system_score_gemma":0.0008352875,"threshold_uncertainty_score":0.9809152},"labels":[],"label_agreement":null},{"id":"W2047745978","doi":"10.1145/1514894.1514901","title":"On approximating optimum repairs for functional dependency violations","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":209,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Functional dependency; Tuple; Computer science; Set (abstract data type); Dependency theory (database theory); Constant (computer programming); Approximation algorithm; Dependency (UML); Algorithm; Database; Mathematics; Relational database; Discrete mathematics; Artificial intelligence","score_opus":0.2489855454233683,"score_gpt":0.4310638159039699,"score_spread":0.18207827048060163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047745978","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":[0.0032147723,0.0000045605866,0.85868675,0.0035694677,0.00023760238,0.00028300635,0.000020016876,0.00008978677,0.13389403],"genre_scores_gemma":[0.86958915,0.0000012528558,0.10117028,0.004783403,0.00014030453,0.00003959616,0.00006795153,0.00000522434,0.024202857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983321,0.00004998971,0.00043063305,0.00033869586,0.00070122926,0.0001473716],"domain_scores_gemma":[0.9982681,0.0010260624,0.00010895532,0.00042667447,0.00011907421,0.000051127005],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002627136,0.00007005617,0.00010590411,0.00013808631,0.0002448274,0.00018825501,0.0002845711,0.000030100424,0.000939228],"category_scores_gemma":[0.002690885,0.00005007814,0.000091242815,0.00025311104,0.0000140976845,0.0003528745,0.000043683896,0.00004825124,0.00035818288],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026236412,0.00009212238,0.00004298326,0.0000013458156,0.0000054067677,3.672549e-7,0.000053251115,0.0016865418,0.000024983554,0.7970377,0.12255045,0.07847858],"study_design_scores_gemma":[0.00035712207,0.00020284267,0.0042795595,0.0000064647734,0.000007944621,0.000001140795,0.0007401217,0.05237868,0.00006663931,0.8995391,0.042290665,0.00012968591],"about_ca_topic_score_codex":0.000004780912,"about_ca_topic_score_gemma":0.000014425516,"teacher_disagreement_score":0.8663744,"about_ca_system_score_codex":0.000019025245,"about_ca_system_score_gemma":0.000019519326,"threshold_uncertainty_score":0.9999741},"labels":[],"label_agreement":null},{"id":"W2048988884","doi":"10.4018/jdm.2011070102","title":"Data Management and Data Administration","year":2011,"lang":"en","type":"article","venue":"Journal of Database Management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Timeline; Quarter (Canadian coin); Set (abstract data type); Perception; Computer science; Data management; Data science; Subject matter; Subject (documents); Knowledge management; Political science; Data mining; Psychology; Library science; Statistics; Geography","score_opus":0.575305156144148,"score_gpt":0.47376205358806345,"score_spread":0.10154310255608456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048988884","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":[0.014935546,0.002478652,0.7063473,0.0076139495,0.0047944887,0.0025028654,0.012512436,0.00011760235,0.24869718],"genre_scores_gemma":[0.3046164,0.00793628,0.6661917,0.0035938811,0.00069120625,0.000015631875,0.004753995,0.0000677792,0.0121331485],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99523,0.00025537383,0.0014156726,0.0008391785,0.0019890135,0.00027076202],"domain_scores_gemma":[0.99260265,0.00015859639,0.00091136224,0.0059873606,0.00012911618,0.00021093222],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.013261108,0.00019529978,0.00033181548,0.00056399003,0.00013383382,0.0004048462,0.007004061,0.000029029554,0.00058959966],"category_scores_gemma":[0.0003588086,0.00014749262,0.000041580846,0.00048953644,0.000109021326,0.003897336,0.011525463,0.00016361814,0.00016839449],"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":[0.0002814679,0.00034032192,0.0005182187,0.00015349072,0.00053029525,0.0013716157,0.00015487646,0.0000013430471,0.00000557846,0.06691253,0.68631387,0.24341638],"study_design_scores_gemma":[0.0009830007,0.0001659637,0.009932301,0.00010179431,0.00041861844,0.00007138436,0.004016402,0.00068333343,0.000022763817,0.0071116663,0.97626233,0.00023041917],"about_ca_topic_score_codex":0.000016696273,"about_ca_topic_score_gemma":0.00006880622,"teacher_disagreement_score":0.28994846,"about_ca_system_score_codex":0.000024286644,"about_ca_system_score_gemma":0.000025628911,"threshold_uncertainty_score":0.9983685},"labels":[],"label_agreement":null},{"id":"W2056689260","doi":"10.1108/13639511111106641","title":"Evidence‐based solution to information sharing between law enforcement agencies","year":2011,"lang":"en","type":"article","venue":"Policing An International Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Canadian Mounted Police; University of the Fraser Valley","funders":"","keywords":"Identifier; Law enforcement; Information sharing; Merge (version control); Analytics; Enforcement; Originality; Computer science; Quality (philosophy); Unique identifier; Computer security; Data sharing; Agency (philosophy); Business; Data science; Law; World Wide Web; Political science; Information retrieval; Sociology","score_opus":0.6284452508351284,"score_gpt":0.4890381055243403,"score_spread":0.13940714531078807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056689260","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":[0.47868982,0.0000048301395,0.4720517,0.0028606423,0.0018340156,0.00020696552,0.000051927364,0.00007194369,0.044228144],"genre_scores_gemma":[0.9893187,0.000008919192,0.004614047,0.0053587807,0.00050887984,0.000005650839,0.00001859748,0.0000045741162,0.00016184767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.996792,0.00010966002,0.00081984315,0.00018213558,0.0018563672,0.00023995247],"domain_scores_gemma":[0.9982805,0.0001676076,0.00037797287,0.0003271178,0.00062025205,0.00022652907],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0046253316,0.00010721649,0.00013242089,0.0006348882,0.00028530788,0.0011577958,0.0016980135,0.000034115157,0.0008468853],"category_scores_gemma":[0.0011401207,0.000088258814,0.00008387387,0.0002128183,0.000041584048,0.005792901,0.00034120854,0.00015062634,0.0005636387],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025293897,0.00010879518,0.09008048,0.000010984663,0.00019611948,0.000018222054,0.03597536,0.0045881225,0.0003715326,0.6247855,0.010699521,0.23291244],"study_design_scores_gemma":[0.0017117601,0.0011280996,0.702821,0.0010447269,0.00011078656,0.00009181204,0.0062457044,0.03410129,0.009602321,0.12064129,0.121413335,0.0010878533],"about_ca_topic_score_codex":0.010686717,"about_ca_topic_score_gemma":0.00055915205,"teacher_disagreement_score":0.6127405,"about_ca_system_score_codex":0.00028077068,"about_ca_system_score_gemma":0.000068319976,"threshold_uncertainty_score":0.9998791},"labels":[],"label_agreement":null},{"id":"W2058683286","doi":"10.1109/iccke.2014.6993457","title":"Data accuracy: What does it mean to LOD?","year":2014,"lang":"en","type":"article","venue":"","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Viewpoints; Data quality; Quality (philosophy); Linked data; Semantic Web; Realization (probability); Data mining; Set (abstract data type); Information retrieval; Data set; Data publishing; Data modeling; Open data; Data science; Artificial intelligence; World Wide Web; Publishing; Database; Statistics","score_opus":0.38382522781161926,"score_gpt":0.48710970674891013,"score_spread":0.10328447893729087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058683286","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":[0.012377566,0.00004007099,0.50612617,0.2875705,0.0040390445,0.0006660599,0.0003315747,0.00022049504,0.18862852],"genre_scores_gemma":[0.6108891,0.00013261237,0.028893229,0.14916442,0.00070114847,0.000020630732,0.00035505128,0.000025728861,0.20981812],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972776,0.00020494599,0.00042651666,0.00069573603,0.0011775985,0.00021760493],"domain_scores_gemma":[0.99428654,0.0015926273,0.00008517201,0.003781677,0.00008635133,0.00016761692],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008265348,0.00009409475,0.00017068992,0.00012599643,0.00010058883,0.0019886505,0.0039856895,0.000026421825,0.0045113317],"category_scores_gemma":[0.006560461,0.000049663107,0.00002959007,0.00036410993,0.00003810964,0.00337872,0.0031916248,0.000050137725,0.011654594],"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":[0.000004572511,0.000023610024,0.00002435785,0.0000019352815,0.0000057489506,5.8018446e-7,0.000540236,0.000006178127,0.000018869781,0.0346855,0.6822351,0.2824533],"study_design_scores_gemma":[0.00008449498,0.000020203819,0.00021996241,0.000008819767,0.0000049118507,2.6838134e-7,0.010137923,0.0006738536,0.00015008444,0.022226095,0.9663683,0.00010504648],"about_ca_topic_score_codex":0.00011360412,"about_ca_topic_score_gemma":0.009944108,"teacher_disagreement_score":0.5985115,"about_ca_system_score_codex":0.000008454025,"about_ca_system_score_gemma":0.000013876546,"threshold_uncertainty_score":0.9990474},"labels":[],"label_agreement":null},{"id":"W2060060279","doi":"10.1109/mesoca.2014.13","title":"Prison Break: A Generic Schema Matching Solution to the Cloud Vendor Lock-in Problem","year":2014,"lang":"en","type":"article","venue":"","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","funders":"","keywords":"Cloud computing; Computer science; Vendor; Schema (genetic algorithms); Schema matching; Schema migration; Porting; Prison; Star schema; Artificial intelligence; World Wide Web; Information retrieval; Database; Programming language; Database schema; Operating system; Data integration; Semi-structured model; Software","score_opus":0.11157983450787211,"score_gpt":0.3718781701238266,"score_spread":0.2602983356159545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060060279","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":[0.12835096,0.000043261745,0.8035912,0.029616678,0.0005534308,0.00070751895,0.000007477329,0.00008256134,0.037046924],"genre_scores_gemma":[0.96989584,0.000004504802,0.018182004,0.003961245,0.0002056579,0.000049630282,0.0000054242237,0.000007989617,0.0076877186],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977726,0.000304249,0.0004483204,0.00039774246,0.00080590195,0.00027120498],"domain_scores_gemma":[0.9987135,0.0003443748,0.00010168766,0.0007205128,0.000049979575,0.00006992374],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007346849,0.00009468255,0.0001559063,0.00013453948,0.00014669566,0.00029762744,0.000879991,0.000032569413,0.00021208893],"category_scores_gemma":[0.00054383103,0.00005413179,0.000048403832,0.0006466626,0.000024562505,0.00024584238,0.00052458106,0.00008892008,0.0020784806],"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":[0.000033533663,0.00011717506,0.00034438653,0.000014529547,0.0000093756435,0.0000021306143,0.0018865542,0.0023580615,0.00084742665,0.122368865,0.25156838,0.62044954],"study_design_scores_gemma":[0.0002739142,0.000055646913,0.0028244609,0.000018787037,0.000004741571,0.0000025972784,0.0010815143,0.0068940725,0.00040224465,0.04184024,0.94646657,0.00013524276],"about_ca_topic_score_codex":0.0006614926,"about_ca_topic_score_gemma":0.0020890273,"teacher_disagreement_score":0.84154487,"about_ca_system_score_codex":0.000038688915,"about_ca_system_score_gemma":0.000017916358,"threshold_uncertainty_score":0.99869853},"labels":[],"label_agreement":null},{"id":"W2062133553","doi":"10.2218/ijdc.v7i2.227","title":"Digital Forensics Formats: Seeking a Digital Preservation Storage Container Format for Web Archiving","year":2012,"lang":"en","type":"article","venue":"International Journal of Digital Curation","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"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 Toronto","funders":"European Commission","keywords":"Computer science; Container (type theory); File format; Digital forensics; Digital preservation; Image file formats; Database; World Wide Web; Point (geometry); File system; Information retrieval; Operating system; Engineering","score_opus":0.12336317467511576,"score_gpt":0.3905250777087929,"score_spread":0.26716190303367715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062133553","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":[0.1350752,0.000047290905,0.84658235,0.0018159974,0.0020456875,0.00031546544,0.00089904177,0.000029012486,0.013189931],"genre_scores_gemma":[0.99690014,0.0000048821976,0.0007112989,0.00023130629,0.0009000104,0.000008231188,0.00039771924,0.000014970725,0.00083144923],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996238,0.00002780698,0.0013357528,0.00015904842,0.0019580878,0.00028133485],"domain_scores_gemma":[0.99619645,0.00091118074,0.0012060009,0.00020428539,0.001331589,0.00015049685],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0014325152,0.00016638881,0.00023944616,0.0004307195,0.000098982055,0.0046199416,0.00088070804,0.00004984181,0.00001971596],"category_scores_gemma":[0.00491031,0.00012909323,0.00026675034,0.00018698181,0.000056257402,0.06410739,0.00027363535,0.00013273193,0.000051267496],"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":[0.0009819688,0.0005622851,0.026592674,0.00003762144,0.0004311036,0.000014035015,0.0031256948,0.0010254909,0.000343414,0.08937727,0.03977892,0.8377295],"study_design_scores_gemma":[0.0029799123,0.00049684366,0.007265578,0.00019265903,0.00004934685,0.0002907053,0.0052358247,0.03358188,0.00018564377,0.1719073,0.77725714,0.0005571709],"about_ca_topic_score_codex":7.7961937e-7,"about_ca_topic_score_gemma":0.0000038497296,"teacher_disagreement_score":0.8618249,"about_ca_system_score_codex":0.00015945514,"about_ca_system_score_gemma":0.00007789496,"threshold_uncertainty_score":0.99641335},"labels":[],"label_agreement":null},{"id":"W2068713655","doi":"10.3138/m457-6736-3l06-160p","title":"On-line Reporting and Mapping of Spatially Aggregated Individual Records Selected by User Queries","year":2004,"lang":"en","type":"article","venue":"Cartographica The International Journal for Geographic Information and Geovisualization","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confidentiality; Computer science; Table (database); Public access; Profiling (computer programming); Database; World Wide Web; Computer security; Internet privacy; Information retrieval","score_opus":0.06447403285041445,"score_gpt":0.36770500764816144,"score_spread":0.30323097479774697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068713655","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":[0.7832669,0.00012983999,0.2105711,0.0044450145,0.0008095281,0.00041720268,0.00018542696,0.000034837747,0.00014014533],"genre_scores_gemma":[0.99649096,0.0006377131,0.0006609261,0.0015932273,0.00006863719,0.000019830242,0.0004790038,0.00000740248,0.00004228702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962237,0.00010956217,0.0019581413,0.00018039363,0.0013506751,0.00017755026],"domain_scores_gemma":[0.99443924,0.00040707242,0.0028302744,0.0001833515,0.002053304,0.00008676617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00524081,0.00015477686,0.00022901532,0.0011316197,0.00047134806,0.0009182433,0.0004894125,0.00008676098,0.0000238839],"category_scores_gemma":[0.0055692233,0.00010730831,0.000118606826,0.0010757664,0.00017720446,0.0014092715,0.00013329496,0.00017303454,0.0000013829895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001340151,0.00042330226,0.07298038,0.00015540147,0.0017578724,0.000008879269,0.01710844,0.011379902,0.0011087722,0.5934128,0.026201956,0.27412215],"study_design_scores_gemma":[0.010600931,0.0021076265,0.12198229,0.00084719295,0.0002995392,0.00051311863,0.013488331,0.015164264,0.0028940153,0.44645387,0.38441306,0.0012357581],"about_ca_topic_score_codex":0.00013343577,"about_ca_topic_score_gemma":0.00008688199,"teacher_disagreement_score":0.3582111,"about_ca_system_score_codex":0.000017244765,"about_ca_system_score_gemma":0.00007617862,"threshold_uncertainty_score":0.8854642},"labels":[],"label_agreement":null},{"id":"W2070702247","doi":"10.1145/1328964.1328967","title":"Meeting of the MINDS","year":2007,"lang":"en","type":"article","venue":"ACM SIGIR Forum","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":76,"is_retracted":false,"has_abstract":true,"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; Field (mathematics); Key (lock); Space (punctuation); Probabilistic logic; Vector space model; Work (physics); Development (topology); Data science; World Wide Web; Information retrieval; Artificial intelligence","score_opus":0.12089356568520415,"score_gpt":0.4059370702158174,"score_spread":0.2850435045306132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070702247","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":[0.714979,0.0001446283,0.010209378,0.016522158,0.0012296287,0.00030376398,0.000034294106,0.000037162023,0.25653997],"genre_scores_gemma":[0.9930308,0.0000016161671,0.001276759,0.0013267731,0.000024672427,0.0000010167819,0.0000011445323,0.0000031861168,0.004334018],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827665,0.000057930494,0.0004129338,0.00017880872,0.0008529299,0.00022076722],"domain_scores_gemma":[0.9974316,0.0010434678,0.00018870736,0.0012341567,0.00006682317,0.000035247424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054653725,0.000054240554,0.00010488696,0.000071062954,0.00010765883,0.00005077072,0.0018580314,0.000029565226,0.00013337957],"category_scores_gemma":[0.0056653284,0.000030360472,0.00008591675,0.00047477765,0.00008568238,0.00015090859,0.0011407337,0.00005500689,0.0001413788],"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":[0.000031307056,0.0001217279,0.04894946,0.000009519662,0.00002791656,0.0000043670852,0.0009566504,0.00002674349,0.0016428286,0.09138636,0.2979901,0.55885303],"study_design_scores_gemma":[0.00017048871,0.000028603456,0.0459527,0.0000142845465,0.000008359959,0.0000010803627,0.0047865007,0.000032390235,0.012188127,0.07404162,0.86269724,0.00007862515],"about_ca_topic_score_codex":0.00005441898,"about_ca_topic_score_gemma":0.00024273859,"teacher_disagreement_score":0.5647071,"about_ca_system_score_codex":0.0000094074785,"about_ca_system_score_gemma":0.000011410085,"threshold_uncertainty_score":0.6782337},"labels":[],"label_agreement":null},{"id":"W2074916233","doi":"10.4067/s0718-18762014000200006","title":"A Metrics-Driven Approach for Quality Assessment of Linked Open Data","year":2014,"lang":"en","type":"article","venue":"Journal of theoretical and applied electronic commerce research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Data quality; Data mining; Quality (philosophy); Consistency (knowledge bases); Set (abstract data type); Completeness (order theory); Cloud computing; Linked data; Metric (unit); Data science; Information retrieval; Semantic Web; Artificial intelligence","score_opus":0.4695965841699453,"score_gpt":0.5772331107280245,"score_spread":0.1076365265580792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074916233","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":[0.021507582,0.00015282391,0.922012,0.010199155,0.000045413082,0.0011374427,0.00008236461,0.000005765145,0.044857495],"genre_scores_gemma":[0.98027617,0.00015293971,0.019067422,0.00021155798,0.000096322765,0.000017840184,0.000027327977,0.000009821806,0.00014062383],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99336714,0.0017958051,0.001280977,0.0004895304,0.002461095,0.0006054304],"domain_scores_gemma":[0.9867474,0.01058436,0.00048818596,0.001358806,0.00058708066,0.00023419796],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.09938728,0.00012431425,0.00072611857,0.00040747225,0.00022693664,0.00048958254,0.005953146,0.000084153515,0.000121815014],"category_scores_gemma":[0.0061260406,0.000079375284,0.00009873258,0.0009095216,0.0007928681,0.00033043162,0.004465358,0.0008193135,0.0000026394305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034592685,0.0003679471,0.000075562966,0.000043186752,0.00007300869,1.470766e-7,0.000054018008,0.000032784264,0.00031754887,0.8934806,0.005847617,0.099361636],"study_design_scores_gemma":[0.0017866541,0.0009527955,0.0013044846,0.00001738906,0.00004512005,0.0000049645087,0.0011772198,0.032828607,0.000121698955,0.89347714,0.06814774,0.00013616409],"about_ca_topic_score_codex":0.000016908027,"about_ca_topic_score_gemma":0.000006055863,"teacher_disagreement_score":0.95876855,"about_ca_system_score_codex":0.00008273184,"about_ca_system_score_gemma":0.00030638682,"threshold_uncertainty_score":0.9994251},"labels":[],"label_agreement":null},{"id":"W2080549944","doi":"10.1145/1394251.1394257","title":"Advances in information and knowledge management","year":2008,"lang":"en","type":"article","venue":"ACM SIGIR Forum","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":"Simon Fraser University","funders":"Universidade de Lisboa; Pennsylvania State University","keywords":"Computer science; Data science; Knowledge extraction; Data management; Personal information management; XML; Digital library; World Wide Web; Information management; Information extraction; Knowledge management; Information system; Information retrieval; Management information systems; Database; Data mining","score_opus":0.07697138455936814,"score_gpt":0.3808004260670133,"score_spread":0.30382904150764517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080549944","genre_codex":"other","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":[0.14899205,0.0035544597,0.017015602,0.007117624,0.001049615,0.00095781253,0.000043654025,0.00013616637,0.821133],"genre_scores_gemma":[0.9925918,0.0025288614,0.0020048958,0.00092521263,0.0000142368,0.000025363304,0.000015908468,0.0000030176218,0.0018907278],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99875516,0.000050106195,0.00040229587,0.00018104709,0.00041327524,0.00019813981],"domain_scores_gemma":[0.9990746,0.00021292659,0.00008928518,0.00053883175,0.000037988135,0.000046410303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010483605,0.000076916294,0.00012117498,0.00030101324,0.000113818525,0.00009071332,0.0006074062,0.00002522538,0.000049568902],"category_scores_gemma":[0.00052252726,0.000060459766,0.000023492015,0.0004555489,0.000070123686,0.0025240846,0.0008027368,0.000049897983,0.00071404804],"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":[0.000015859725,0.00003814165,0.009543776,0.000017146172,0.0000033867962,0.0000067911774,0.0009378268,0.000015084687,6.5912997e-7,0.0627684,0.041122943,0.88553],"study_design_scores_gemma":[0.00035282582,0.000026714426,0.028364662,0.000009314992,0.0000019844442,0.000003004912,0.003379293,0.00012478937,0.000014437186,0.046994437,0.9206458,0.00008275341],"about_ca_topic_score_codex":0.000011495609,"about_ca_topic_score_gemma":0.00014077549,"teacher_disagreement_score":0.8854472,"about_ca_system_score_codex":0.000018783214,"about_ca_system_score_gemma":0.000009108003,"threshold_uncertainty_score":0.91778815},"labels":[],"label_agreement":null},{"id":"W2083200098","doi":"10.6017/ital.v33i2.5341","title":"The Importance of Identifying and Accommodating E-Resource Usage Data for the Presence of Outliers. The Negative Impacts of Inaccurate E-Journal Usage Data.","year":2014,"lang":"en","type":"article","venue":"Information Technology and Libraries","topic":"Data Quality and Management","field":"Decision Sciences","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":"Laurentian University","funders":"","keywords":"Outlier; Upload; Computer science; Identification (biology); Sample (material); Usage data; Resource (disambiguation); Data mining; Statistics; Data science; Information retrieval; World Wide Web; Mathematics; Artificial intelligence","score_opus":0.13256765051236072,"score_gpt":0.3760560784491905,"score_spread":0.24348842793682976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083200098","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":[0.48653847,0.003820396,0.4534441,0.04886531,0.00046412178,0.001982598,0.0024986651,0.00008149719,0.0023048413],"genre_scores_gemma":[0.9972798,0.0002410401,0.0021421118,0.00024119164,0.000013686287,0.0000066465536,0.000040930012,0.0000023507043,0.00003220146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983828,0.00014202992,0.00085674523,0.00012724001,0.0003565211,0.00013464535],"domain_scores_gemma":[0.99064094,0.006110462,0.0015210222,0.0015849337,0.00012272455,0.00001989786],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075720493,0.00007889903,0.00018469646,0.0001586734,0.0006501535,0.0004715378,0.0031782323,0.000060557963,0.0000059493527],"category_scores_gemma":[0.015912179,0.00003576897,0.000017138553,0.00046644663,0.0014416709,0.006341713,0.0027795518,0.00017823203,6.2392746e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015868824,0.000015943848,0.013565782,0.00012530196,0.00012901663,1.5851187e-7,0.008353327,0.000042160347,0.000046314002,0.49875808,0.023343336,0.4554619],"study_design_scores_gemma":[0.000926287,0.0001742232,0.024758797,0.0001414242,0.0000879375,0.000019108968,0.14782397,0.042253423,0.0037884393,0.43207946,0.34777018,0.00017673572],"about_ca_topic_score_codex":0.000017440549,"about_ca_topic_score_gemma":0.000046272442,"teacher_disagreement_score":0.51074135,"about_ca_system_score_codex":0.0000020183818,"about_ca_system_score_gemma":0.00004244549,"threshold_uncertainty_score":0.9923772},"labels":[],"label_agreement":null},{"id":"W2083947418","doi":"10.1504/ijiq.2014.068653","title":"Repairing integrity rules for improved data quality","year":2014,"lang":"en","type":"article","venue":"International Journal of Information Quality","topic":"Data Quality and Management","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Computer science; Data integrity; Constraint (computer-aided design); Data quality; Data mining; Data cleansing; Quality (philosophy); Set (abstract data type); Business rule; Domain (mathematical analysis); Data science; Business process; Database; Work in process","score_opus":0.37274437675812616,"score_gpt":0.5310786126391739,"score_spread":0.15833423588104772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083947418","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":[0.031141946,0.000013153505,0.9475502,0.013307463,0.0027067803,0.00020649975,0.0011439088,0.000032013155,0.00389803],"genre_scores_gemma":[0.8870209,0.000042575328,0.10140817,0.008551,0.0012665732,0.000010722303,0.0012483132,0.000011364555,0.00044038714],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933285,0.00065964105,0.0035359643,0.00021574345,0.0020837889,0.00017634776],"domain_scores_gemma":[0.98815656,0.0031771136,0.0036021126,0.0011233803,0.003806297,0.00013451505],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051898304,0.00013403854,0.00038643111,0.00040908862,0.000111608555,0.0008637617,0.0039949645,0.00007901588,0.00014115796],"category_scores_gemma":[0.055673283,0.00010037231,0.00022577969,0.00016123493,0.000085095504,0.0073385113,0.0007597962,0.00026718254,0.00011509274],"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":[0.00068337866,0.00014681985,0.0013630362,0.00004185583,0.00020918866,3.970289e-7,0.0009889505,0.00010668633,0.00010168773,0.28382495,0.06543984,0.6470932],"study_design_scores_gemma":[0.0015015124,0.00008549156,0.024576226,0.00003624385,0.000016650682,0.000011315449,0.0018569365,0.012318179,0.00018166902,0.12780358,0.83142066,0.0001915221],"about_ca_topic_score_codex":0.00016279459,"about_ca_topic_score_gemma":0.00007386596,"teacher_disagreement_score":0.85587895,"about_ca_system_score_codex":0.00011584738,"about_ca_system_score_gemma":0.0001387681,"threshold_uncertainty_score":0.9762702},"labels":[],"label_agreement":null},{"id":"W2087155295","doi":"10.1007/978-1-4419-1325-8_6","title":"Identity Management Architecture","year":2009,"lang":"en","type":"book-chapter","venue":"Annals of information systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Identity management; Identity (music); Interoperability; Computer science; Knowledge management; Variety (cybernetics); Homeland security; Key (lock); Government (linguistics); Computer security; World Wide Web; Political science; Authentication (law); Artificial intelligence; Linguistics","score_opus":0.19661352234585502,"score_gpt":0.40444497690502096,"score_spread":0.20783145455916593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087155295","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000055977525,0.00031518098,0.027015705,0.0007596453,0.00066545786,0.0006748666,0.00035445482,0.000046580968,0.9701625],"genre_scores_gemma":[0.0051068435,0.00090908434,0.0004038471,0.003548253,0.0001992193,0.000019871988,0.0005331738,0.000016086888,0.9892636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.994238,0.000068984606,0.0021840848,0.00024047133,0.003062704,0.00020571351],"domain_scores_gemma":[0.9958444,0.00013927426,0.001980765,0.0012191558,0.0007167941,0.000099577774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005161849,0.00025811416,0.000585041,0.0010890127,0.00008619992,0.00068811973,0.0014097221,0.00019419426,0.00027950783],"category_scores_gemma":[0.00017604015,0.00020433005,0.00027719437,0.00016359746,0.000066972585,0.0025066065,0.0003448253,0.00017936114,0.0034716136],"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":[0.000012286894,0.0000057086154,5.2929937e-7,0.00016755456,0.00007122274,0.000002065667,0.0002291188,0.0003222289,5.5480708e-8,0.64997035,0.17825371,0.17096516],"study_design_scores_gemma":[0.00010297416,0.000042129297,0.00007186954,0.00023693913,0.000017223656,0.0000031559255,0.00034407765,0.00003309493,0.000002984992,0.12031073,0.87865716,0.00017768351],"about_ca_topic_score_codex":0.000033077282,"about_ca_topic_score_gemma":0.000011203153,"teacher_disagreement_score":0.70040345,"about_ca_system_score_codex":0.000019620229,"about_ca_system_score_gemma":0.000025382493,"threshold_uncertainty_score":0.9973043},"labels":[],"label_agreement":null},{"id":"W2092295977","doi":"10.1145/2335484.2335520","title":"Solving manufacturing equipment monitoring through efficient complex event processing","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"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 Toronto","funders":"","keywords":"Complex event processing; Computer science; Event (particle physics); Visualization; Latency (audio); Key (lock); Real-time computing; Throughput; Distributed computing; Data mining; Operating system","score_opus":0.3285297737278659,"score_gpt":0.458375936229109,"score_spread":0.1298461625012431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092295977","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":[0.37078094,0.0004610179,0.5528609,0.0012543354,0.0019401958,0.00048420404,0.000007312511,0.00023490126,0.0719762],"genre_scores_gemma":[0.9797473,0.0000075464363,0.017617859,0.00033421596,0.000337934,0.000018346776,0.000004349153,0.00001230781,0.0019201522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961469,0.0001377325,0.0007348,0.00044844777,0.0018263428,0.000705779],"domain_scores_gemma":[0.9986141,0.00028756153,0.0002299356,0.00062461034,0.00007148073,0.00017232176],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004242142,0.00019116413,0.00024845678,0.00013014665,0.00044606702,0.0005478289,0.00078827975,0.00004069019,0.0009886887],"category_scores_gemma":[0.00024165194,0.00013717759,0.000108987566,0.00025536117,0.00005647921,0.0009985275,0.00093075563,0.00011851023,0.00067658146],"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":[0.000047062244,0.0011728475,0.010335432,0.00016625859,0.00008612903,0.000012540539,0.017304098,0.016911456,0.0030340743,0.023754105,0.021759506,0.9054165],"study_design_scores_gemma":[0.0012804279,0.0001012324,0.1272477,0.00028819047,0.00008013323,0.000019871943,0.04361391,0.022820285,0.10173951,0.0082774665,0.6930489,0.0014823426],"about_ca_topic_score_codex":0.00007008944,"about_ca_topic_score_gemma":0.000004284689,"teacher_disagreement_score":0.9039341,"about_ca_system_score_codex":0.00013569416,"about_ca_system_score_gemma":0.00001955878,"threshold_uncertainty_score":0.99992454},"labels":[],"label_agreement":null},{"id":"W2093594738","doi":"10.7152/acro.v24i1.14671","title":"Veracity Roadmap: Is Big Data Objective, Truthful and Credible?","year":2014,"lang":"en","type":"article","venue":"Advances in Classification Research Online","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Big data; Computer science; Data science; Operationalization; Objectivity (philosophy); Credibility; Data quality; Variety (cybernetics); Quality (philosophy); Data mining; Artificial intelligence","score_opus":0.68969663109607,"score_gpt":0.5918893972658551,"score_spread":0.09780723383021495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093594738","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":[0.3655248,0.011091108,0.2824011,0.20158264,0.0042730896,0.0044514425,0.007586992,0.00040999765,0.1226788],"genre_scores_gemma":[0.98198944,0.0059658587,0.0069114566,0.00078532373,0.0003379488,0.000046679495,0.00057092466,0.000015684112,0.003376657],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99393725,0.0013173445,0.00073118956,0.0012329175,0.002357986,0.00042331615],"domain_scores_gemma":[0.99174,0.004552478,0.00019776043,0.002775712,0.000560224,0.00017384267],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017279988,0.00013270757,0.0002677155,0.00070960145,0.00025740426,0.00035945783,0.0024016756,0.0000779112,0.00015420889],"category_scores_gemma":[0.019658806,0.00010661141,0.000024084877,0.0019243301,0.000567797,0.0018970317,0.0014118933,0.00045732316,0.00020207549],"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":[0.00007292033,0.00028160424,0.008245844,0.000025064013,0.000006152666,0.0000016718357,0.00021098688,0.00001772663,0.0001364671,0.026098944,0.013898789,0.95100385],"study_design_scores_gemma":[0.0004013264,0.00007229761,0.08145236,0.000023750867,0.0000023719583,8.204018e-7,0.0016565965,0.027809095,0.000060112518,0.1149682,0.7734367,0.00011636145],"about_ca_topic_score_codex":0.00012000405,"about_ca_topic_score_gemma":0.002273481,"teacher_disagreement_score":0.95088744,"about_ca_system_score_codex":0.00006805903,"about_ca_system_score_gemma":0.000095847514,"threshold_uncertainty_score":0.988599},"labels":[],"label_agreement":null},{"id":"W2100287013","doi":"10.5267/j.msl.2012.07.007","title":"A new approach to measure believability dimension of data quality","year":2012,"lang":"en","type":"article","venue":"Management Science Letters","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Measure (data warehouse); Dimension (graph theory); Computer science; Quality (philosophy); Psychology; Statistics; Data mining; Mathematics","score_opus":0.38560542171465445,"score_gpt":0.44313896161605776,"score_spread":0.05753353990140331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100287013","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":[0.09224887,0.000034252673,0.8307664,0.021068789,0.0010235427,0.0014285529,0.00006649178,0.00008809699,0.053275052],"genre_scores_gemma":[0.85164636,0.0000024832384,0.13735172,0.0095105665,0.00010380824,0.000014785479,0.00002605227,0.00000896923,0.00133525],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.991368,0.00040202515,0.00094198977,0.0014166215,0.005118257,0.00075311516],"domain_scores_gemma":[0.9935855,0.00026517687,0.00031503986,0.0052858456,0.00007505747,0.00047336615],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.04460675,0.00019643613,0.00035075084,0.00061015197,0.00028687037,0.00033725976,0.006878006,0.000028837143,0.00016203854],"category_scores_gemma":[0.0017141713,0.00015140031,0.00007361056,0.0034735359,0.00045029036,0.0034854878,0.0061625224,0.00010745109,0.0006813594],"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":[0.000088193614,0.00071263796,0.027689544,0.0001045648,0.00005693186,0.0000015428295,0.0025278116,0.0004738689,0.0069677285,0.09809916,0.55841064,0.30486742],"study_design_scores_gemma":[0.0008928801,0.000047905032,0.59416413,0.000047703856,0.00009902099,0.0000017489683,0.005471122,0.00082527235,0.0010102062,0.003914913,0.39271522,0.0008098637],"about_ca_topic_score_codex":0.00028309488,"about_ca_topic_score_gemma":0.000013498104,"teacher_disagreement_score":0.7593975,"about_ca_system_score_codex":0.00010503053,"about_ca_system_score_gemma":0.000023242106,"threshold_uncertainty_score":0.9984953},"labels":[],"label_agreement":null},{"id":"W2100680488","doi":"10.1109/ic2e.2014.15","title":"Analytics-as-a-Service (AaaS) Tool for Unstructured Data Mining","year":2014,"lang":"en","type":"article","venue":"","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":"University of Saskatchewan","funders":"","keywords":"NoSQL; Computer science; Unstructured data; Data warehouse; Big data; Schema (genetic algorithms); Analytics; Standardization; Data science; Service (business); Database; Data mining; Information retrieval","score_opus":0.36105620000405164,"score_gpt":0.46441128180952956,"score_spread":0.10335508180547792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100680488","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":[0.028793298,0.000015846468,0.86578524,0.01788814,0.0011156698,0.00060332194,0.0005024432,0.00014072139,0.08515534],"genre_scores_gemma":[0.73468304,0.0000072506937,0.18539344,0.04130672,0.00051608257,0.000023187666,0.0009767951,0.00002871999,0.037064787],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997599,0.000113968395,0.00052867475,0.0006674714,0.0008452274,0.00024564614],"domain_scores_gemma":[0.9951152,0.0016909777,0.0001581609,0.0027468328,0.00020535251,0.00008343052],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005959029,0.000115519724,0.0002308704,0.00013177528,0.0001539428,0.0005135718,0.003066927,0.000051863146,0.0015059584],"category_scores_gemma":[0.005728677,0.00008069481,0.000047332964,0.00049545284,0.000036297497,0.00069115765,0.0012612365,0.00004869178,0.00059342745],"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":[0.000036562622,0.00002768894,0.00030660105,0.000019860152,0.000037288584,7.26359e-7,0.00024029774,0.0000925602,0.000043624863,0.15857624,0.55605143,0.28456712],"study_design_scores_gemma":[0.0003959014,0.00003441836,0.0009030684,0.000005049867,0.000027533466,0.0000011540112,0.0012559679,0.07161363,0.00007916759,0.050967738,0.8745667,0.00014968838],"about_ca_topic_score_codex":0.00012644423,"about_ca_topic_score_gemma":0.00085476384,"teacher_disagreement_score":0.7058897,"about_ca_system_score_codex":0.000010061832,"about_ca_system_score_gemma":0.00003524771,"threshold_uncertainty_score":0.9994068},"labels":[],"label_agreement":null},{"id":"W2103884285","doi":"10.1109/icdmw.2009.116","title":"LNBC: A Link-Based Naive Bayes Classifier","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Simon Fraser University","funders":"","keywords":"Computer science; Naive Bayes classifier; Artificial intelligence; Classifier (UML); Object (grammar); Data mining; Class (philosophy); Machine learning; Relational database; Link (geometry); Pattern recognition (psychology); Support vector machine","score_opus":0.23947869679751588,"score_gpt":0.443369581860508,"score_spread":0.20389088506299213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103884285","genre_codex":"other","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":[0.006083453,0.000052719737,0.28696978,0.08380408,0.0004954398,0.00031127178,0.000035638215,0.00021355353,0.6220341],"genre_scores_gemma":[0.9138891,0.000004791363,0.008155247,0.029586202,0.00012528831,0.0000050241356,0.000015278512,0.0000041379108,0.048214912],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997875,0.00013347494,0.00038859746,0.00039461625,0.0009997186,0.00020860434],"domain_scores_gemma":[0.99845946,0.0004930422,0.00008736633,0.00074597605,0.00011197045,0.00010220988],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021405525,0.000095386,0.00016271058,0.0001711741,0.00010103143,0.0003529318,0.0007478983,0.000050029754,0.003820073],"category_scores_gemma":[0.0010143779,0.000061951476,0.00009206685,0.00046616205,0.000052568696,0.00031759072,0.00008018888,0.00007898712,0.0032890993],"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":[0.000022887087,0.000087275184,0.00018605577,0.0000013431437,0.000005831443,0.000010495594,0.00010551592,0.000047773563,0.00007695456,0.13428453,0.4675134,0.39765793],"study_design_scores_gemma":[0.0003150262,0.00011868282,0.0102242865,0.000005623631,0.0000060862485,4.2753229e-7,0.00044320966,0.002938181,0.0004962947,0.112435155,0.87288004,0.00013698412],"about_ca_topic_score_codex":0.00002511583,"about_ca_topic_score_gemma":0.00005303859,"teacher_disagreement_score":0.9078057,"about_ca_system_score_codex":0.000016175696,"about_ca_system_score_gemma":0.00003882997,"threshold_uncertainty_score":0.99748695},"labels":[],"label_agreement":null},{"id":"W2104345001","doi":"10.1109/icif.2010.5711858","title":"Measures of effectiveness for high-level fusion","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Robustness (evolution); Sensor fusion; Computer science; Situation awareness; Workload; Data collection; Reliability engineering; Data mining; Engineering; Artificial intelligence","score_opus":0.36313919370976094,"score_gpt":0.4469914579324498,"score_spread":0.08385226422268888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104345001","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":[0.45101568,0.0000065469385,0.53769636,0.0005401995,0.0011736079,0.00049258,0.00011660683,0.000027184371,0.008931231],"genre_scores_gemma":[0.9893917,0.0000012329058,0.008413096,0.000110400426,0.00003278347,0.000018828021,0.00000835831,0.0000029748182,0.002020642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986887,0.00010093368,0.0002620165,0.00022092981,0.00063126953,0.00009613366],"domain_scores_gemma":[0.9975103,0.0016435424,0.00008774287,0.0004724588,0.0002502942,0.000035658733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006593028,0.00005346245,0.00015555207,0.00009814702,0.000058682523,0.000053417643,0.00050196936,0.00003810033,0.00034959224],"category_scores_gemma":[0.0023867204,0.00003314935,0.000056303783,0.0001764297,0.000055006996,0.00017219402,0.0001576954,0.00004161345,0.000077892466],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009946861,0.000106815285,0.0007883076,0.000030791707,0.000013651487,2.6580557e-7,0.0000713847,0.000006650998,0.05934216,0.5620355,0.012774142,0.36473083],"study_design_scores_gemma":[0.001109168,0.00017119801,0.15636608,0.000015268077,0.000018558278,5.5801934e-7,0.00034857623,0.00016234291,0.1740354,0.42380235,0.24379921,0.00017129185],"about_ca_topic_score_codex":0.00018176726,"about_ca_topic_score_gemma":0.00056369585,"teacher_disagreement_score":0.538376,"about_ca_system_score_codex":0.0000032560793,"about_ca_system_score_gemma":0.000016738371,"threshold_uncertainty_score":0.382779},"labels":[],"label_agreement":null},{"id":"W2107080109","doi":"10.14778/1454159.1454220","title":"A revival of integrity constraints for data cleaning","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Data integrity; Data quality; Computer science; Schema (genetic algorithms); Constraint (computer-aided design); Quality (philosophy); Risk analysis (engineering); Data science; Reliability engineering; Database; Information retrieval; Engineering; Operations management; Business; Mechanical engineering","score_opus":0.5397355688626213,"score_gpt":0.44987919658589165,"score_spread":0.08985637227672966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107080109","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":[0.8500509,0.00042490062,0.015139266,0.015039472,0.0016823104,0.005372691,0.0019499043,0.00011654823,0.11022396],"genre_scores_gemma":[0.9887461,0.00005381473,0.010149397,0.0002228591,0.000044572043,0.000017758673,0.0000071551717,0.0000061189994,0.0007522038],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976048,0.000018350816,0.0007493781,0.0003989694,0.0010432224,0.00018526842],"domain_scores_gemma":[0.99792594,0.00037583546,0.000643418,0.0005806316,0.0004252218,0.00004893055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048403526,0.000104420156,0.00031074267,0.00008824202,0.00013447949,0.00004258924,0.0028582267,0.000033695203,0.00007508502],"category_scores_gemma":[0.0055664913,0.00006296614,0.00011732032,0.00033269677,0.0004278637,0.0004206564,0.0016765116,0.00011009029,0.000009113499],"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":[0.00029208272,0.00060982816,0.013644658,0.00044162272,0.0002077467,9.020353e-7,0.0036846737,0.000005585712,0.014417396,0.33226407,0.51643145,0.11799998],"study_design_scores_gemma":[0.0051201885,0.0007756673,0.018781621,0.0009966926,0.0003461252,0.00007815339,0.025198024,0.0046057715,0.18076989,0.23142816,0.5310311,0.00086862466],"about_ca_topic_score_codex":0.000054789252,"about_ca_topic_score_gemma":0.0000049058367,"teacher_disagreement_score":0.1663525,"about_ca_system_score_codex":0.000023642877,"about_ca_system_score_gemma":0.000046541118,"threshold_uncertainty_score":0.6664012},"labels":[],"label_agreement":null},{"id":"W2108075439","doi":"","title":"Approximate joins: concepts and techniques","year":2005,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"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 Toronto","funders":"","keywords":"Joins; Multitude; Computer science; Database; Quality (philosophy); Data quality; Character (mathematics); Service (business); Relational database; Missing data; Data science; Data mining; World Wide Web; Business; Marketing","score_opus":0.2365840025725053,"score_gpt":0.4607702635409333,"score_spread":0.224186260968428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108075439","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":[0.20048073,0.013239764,0.43105653,0.045980193,0.0024084847,0.004996289,0.16859552,0.003369529,0.12987296],"genre_scores_gemma":[0.86281246,0.002198087,0.09010569,0.026850669,0.0010463619,0.00008473015,0.008422949,0.000056528883,0.00842254],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99783295,0.00016880377,0.00041166577,0.0006506177,0.0006721424,0.0002638179],"domain_scores_gemma":[0.9972637,0.00046546268,0.000121871766,0.0020039612,0.00005401519,0.00009098494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038566452,0.0001260537,0.00021340873,0.00014633607,0.00016178815,0.00044000914,0.0014180073,0.00004111492,0.00088553363],"category_scores_gemma":[0.0017584559,0.00009404742,0.00002534918,0.00026782378,0.000118086886,0.0023115715,0.0021986165,0.00007824468,0.0004176799],"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":[0.000014160986,0.00013029581,0.0005217004,0.000012562163,0.000012530635,0.0000104067485,0.000080427664,4.638468e-7,0.000091577785,0.015689623,0.8023581,0.18107818],"study_design_scores_gemma":[0.00017521351,0.000023170918,0.00041118494,0.00001660637,0.000011786124,0.0000043378113,0.00042672365,0.0010603921,0.0011789819,0.0019750288,0.99458057,0.00013600338],"about_ca_topic_score_codex":0.000037209193,"about_ca_topic_score_gemma":0.00018238685,"teacher_disagreement_score":0.6623317,"about_ca_system_score_codex":0.000010940354,"about_ca_system_score_gemma":0.000024045597,"threshold_uncertainty_score":0.9695972},"labels":[],"label_agreement":null},{"id":"W2110848713","doi":"","title":"Linked Movie Data Base","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"RDF; Linked data; Computer science; Metadata; World Wide Web; Database; Cloud computing; Information retrieval; Semantic Web","score_opus":0.5971839626278773,"score_gpt":0.5128323344859844,"score_spread":0.0843516281418929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110848713","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050227907,0.00009981816,0.22933044,0.072386086,0.0005701613,0.0003043031,0.00024443667,0.00021076982,0.6918312],"genre_scores_gemma":[0.75906754,0.000052683074,0.04554096,0.05871198,0.00026815812,0.0000023698178,0.00040392537,0.000006452879,0.13594596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982322,0.00008991347,0.00031593489,0.0004301849,0.0007950469,0.00013672674],"domain_scores_gemma":[0.99693584,0.00030175957,0.000054669963,0.0025847729,0.000045012337,0.00007791618],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004081734,0.00005677115,0.00010727054,0.00008340297,0.00006293753,0.00029539515,0.002328949,0.000021596883,0.00361188],"category_scores_gemma":[0.0020201772,0.00003650563,0.000023448345,0.00033267352,0.000023556844,0.0007746493,0.0005982779,0.00004682578,0.004341141],"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":[0.0000036214972,0.000042585492,0.000029234932,3.3358953e-7,0.0000018369516,0.0000053740137,0.000023147777,0.0000034295567,0.000019856412,0.051982664,0.6419196,0.30596828],"study_design_scores_gemma":[0.0001291814,0.000024530651,0.0036258718,0.0000014632076,0.0000036930476,5.330059e-7,0.0002684644,0.0029441877,0.00002857787,0.075182945,0.9177235,0.00006710381],"about_ca_topic_score_codex":0.000035337656,"about_ca_topic_score_gemma":0.00006411846,"teacher_disagreement_score":0.7540447,"about_ca_system_score_codex":0.0000049143882,"about_ca_system_score_gemma":0.00001689507,"threshold_uncertainty_score":0.99729896},"labels":[],"label_agreement":null},{"id":"W2111094784","doi":"10.1109/iccit.2008.210","title":"Social Network Analysis on Name Disambiguation and More","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"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 British Columbia","funders":"","keywords":"Computer science; Disk formatting; String metric; Social network analysis; Information retrieval; Similarity (geometry); String (physics); Correct name; Social network (sociolinguistics); Natural language processing; Graph; World Wide Web; Artificial intelligence; String searching algorithm; Social media; Theoretical computer science; Pattern matching; Mathematics","score_opus":0.21796064294121784,"score_gpt":0.44268466009588664,"score_spread":0.2247240171546688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111094784","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":[0.84993815,0.00003454602,0.08669509,0.012964713,0.0001675491,0.00014916755,0.000017364431,0.00006745855,0.04996594],"genre_scores_gemma":[0.9893189,0.000013625453,0.0005489985,0.0017404709,0.00009438241,0.0000028306736,0.000021786595,0.0000017012933,0.008257282],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99861807,0.000096593016,0.00021973351,0.00025096055,0.000704839,0.00010982888],"domain_scores_gemma":[0.9993876,0.00023151119,0.00006675044,0.00022773692,0.000049732607,0.000036630292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012281295,0.00005268533,0.00014515469,0.000120669305,0.0002830509,0.00009623824,0.00018421747,0.000024987308,0.00050835195],"category_scores_gemma":[0.00021242166,0.00003630235,0.000067038294,0.00089988596,0.00008210721,0.00016908305,0.00010081749,0.000033963865,0.00018935748],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004711072,0.000113006936,0.040678475,0.0000019399606,0.00027277894,0.000011318383,0.0023048385,0.0029680482,0.0000018938598,0.18864305,0.6400792,0.12487831],"study_design_scores_gemma":[0.00024310702,0.000043097225,0.815884,0.0000011988205,0.000115277064,6.553122e-7,0.0012733503,0.009447567,0.0000057236994,0.039496943,0.13333234,0.00015673677],"about_ca_topic_score_codex":0.00007944344,"about_ca_topic_score_gemma":0.00014754437,"teacher_disagreement_score":0.7752055,"about_ca_system_score_codex":0.000009068522,"about_ca_system_score_gemma":0.000005593671,"threshold_uncertainty_score":0.5566097},"labels":[],"label_agreement":null},{"id":"W2111589117","doi":"10.1186/1471-2288-14-36","title":"Evaluating bias due to data linkage error in electronic healthcare records","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Hospital for Sick Children; Intensive Care Society; Medical Research Council; National Institute for Health and Care Research; NHS Health Scotland","keywords":"Identifier; Record linkage; Linkage (software); Gold standard (test); Word error rate; Computer science; Imputation (statistics); Statistics; Probabilistic logic; Data mining; Missing data; Data set; Standard error; Medicine; Artificial intelligence; Mathematics; Population","score_opus":0.9728506852504919,"score_gpt":0.764426510343351,"score_spread":0.20842417490714094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111589117","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","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":[0.0874657,0.00046079277,0.85246366,0.0551026,0.0008368647,0.00096856384,0.000043540906,0.000052000672,0.002606248],"genre_scores_gemma":[0.27826628,0.00040277358,0.6975009,0.016152442,0.0016253075,0.00037707266,0.00027618324,0.000064027205,0.0053350283],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.734938,0.241934,0.0026987328,0.0031150456,0.014212316,0.0031018776],"domain_scores_gemma":[0.45397106,0.5336879,0.00040004126,0.00838872,0.0012728053,0.002279496],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.6394793,0.00016696288,0.0008231283,0.001223558,0.00022914207,0.0001526727,0.006863059,0.00032223633,0.0032934065],"category_scores_gemma":[0.8603182,0.00012445883,0.00006607333,0.002723577,0.0004164986,0.0002635641,0.0061264667,0.0017980075,0.0016729546],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023313474,0.00008126542,0.0012672495,0.00007418097,0.000009832858,0.000033975448,0.00045877995,0.00002069424,0.000032079566,0.038508657,0.041158687,0.91812146],"study_design_scores_gemma":[0.001343295,0.0018717599,0.01666641,0.00019994505,0.000008734478,0.000030486835,0.0032005247,0.09765793,0.00005937495,0.40022507,0.47842166,0.00031480673],"about_ca_topic_score_codex":0.0043693315,"about_ca_topic_score_gemma":0.09030966,"teacher_disagreement_score":0.9178067,"about_ca_system_score_codex":0.00018802984,"about_ca_system_score_gemma":0.0026326496,"threshold_uncertainty_score":0.9991044},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2112840274","doi":"10.14778/1920841.1920870","title":"Sampling the repairs of functional dependency violations under hard constraints","year":2010,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":127,"is_retracted":false,"has_abstract":true,"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; Dependency (UML); Class (philosophy); Functional dependency; Context (archaeology); Sampling (signal processing); Relation (database); Data integrity; Variety (cybernetics); Space (punctuation); Data mining; Metric (unit); Theoretical computer science; Relational database; Database; Artificial intelligence","score_opus":0.1812498346188758,"score_gpt":0.3696657815601582,"score_spread":0.18841594694128241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112840274","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":[0.92629546,0.000039803046,0.008185695,0.014130897,0.002090576,0.0010873767,0.00012208807,0.00005823748,0.047989838],"genre_scores_gemma":[0.99623656,0.0000070606734,0.00241368,0.00029666667,0.00006387834,0.000024664614,0.0000018669967,0.000005380852,0.000950246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99753034,0.000019346113,0.00064790936,0.00029311297,0.0013378346,0.00017142981],"domain_scores_gemma":[0.9980634,0.000503447,0.0005448339,0.00036893235,0.00047173174,0.00004766303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036449814,0.00010588369,0.00017233849,0.00010136135,0.00025766712,0.00010931443,0.0011034026,0.000044866978,0.0007046714],"category_scores_gemma":[0.001882149,0.00005459006,0.00016978575,0.00041298583,0.00042693946,0.0002808494,0.0005194222,0.00021372054,0.000032872733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000406563,0.00019969494,0.012779158,0.000028710534,0.000108756765,7.878107e-8,0.000861121,0.0001811694,0.08822781,0.8685724,0.014871586,0.014128816],"study_design_scores_gemma":[0.000885231,0.000087893015,0.22748715,0.0000849232,0.0001446285,0.000021484751,0.01379489,0.0007074735,0.035416216,0.68228227,0.03880276,0.00028507336],"about_ca_topic_score_codex":0.00004213702,"about_ca_topic_score_gemma":0.000041650997,"teacher_disagreement_score":0.21470799,"about_ca_system_score_codex":0.000020480677,"about_ca_system_score_gemma":0.000051850035,"threshold_uncertainty_score":0.77156574},"labels":[],"label_agreement":null},{"id":"W2113415503","doi":"10.14778/1687627.1687695","title":"Modeling and querying possible repairs in duplicate detection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":57,"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; Scalability; Data mining; Parameterized complexity; Cluster analysis; Identification (biology); Set (abstract data type); Database; Algorithm; Machine learning","score_opus":0.08693929288766766,"score_gpt":0.34729863073080464,"score_spread":0.260359337843137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113415503","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":[0.98984903,0.00009880213,0.0009361174,0.0031920713,0.00008745865,0.00035117197,0.0000019119432,0.000031364234,0.005452071],"genre_scores_gemma":[0.99872917,0.000051061652,0.0006796776,0.0002749681,0.000017679171,0.000012808088,1.6895997e-7,0.0000033024846,0.0002311365],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837416,0.00001306557,0.00048557957,0.0003369924,0.0006125953,0.00017761232],"domain_scores_gemma":[0.9994571,0.000045437155,0.00017373641,0.00017864746,0.000104446466,0.00004060034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027393175,0.00009031103,0.00016443146,0.00013561318,0.00010704423,0.00015058336,0.00048287498,0.000031039086,0.0000061367723],"category_scores_gemma":[0.0005686248,0.000058522335,0.000055368604,0.00050589826,0.000032900443,0.00043352577,0.00026482166,0.00009461305,0.0000054743105],"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":[0.00033501125,0.0005314434,0.010654226,0.000138553,0.000049845905,0.0000018954241,0.0068016145,0.007408602,0.14498919,0.07114186,0.002017694,0.75593007],"study_design_scores_gemma":[0.0017237636,0.00036844655,0.030036906,0.00032865774,0.000054425847,0.00002011553,0.009990656,0.27121586,0.14676873,0.5345029,0.004465778,0.0005237359],"about_ca_topic_score_codex":0.00018582193,"about_ca_topic_score_gemma":0.000045618708,"teacher_disagreement_score":0.7554063,"about_ca_system_score_codex":0.000048131842,"about_ca_system_score_gemma":0.000006082922,"threshold_uncertainty_score":0.23864715},"labels":[],"label_agreement":null},{"id":"W2115008552","doi":"10.5539/mas.v4n9p142","title":"Entropy Based Measurement of Text Dissimilarity for Duplicate – Detection","year":2010,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Similarity (geometry); Entropy (arrow of time); Data mining; Pattern recognition (psychology); Artificial intelligence; Physics; Image (mathematics)","score_opus":0.14603902885909179,"score_gpt":0.3735185434045063,"score_spread":0.2274795145454145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115008552","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":[0.043927614,0.0000032204853,0.95120996,0.00066046196,0.0003331129,0.000626922,0.00003423583,0.00003735025,0.0031670928],"genre_scores_gemma":[0.9909896,3.9510036e-7,0.008554999,0.000252715,0.000029272693,0.00010038136,0.0000018354224,0.000005512746,0.000065236374],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99564093,0.000027500737,0.00048557835,0.0007462484,0.0027618706,0.00033789067],"domain_scores_gemma":[0.99775714,0.0002214726,0.00026868292,0.001123465,0.00048180023,0.00014743676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012562683,0.00011903489,0.00020235559,0.00025415965,0.0004010502,0.00025636633,0.0016385369,0.000047227375,0.000070833616],"category_scores_gemma":[0.0014847877,0.00009104715,0.000076353266,0.00080813206,0.00061421364,0.0002931279,0.00024217775,0.00012524411,0.000042425356],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004895011,0.000090012334,0.000045734287,0.000007671457,0.0000020242173,7.1027365e-8,0.0000821832,0.00011845384,0.85948044,0.021201767,0.00022348155,0.118699186],"study_design_scores_gemma":[0.00057440024,0.000052878717,0.0057629636,0.000003786658,0.000013702401,2.9559223e-7,0.000100180965,0.2941508,0.53998744,0.13619547,0.022968134,0.00018995513],"about_ca_topic_score_codex":0.000021984157,"about_ca_topic_score_gemma":0.00021905388,"teacher_disagreement_score":0.947062,"about_ca_system_score_codex":0.000049716942,"about_ca_system_score_gemma":0.0001566179,"threshold_uncertainty_score":0.4354},"labels":[],"label_agreement":null},{"id":"W2115215982","doi":"10.14778/1453856.1453883","title":"Hashed samples","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Similarity (geometry); Estimator; A priori and a posteriori; Computer science; Overhead (engineering); Set (abstract data type); Sampling (signal processing); Cosine similarity; Algorithm; Data mining; Pattern recognition (psychology); Mathematics; Artificial intelligence; Statistics","score_opus":0.2910039101624485,"score_gpt":0.3717421828373335,"score_spread":0.08073827267488504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115215982","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":[0.9066988,0.00011239092,0.00029726283,0.008024189,0.0005471967,0.00058889657,0.00003887616,0.00006138077,0.08363099],"genre_scores_gemma":[0.99176335,0.000049432107,0.0014904855,0.00058604486,0.0000533831,0.000022701443,8.843631e-7,0.0000060975512,0.006027601],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974399,0.000015017461,0.0005259413,0.00032169532,0.0014859284,0.00021151378],"domain_scores_gemma":[0.99886304,0.00017271173,0.00033943067,0.0003123499,0.00025066856,0.00006179988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017999941,0.00011015458,0.00021698805,0.0001112632,0.00022911745,0.00008475884,0.001608782,0.000027633067,0.00023881749],"category_scores_gemma":[0.001475403,0.000061291445,0.00014360069,0.00051403855,0.00020424642,0.0003230026,0.0007911863,0.000077072356,0.0001401256],"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":[0.000083478175,0.00041628364,0.040988997,0.000052196898,0.000093921975,0.000001707678,0.0040231203,0.00002868511,0.018716447,0.2555075,0.6621273,0.017960351],"study_design_scores_gemma":[0.0008811202,0.00011983084,0.08030357,0.000049378672,0.000037110385,0.000025026126,0.0033977728,0.00008660491,0.11935536,0.13068919,0.6647803,0.0002747251],"about_ca_topic_score_codex":0.00008477276,"about_ca_topic_score_gemma":0.0000065381923,"teacher_disagreement_score":0.12481832,"about_ca_system_score_codex":0.000032165433,"about_ca_system_score_gemma":0.000021156167,"threshold_uncertainty_score":0.2989544},"labels":[],"label_agreement":null},{"id":"W2119457846","doi":"","title":"Privacy-Enhanced Public Name-Authority System for Building Research Communities","year":2011,"lang":"en","type":"article","venue":"Library and Archives Canada (Government of Canada)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Internet privacy; Information privacy; Public authority; Political science; Business; World Wide Web; Public administration; Computer science; Public relations","score_opus":0.1574086523976547,"score_gpt":0.3013402557264683,"score_spread":0.14393160332881358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119457846","genre_codex":"other","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":[0.2376306,0.00032129383,0.017475514,0.008327752,0.00091105053,0.001030618,0.0011155294,0.000049637838,0.733138],"genre_scores_gemma":[0.9888908,0.000037682024,0.0049714902,0.0003434215,0.000042561485,0.000038626604,0.000008623322,0.000013096459,0.0056536617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99389833,0.00058111665,0.00057961524,0.00032243982,0.004125924,0.0004925691],"domain_scores_gemma":[0.99631065,0.002380759,0.00023277297,0.0007642951,0.000006885886,0.00030465375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058648986,0.00015387706,0.00031862294,0.00009618662,0.0007208225,0.00017491539,0.0015217527,0.000028885523,0.000077490586],"category_scores_gemma":[0.00011369329,0.00013147845,0.00004179341,0.0002449095,0.00022974316,0.0010200806,0.00106284,0.00020246072,1.7114157e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027688715,0.000039052044,0.0025072987,0.00020628735,0.00005212471,0.000010381292,0.0009448466,0.0000033421793,0.0010761691,0.96525514,0.0045566084,0.025071857],"study_design_scores_gemma":[0.0010353473,0.00034307584,0.026685622,0.00032454444,0.000028720397,0.0000058947203,0.26662484,0.0037793838,0.11795923,0.10883736,0.47372326,0.0006527036],"about_ca_topic_score_codex":0.010066485,"about_ca_topic_score_gemma":0.042850927,"teacher_disagreement_score":0.8564178,"about_ca_system_score_codex":0.000016654527,"about_ca_system_score_gemma":0.0010762927,"threshold_uncertainty_score":0.9965256},"labels":[],"label_agreement":null},{"id":"W2125819120","doi":"10.1109/i-society18435.2011.5978521","title":"Managing and mapping data lineage for business intelligence and analytics applications in health care","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Ottawa","funders":"","keywords":"Dashboard; Computer science; Business intelligence; Analytics; Data science; Architecture; Automation; Health care; Interface (matter); World Wide Web; Database; Engineering","score_opus":0.556294991467182,"score_gpt":0.47637182578268755,"score_spread":0.07992316568449442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125819120","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":[0.00061329105,0.00042025687,0.994638,0.0012600663,0.000029645038,0.0004431715,0.000100833044,0.000015233524,0.0024794806],"genre_scores_gemma":[0.77541703,0.0014228375,0.21910597,0.002288456,0.000054979857,0.00006588223,0.00035861245,0.000013475633,0.0012727573],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99881077,0.000036759466,0.0004075254,0.0004349287,0.00017447007,0.00013552536],"domain_scores_gemma":[0.99869275,0.00030432944,0.000100162935,0.0007573525,0.00008777951,0.00005760275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002192955,0.000063832296,0.0001435021,0.00020689821,0.000110413646,0.00013602493,0.00061851117,0.000016689664,0.000020330628],"category_scores_gemma":[0.00030842627,0.00004959918,0.000007075994,0.0005621216,0.000060438433,0.00030279483,0.0007734744,0.00003508523,0.0000047387316],"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":[0.000011522521,0.000053221993,0.0069348617,0.0003628084,0.000013416223,0.0000012238783,0.007296694,0.00004849198,0.0000012502765,0.19150661,0.0031852568,0.7905846],"study_design_scores_gemma":[0.00040086627,0.000059933405,0.061222102,0.000108443644,0.000022486578,0.000002553489,0.19254105,0.08980148,0.000048255675,0.09250876,0.5628388,0.00044524757],"about_ca_topic_score_codex":0.00074676593,"about_ca_topic_score_gemma":0.002172066,"teacher_disagreement_score":0.7901394,"about_ca_system_score_codex":0.000010973066,"about_ca_system_score_gemma":0.00002390895,"threshold_uncertainty_score":0.20225959},"labels":[],"label_agreement":null},{"id":"W2127665671","doi":"10.2196/medinform.3090","title":"Designing an Algorithm to Preserve Privacy for Medical Record Linkage With Error-Prone Data","year":2014,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University at Buffalo; National Natural Science Foundation of China; Oklahoma Center for the Advancement of Science and Technology; National Science Foundation","keywords":"Computer science; Record linkage; Linkage (software); Information privacy; Exception handling; Data mining; Computer security; Algorithm; Medicine; Programming language","score_opus":0.22247027615608875,"score_gpt":0.4594914703253406,"score_spread":0.23702119416925185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127665671","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":[0.00541402,0.0000045049815,0.9844952,0.0063453363,0.0003029367,0.001109968,0.00013579462,0.00011295827,0.0020792808],"genre_scores_gemma":[0.0061576036,0.000013615822,0.9741135,0.016710214,0.0007152044,0.00028335146,0.00091871613,0.00003212818,0.001055646],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.991275,0.00029954137,0.0016621221,0.00044322814,0.0057561724,0.0005639324],"domain_scores_gemma":[0.99269706,0.0024075406,0.00038895104,0.002821538,0.0002701515,0.0014147621],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.019898275,0.00022612828,0.0004923257,0.00022168434,0.00021282544,0.00047119375,0.006236363,0.00025103323,0.0009092438],"category_scores_gemma":[0.019251386,0.00014406486,0.000049996775,0.0005780962,0.00022030779,0.00219956,0.0026852216,0.00041662334,0.00041637287],"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":[0.00004894394,0.0001301328,0.00006323808,0.00008318757,0.000025223831,0.0000058095598,0.002895963,0.0000072850094,4.0417754e-7,0.0011079195,0.1597318,0.83590007],"study_design_scores_gemma":[0.000960503,0.0006118847,0.00013548302,0.0001505185,0.000015871286,0.000008704689,0.0029018298,0.34608316,0.00001300624,0.0023384192,0.6465567,0.0002239349],"about_ca_topic_score_codex":0.00003715764,"about_ca_topic_score_gemma":0.00017002999,"teacher_disagreement_score":0.83567613,"about_ca_system_score_codex":0.000028685192,"about_ca_system_score_gemma":0.00031705963,"threshold_uncertainty_score":0.9991404},"labels":[],"label_agreement":null},{"id":"W2128322880","doi":"10.4018/jdwm.2005040101","title":"The Use of Smart Tokens in Cleaning Integrated Warehouse Data","year":2005,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":24,"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; Data warehouse; Security token; Database; Alphanumeric; Matching (statistics); Data mining; Unique identifier; Identifier; Computer security","score_opus":0.5821457750325668,"score_gpt":0.47436071499941795,"score_spread":0.10778506003314886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128322880","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":[0.92222226,0.001280303,0.05856626,0.013493236,0.002221673,0.0001600704,0.0017391635,0.000025577168,0.00029147408],"genre_scores_gemma":[0.9577079,0.000624631,0.040554605,0.00052630255,0.00025410892,2.8920726e-7,0.00013728805,0.000012135222,0.00018273189],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99686223,0.00023211338,0.0012441047,0.0002994127,0.001202144,0.00015997453],"domain_scores_gemma":[0.9953704,0.0022580156,0.0008217167,0.0010379534,0.00044961183,0.000062341845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069025056,0.00010224451,0.00023141582,0.00036150982,0.0001041627,0.00072538835,0.0038841926,0.00003392077,0.000024486024],"category_scores_gemma":[0.007062009,0.0000656079,0.00003136472,0.00025289075,0.00012865584,0.003771463,0.0023577914,0.00021561277,0.000004682942],"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":[0.00018133433,0.0000729918,0.004116633,0.0000023004206,0.00009823968,0.000047148038,0.0011775099,0.0013580807,0.000052210835,0.00023706906,0.042115923,0.95054054],"study_design_scores_gemma":[0.0006335841,0.000053594722,0.0022566149,0.00027160277,0.000025671114,0.00009836535,0.0046516424,0.049230497,0.000048526148,0.00018970392,0.9424344,0.00010584741],"about_ca_topic_score_codex":0.00020505837,"about_ca_topic_score_gemma":0.0015587712,"teacher_disagreement_score":0.9504347,"about_ca_system_score_codex":0.00004203997,"about_ca_system_score_gemma":0.00011139021,"threshold_uncertainty_score":0.84543943},"labels":[],"label_agreement":null},{"id":"W2129197327","doi":"10.1145/2661829.2661858","title":"CONDOR","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Computer science; Data integrity; Functional dependency; Constraint (computer-aided design); Visualization; Set (abstract data type); Semantics (computer science); Dependency (UML); Data mining; Database; Software engineering; Programming language; Relational database","score_opus":0.3088274691573679,"score_gpt":0.4778635020973403,"score_spread":0.16903603293997238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129197327","genre_codex":"other","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":[0.005731976,0.000002961848,0.24103722,0.0036337606,0.00020339234,0.0000350232,0.0000018697145,0.00003396936,0.74931985],"genre_scores_gemma":[0.8737236,8.05304e-7,0.0023153531,0.0066778315,0.000040998708,0.0000018209699,0.0000018526243,0.0000013529633,0.117236376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991389,0.00008061927,0.00014983525,0.00013833887,0.00042478257,0.000067525885],"domain_scores_gemma":[0.99907637,0.0004314986,0.000026754155,0.00039820533,0.000032401036,0.000034803004],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002911843,0.000024378747,0.000057603494,0.000041380812,0.000032596392,0.00013135631,0.0003907347,0.000008814491,0.0046308786],"category_scores_gemma":[0.0014786674,0.000014517328,0.000020603391,0.00012082597,0.000023425353,0.0001348813,0.00012515862,0.000015554624,0.009702091],"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":[8.00996e-7,0.000006055491,0.00013958769,2.4324274e-7,8.662142e-7,1.3223085e-7,0.000016008777,0.0000018385792,0.000012796654,0.5175249,0.33293328,0.1493635],"study_design_scores_gemma":[0.00006313743,0.00000962587,0.0015415129,2.4433854e-7,6.055858e-7,1.3844492e-7,0.00011990021,0.0005035028,0.00011384494,0.12544693,0.87217677,0.000023787588],"about_ca_topic_score_codex":0.000020643318,"about_ca_topic_score_gemma":0.000037537055,"teacher_disagreement_score":0.8679916,"about_ca_system_score_codex":0.0000018582368,"about_ca_system_score_gemma":0.000002672087,"threshold_uncertainty_score":0.996279},"labels":[],"label_agreement":null},{"id":"W2129684888","doi":"10.1145/1458082.1458197","title":"Records retention in relational database systems","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":28,"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","keywords":"Data retention; Records management; Scope (computer science); Legislation; Computer science; Identification (biology); Database; Relational database; Business; Information retrieval; Knowledge management; Computer security; Law; Political science","score_opus":0.4765472888744886,"score_gpt":0.41720244780285376,"score_spread":0.059344841071634846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129684888","genre_codex":"other","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":[0.31263152,0.0001654707,0.2372552,0.0028264527,0.0022918025,0.0005360763,0.00015722557,0.00010545334,0.4440308],"genre_scores_gemma":[0.8903721,0.000048448237,0.0035750137,0.00032912474,0.000070469636,0.000014768281,0.00016253021,0.0000036466558,0.10542388],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808484,0.00019617868,0.0004687563,0.00027067543,0.00087727216,0.00010228477],"domain_scores_gemma":[0.999038,0.00032312697,0.00008405472,0.00045117846,0.000065294415,0.00003836359],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003733236,0.0000459284,0.00009673256,0.00021331757,0.00007508365,0.00005592879,0.00027489493,0.000025434345,0.00095247943],"category_scores_gemma":[0.0010660859,0.000034114888,0.000026811982,0.00047668564,0.000034764536,0.0007353862,0.00013327033,0.00005790035,0.0015399549],"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":[0.000025130914,0.00009058279,0.034523997,0.0000065209397,0.000005221748,0.000044092376,0.00019000054,0.00037629323,0.000032034444,0.39803487,0.56224597,0.004425312],"study_design_scores_gemma":[0.0005605252,0.000035122866,0.20463638,0.000026704356,0.0000033217523,0.000023403429,0.0016773385,0.016800435,0.000012359629,0.011933246,0.76411223,0.00017891705],"about_ca_topic_score_codex":0.00069410086,"about_ca_topic_score_gemma":0.0003013516,"teacher_disagreement_score":0.5777406,"about_ca_system_score_codex":0.000026698246,"about_ca_system_score_gemma":0.000023652245,"threshold_uncertainty_score":0.9999608},"labels":[],"label_agreement":null},{"id":"W2131060875","doi":"","title":"Extending dependencies with conditions","year":2007,"lang":"en","type":"article","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council","keywords":"Undecidable problem; Computer science; Functional dependency; EXPTIME; Consistency (knowledge bases); Theoretical computer science; Data integrity; Inference; Decidability; Static analysis; Heuristic; Schema (genetic algorithms); Algorithm; Data mining; Computational complexity theory; Programming language; PSPACE; Artificial intelligence; Machine learning; Relational database; Database","score_opus":0.36871996505199645,"score_gpt":0.4567409499993181,"score_spread":0.08802098494732163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131060875","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":[0.6753179,0.000253275,0.17353146,0.0068095797,0.0012760788,0.0011816452,0.00017650926,0.0002288648,0.14122471],"genre_scores_gemma":[0.977205,0.0001323944,0.002529804,0.000068597816,0.00028647043,0.0000020695347,0.000037644015,0.000013737827,0.019724298],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99197805,0.00024179807,0.0004784186,0.00086843554,0.00541217,0.0010210999],"domain_scores_gemma":[0.9924735,0.003788998,0.00026625494,0.0012305769,0.0017173456,0.0005233702],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022389434,0.00021028475,0.00044043697,0.0021762266,0.0011242342,0.00020099993,0.0023650425,0.00013458781,0.018868087],"category_scores_gemma":[0.002267452,0.00018838434,0.00017200058,0.0032755658,0.0015441909,0.0020024541,0.001222966,0.0006119211,0.0001254095],"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":[0.00056461967,0.0003745437,0.004496933,0.0000114197255,0.00015693308,0.00061717647,0.012365985,0.000087282904,0.001929283,0.019780815,0.9367011,0.022913894],"study_design_scores_gemma":[0.001537613,0.0006666294,0.010912622,0.0001356643,0.000049178714,0.000022617885,0.34994486,0.00035835645,0.0011328872,0.06766613,0.5670775,0.00049594627],"about_ca_topic_score_codex":0.0004395611,"about_ca_topic_score_gemma":0.0005272553,"teacher_disagreement_score":0.36962363,"about_ca_system_score_codex":0.00017726715,"about_ca_system_score_gemma":0.00020056072,"threshold_uncertainty_score":0.9820288},"labels":[],"label_agreement":null},{"id":"W2131815873","doi":"10.1145/1559845.1559891","title":"Incremental maintenance of length normalized indexes for approximate string matching","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Toronto","funders":"","keywords":"Search engine indexing; Computer science; Security token; String (physics); Approximate string matching; Data mining; String searching algorithm; Matching (statistics); Key (lock); Similarity (geometry); False positive paradox; Feature (linguistics); Information retrieval; String metric; Limit (mathematics); Pattern matching; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.13023303475302814,"score_gpt":0.40500304611254945,"score_spread":0.2747700113595213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131815873","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":[0.33351138,0.000026278958,0.6426237,0.0014468306,0.00018292839,0.0006227885,0.00009586925,0.00006720125,0.021422977],"genre_scores_gemma":[0.97082096,0.000009201462,0.026727274,0.00077139674,0.000021986638,0.000008151767,0.000009775209,0.0000035943576,0.0016276641],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99812955,0.00005893574,0.00061852735,0.0002846738,0.00067362905,0.00023466116],"domain_scores_gemma":[0.99893206,0.00030380368,0.0002274572,0.00039813324,0.00009094511,0.000047623158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036449295,0.00009488551,0.00023923333,0.00014035152,0.0000930063,0.00013322945,0.0006540548,0.0000275939,0.00016961725],"category_scores_gemma":[0.00043377557,0.00006664589,0.000090167516,0.00023347104,0.000036765217,0.00056132465,0.00017341133,0.00004740156,0.000020560825],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020925104,0.00018406195,0.0004870936,0.0000339462,0.000029655917,0.0000018227424,0.00082102936,0.0001750506,0.004972154,0.7796524,0.01686542,0.1965681],"study_design_scores_gemma":[0.0045398595,0.0005273489,0.012748862,0.0001146911,0.00004189234,0.000005011044,0.01541176,0.006552519,0.04631647,0.8481599,0.06495101,0.00063067424],"about_ca_topic_score_codex":0.00009008196,"about_ca_topic_score_gemma":0.00005204213,"teacher_disagreement_score":0.63730955,"about_ca_system_score_codex":0.000019515544,"about_ca_system_score_gemma":0.00001406123,"threshold_uncertainty_score":0.27177405},"labels":[],"label_agreement":null},{"id":"W2131821459","doi":"10.5539/cis.v4n4p46","title":"An Integrated Conceptual Model for Temporal Data Warehouse Security","year":2011,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data warehouse; Conceptual model; Dimensional modeling; Temporal database; Warehouse; Data science; Data mining; Database","score_opus":0.40095079336145106,"score_gpt":0.4196588554264984,"score_spread":0.018708062065047326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131821459","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":[0.020501725,0.0000034903494,0.97740513,0.000089769695,0.0002663514,0.00022349888,0.00031414235,0.000053444957,0.001142425],"genre_scores_gemma":[0.9144179,0.000005095091,0.08351019,0.0018303483,0.000024060619,0.0000056245863,0.00017889487,0.0000016271231,0.000026260504],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824244,0.000038383085,0.000491514,0.00032897384,0.00070797256,0.00019071795],"domain_scores_gemma":[0.99811757,0.00008419246,0.00016912114,0.0010211476,0.00045431269,0.00015365191],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0053700735,0.00008545324,0.00012247497,0.00025406474,0.0003069205,0.0008171018,0.0024088516,0.000026729002,0.000030181292],"category_scores_gemma":[0.0003598372,0.000060508366,0.000016031556,0.0005513203,0.0006175935,0.027685083,0.00085656444,0.00005476024,0.00004824109],"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":[0.00008988681,0.00014065312,0.0011790749,0.000019117384,0.00000812076,4.996828e-7,0.08909682,0.001786553,0.000006504798,0.28746304,0.07066248,0.54954726],"study_design_scores_gemma":[0.00021090909,0.000077993274,0.0009973746,0.0000031517172,0.0000020868476,0.0000012282305,0.0018408952,0.92517245,0.00002264256,0.006762921,0.06481486,0.000093502014],"about_ca_topic_score_codex":0.000042419884,"about_ca_topic_score_gemma":0.000015607204,"teacher_disagreement_score":0.92338586,"about_ca_system_score_codex":0.000012524516,"about_ca_system_score_gemma":0.0001395699,"threshold_uncertainty_score":0.9859142},"labels":[],"label_agreement":null},{"id":"W2132698877","doi":"10.5596/c13-009","title":"Systematic Approaches to a Successful Literature Review","year":2013,"lang":"fr","type":"article","venue":"Journal of the Canadian Health Libraries Association / Journal de l Association de bilbiothèques de la santé du Canada","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":871,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Systematic review; Epistemology; History; Psychology; Engineering ethics; Political science; Philosophy; MEDLINE; Engineering; Law","score_opus":0.033106520738290075,"score_gpt":0.2956478694425366,"score_spread":0.26254134870424656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132698877","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028428764,0.53701717,0.0005802382,0.4522319,0.004130302,0.001288384,0.00052899146,0.0000135033115,0.001366602],"genre_scores_gemma":[0.077533185,0.5000281,0.0075903167,0.3731729,0.006142571,0.00010055307,0.000041384952,0.00014194394,0.035249066],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9750219,0.015414803,0.003745244,0.0003364936,0.003610084,0.001871497],"domain_scores_gemma":[0.9758449,0.008238387,0.009963109,0.0006060528,0.002189385,0.0031581284],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042812712,0.00045300034,0.0015330976,0.00065610715,0.0016334796,0.009237141,0.0025795712,0.0006356114,0.00091616175],"category_scores_gemma":[0.053617597,0.00034707427,0.0006287993,0.002355152,0.0000686936,0.0037231755,0.00019990822,0.0022670205,0.000036382233],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000010190784,0.00005395401,0.020308813,0.004763381,0.0005700068,0.00012760438,0.0034388597,0.00024890146,5.9044874e-7,0.0042771087,0.96379524,0.0024053412],"study_design_scores_gemma":[0.00059986464,0.00014861731,0.027874338,0.031589463,0.00038649174,0.0014175976,0.0026404157,0.00049944036,0.000008342927,0.01601362,0.9183198,0.0005020105],"about_ca_topic_score_codex":0.3774697,"about_ca_topic_score_gemma":0.64958155,"teacher_disagreement_score":0.27211183,"about_ca_system_score_codex":0.048521813,"about_ca_system_score_gemma":0.050052408,"threshold_uncertainty_score":0.99999714},"labels":[],"label_agreement":null},{"id":"W2133647765","doi":"10.1109/wi.2006.134","title":"Privacy Preserving Multiagent Probabilistic Reasoning about Ambiguous Contexts: A Case Study","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Dalhousie University; Saint Mary's University","funders":"","keywords":"Computer science; Probabilistic logic; Inference; Context (archaeology); Bayesian network; Multi-agent system; Representation (politics); Artificial intelligence; Domain (mathematical analysis); Ubiquitous computing; Intelligent agent; Human–computer interaction; Data science","score_opus":0.1407579980479361,"score_gpt":0.4195611289486224,"score_spread":0.2788031309006863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133647765","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":[0.9606822,0.00011459938,0.016808132,0.00038391343,0.0002643568,0.0016659045,0.000021211132,0.00018234715,0.019877303],"genre_scores_gemma":[0.97966135,0.0000013381208,0.0027354576,0.00026650963,0.00008431765,0.000101121026,0.0000074803856,0.000013535042,0.017128907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956932,0.00057481055,0.0010447673,0.00085766654,0.0014215466,0.00040802942],"domain_scores_gemma":[0.9970183,0.00067376776,0.00026435117,0.0016474498,0.00027009277,0.00012604007],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054406985,0.00020837742,0.00034294353,0.00019374775,0.00037182876,0.0009809351,0.0011502512,0.000042417076,0.00095937686],"category_scores_gemma":[0.0044391616,0.00014895001,0.00009643294,0.00057339703,0.000079714635,0.00063995906,0.0012162295,0.00013048499,0.00041680754],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027019362,0.013643296,0.07907989,0.00018851002,0.00034010297,0.031038497,0.028120967,0.008399836,0.00015006129,0.07444852,0.35384282,0.4104773],"study_design_scores_gemma":[0.01051445,0.0016536453,0.2992029,0.0002399746,0.00039227665,0.0017011436,0.20488021,0.07053066,0.00018350227,0.072270624,0.3357508,0.0026798535],"about_ca_topic_score_codex":0.032373596,"about_ca_topic_score_gemma":0.0143539235,"teacher_disagreement_score":0.40779746,"about_ca_system_score_codex":0.00006831903,"about_ca_system_score_gemma":0.000041607593,"threshold_uncertainty_score":0.99995387},"labels":[],"label_agreement":null},{"id":"W2134077349","doi":"","title":"The TALP participation at TAC-KBP 2012","year":2012,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.07575633838207113,"score_gpt":0.39478770219948534,"score_spread":0.3190313638174142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134077349","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":[0.45912373,0.010330654,0.4135467,0.0063994317,0.00055863085,0.0017589633,0.00019080513,0.00013573519,0.107955344],"genre_scores_gemma":[0.98938257,0.000119574535,0.0000740396,0.000098889184,0.00007744468,0.0001789246,0.000015062926,0.0000032396267,0.010050279],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99886686,0.00024485835,0.00030926295,0.00012484178,0.000295769,0.00015842791],"domain_scores_gemma":[0.99724907,0.0018642343,0.00016910746,0.00056971936,0.00008431916,0.00006352574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057288595,0.00006192035,0.00009641535,0.00003884984,0.00049243757,0.0000766454,0.00035081842,0.000024482642,0.00018175566],"category_scores_gemma":[0.00040784222,0.00003657915,0.000028175873,0.00023784844,0.00045033978,0.00047059622,0.00022216192,0.000035007415,0.00023094093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002814335,0.000033241035,0.0005833757,0.0000034566995,0.000008027095,8.893037e-9,0.0006456997,0.0000022075235,0.000085146436,0.91427267,0.0048127337,0.07952526],"study_design_scores_gemma":[0.000041915522,0.000008854599,0.005309023,6.398066e-7,0.000014070245,4.2717488e-7,0.0015684875,0.0000035737437,0.0011882246,0.48075655,0.51106864,0.000039569462],"about_ca_topic_score_codex":0.000007479947,"about_ca_topic_score_gemma":0.000022356524,"teacher_disagreement_score":0.53025883,"about_ca_system_score_codex":0.0000074090194,"about_ca_system_score_gemma":0.000007742344,"threshold_uncertainty_score":0.37874815},"labels":[],"label_agreement":null},{"id":"W2135797260","doi":"10.1287/isre.2014.0537","title":"The IQ of the Crowd: Understanding and Improving Information Quality in Structured User-Generated Content","year":2014,"lang":"en","type":"article","venue":"Information Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":152,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Information quality; Quality (philosophy); Class (philosophy); Data science; Data mining; Knowledge management; Information retrieval; Information system; Artificial intelligence","score_opus":0.5163197398913468,"score_gpt":0.4719992757335768,"score_spread":0.04432046415777002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135797260","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":[0.860241,0.00010699713,0.11327121,0.0038494638,0.0015878659,0.0031829923,0.0001602752,0.00004581218,0.01755441],"genre_scores_gemma":[0.9996291,0.000010025643,0.000021507723,0.00008398588,0.000017344015,0.000028110904,0.000012900098,0.0000017564806,0.00019526246],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938134,0.001787576,0.0015160146,0.00010372997,0.0025110682,0.00026819535],"domain_scores_gemma":[0.9960116,0.0018745294,0.0005778554,0.0006620565,0.00081932574,0.0000546294],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036874745,0.00007746203,0.00017644287,0.00038735845,0.0005621746,0.0016930446,0.00078252336,0.00006800729,0.0000056299714],"category_scores_gemma":[0.008748434,0.000039393406,0.000033102817,0.0010189431,0.00022361305,0.0031797835,0.00046044224,0.00023225331,0.000034740482],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013206234,0.000010683678,0.007926916,0.00029098048,0.000023050616,7.2141304e-8,0.011058658,0.0018316936,0.00043436696,0.90936536,0.006430561,0.06249559],"study_design_scores_gemma":[0.0027200978,0.00014006787,0.16594416,0.00019108997,0.000006861666,0.000005377116,0.29726937,0.11922998,0.00127674,0.0150867365,0.3977943,0.00033520584],"about_ca_topic_score_codex":0.002320025,"about_ca_topic_score_gemma":0.00076469686,"teacher_disagreement_score":0.89427865,"about_ca_system_score_codex":0.00018069039,"about_ca_system_score_gemma":0.00008854785,"threshold_uncertainty_score":0.9996013},"labels":[],"label_agreement":null},{"id":"W2137775416","doi":"","title":"Improving data quality: consistency and accuracy","year":2007,"lang":"en","type":"article","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":312,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"Biotechnology and Biological Sciences Research Council; Engineering and Physical Sciences Research Council; Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Consistency (knowledge bases); Computer science; Data consistency; Data integrity; Consistency model; Sequential consistency; Set (abstract data type); Weak consistency; Heuristic; Data mining; Data quality; Quality (philosophy); Strong consistency; Database; Artificial intelligence; Mathematics; Programming language","score_opus":0.5859534533824458,"score_gpt":0.5006272625830552,"score_spread":0.08532619079939052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137775416","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":[0.68779165,0.0017886609,0.2007928,0.025579656,0.00316596,0.0024372502,0.00087880186,0.00033278903,0.077232435],"genre_scores_gemma":[0.9793284,0.0007114592,0.0068080877,0.00021645853,0.00059778546,0.0000012603306,0.00014986635,0.00002147095,0.01216522],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9915153,0.00048537855,0.0008395064,0.001484528,0.004661797,0.0010135111],"domain_scores_gemma":[0.9816967,0.011745713,0.00054227514,0.0036943196,0.0016184957,0.0007024857],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054474242,0.00023196223,0.00059742236,0.0014731847,0.0009555885,0.0003199072,0.004640433,0.00017603466,0.00505869],"category_scores_gemma":[0.02253627,0.00022994717,0.00012254153,0.0021321608,0.0017340773,0.0034312073,0.007978522,0.0006815409,0.00004847823],"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":[0.00038799347,0.00023722078,0.0026316736,0.000029033203,0.00009950793,0.00016422344,0.007009476,0.0000019526242,0.001838142,0.0074478444,0.628711,0.35144195],"study_design_scores_gemma":[0.0016257545,0.00027437892,0.0056421016,0.000081656784,0.000049830745,0.000009355788,0.23389529,0.0014653686,0.00026303492,0.04320715,0.71297544,0.00051060814],"about_ca_topic_score_codex":0.0023503422,"about_ca_topic_score_gemma":0.00060308113,"teacher_disagreement_score":0.35093135,"about_ca_system_score_codex":0.0001003866,"about_ca_system_score_gemma":0.0002726957,"threshold_uncertainty_score":0.9958508},"labels":[],"label_agreement":null},{"id":"W2137811660","doi":"10.1140/epjds/s13688-014-0011-3","title":"Exploiting citation networks for large-scale author name disambiguation","year":2014,"lang":"en","type":"article","venue":"EPJ Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Metadata; Ranking (information retrieval); Citation; Similarity (geometry); Cluster analysis; Precision and recall; Bibliographic coupling; Parameterized complexity; Heuristics","score_opus":0.3376502821107572,"score_gpt":0.46811139645195754,"score_spread":0.13046111434120033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137811660","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":[0.010366115,0.000016036676,0.9838091,0.0023691903,0.0009880613,0.00030379582,0.00032421478,0.000054194355,0.0017692922],"genre_scores_gemma":[0.94888914,0.0000056571007,0.047843687,0.0010523499,0.00032146164,0.0000376039,0.00066229457,0.000008421314,0.0011793865],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961376,0.00017339672,0.00052927295,0.0010376145,0.0016696863,0.00045243354],"domain_scores_gemma":[0.99593645,0.0013051842,0.00028571786,0.0020501306,0.00028329328,0.00013923249],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03493439,0.00010174597,0.00015646641,0.00021792413,0.000809848,0.0011719317,0.0036839843,0.000034471876,0.00009560783],"category_scores_gemma":[0.017893953,0.00008225974,0.000032428245,0.0012826668,0.00022939655,0.0051701115,0.0013769515,0.00007587486,0.00020451988],"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":[0.000030627107,0.00014335386,0.0012079381,0.00001758145,0.000005758546,4.9335546e-7,0.002202626,0.002575997,0.0007175249,0.24468563,0.09711516,0.6512973],"study_design_scores_gemma":[0.00020867826,0.000036720678,0.0053847646,0.000011961335,0.0000070949536,4.2407942e-7,0.002097685,0.7581882,0.00006551889,0.019250482,0.21461946,0.00012904497],"about_ca_topic_score_codex":0.000023081107,"about_ca_topic_score_gemma":0.0001291563,"teacher_disagreement_score":0.938523,"about_ca_system_score_codex":0.000033677377,"about_ca_system_score_gemma":0.00005842218,"threshold_uncertainty_score":0.99986494},"labels":[],"label_agreement":null},{"id":"W2140609014","doi":"10.1145/1007568.1007650","title":"Information-theoretic tools for mining database structure from large data sets","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":55,"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 Toronto","funders":"","keywords":"Computer science; Data mining; Redundancy (engineering); Categorical variable; Ranking (information retrieval); Data redundancy; Data modeling; Set (abstract data type); Information retrieval; Database; Machine learning","score_opus":0.21997362013458427,"score_gpt":0.4288470871589206,"score_spread":0.20887346702433635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140609014","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":[0.058004178,0.000028114562,0.86764926,0.0030478498,0.00055643765,0.0005469297,0.06534448,0.00007341007,0.0047493326],"genre_scores_gemma":[0.78367525,0.000011034987,0.16384673,0.009574618,0.00011715085,0.000015437992,0.0423777,0.000009415262,0.00037266474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980547,0.000050123766,0.0005562114,0.00031826747,0.0007876337,0.00023310672],"domain_scores_gemma":[0.9965046,0.0009584162,0.00016623805,0.0021824117,0.00010319009,0.00008516572],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023737205,0.00010870059,0.00016518804,0.00011017703,0.00017006365,0.0011420049,0.0021077297,0.00004376587,0.002035787],"category_scores_gemma":[0.0061313454,0.000075993674,0.00003180579,0.00024697307,0.000044390996,0.007230584,0.0013132088,0.00005734218,0.00044551984],"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":[0.000038575785,0.00004880699,0.00008124265,0.000020423844,0.000038829447,0.0000022447555,0.0020273968,0.00018889386,0.000025495689,0.5513182,0.3340656,0.11214425],"study_design_scores_gemma":[0.0013104781,0.000024018718,0.0006385615,0.000017498398,0.000024702831,9.173102e-7,0.010356602,0.0034648485,0.0001928241,0.21460453,0.7691741,0.00019090842],"about_ca_topic_score_codex":0.00010073519,"about_ca_topic_score_gemma":0.00043657696,"teacher_disagreement_score":0.72567105,"about_ca_system_score_codex":0.000017295384,"about_ca_system_score_gemma":0.000064431755,"threshold_uncertainty_score":0.9998949},"labels":[],"label_agreement":null},{"id":"W2142472956","doi":"10.1109/icde.2011.5767833","title":"A unified model for data and constraint repair","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Data integrity; Scalability; Constraint (computer-aided design); Data quality; Data modeling; Set (abstract data type); Data mining; Semantics (computer science); Data model (GIS); Quality (philosophy); Database; Artificial intelligence; Programming language; Engineering","score_opus":0.7150539177874393,"score_gpt":0.46880357717375065,"score_spread":0.24625034061368867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142472956","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":[0.0019669165,0.000012405332,0.9197759,0.0005778829,0.00006147511,0.0002342874,0.00027979235,0.00006592048,0.07702541],"genre_scores_gemma":[0.5957312,0.000014628129,0.37357965,0.0026136383,0.000017776045,0.000014987006,0.00007094664,0.0000056323165,0.027951557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895984,0.00003245888,0.00026112434,0.0003909208,0.00024831007,0.0001073466],"domain_scores_gemma":[0.99836373,0.000260719,0.00005036132,0.0012095565,0.000055985256,0.000059627666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036804986,0.000049381313,0.00009880316,0.000052166462,0.000057692625,0.00007262633,0.00074203085,0.000020820607,0.00030043456],"category_scores_gemma":[0.000997706,0.000032782053,0.000022623324,0.000074712036,0.00010293257,0.0003787222,0.00072899245,0.000021413161,0.000045220982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028019873,0.000041800267,0.0001042755,0.0000055160795,0.000015039605,0.0000012004627,0.00067718566,0.0000036638403,0.000005540262,0.70500517,0.24509294,0.049019635],"study_design_scores_gemma":[0.00020542543,0.000023344866,0.00015404275,0.0000016151718,0.000009602936,9.2989774e-7,0.0016647257,0.6854412,0.000013858426,0.22719693,0.08522347,0.000064828244],"about_ca_topic_score_codex":0.00007767727,"about_ca_topic_score_gemma":0.0002344562,"teacher_disagreement_score":0.68543756,"about_ca_system_score_codex":0.0000024444582,"about_ca_system_score_gemma":0.000024344232,"threshold_uncertainty_score":0.3289548},"labels":[],"label_agreement":null},{"id":"W2143101325","doi":"10.1287/isre.1080.0189","title":"Is Query Reuse Potentially Harmful? Anchoring and Adjustment in Adapting Existing Database Queries","year":2008,"lang":"en","type":"article","venue":"Information Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Database; Anchoring; Domain (mathematical analysis); Correctness; Reuse; Sample (material); Task (project management); SQL; Information retrieval; Query language; Quality (philosophy); Psychology; Programming language","score_opus":0.5884636912233069,"score_gpt":0.5004324123803812,"score_spread":0.08803127884292572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143101325","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":[0.8782135,0.002255283,0.041660994,0.0031909526,0.0017035188,0.0031577032,0.00048460302,0.00021440253,0.06911904],"genre_scores_gemma":[0.99477255,0.0004883873,0.0018885451,0.00021303348,0.00017640209,0.000116129915,0.00006685932,0.000008391315,0.0022697062],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99400574,0.0007352798,0.0013539082,0.00031565127,0.0031144882,0.00047495455],"domain_scores_gemma":[0.99688363,0.0009140027,0.00027614902,0.0010381822,0.0007414144,0.00014662166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018830696,0.00012273928,0.00025098128,0.0011577886,0.00050006586,0.0007468474,0.0008621597,0.000063288164,0.000052998792],"category_scores_gemma":[0.007244786,0.00010320793,0.00003183967,0.0011412412,0.00016451025,0.005607742,0.0013822882,0.00032166715,0.0004812626],"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":[0.00042246754,0.00020941856,0.02748586,0.0015338882,0.000100247205,0.00022183148,0.11432608,0.0021767656,0.0006937404,0.07377587,0.3529612,0.42609262],"study_design_scores_gemma":[0.001275324,0.00011011674,0.036511697,0.00058172515,0.000004248765,0.000076599164,0.09042189,0.02241226,0.00031165069,0.0006127571,0.8472672,0.00041454533],"about_ca_topic_score_codex":0.0034852207,"about_ca_topic_score_gemma":0.00013678591,"teacher_disagreement_score":0.494306,"about_ca_system_score_codex":0.00013837183,"about_ca_system_score_gemma":0.00013986124,"threshold_uncertainty_score":0.86732084},"labels":[],"label_agreement":null},{"id":"W2143280119","doi":"10.1111/j.1749-8198.2008.00150.x","title":"Database Ethnographies Using Social Science Methodologies to Enhance Data Analysis and Interpretation","year":2008,"lang":"en","type":"article","venue":"Geography Compass","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":36,"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":"Metadata; Data science; Context (archaeology); Ethnography; Meaning (existential); Computer science; Data collection; Sociology; World Wide Web; Social science; Geography; Epistemology","score_opus":0.44097812542131515,"score_gpt":0.5281685338296038,"score_spread":0.08719040840828868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143280119","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":[0.33078185,0.00013008584,0.6675084,0.00051568437,0.00016950653,0.00013534319,0.00030044635,0.000050196453,0.00040849412],"genre_scores_gemma":[0.84953946,0.00005286343,0.14975195,0.00052714284,0.000030039851,0.0000059801278,0.00007594978,0.0000035266694,0.000013109083],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9960658,0.0005005166,0.0005270644,0.0011173481,0.0014400124,0.00034925036],"domain_scores_gemma":[0.99676025,0.00094781065,0.0002325762,0.0016556613,0.00027397153,0.0001297173],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009708982,0.00015445497,0.0004101834,0.0033562635,0.0010507929,0.0004757222,0.0026101505,0.000032483975,0.0000336785],"category_scores_gemma":[0.0021209288,0.00012841927,0.00012000003,0.012223196,0.0015119988,0.001810423,0.0028656824,0.000114145,0.000013481723],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038667824,0.00025745985,0.21689086,0.000055460267,0.0015390386,0.000046714824,0.017679852,0.0012026135,0.008459611,0.010679634,0.028446011,0.71435606],"study_design_scores_gemma":[0.00025059335,0.00008793485,0.92755127,0.00002508519,0.00064818707,0.0000075691855,0.0096371705,0.028361782,0.0019389582,0.014994606,0.015755067,0.0007417612],"about_ca_topic_score_codex":0.0006037908,"about_ca_topic_score_gemma":0.0002927644,"teacher_disagreement_score":0.7136143,"about_ca_system_score_codex":0.000010487707,"about_ca_system_score_gemma":0.0000354142,"threshold_uncertainty_score":0.8081956},"labels":[],"label_agreement":null},{"id":"W2146738361","doi":"10.1145/1242572.1242802","title":"BlogScope","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Blogosphere; Computer science; Ranking (information retrieval); Information retrieval; Relevance (law); Set (abstract data type); World Wide Web; Data mining; The Internet","score_opus":0.36278635790261693,"score_gpt":0.5270323869453386,"score_spread":0.16424602904272168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146738361","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011287616,0.000009226728,0.19264877,0.0013410075,0.00017082214,0.000038305672,0.0000013209727,0.000030989264,0.7944719],"genre_scores_gemma":[0.8689656,0.0000020333757,0.0054967557,0.004621053,0.000039446968,5.3200444e-7,0.0000017130174,0.0000017951066,0.120871074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988834,0.00002443773,0.00023120394,0.00015500822,0.00058630115,0.00011962012],"domain_scores_gemma":[0.9990956,0.0003993428,0.000031177147,0.00038366875,0.000039814415,0.000050388873],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0071776165,0.000028846556,0.00005402086,0.000087331995,0.000039301955,0.000101639474,0.00043544965,0.000013412923,0.004403999],"category_scores_gemma":[0.0007118637,0.000017831633,0.00002386092,0.0002907535,0.000026578175,0.00016489661,0.00015557368,0.000023523613,0.006965039],"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":[0.00000485485,0.000022618095,0.00062336767,3.5003296e-7,0.0000023346279,0.0000068208005,0.00005374524,0.0000012447871,0.000050072416,0.45743507,0.28651902,0.25528052],"study_design_scores_gemma":[0.00005652782,0.00000984286,0.009888556,3.880161e-7,7.9087533e-7,5.058571e-7,0.0006265869,0.0000119352635,0.00055477594,0.046389,0.9424286,0.000032482054],"about_ca_topic_score_codex":0.000033852546,"about_ca_topic_score_gemma":0.00023389018,"teacher_disagreement_score":0.857678,"about_ca_system_score_codex":0.0000047853914,"about_ca_system_score_gemma":0.000004712202,"threshold_uncertainty_score":0.9965061},"labels":[],"label_agreement":null},{"id":"W2148524305","doi":"10.14778/1687627.1687771","title":"Framework for evaluating clustering algorithms in duplicate detection","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":232,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scalability; Cluster analysis; Data mining; Data deduplication; Process (computing); Algorithm; Machine learning; Database","score_opus":0.2418184006816228,"score_gpt":0.4629068859449667,"score_spread":0.2210884852633439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148524305","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":[0.6674408,0.00016132377,0.30533537,0.016225928,0.0012386088,0.0041166223,0.00002894418,0.0001130461,0.005339356],"genre_scores_gemma":[0.9677308,0.000009590512,0.031421784,0.00048005677,0.000062763924,0.00009428709,4.5452225e-7,0.000005713973,0.00019453176],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978746,0.000017025968,0.000615692,0.0003701682,0.0008803767,0.00024213053],"domain_scores_gemma":[0.9988445,0.00029036397,0.0004058883,0.00022132986,0.00019980743,0.00003808988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050753765,0.00010910629,0.0002029045,0.00011357587,0.00012783127,0.00015875141,0.00087569474,0.000049476246,0.0000142673825],"category_scores_gemma":[0.002896374,0.00007238074,0.00010822406,0.0005809948,0.000031867115,0.00029746705,0.00028571495,0.00011608299,0.000009187585],"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":[0.00014245746,0.00016941174,0.0004795575,0.000051535797,0.000017554423,1.2090392e-7,0.0015157416,0.00055106037,0.029401027,0.028678663,0.00073739997,0.9382555],"study_design_scores_gemma":[0.0009947035,0.00048885896,0.015678296,0.00022552047,0.00003471868,0.0000030283948,0.002768579,0.04831654,0.121707596,0.80476844,0.0047707963,0.00024289833],"about_ca_topic_score_codex":0.00002863098,"about_ca_topic_score_gemma":0.000012477404,"teacher_disagreement_score":0.9380126,"about_ca_system_score_codex":0.00008238278,"about_ca_system_score_gemma":0.000007840089,"threshold_uncertainty_score":0.34674394},"labels":[],"label_agreement":null},{"id":"W2153257312","doi":"10.14778/1687553.1687599","title":"Linkage Query Writer","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"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 Toronto","funders":"","keywords":"Computer science; SQL; Linkage (software); Interface (matter); Query language; Relational database; Linked data; Information retrieval; Process (computing); Programming language; Semantic Web","score_opus":0.1069606726619127,"score_gpt":0.37673219067138963,"score_spread":0.26977151800947696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153257312","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":[0.52583367,0.00033293842,0.0005984133,0.060149252,0.001165907,0.0013792233,0.000054156266,0.00014660775,0.4103398],"genre_scores_gemma":[0.987714,0.000028470464,0.0011292371,0.0030998958,0.00008960261,0.000010192375,8.515854e-7,0.000004637972,0.00792313],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974978,0.000016371505,0.0005678878,0.00034101374,0.0013441306,0.00023278913],"domain_scores_gemma":[0.998924,0.000103251616,0.0003309851,0.00035624963,0.00021935489,0.00006612787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002614618,0.000121788005,0.00021339851,0.00013023934,0.000113978145,0.00023526562,0.0016816239,0.000039460756,0.00017769769],"category_scores_gemma":[0.0008320099,0.000068434376,0.00015776599,0.00050039805,0.00007421353,0.00042646716,0.0004456585,0.00011386843,0.00014676094],"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":[0.000071081195,0.0004986149,0.0031908536,0.00004247603,0.00004835114,0.0000014295003,0.0020303852,0.000012882975,0.022937521,0.3614002,0.4590149,0.15075134],"study_design_scores_gemma":[0.0007251982,0.0002346121,0.035571966,0.000105847656,0.00004529116,0.0000064506507,0.002255354,0.00013275868,0.06783639,0.370855,0.52194834,0.00028280387],"about_ca_topic_score_codex":0.000016949567,"about_ca_topic_score_gemma":0.0000021430108,"teacher_disagreement_score":0.4618803,"about_ca_system_score_codex":0.00003447633,"about_ca_system_score_gemma":0.000012256058,"threshold_uncertainty_score":0.31249034},"labels":[],"label_agreement":null},{"id":"W2156897283","doi":"10.1002/asi.22695","title":"Author name disambiguation: What difference does it make in author‐based citation analysis?","year":2012,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Workaround; Citation; Computer science; Ambiguity; Ranking (information retrieval); Field (mathematics); Information retrieval; Citation analysis; Journal ranking; Publication; Data science; World Wide Web; Political science; Mathematics","score_opus":0.09078199573774924,"score_gpt":0.4091928979380296,"score_spread":0.31841090220028034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156897283","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":[0.8012107,0.000054753753,0.10133003,0.09650245,0.0005437273,0.00025599648,0.000017425044,0.000015889886,0.00006904471],"genre_scores_gemma":[0.99050653,0.000042334537,0.006253454,0.0030643258,0.000024249992,0.000012037797,0.00000227845,0.0000015927948,0.00009318952],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997117,0.00006428365,0.0008877515,0.00012735183,0.0015257964,0.0002778135],"domain_scores_gemma":[0.99633515,0.0004701557,0.0017376984,0.0003898343,0.0009873743,0.000079803656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012186533,0.00009163265,0.00029784805,0.0012013484,0.00034191468,0.0006052165,0.0011482148,0.00004997226,0.000008541886],"category_scores_gemma":[0.0042016404,0.00004900637,0.00021719353,0.009250639,0.0014194024,0.0054898052,0.00021739994,0.00017378166,0.0000048996176],"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":[0.000051615858,0.00011203617,0.04618249,0.000019187704,0.00011431309,1.2933687e-7,0.011564542,0.00044732986,0.0005035694,0.031289794,0.004732374,0.9049826],"study_design_scores_gemma":[0.0010772519,0.0003516331,0.39763194,0.00007015421,0.00030202253,0.000013529035,0.33107638,0.04945956,0.001191119,0.035377383,0.18306804,0.0003809643],"about_ca_topic_score_codex":0.000011011733,"about_ca_topic_score_gemma":0.000025999654,"teacher_disagreement_score":0.90460163,"about_ca_system_score_codex":0.0001254322,"about_ca_system_score_gemma":0.0001692373,"threshold_uncertainty_score":0.58361167},"labels":[{"model":"gemma","categories":["metaresearch","bibliometrics"],"domain":"methods","study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch","bibliometrics"],"domain":"methods","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2156965754","doi":"10.4338/aci-2012-10-cr-0041","title":"Developing a Tool to Assess the Quality of Socio-Demographic Data in Community Health Centres","year":2013,"lang":"en","type":"article","venue":"Applied Clinical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Quality (philosophy); Community health; Data quality; Scale (ratio); Computer science; Test (biology); Medicine; Knowledge management; Data science; Nursing; Public health; Metric (unit); Engineering; Operations management","score_opus":0.6774011052767211,"score_gpt":0.5819635008242714,"score_spread":0.09543760445244975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156965754","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":[0.90272284,0.000012505823,0.07897182,0.0121565,0.00022081462,0.0015425269,0.0001511355,0.000039980765,0.004181858],"genre_scores_gemma":[0.94739485,0.00008960048,0.029192412,0.023098577,0.000025941998,0.00003981765,0.00012258993,0.0000057961684,0.000030434956],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99154097,0.0014716174,0.005070744,0.00020363927,0.0013388479,0.00037420896],"domain_scores_gemma":[0.9810661,0.013601322,0.0013287072,0.0036729835,0.00018621044,0.00014464858],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05924502,0.00013500397,0.00062917673,0.00013996319,0.0002623949,0.00029641506,0.004433912,0.000090785274,0.0000680088],"category_scores_gemma":[0.008883423,0.000083750274,0.00007938252,0.000998877,0.00029385282,0.0006742275,0.0037073724,0.0006083134,0.0003936499],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044471944,0.00049499416,0.06677923,0.00025660748,0.000076708755,9.0246616e-8,0.008761132,0.00009551788,0.0000012780787,0.4209826,0.07544794,0.42705944],"study_design_scores_gemma":[0.0007997537,0.00007377588,0.71802694,0.00006307668,0.000008301121,1.7087908e-7,0.075851135,0.0012155046,0.000004584307,0.14443162,0.059253346,0.0002717754],"about_ca_topic_score_codex":0.0017523956,"about_ca_topic_score_gemma":0.002340335,"teacher_disagreement_score":0.65124774,"about_ca_system_score_codex":0.00003777369,"about_ca_system_score_gemma":0.00021495033,"threshold_uncertainty_score":0.99946517},"labels":[],"label_agreement":null},{"id":"W2159146278","doi":"10.1145/1142473.1142557","title":"Using SPIDER","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 Toronto","funders":"","keywords":"Spider; Computer science; Matching (statistics); Variety (cybernetics); Component (thermodynamics); Key (lock); Database; Artificial intelligence; Computer security; Mathematics","score_opus":0.5106669315941896,"score_gpt":0.5048891074743921,"score_spread":0.005777824119797548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159146278","genre_codex":"other","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":[0.051533297,0.00001632935,0.36385858,0.0013672581,0.00022884189,0.000054865577,0.000003963854,0.00003679288,0.58290005],"genre_scores_gemma":[0.89792556,4.5229976e-7,0.025914392,0.0018653988,0.00011979294,7.787121e-7,0.000003089378,0.0000028735744,0.0741677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902964,0.00004074994,0.00020882874,0.0001511664,0.00048181848,0.000087814165],"domain_scores_gemma":[0.9994896,0.00011830523,0.00003647259,0.00030366654,0.00003473039,0.00001719354],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013837192,0.000030784755,0.00005750426,0.00006209292,0.000049903058,0.00017585637,0.0002548819,0.000011086538,0.0026127317],"category_scores_gemma":[0.00017145512,0.000019848538,0.000027110289,0.00021549576,0.000022094255,0.00022757179,0.00011841014,0.00001567633,0.0014193667],"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":[0.0000015060373,0.000048283102,0.0014553017,6.7890494e-7,0.0000018353544,0.0000038245958,0.000012409075,0.00038477438,0.00020149355,0.52932566,0.45084423,0.017719992],"study_design_scores_gemma":[0.00006601012,0.0000048303887,0.005670517,7.6329405e-7,0.000002024838,8.511154e-7,0.0001993341,0.002366188,0.00028276432,0.21641217,0.7749433,0.000051255018],"about_ca_topic_score_codex":0.00071360247,"about_ca_topic_score_gemma":0.00021141006,"teacher_disagreement_score":0.8463922,"about_ca_system_score_codex":0.0000070626475,"about_ca_system_score_gemma":0.000005972501,"threshold_uncertainty_score":0.9993581},"labels":[],"label_agreement":null},{"id":"W2160348740","doi":"10.2218/ijdc.v6i1.176","title":"Towards a Holistic Approach to Policy Interoperability in Digital Libraries and Digital Repositories","year":2011,"lang":"en","type":"article","venue":"International Journal of Digital Curation","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"U.S. Geological Survey","keywords":"Interoperability; Digital library; Computer science; World Wide Web; Metadata; Digital transformation; Digital preservation; Reuse; Key (lock); Digital curation; Domain (mathematical analysis); Cross-domain interoperability; Semantic interoperability; Computer security; Engineering","score_opus":0.20938298116014792,"score_gpt":0.3937515392860538,"score_spread":0.18436855812590586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160348740","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":[0.7927015,0.00004452895,0.10077623,0.002276351,0.0011419726,0.00021955787,0.00034618186,0.000023680881,0.10247002],"genre_scores_gemma":[0.9983625,0.000003527225,0.00073060655,0.00013381563,0.00028285643,0.0000032198482,0.00003036416,0.0000068364866,0.00044629595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973471,0.000031599557,0.0010428344,0.00026410312,0.0011793212,0.00013505116],"domain_scores_gemma":[0.99842834,0.0001747988,0.0003768324,0.00020597198,0.0006760016,0.0001380237],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0005932123,0.00013106281,0.00022619203,0.00077837496,0.000034675297,0.0050131734,0.0008533098,0.000040377745,0.000011779972],"category_scores_gemma":[0.007239138,0.000097511234,0.000085999076,0.00045283066,0.00013641735,0.01836336,0.00046455025,0.00012247587,0.000023999879],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001508245,0.0015860363,0.078019544,0.000020972368,0.00019958099,0.00011254336,0.020616239,0.00009767021,0.00004151585,0.45861188,0.00290976,0.436276],"study_design_scores_gemma":[0.0013235633,0.0008435978,0.120181836,0.00012942248,0.000015636751,0.00046568265,0.011408739,0.0004534826,0.00032526843,0.8345644,0.029794952,0.00049344497],"about_ca_topic_score_codex":0.00002830951,"about_ca_topic_score_gemma":0.000005439092,"teacher_disagreement_score":0.43578255,"about_ca_system_score_codex":0.00010771673,"about_ca_system_score_gemma":0.00013173108,"threshold_uncertainty_score":0.9960197},"labels":[],"label_agreement":null},{"id":"W2161086867","doi":"10.1109/hicss.2003.1174352","title":"Storage model for CDA documents","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Dalhousie University","funders":"","keywords":"Computer science; Relational database; XML; Information retrieval; Object (grammar); Markup language; Semantics (computer science); Database; Programming language; World Wide Web; Artificial intelligence","score_opus":0.32907078921171257,"score_gpt":0.47476268010164474,"score_spread":0.14569189088993217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161086867","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":[0.002274935,0.000010008825,0.8252503,0.00047671478,0.00019348471,0.00019967071,0.00002380913,0.000022571961,0.17154847],"genre_scores_gemma":[0.5715453,0.0000046719074,0.037722424,0.0031225414,0.000014631895,0.00003716422,0.00000805913,0.0000058055957,0.38753942],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99868745,0.00006475674,0.00026078065,0.00026827183,0.0005622422,0.00015649194],"domain_scores_gemma":[0.9990699,0.00026088345,0.000053821543,0.00048702725,0.00006852694,0.0000598263],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0032327045,0.000057684447,0.00010058338,0.000069546986,0.000095439354,0.00020199204,0.00041563303,0.000020452886,0.0010753385],"category_scores_gemma":[0.0011492522,0.00003942506,0.000055413373,0.00014972505,0.000020766349,0.00039778993,0.000074365336,0.000022064196,0.00060485513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005163458,0.000037926424,0.0000266577,0.000001875057,0.0000056245676,3.6457686e-7,0.00012583956,0.0016372487,0.000014058634,0.60324854,0.38859868,0.0062980317],"study_design_scores_gemma":[0.00025796573,0.000014558103,0.000020542395,7.670484e-7,0.0000035463684,1.7005955e-7,0.00040642245,0.059022073,0.00010271352,0.38797623,0.55212706,0.00006795911],"about_ca_topic_score_codex":0.000011358196,"about_ca_topic_score_gemma":0.000049643862,"teacher_disagreement_score":0.7875279,"about_ca_system_score_codex":0.000013973999,"about_ca_system_score_gemma":0.000020446387,"threshold_uncertainty_score":0.9998378},"labels":[],"label_agreement":null},{"id":"W2169710203","doi":"10.1504/ijiq.2008.019560","title":"Information quality chain analysis for total information quality management","year":2008,"lang":"en","type":"article","venue":"International Journal of 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":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information quality; Quality (philosophy); Data quality; Information management; Knowledge management; Information system; Information retrieval; Business","score_opus":0.1660276901368132,"score_gpt":0.459138105283643,"score_spread":0.2931104151468298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169710203","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":[0.16612782,0.000013061433,0.8154219,0.004104373,0.002043889,0.0006434594,0.0012375332,0.00006029133,0.010347721],"genre_scores_gemma":[0.9826589,0.000078540426,0.010117763,0.004897316,0.0002325697,0.00004756288,0.0015829905,0.0000058479286,0.00037849037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9845867,0.00079277164,0.007947684,0.0001784368,0.0061186953,0.00037572047],"domain_scores_gemma":[0.98403734,0.0013423506,0.007415262,0.00077934825,0.0061749816,0.00025071364],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.026690131,0.00031442122,0.00081816193,0.0027857267,0.00036180887,0.0011712215,0.0020242217,0.00016708809,0.00039710428],"category_scores_gemma":[0.008049459,0.00026467993,0.0009516955,0.0014953723,0.00016466374,0.027495531,0.00042697377,0.000302792,0.00050284015],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003429207,0.00052205735,0.019657543,0.00031223113,0.004645427,0.0000055707496,0.027705612,0.023708174,0.00001833271,0.48385608,0.047929827,0.38820994],"study_design_scores_gemma":[0.004435803,0.00019144149,0.56170774,0.000038054754,0.00019343801,0.00004503136,0.019003844,0.0028136917,0.00015818376,0.014864705,0.39592654,0.00062153756],"about_ca_topic_score_codex":0.0003259067,"about_ca_topic_score_gemma":0.000042681113,"teacher_disagreement_score":0.8165311,"about_ca_system_score_codex":0.00048723866,"about_ca_system_score_gemma":0.00020580135,"threshold_uncertainty_score":0.99998057},"labels":[],"label_agreement":null},{"id":"W2170688652","doi":"10.1007/s00778-007-0067-9","title":"Applications of corpus-based semantic similarity and word segmentation to database schema matching","year":2007,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Schema matching; Computer science; Semantic similarity; Artificial intelligence; Schema (genetic algorithms); Star schema; Natural language processing; Information retrieval; Segmentation; Pattern recognition (psychology); Database schema; Data mining; Data integration","score_opus":0.1166235600128447,"score_gpt":0.4294959857511475,"score_spread":0.3128724257383028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170688652","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":[0.25725114,0.000073870804,0.7390159,0.0031461904,0.00007167492,0.0002022231,0.0000286172,0.0000068843606,0.00020354128],"genre_scores_gemma":[0.9720079,0.000036627316,0.025890436,0.0017521403,0.00010091992,0.0000056048175,0.000009905852,0.0000056362674,0.00019087114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982775,0.00014283304,0.00049826707,0.00015467667,0.0007799368,0.00014681801],"domain_scores_gemma":[0.99824923,0.00080030964,0.0002847238,0.0004223816,0.00012847946,0.00011488975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011068163,0.00006629908,0.00012122143,0.00020601135,0.0003059042,0.00020156655,0.00051331724,0.000017180224,0.000105549974],"category_scores_gemma":[0.00036475615,0.00004171928,0.00003530759,0.0004948014,0.000071425995,0.00026181326,0.00017732287,0.00014647646,0.00004210326],"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":[0.00023437409,0.00023857431,0.003697193,0.00004386875,0.000048859143,0.000014702019,0.0017935543,0.00083321135,0.018868158,0.0137209045,0.0099991,0.9505075],"study_design_scores_gemma":[0.005357501,0.00045217972,0.12669311,0.0004456205,0.0003885247,0.00030671526,0.035678502,0.005412393,0.06898663,0.3467853,0.40843096,0.0010625541],"about_ca_topic_score_codex":0.000045802743,"about_ca_topic_score_gemma":0.00014387032,"teacher_disagreement_score":0.94944495,"about_ca_system_score_codex":0.000019477227,"about_ca_system_score_gemma":0.000030121219,"threshold_uncertainty_score":0.38360268},"labels":[],"label_agreement":null},{"id":"W2170712852","doi":"10.14778/2536258.2536262","title":"Discovering denial constraints","year":2013,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":252,"is_retracted":false,"has_abstract":true,"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; Rotation formalisms in three dimensions; Scalability; Inference; Data integrity; Set (abstract data type); Functional dependency; Constraint (computer-aided design); Theoretical computer science; Rank (graph theory); Semantics (computer science); Function (biology); Data mining; Artificial intelligence; Programming language; Database; Relational database","score_opus":0.08220481571088507,"score_gpt":0.3393964871060694,"score_spread":0.25719167139518434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170712852","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":[0.9038038,0.000025454941,0.00033549845,0.0057185395,0.00057440385,0.0007748185,0.000021429629,0.000032555618,0.08871349],"genre_scores_gemma":[0.99609274,0.0000069362504,0.0008359857,0.00035721285,0.000053452586,0.00004491731,4.5436397e-7,0.000005284103,0.0026030438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997828,0.00001201534,0.00049279537,0.00028836506,0.0011550064,0.0002238247],"domain_scores_gemma":[0.9990573,0.00012386074,0.0003090717,0.0002336129,0.00020846954,0.00006767515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013059851,0.000107117456,0.00018252133,0.00008216985,0.00011224229,0.0003418665,0.0013534825,0.000025906991,0.000868397],"category_scores_gemma":[0.00093292526,0.000059682367,0.00011486481,0.00031202333,0.00024000049,0.0006437655,0.0009307045,0.00008061975,0.00035296645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004327157,0.0003753887,0.024586255,0.00010308034,0.00014666413,7.799481e-7,0.0035542452,0.000041848674,0.07121547,0.41926512,0.27565965,0.20500822],"study_design_scores_gemma":[0.0021791435,0.00022566343,0.104418725,0.00024175047,0.000099229044,0.000023338467,0.023336178,0.00071541825,0.20724429,0.49402764,0.16674235,0.0007462656],"about_ca_topic_score_codex":0.0001441624,"about_ca_topic_score_gemma":0.0000064045,"teacher_disagreement_score":0.20426196,"about_ca_system_score_codex":0.000034927045,"about_ca_system_score_gemma":0.000015266527,"threshold_uncertainty_score":0.9508338},"labels":[],"label_agreement":null},{"id":"W2171332293","doi":"10.1145/1366102.1366103","title":"Conditional functional dependencies for capturing data inconsistencies","year":2008,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":458,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council","keywords":"Computer science; Functional dependency; Data integrity; Consistency (knowledge bases); Relational database; SQL; Data mining; Set (abstract data type); Schema (genetic algorithms); Database; Programming language; Theoretical computer science; Algorithm; Information retrieval; Artificial intelligence","score_opus":0.5917106512846138,"score_gpt":0.4156652633131301,"score_spread":0.17604538797148367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171332293","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":[0.0026714308,0.00017669193,0.95701265,0.000971684,0.0018697069,0.0006627008,0.035718504,0.00011759937,0.0007990051],"genre_scores_gemma":[0.97667843,0.000065417655,0.008499217,0.00051145913,0.00028301758,0.0002859965,0.006512661,0.000022694401,0.0071410956],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99593365,0.0002293184,0.0008280448,0.0009323349,0.0017569346,0.000319692],"domain_scores_gemma":[0.99266,0.0029671756,0.00021845188,0.0037110313,0.00029129686,0.00015204735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030932971,0.00021369765,0.00032669856,0.0004035097,0.0010836925,0.00023164196,0.0021356468,0.00007091129,0.00050959556],"category_scores_gemma":[0.0017802466,0.00017775469,0.00012498145,0.00042363376,0.00023715956,0.0016488457,0.00014348348,0.00018256904,0.00062977045],"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":[0.0007931147,0.0017419991,0.0007502174,0.00047557245,0.0010463743,0.00019186626,0.0012660634,0.036083452,0.0013499265,0.060434796,0.87849313,0.017373497],"study_design_scores_gemma":[0.0021829044,0.0001645838,0.0025568346,0.00013962218,0.00016321427,0.00055515254,0.010516756,0.013975479,0.00066068384,0.0054544746,0.9628404,0.0007898973],"about_ca_topic_score_codex":0.0004541447,"about_ca_topic_score_gemma":0.0005062943,"teacher_disagreement_score":0.974007,"about_ca_system_score_codex":0.000074699645,"about_ca_system_score_gemma":0.00019609793,"threshold_uncertainty_score":0.8334996},"labels":[],"label_agreement":null},{"id":"W2171886215","doi":"","title":"Concordia University at the TREC 2007 QA Track.","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Track (disk drive); Database; Information retrieval; World Wide Web; Operating system","score_opus":0.10365957539795251,"score_gpt":0.34946924935584534,"score_spread":0.24580967395789283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171886215","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08236327,0.00003222073,0.008399719,0.010201025,0.0003469474,0.00012959928,0.000058963404,0.000048593753,0.8984197],"genre_scores_gemma":[0.33482543,0.0000061499395,0.00015593918,0.0012041086,0.000053491673,2.801543e-7,0.000012339761,0.0000019292086,0.66374034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987167,0.00016456663,0.00017689657,0.00024285147,0.0005577752,0.00014120193],"domain_scores_gemma":[0.9986572,0.0006422039,0.00006566992,0.00054766936,0.000049933653,0.000037268335],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018967267,0.000057137404,0.00009078376,0.00005159617,0.00022004271,0.00010943064,0.0006882324,0.000024627292,0.011590806],"category_scores_gemma":[0.000119240525,0.00003190776,0.000067578585,0.00031205345,0.00013069501,0.00023447341,0.000309482,0.00004168531,0.003911741],"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":[0.000011878916,0.000021756096,0.0011172856,3.5209135e-7,0.000003375339,0.000006985407,0.00003178839,0.000026293019,0.000008819237,0.066240035,0.9152892,0.01724223],"study_design_scores_gemma":[0.00016660555,0.000009835495,0.027219787,4.3968146e-7,0.0000063463854,7.8920556e-7,0.0013922827,0.0000813802,0.00007315548,0.006360872,0.96463454,0.00005395055],"about_ca_topic_score_codex":0.0024484557,"about_ca_topic_score_gemma":0.012420937,"teacher_disagreement_score":0.25246218,"about_ca_system_score_codex":0.000041028477,"about_ca_system_score_gemma":0.000015883768,"threshold_uncertainty_score":0.99686384},"labels":[],"label_agreement":null},{"id":"W2175789071","doi":"10.1109/sdsoa.2007.9","title":"Mined-Knowledge and Decision Support Services in Electronic Health","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Service-oriented architecture; Information sharing; Decision support system; Computer science; Service (business); Information system; Clinical decision support system; Knowledge management; Identification (biology); Data sharing; Intelligent transportation system; Business; Computer security; Web service; World Wide Web; Engineering; Data mining; Transport engineering","score_opus":0.0776813602794446,"score_gpt":0.44896466930816425,"score_spread":0.37128330902871964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2175789071","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":[0.8020768,0.0018868543,0.105989136,0.0032524655,0.0004209678,0.00056409586,0.000013656448,0.000082458784,0.08571355],"genre_scores_gemma":[0.9881304,0.0003463194,0.003819203,0.0032981855,0.0000347738,0.0000027179342,0.000013142763,0.0000056712934,0.0043496066],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978324,0.0000695794,0.0006461386,0.00041616807,0.00059638766,0.000439323],"domain_scores_gemma":[0.9985562,0.0007377755,0.00010166157,0.0004148614,0.000055449535,0.00013407624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0137536675,0.00009043653,0.00020422679,0.00038211103,0.00006981966,0.0001336683,0.00047851529,0.00003650485,0.00042841554],"category_scores_gemma":[0.00013164258,0.000064250984,0.000026484053,0.0006729013,0.000030450856,0.0003725026,0.00031114172,0.00008480395,0.0005043151],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040704734,0.0000964538,0.0051175067,0.000011964574,0.000002879059,0.00000463406,0.000816091,0.0000012406874,0.000008636095,0.03438455,0.03004593,0.9294694],"study_design_scores_gemma":[0.00057771895,0.00019639559,0.0878604,0.000016405736,0.0000017029962,0.0000047434173,0.0031933414,0.0004960444,0.00006412271,0.06556529,0.841897,0.00012682848],"about_ca_topic_score_codex":0.00041228306,"about_ca_topic_score_gemma":0.057279013,"teacher_disagreement_score":0.92934257,"about_ca_system_score_codex":0.000061007533,"about_ca_system_score_gemma":0.00007731285,"threshold_uncertainty_score":0.9599232},"labels":[],"label_agreement":null},{"id":"W2181680766","doi":"10.3217/jucs-020-11-1564","title":"A Model to Guide the Open Government Data Implementation in Public Agencies","year":2014,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Open government; Open data; Computer science; Capability Maturity Model; Maturity (psychological); Government (linguistics); Open source; Latin Americans; Data science; Simple (philosophy); Knowledge management; Process management; World Wide Web; Political science; Business","score_opus":0.4763705506484579,"score_gpt":0.4486828361147665,"score_spread":0.0276877145336914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181680766","genre_codex":"other","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":[0.0051477076,0.000013102191,0.2510705,0.03871055,0.00013984121,0.0019468839,0.0016702625,0.0002104115,0.70109075],"genre_scores_gemma":[0.9842808,0.000038724527,0.0028411099,0.0044807675,0.00008161646,3.7212155e-7,0.0019726239,0.00039854244,0.005905397],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962511,0.0008878773,0.0004930263,0.0006162627,0.0014439366,0.00030777097],"domain_scores_gemma":[0.9973446,0.00011645746,0.0001410673,0.0020005926,0.00026432285,0.00013296749],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.013845214,0.00009434244,0.000126341,0.00014227467,0.0013005472,0.0048098667,0.009425927,0.000019521995,0.0069708615],"category_scores_gemma":[0.0045589646,0.000070501104,0.000019426863,0.0009110214,0.00007227008,0.001228789,0.01849235,0.00010967685,0.0055464553],"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":[0.00001162176,0.000034536446,0.000003713446,0.0000026247567,0.0000064821147,6.282964e-7,0.0010156616,0.00025070872,0.00012677207,0.05092241,0.60276043,0.3448644],"study_design_scores_gemma":[0.00026014118,0.00006375682,0.0005005038,0.000004563217,0.000003662045,0.0000024861492,0.0050699464,0.018001692,0.000026735932,0.0038172754,0.9721573,0.00009193009],"about_ca_topic_score_codex":0.0001278049,"about_ca_topic_score_gemma":0.0000822179,"teacher_disagreement_score":0.9791331,"about_ca_system_score_codex":0.00022226223,"about_ca_system_score_gemma":0.000008241029,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W2185266341","doi":"","title":"THUNLP at TAC KBP 2011 in Entity Linking","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Entity linking; Ranking (information retrieval); Pairwise comparison; Task (project management); Information retrieval; String (physics); Context (archaeology); Knowledge base; Similarity (geometry); Key (lock); Rank (graph theory); Artificial intelligence; Natural language processing; Data mining; Image (mathematics); Mathematics","score_opus":0.09715954466342638,"score_gpt":0.3532432388839121,"score_spread":0.2560836942204857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185266341","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":[0.62571394,0.0011787583,0.19109944,0.000452668,0.00016600046,0.0009321249,0.00011956677,0.00008020768,0.1802573],"genre_scores_gemma":[0.9958586,0.00010258664,0.00045504764,0.0000821219,0.000020120975,0.00006955887,0.000014123655,0.0000034101097,0.0033944093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887496,0.0001791575,0.00036309712,0.00023834583,0.0002346939,0.00010972429],"domain_scores_gemma":[0.9986854,0.0004958123,0.00015173208,0.0005598739,0.000070096525,0.000037042635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004042968,0.00007008626,0.00015227354,0.00013926347,0.00013352372,0.000036513655,0.00049018615,0.000036706817,0.00075991073],"category_scores_gemma":[0.00013595865,0.000055473574,0.00002961497,0.00025420747,0.00033819524,0.00028200488,0.00033971475,0.00005409759,0.00021484793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042990505,0.000060140395,0.0033691966,0.000011564697,0.0000056962554,2.5946053e-7,0.0018165878,8.4774877e-7,0.000080828984,0.96147305,0.0003628685,0.03277598],"study_design_scores_gemma":[0.000097013624,0.000016730219,0.011469374,0.0000034976376,0.000008810865,6.626801e-7,0.002383144,0.0000034699938,0.002786127,0.9406883,0.04247558,0.00006730218],"about_ca_topic_score_codex":0.000096935095,"about_ca_topic_score_gemma":0.00016894021,"teacher_disagreement_score":0.3701447,"about_ca_system_score_codex":0.00000844352,"about_ca_system_score_gemma":0.000013204926,"threshold_uncertainty_score":0.83204895},"labels":[],"label_agreement":null},{"id":"W2188957661","doi":"","title":"Linguistic Resources for 2011 Knowledge Base Population Evaluation.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"NIST; Computer science; Annotation; Knowledge base; Information extraction; Entity linking; Resource (disambiguation); Population; Information retrieval; Natural language processing; Artificial intelligence; Data science; World Wide Web","score_opus":0.15970588089702853,"score_gpt":0.40998874252481454,"score_spread":0.250282861627786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188957661","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":[0.0804024,0.0028409818,0.75631493,0.00020661418,0.00027679207,0.0028456287,0.0002968782,0.0001002575,0.15671551],"genre_scores_gemma":[0.9958867,0.000014978913,0.0016960236,0.00003292629,0.0000780657,0.0003939252,0.000050471932,0.0000052006485,0.001841749],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987589,0.00024647338,0.00039286903,0.00024595746,0.00025766488,0.00009812115],"domain_scores_gemma":[0.9975335,0.0012493569,0.00020505548,0.0005041974,0.00046188172,0.000046019068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008393687,0.00007356898,0.00014213864,0.00014314949,0.00020922224,0.000044296958,0.00033709113,0.000032441236,0.0003909956],"category_scores_gemma":[0.0016640738,0.000058063724,0.000038833736,0.00019000532,0.0001956427,0.00015191575,0.000088014014,0.000028449667,0.00005546135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064737105,0.00006394879,0.00021756256,0.000019364536,0.000009638625,1.5170508e-8,0.003032863,0.0000028668846,0.000013707857,0.9224995,0.0005370373,0.07353878],"study_design_scores_gemma":[0.00015411599,0.00003159798,0.0043813754,0.0000031706522,0.000059593836,2.8070275e-7,0.00224067,0.00015088136,0.00037207984,0.936503,0.05603423,0.000068997455],"about_ca_topic_score_codex":0.000050403814,"about_ca_topic_score_gemma":0.00003374664,"teacher_disagreement_score":0.91548425,"about_ca_system_score_codex":0.000007728562,"about_ca_system_score_gemma":0.00002342157,"threshold_uncertainty_score":0.42811278},"labels":[],"label_agreement":null},{"id":"W2189052568","doi":"10.14778/2850583.2850586","title":"The iBench integration metadata generator","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":59,"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 Toronto","funders":"","keywords":"Metadata; Computer science; Schema evolution; Data integration; Generality; Schema (genetic algorithms); Generator (circuit theory); Data mapping; Data element; Data science; Information retrieval; Data mining; Database; World Wide Web; Database schema","score_opus":0.2684436286050799,"score_gpt":0.39426327919983467,"score_spread":0.12581965059475475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189052568","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":[0.56227,0.0032114782,0.012688137,0.14513184,0.010125631,0.0055021625,0.00031568826,0.00026482655,0.26049027],"genre_scores_gemma":[0.98278195,0.0000670096,0.0018297815,0.00080366945,0.00015287891,0.00007074004,0.000004070435,0.0000088888255,0.014280998],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971278,0.000040877665,0.00055919576,0.0002971171,0.0017786515,0.00019641424],"domain_scores_gemma":[0.9982618,0.00018957251,0.0004106837,0.00046310536,0.0005876063,0.00008720911],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070192185,0.00011305642,0.00016360453,0.000065071916,0.00023543838,0.00075538893,0.0022563084,0.000027457436,0.0000224907],"category_scores_gemma":[0.0036645127,0.000047692887,0.000094306466,0.000526696,0.00013574363,0.0008420558,0.0010083524,0.000098844714,0.00007023685],"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":[0.000038690298,0.00007532341,0.00043589034,0.0000057694615,0.0000460658,1.2720135e-7,0.0010051575,0.000011203437,0.004470577,0.4131789,0.5342453,0.046486977],"study_design_scores_gemma":[0.00036845575,0.00007872825,0.0006366902,0.000017712851,0.000042707343,0.0000024377914,0.008432384,0.0005202109,0.07559018,0.13771304,0.7764785,0.00011892461],"about_ca_topic_score_codex":0.000089172674,"about_ca_topic_score_gemma":0.000051044895,"teacher_disagreement_score":0.420512,"about_ca_system_score_codex":0.00006292882,"about_ca_system_score_gemma":0.000045064586,"threshold_uncertainty_score":0.7284233},"labels":[],"label_agreement":null},{"id":"W2190899134","doi":"10.14778/2850578.2850579","title":"Messing up with BART","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Scalability; Tuple; Computer science; Benchmarking; Completeness (order theory); Greedy algorithm; Process (computing); Benchmark (surveying); Property (philosophy); Scale (ratio); Control (management); Mathematical optimization; Algorithm; Database; Mathematics; Artificial intelligence; Programming language","score_opus":0.2772987549438379,"score_gpt":0.3926154589624858,"score_spread":0.11531670401864791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2190899134","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":[0.5979908,0.00022995513,0.0013640509,0.022348074,0.0015784419,0.001216744,0.000026919257,0.00012045311,0.37512457],"genre_scores_gemma":[0.9887018,0.0000043793625,0.0019050792,0.00053653354,0.000050126506,0.000019953326,5.894613e-7,0.000007730512,0.008773807],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997272,0.000016838409,0.00038806433,0.00030152523,0.0018181411,0.00020340877],"domain_scores_gemma":[0.998772,0.00007504292,0.00033293464,0.00027549115,0.0004345559,0.000109954715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003346509,0.00011066196,0.00019715393,0.00009599598,0.00009975187,0.0002522856,0.0012115131,0.0000230524,0.000053414624],"category_scores_gemma":[0.0008722148,0.000054171618,0.000061510655,0.00052173494,0.00013228925,0.00050013873,0.00064812537,0.000078854784,0.0000786362],"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":[0.00031506005,0.00029908743,0.016755618,0.00006978135,0.00012665632,0.0000016025798,0.008404786,0.000090169684,0.004001799,0.21043591,0.7078582,0.05164132],"study_design_scores_gemma":[0.0022609094,0.00034659193,0.0050262087,0.00018449091,0.000094023235,0.000019369776,0.02731994,0.0003347774,0.07325927,0.1365034,0.7542753,0.00037569588],"about_ca_topic_score_codex":0.000050009403,"about_ca_topic_score_gemma":0.000008549571,"teacher_disagreement_score":0.390711,"about_ca_system_score_codex":0.000051422918,"about_ca_system_score_gemma":0.00004377445,"threshold_uncertainty_score":0.24327958},"labels":[],"label_agreement":null},{"id":"W2218881374","doi":"","title":"Trusted Data in IBM's Master Data Management","year":2011,"lang":"en","type":"article","venue":"Databases, Knowledge, and Data Applications","topic":"Data Quality and Management","field":"Decision Sciences","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":"York University","funders":"","keywords":"IBM; Computer science; Master data; Data quality; Quality (philosophy); Data warehouse; Process (computing); Data governance; Data modeling; Database; Process management; Data science; Operating system; Engineering; Operations management","score_opus":0.6106244189975273,"score_gpt":0.4788549332639887,"score_spread":0.13176948573353858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2218881374","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033769372,0.0044406406,0.50859994,0.0009297828,0.00051068055,0.0033389127,0.333916,0.000230599,0.14769575],"genre_scores_gemma":[0.0277308,0.0049577532,0.14852144,0.0014783132,0.0005294917,0.0006102577,0.80697286,0.000086768516,0.009112295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99450713,0.00028659252,0.0011037659,0.0029377216,0.0007130531,0.00045173097],"domain_scores_gemma":[0.969142,0.0005914402,0.0002540281,0.029678866,0.00009397157,0.00023965347],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.007150239,0.00028548628,0.00038417472,0.0004876693,0.00027370278,0.00033331924,0.015900532,0.000057088022,0.0009843373],"category_scores_gemma":[0.0006086133,0.00024595603,0.000017813063,0.0013920148,0.00027570428,0.004508195,0.037703335,0.00021023832,0.0025043169],"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":[0.000030925494,0.0008207346,0.0020983818,0.00007650081,0.00005608073,0.000012117876,0.00016857122,1.3673383e-7,0.0000030986487,0.06775245,0.59210765,0.33687332],"study_design_scores_gemma":[0.00061527546,0.000009718618,0.011165136,0.000031580945,0.0001043942,0.0000053492263,0.0013959365,0.004300643,0.0000035454013,0.0031745555,0.9788888,0.0003050509],"about_ca_topic_score_codex":0.0006969771,"about_ca_topic_score_gemma":0.0080273105,"teacher_disagreement_score":0.47305688,"about_ca_system_score_codex":0.00002191133,"about_ca_system_score_gemma":0.000072776165,"threshold_uncertainty_score":0.9999993},"labels":[],"label_agreement":null},{"id":"W2229414573","doi":"10.1007/978-3-319-23201-0_10","title":"Data Warehouse Design Methods Review: Trends, Challenges and Future Directions for the Healthcare Domain","year":2015,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier Universitaire de Sherbrooke; Université de Sherbrooke","funders":"","keywords":"Computer science; Data warehouse; Traceability; Schema (genetic algorithms); Data integration; Data science; Information integration; Domain (mathematical analysis); Information retrieval; Software engineering; Database; Data mining","score_opus":0.6732383815595341,"score_gpt":0.543693081677569,"score_spread":0.12954529988196506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2229414573","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.9096644e-8,0.27147704,0.58454937,0.10679663,0.000587398,0.0010799086,0.0004923876,0.000046376816,0.03497085],"genre_scores_gemma":[0.000009426927,0.6630327,0.3324037,0.0028182932,0.00009372531,0.00008233656,0.00023391322,0.0000066240536,0.0013192848],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972741,0.00037833964,0.000973967,0.00041850962,0.00077452156,0.00018053425],"domain_scores_gemma":[0.99050283,0.0028392903,0.0005199704,0.0053412225,0.0006803089,0.000116382675],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.027962858,0.00018317292,0.00034472195,0.00069236493,0.000853305,0.0005554814,0.0055951006,0.00008762954,0.0000118492535],"category_scores_gemma":[0.0006844412,0.0001215592,0.000036497542,0.00046395962,0.0008936714,0.0045948373,0.0045249625,0.00029634175,0.000014060042],"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":[0.0000022435145,0.0000045703196,1.16375105e-7,0.00004029657,0.0000048335964,2.1463357e-8,0.0012832778,0.0000057853827,7.81641e-9,0.22910318,0.027718736,0.74183697],"study_design_scores_gemma":[0.00012469475,0.000035171262,0.00008381263,0.00017945723,0.000016879605,0.0000070699953,0.0005183663,0.018302651,3.8319648e-8,0.043146778,0.9374493,0.00013581412],"about_ca_topic_score_codex":0.000011467245,"about_ca_topic_score_gemma":0.00011808751,"teacher_disagreement_score":0.90973055,"about_ca_system_score_codex":0.000062614374,"about_ca_system_score_gemma":0.00020337987,"threshold_uncertainty_score":0.9997851},"labels":[],"label_agreement":null},{"id":"W2237543400","doi":"","title":"Declarative entity resolution via matching dependencies and answer set programs","year":2012,"lang":"en","type":"article","venue":"Principles of Knowledge Representation and Reasoning","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":22,"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 British Columbia; Carleton University","funders":"","keywords":"Computer science; Expressive power; Matching (statistics); Programming language; Set (abstract data type); Theoretical computer science; Invariant (physics); Semantics (computer science); Task (project management); Class (philosophy); Artificial intelligence; Mathematics","score_opus":0.23934077864338069,"score_gpt":0.4310733909013771,"score_spread":0.1917326122579964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237543400","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":[0.9245435,0.00239615,0.060024004,0.00014838259,0.0003136909,0.000350961,0.000011309146,0.00004221923,0.0121697895],"genre_scores_gemma":[0.9923027,0.00015126198,0.0061880164,0.000014353429,0.00007068693,0.000016086857,0.000027098027,0.0000062618615,0.001223493],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99805474,0.0003818805,0.000479934,0.0003398931,0.00051242515,0.00023114939],"domain_scores_gemma":[0.9985829,0.00046766142,0.00029451953,0.00030366794,0.00020838168,0.0001428949],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003496238,0.00011751986,0.00022735895,0.00016900599,0.00025696654,0.00018274796,0.00019361806,0.000058616613,0.00003318459],"category_scores_gemma":[0.001229875,0.000092262744,0.00005092088,0.0003349496,0.00018804996,0.0011152461,0.0005014954,0.00009788104,0.00002476467],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086795706,0.00031273536,0.58956945,0.00013329607,0.00010149419,0.0000023773894,0.045860186,0.00007036058,0.0010118373,0.11123287,0.00043687085,0.25118172],"study_design_scores_gemma":[0.0010632899,0.000115977884,0.8704777,0.00025838436,0.00010928272,0.000057396104,0.041381072,0.01415121,0.0033867364,0.014272173,0.054228086,0.0004987387],"about_ca_topic_score_codex":0.00016965212,"about_ca_topic_score_gemma":0.00034160988,"teacher_disagreement_score":0.2809082,"about_ca_system_score_codex":0.000023375433,"about_ca_system_score_gemma":0.000021838498,"threshold_uncertainty_score":0.37623656},"labels":[],"label_agreement":null},{"id":"W2237788583","doi":"","title":"Stepwise Variable Selection for Loglinear Mixture in Record Linkage","year":2010,"lang":"en","type":"article","venue":"","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":"University of New Brunswick; McMaster University","funders":"","keywords":"Log-linear model; Overfitting; Mathematics; Model selection; Covariate; Selection (genetic algorithm); Mixture model; Statistical model; Linkage (software); Probabilistic logic; Statistics; Linear model; Artificial intelligence; Computer science","score_opus":0.09442882874722106,"score_gpt":0.404395673341274,"score_spread":0.309966844594053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237788583","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":[0.06804915,0.000009133245,0.86120754,0.00393399,0.002595759,0.0009417933,0.0000687779,0.000119060656,0.06307477],"genre_scores_gemma":[0.19247979,0.00001093261,0.6184823,0.0048374063,0.00071184756,0.0001414342,0.000078285746,0.000024737774,0.18323326],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99863136,0.0000712994,0.0003910885,0.00036065694,0.00035128932,0.00019428109],"domain_scores_gemma":[0.9986856,0.00064391823,0.00008344345,0.00039245232,0.00013943869,0.00005515981],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0044406964,0.00007550793,0.00014649046,0.0001813661,0.0000731553,0.0002118902,0.00044837827,0.000101948266,0.0019686425],"category_scores_gemma":[0.0023464619,0.000054786542,0.00004224157,0.00059730833,0.000022727176,0.00037552515,0.0001031754,0.00018320636,0.00029669196],"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":[0.000109604574,0.00027308462,0.0047988044,0.000023362078,0.000013472621,0.0000016318609,0.00024001757,0.0000978917,0.005108053,0.31880406,0.46237618,0.20815384],"study_design_scores_gemma":[0.00034776656,0.000051941028,0.00068478787,0.0000027336819,0.0000037164912,6.7631186e-7,0.00017435191,0.010479884,0.0005335969,0.097969316,0.8896634,0.0000878365],"about_ca_topic_score_codex":0.00031496215,"about_ca_topic_score_gemma":0.0062096315,"teacher_disagreement_score":0.42728722,"about_ca_system_score_codex":0.000011473916,"about_ca_system_score_gemma":0.00003491462,"threshold_uncertainty_score":0.9989437},"labels":[],"label_agreement":null},{"id":"W2238711864","doi":"10.1561/9781680830231","title":"Trends in Cleaning Relational Data: Consistency and Deduplication","year":2015,"lang":"en","type":"book","venue":"now publishers, Inc. eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data quality; Computer science; Data deduplication; Data integrity; Relational database; Consistency (knowledge bases); Anomaly detection; Data consistency; Data mining; Data science; Automation; Process (computing); Data warehouse; Database; Quality (philosophy); Artificial intelligence; Engineering","score_opus":0.32777355947557785,"score_gpt":0.4006223382773515,"score_spread":0.07284877880177365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2238711864","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000044782475,0.000347872,0.00040445346,0.001565067,0.0006189618,0.0002834307,0.00064849353,0.00006980323,0.99601716],"genre_scores_gemma":[0.0009272893,0.000008588653,0.0019445869,0.0011390042,0.00034451074,0.000029184057,0.008147668,0.00003770042,0.98742145],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99447644,0.00029108304,0.0012782861,0.0014381758,0.0021772054,0.00033880494],"domain_scores_gemma":[0.9951984,0.0008436409,0.0007438368,0.0025046451,0.00047410265,0.00023536054],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009891309,0.00032770124,0.0005639128,0.0014471257,0.00016410604,0.0023116923,0.002215031,0.0004410967,0.00050177256],"category_scores_gemma":[0.0020697205,0.00029904387,0.00006239859,0.00027313404,0.0003509328,0.0030961172,0.0021206567,0.0006385488,0.00028781153],"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":[0.00001530237,0.000015806914,0.00012433778,0.000009608429,0.000022681457,0.0000068558093,0.00020352179,0.000001950162,2.3458801e-7,0.06580677,0.73669285,0.19710006],"study_design_scores_gemma":[0.00044831712,0.000027463177,0.0012182451,0.00004694225,0.00003622905,0.0000062066497,0.00033638751,0.0003578584,1.5540543e-7,0.10258902,0.89464015,0.00029301678],"about_ca_topic_score_codex":0.00012672423,"about_ca_topic_score_gemma":0.0022894423,"teacher_disagreement_score":0.19680704,"about_ca_system_score_codex":0.00028164132,"about_ca_system_score_gemma":0.00078197365,"threshold_uncertainty_score":0.9999462},"labels":[],"label_agreement":null},{"id":"W2250240387","doi":"","title":"How Joe and Jane Tweet about Their Health: Mining for Personal Health Information on Twitter","year":2013,"lang":"en","type":"article","venue":"Recent Advances in Natural Language Processing","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":"Dalhousie University; University of Ottawa","funders":"","keywords":"WordNet; Computer science; Social media; World Wide Web; Ontology; The Internet; Personally identifiable information; Information retrieval; Internet privacy; Information extraction; Health information; Data science; Health care; Computer security","score_opus":0.06336643424205922,"score_gpt":0.40170521289053357,"score_spread":0.33833877864847434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250240387","genre_codex":"review","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":[0.319914,0.4678303,0.03053282,0.1726304,0.002264407,0.004524616,0.0002345318,0.00024569614,0.0018232194],"genre_scores_gemma":[0.9751705,0.0027097543,0.008029607,0.01315012,0.00014128698,0.000076836615,0.00015727054,0.000011140055,0.00055348285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979951,0.00012558729,0.00053303206,0.0003404223,0.0005920284,0.00041387693],"domain_scores_gemma":[0.9987092,0.0003879252,0.00050011295,0.0001547928,0.00014495819,0.00010299659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017358116,0.00017127136,0.00030965396,0.00027529884,0.00025509132,0.0008821737,0.0002725445,0.00004102422,0.000027111104],"category_scores_gemma":[0.0009508833,0.0001140833,0.000035855475,0.00041353985,0.00006165789,0.0041571455,0.00009845287,0.00018905183,0.000010245951],"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":[0.000032433916,0.000016152402,0.00013059944,0.00019823715,0.000002236499,3.2248903e-7,0.017792758,0.000007324417,0.0000060702864,0.00005438141,0.0022737687,0.9794857],"study_design_scores_gemma":[0.0015312849,0.00031730134,0.0031421229,0.00089529745,0.0000033351942,0.000009508195,0.12890053,0.031759404,0.000118751406,0.0021402393,0.83070874,0.0004734997],"about_ca_topic_score_codex":0.000027968958,"about_ca_topic_score_gemma":0.00012732655,"teacher_disagreement_score":0.9790122,"about_ca_system_score_codex":0.00011920111,"about_ca_system_score_gemma":0.00006683783,"threshold_uncertainty_score":0.85068214},"labels":[],"label_agreement":null},{"id":"W2250317589","doi":"10.63317/5oexzp4sjvme","title":"Improving Entity Linking using Surface Form Refinement","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Polytechnique Montréal","funders":"","keywords":"Entity linking; Computer science; Rewriting; Natural language processing; Context (archaeology); NIST; Annotation; Task (project management); Word (group theory); Matching (statistics); Information retrieval; Artificial intelligence; Knowledge base; Similarity (geometry); Process (computing); Named entity; Linguistics; Programming language; Mathematics","score_opus":0.20972799306754583,"score_gpt":0.4123134049304373,"score_spread":0.20258541186289145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2250317589","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":[0.2608907,0.000010836257,0.6994624,0.0005648006,0.0005069338,0.00012531455,0.0000045228435,0.00006420694,0.038370263],"genre_scores_gemma":[0.9417626,0.0000025320699,0.050358042,0.0012168813,0.00009498955,0.0000011635508,0.000006887123,0.000006968354,0.0065499377],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99766093,0.00012937989,0.0005031075,0.00040338305,0.0010469405,0.00025627046],"domain_scores_gemma":[0.99854594,0.0003304318,0.00018958861,0.0007462042,0.00011337502,0.0000744597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007947532,0.00009638659,0.00016846893,0.00008869218,0.0002315378,0.00053641037,0.0006691803,0.00003547873,0.0007918316],"category_scores_gemma":[0.0009635821,0.00006991119,0.0000688902,0.0003085389,0.000034070763,0.00058429927,0.00069726,0.000073605246,0.00041347317],"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":[0.000020352607,0.00016047896,0.0075166603,0.000057267225,0.00003362439,0.0000033944018,0.0006436428,0.0019431356,0.007175549,0.2605816,0.015303591,0.70656073],"study_design_scores_gemma":[0.00062533806,0.00008629761,0.0023664963,0.000032185362,0.000030845073,0.0000019906538,0.0014886527,0.2716252,0.003535239,0.06747489,0.65230554,0.00042734644],"about_ca_topic_score_codex":0.00093603635,"about_ca_topic_score_gemma":0.00060930394,"teacher_disagreement_score":0.70613337,"about_ca_system_score_codex":0.000046532838,"about_ca_system_score_gemma":0.000019996056,"threshold_uncertainty_score":0.86700004},"labels":[],"label_agreement":null},{"id":"W2253088421","doi":"10.4018/978-1-61520-733-6.ch012","title":"New Technology and Implications for Healthcare and Public Health","year":2010,"lang":"en","type":"book-chapter","venue":"Advances in healthcare information systems and administration book series","topic":"Data Quality and Management","field":"Decision Sciences","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":"Brock University","funders":"","keywords":"Confidentiality; Linkage (software); Record linkage; Health care; Probabilistic logic; Medical record; Public health; Bridge (graph theory); Data science; Computer science; Business; Internet privacy; Knowledge management; Medicine; Computer security; Political science; Nursing; Population; Environmental health; Artificial intelligence","score_opus":0.10694852750238662,"score_gpt":0.40972359454677765,"score_spread":0.30277506704439106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2253088421","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016317295,0.12281045,0.054637834,0.7847909,0.002116405,0.008608134,0.0045212465,0.00033006494,0.022021815],"genre_scores_gemma":[0.25099885,0.42270568,0.052908074,0.03858912,0.0016391437,0.0033548702,0.007567308,0.00023730591,0.22199963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966351,0.0000632513,0.0020113313,0.00050388055,0.00043348543,0.00035298188],"domain_scores_gemma":[0.99673754,0.0003276661,0.0014532395,0.00055866287,0.00052538706,0.00039752576],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018230994,0.00030993627,0.0006585313,0.00097474613,0.00056442973,0.0007672797,0.0002608609,0.00042458222,0.000009295344],"category_scores_gemma":[0.00041620844,0.0002827153,0.00003649866,0.00018991959,0.00027537596,0.0061396463,0.00014512108,0.0003657978,0.0000074273626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018655757,0.0000026015382,0.00040397537,0.0006152182,0.000004448256,1.843054e-7,0.0003700716,3.5918023e-7,1.550602e-7,0.75347114,0.000539931,0.24457328],"study_design_scores_gemma":[0.00024220253,0.00040504086,0.00041615858,0.00016364483,0.000003116071,0.00006599071,0.0020543286,0.00000836727,8.4577545e-7,0.13167077,0.8647616,0.00020793338],"about_ca_topic_score_codex":0.00016974243,"about_ca_topic_score_gemma":0.0047671506,"teacher_disagreement_score":0.8642217,"about_ca_system_score_codex":0.00008107951,"about_ca_system_score_gemma":0.00087198766,"threshold_uncertainty_score":0.9999625},"labels":[],"label_agreement":null},{"id":"W2256186403","doi":"10.1108/lhtn-12-2015-0084","title":"Technological change, today and yesterday","year":2016,"lang":"en","type":"article","venue":"Library Hi Tech News","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 Saskatchewan","funders":"","keywords":"Yesterday; Context (archaeology); Column (typography); Computer science; Metadata; Originality; World Wide Web; Publishing; Data science; Data sharing; Value (mathematics); Telecommunications; Sociology; History; Political science; Qualitative research","score_opus":0.20770992933145518,"score_gpt":0.36826680356743635,"score_spread":0.16055687423598117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2256186403","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":[0.19778219,0.0015404592,0.047543913,0.5712131,0.0011769608,0.0019314996,0.00043302443,0.0030002752,0.17537856],"genre_scores_gemma":[0.89723736,0.00091247406,0.0096000945,0.014441326,0.00029546517,0.00013467338,0.000014279517,0.000029287656,0.07733504],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983309,0.00012708876,0.00033669636,0.0005070155,0.00046160986,0.00023669882],"domain_scores_gemma":[0.9984936,0.0004765917,0.000095723124,0.0008212433,0.000009944424,0.00010288554],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006673326,0.00012106664,0.00019377425,0.00022560766,0.00007791087,0.00024121432,0.0009452553,0.00010923203,0.0013857811],"category_scores_gemma":[0.0004520993,0.000060110437,0.000044550397,0.00047666574,0.00029002604,0.0022931509,0.0012173975,0.00007533649,0.00095089735],"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":[0.000009385259,0.000026591351,0.004510496,0.0000022124127,0.0000033141769,0.000015082766,0.00003413711,5.0667435e-9,0.00027282373,0.09111709,0.114205435,0.78980345],"study_design_scores_gemma":[0.00017836125,0.000055975306,0.0076307086,0.00001798426,0.000002354563,0.0000043185146,0.0001314708,0.0000026313548,0.0013011026,0.13176304,0.8588013,0.00011075476],"about_ca_topic_score_codex":0.0000045623856,"about_ca_topic_score_gemma":0.000004815889,"teacher_disagreement_score":0.7896927,"about_ca_system_score_codex":0.0000047469453,"about_ca_system_score_gemma":0.000009157765,"threshold_uncertainty_score":0.99982697},"labels":[],"label_agreement":null},{"id":"W2260484439","doi":"10.14778/2824032.2824036","title":"SEMA-JOIN","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"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; Joins; Join (topology); Hash join; Table (database); Theoretical computer science; Data mining; Database; Programming language; Mathematics","score_opus":0.2932342444414948,"score_gpt":0.4016846612147633,"score_spread":0.1084504167732685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2260484439","genre_codex":"other","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":[0.43994513,0.00027912902,0.0005336356,0.030319914,0.001955734,0.0012935428,0.000052827963,0.000118911725,0.5255012],"genre_scores_gemma":[0.9859812,0.000009056158,0.0013921544,0.00085359847,0.000077642915,0.000024651386,7.039278e-7,0.0000071393297,0.011653826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971752,0.000019333223,0.0004998872,0.00029988968,0.0018020106,0.00020364292],"domain_scores_gemma":[0.9987275,0.00009267046,0.00034512812,0.00031042256,0.0004077383,0.00011655031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004506487,0.000104631836,0.00019964241,0.00010627566,0.000071584924,0.00017336388,0.0016081008,0.00002890498,0.00009238273],"category_scores_gemma":[0.0021712196,0.000057614587,0.000105742736,0.0005442548,0.00009932725,0.00037151197,0.0010611337,0.000078993304,0.00026981288],"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":[0.000047495738,0.00018033956,0.004232143,0.00002544698,0.000036928286,4.7956195e-7,0.002107809,0.00002234002,0.0024244182,0.19565849,0.77837974,0.016884403],"study_design_scores_gemma":[0.0007256248,0.00011260732,0.00270726,0.0000387251,0.000029683872,0.000005298719,0.007430501,0.0001606574,0.03601578,0.26492023,0.68769,0.00016360579],"about_ca_topic_score_codex":0.00006553871,"about_ca_topic_score_gemma":0.000007710871,"teacher_disagreement_score":0.5460361,"about_ca_system_score_codex":0.00005517833,"about_ca_system_score_gemma":0.000031029544,"threshold_uncertainty_score":0.3467989},"labels":[],"label_agreement":null},{"id":"W2260968375","doi":"10.6084/m9.figshare.1040467.v1","title":"#G2B2014 talk: Troubleshooting public data archiving: suggestions to increase participation","year":2014,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Troubleshooting; Public relations; Internet privacy; Computer science; World Wide Web; Business; Political science; Data science","score_opus":0.5569159018648346,"score_gpt":0.47340882206288176,"score_spread":0.08350707980195288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2260968375","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016908893,0.00004763636,0.029378606,0.027237242,0.00057701836,0.0016634534,0.8059176,0.00063060893,0.117638946],"genre_scores_gemma":[0.8460788,2.661177e-7,0.0013009956,0.001761006,0.00022049512,0.00013223894,0.14874801,0.000012219851,0.0017459631],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99703336,0.00042768926,0.0005090156,0.0006877791,0.0009720423,0.00037010567],"domain_scores_gemma":[0.99441177,0.0021395665,0.00021807522,0.0026039842,0.00022254506,0.00040406059],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002676778,0.00012790122,0.00018569683,0.00026033903,0.00027274806,0.0009964643,0.002469211,0.00003779595,0.07753937],"category_scores_gemma":[0.099534914,0.00010877962,0.00004365453,0.0006811627,0.000010175623,0.0011518616,0.0024662241,0.00011460937,0.02156941],"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":[0.000003828993,0.000052791434,0.00016381306,0.000013063641,0.0000056397216,0.0000016798463,0.000083963634,0.00008677107,0.000009877948,0.0028124533,0.89908504,0.09768105],"study_design_scores_gemma":[0.00013272828,0.00003132707,0.016633607,0.000126188,0.0000067104816,0.0000011783168,0.00010388329,0.013754526,0.000017657085,0.0020805872,0.9669566,0.00015497567],"about_ca_topic_score_codex":0.00006307818,"about_ca_topic_score_gemma":0.0007565143,"teacher_disagreement_score":0.8291699,"about_ca_system_score_codex":0.00002169862,"about_ca_system_score_gemma":0.000045894092,"threshold_uncertainty_score":0.97919244},"labels":[],"label_agreement":null},{"id":"W2262592273","doi":"10.14778/2824032.2824109","title":"KATARA","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":45,"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; Table (database); Crowdsourcing; Ambiguity; Tuple; Information retrieval; Annotation; Task (project management); Semantics (computer science); Reliability (semiconductor); Data mining; World Wide Web; Programming language; Artificial intelligence","score_opus":0.34404765762554373,"score_gpt":0.4117242000185209,"score_spread":0.06767654239297716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2262592273","genre_codex":"other","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":[0.4788121,0.00027195603,0.00041791852,0.02637879,0.0019338108,0.0011111654,0.00005469319,0.000101510384,0.49091807],"genre_scores_gemma":[0.9904682,0.000007201678,0.0010645605,0.00070658646,0.00006562925,0.000019416075,7.5012537e-7,0.000005446402,0.007662233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973964,0.000014970492,0.00044493604,0.00027100352,0.0016916761,0.00018101264],"domain_scores_gemma":[0.99885494,0.0000811193,0.00030329896,0.00027498003,0.00038114854,0.00010450634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038696777,0.000091712696,0.00017262471,0.00009248174,0.00006401042,0.00015642121,0.001688209,0.000024278228,0.00008126148],"category_scores_gemma":[0.0019589872,0.00004972197,0.00009150177,0.0004905285,0.000099061384,0.0003781865,0.0010013727,0.000070292015,0.00025454286],"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":[0.000051583163,0.00016946271,0.005958328,0.00002003826,0.00003560149,3.9031346e-7,0.0019413386,0.000023848972,0.0014267978,0.23066008,0.74037254,0.019339977],"study_design_scores_gemma":[0.00063827843,0.00009866243,0.0031026935,0.000027972552,0.000026041062,0.000003994799,0.0062122,0.00012786972,0.031369224,0.24951574,0.7087362,0.0001411328],"about_ca_topic_score_codex":0.00006843983,"about_ca_topic_score_gemma":0.0000044513918,"teacher_disagreement_score":0.5116561,"about_ca_system_score_codex":0.00004662251,"about_ca_system_score_gemma":0.000027515853,"threshold_uncertainty_score":0.32717186},"labels":[],"label_agreement":null},{"id":"W2284343953","doi":"10.1111/cobi.12706","title":"Emerging problems of data quality in citizen science","year":2016,"lang":"en","type":"editorial","venue":"Conservation Biology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":209,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Citizen science; Crowdsourcing; Citizen journalism; Open science; Data science; Open data; Resource (disambiguation); World Wide Web; Computer science; Political science; Public relations","score_opus":0.33745717628879024,"score_gpt":0.5204741367644338,"score_spread":0.18301696047564353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284343953","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":[0.00236915,0.00026687345,0.015450512,0.00897131,0.96097183,0.00070941367,0.006072109,0.00005096409,0.005137814],"genre_scores_gemma":[0.03865765,0.0023827103,0.009695689,0.0036571175,0.9068984,0.00026402215,0.021036793,0.00010725114,0.017300393],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940971,0.0008863985,0.0018345879,0.0013361167,0.0014935662,0.00035221686],"domain_scores_gemma":[0.986258,0.007824603,0.0015048,0.0031264434,0.0012187981,0.000067407826],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033924274,0.00017604935,0.00061944936,0.0007978627,0.00010007084,0.000109015025,0.005622295,0.000361444,0.00023573382],"category_scores_gemma":[0.056279153,0.0001231673,0.00004353419,0.0013260207,0.0012433016,0.0009043169,0.0027952928,0.00024349017,0.000113193484],"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":[0.000022463442,0.000028267745,0.00234826,0.00004019408,0.000008590725,4.7106448e-7,0.00008338658,5.52996e-7,0.00059381407,0.014061058,0.9585156,0.024297332],"study_design_scores_gemma":[0.00035886877,0.000030707466,0.0018549612,0.00008372658,0.000005126183,7.9467775e-8,0.000093300696,0.00006785487,0.000025382556,0.04730366,0.95002234,0.00015401008],"about_ca_topic_score_codex":0.0012918741,"about_ca_topic_score_gemma":0.0017738407,"teacher_disagreement_score":0.054073483,"about_ca_system_score_codex":0.00007504869,"about_ca_system_score_gemma":0.0009809454,"threshold_uncertainty_score":0.99975777},"labels":[],"label_agreement":null},{"id":"W2286638398","doi":"10.15353/joci.v12i2.3221","title":"User Centred Methods for Measuring the Value of Open Data","year":2016,"lang":"en","type":"article","venue":"The Journal of Community Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre","keywords":"Open data; Computer science; Key (lock); Measure (data warehouse); Data science; Data quality; Quality (philosophy); Open source; Knowledge management; World Wide Web; Data mining; Engineering; Software; Operations management; Computer security; Metric (unit)","score_opus":0.6407874768984645,"score_gpt":0.5418677551865244,"score_spread":0.09891972171194008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286638398","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":[0.034780663,0.00008916568,0.9494325,0.010843257,0.00033208713,0.00046047365,0.0001619624,0.0000042063293,0.0038956853],"genre_scores_gemma":[0.81139463,0.0005919851,0.18241394,0.0043316064,0.00010587615,0.000003874912,0.000014597285,0.00001722995,0.0011262557],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99370617,0.0036672899,0.0016265269,0.000014809037,0.0008349512,0.0001502786],"domain_scores_gemma":[0.97593886,0.018414462,0.0018724523,0.0031597435,0.0005641405,0.000050321672],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08041298,0.00007744776,0.00029421627,0.00009059844,0.0004548857,0.0003018768,0.018930463,0.00002436675,0.000045717305],"category_scores_gemma":[0.013282735,0.000026849175,0.00007368773,0.00023627849,0.00019624515,0.0024134414,0.0069099786,0.00026588162,0.000011668226],"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":[0.0003294932,0.00015920826,0.00006160804,0.000053955915,0.00028316904,5.1696137e-8,0.09007178,0.00034171165,0.0001714592,0.025902055,0.1515738,0.7310517],"study_design_scores_gemma":[0.0011045375,0.00014954865,0.00085303513,0.00013430396,0.00014691154,0.00001778577,0.21770251,0.0015070703,0.0012662482,0.0972589,0.6797711,0.00008803212],"about_ca_topic_score_codex":0.00008404275,"about_ca_topic_score_gemma":0.000041856,"teacher_disagreement_score":0.776614,"about_ca_system_score_codex":0.000021924321,"about_ca_system_score_gemma":0.00009757075,"threshold_uncertainty_score":0.9950288},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["open_science"],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W2290810428","doi":"","title":"Disambiguating Multiple Links in Historical Record Linkage","year":2013,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linkage (software); Record linkage; Genealogy; Data science; Geography; Computer science; History; Biology; Genetics; Sociology; Demography; Gene","score_opus":0.09021744308175651,"score_gpt":0.31516764603830777,"score_spread":0.22495020295655127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290810428","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":[0.96584404,0.00042191803,0.0025491966,0.0051804595,0.002381401,0.0008429695,0.0000790571,0.00006727434,0.022633707],"genre_scores_gemma":[0.87176156,0.00014833092,0.0012278615,0.000076185555,0.00008946398,8.566745e-7,0.00024707484,0.000013459104,0.12643522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972648,0.00040957762,0.00050986133,0.00050847913,0.001056266,0.00025098794],"domain_scores_gemma":[0.99662024,0.0013325386,0.00077410386,0.0009791682,0.00021665108,0.00007730972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026812996,0.0001884245,0.00050816324,0.00042564678,0.00025120107,0.00007318478,0.0022892766,0.00037174404,0.0008188362],"category_scores_gemma":[0.001515042,0.00016242613,0.0002539743,0.0007755364,0.000077124474,0.00042213744,0.00038517808,0.0007052836,0.00068642147],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078114186,0.00056084216,0.0049346946,0.0003840963,0.00018605686,0.00009208317,0.04613914,0.0001716479,0.007082099,0.0038677517,0.394077,0.54172343],"study_design_scores_gemma":[0.0015208843,0.000188164,0.39916858,0.00023454428,0.0001971226,0.0000010797916,0.1259213,0.0044273906,0.00004513238,0.012780895,0.45477706,0.00073784805],"about_ca_topic_score_codex":0.016875312,"about_ca_topic_score_gemma":0.018157987,"teacher_disagreement_score":0.5409856,"about_ca_system_score_codex":0.00026491686,"about_ca_system_score_gemma":0.000076315715,"threshold_uncertainty_score":0.99975806},"labels":[],"label_agreement":null},{"id":"W2294032921","doi":"10.1371/journal.pone.0150176","title":"Assessing Hepatitis C Burden and Treatment Effectiveness through the British Columbia Hepatitis Testers Cohort (BC-HTC): Design and Characteristics of Linked and Unlinked Participants","year":2016,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario HIV Treatment Network; BC Cancer Agency; Ministry of Health; BC Centre for Disease Control; University of British Columbia; Provincial Health Services Authority","funders":"National Institute on Minority Health and Health Disparities; British Columbia Centre for Disease Control; BC Cancer Agency; Provincial Health Services Authority","keywords":"Medicine; Cohort; Hepatitis C; Record linkage; Epidemiology; Linkage (software); Tuberculosis; Hepatitis B; Cohort study; Environmental health; Internal medicine; Population; Pathology; Biology","score_opus":0.21807034899535468,"score_gpt":0.3528604604680532,"score_spread":0.1347901114726985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294032921","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":[0.9934933,0.00013966438,0.0045862086,0.0005152219,0.000051133633,0.00095393544,0.00017706896,0.00002422738,0.00005923478],"genre_scores_gemma":[0.9938014,0.003068488,0.0023629179,0.00008048382,0.000049954346,0.00011161326,0.000010092538,0.000013337884,0.00050169986],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973027,0.00077909935,0.0005241253,0.0004984363,0.000631072,0.00026456517],"domain_scores_gemma":[0.99519074,0.0038471993,0.0002780769,0.0004153126,0.00016502311,0.00010366658],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020468256,0.00013477806,0.0005427723,0.000029204466,0.00038055822,0.0018230537,0.0001998802,0.00006485122,0.000048898815],"category_scores_gemma":[0.0015661806,0.00010456079,0.000028527018,0.00015894012,0.0004688833,0.0006820767,0.00022093146,0.00005038094,0.0000063701423],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026450623,0.00023181029,0.83438146,0.000057069978,0.00026453505,0.000021573303,0.00051613746,3.821443e-7,0.0017113134,0.000032363332,0.00008851722,0.16266839],"study_design_scores_gemma":[0.00086833833,0.00034283745,0.99368584,0.00059795944,0.0002863582,0.0000044601256,0.00018434502,0.00038825822,0.0004209125,0.0027892578,0.00027396274,0.00015749635],"about_ca_topic_score_codex":0.033635963,"about_ca_topic_score_gemma":0.008736778,"teacher_disagreement_score":0.1625109,"about_ca_system_score_codex":0.00004681979,"about_ca_system_score_gemma":0.000038254835,"threshold_uncertainty_score":0.99921316},"labels":[],"label_agreement":null},{"id":"W2294497255","doi":"10.1007/978-3-319-26187-4_35","title":"A Data Quality Framework for Customer Relationship Analytics","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data quality; Inefficiency; Key (lock); Quality (philosophy); Data analysis; Data science; Customer relationship management; Analytics; Set (abstract data type); Data management; Data set; Data modeling; Data mining; Database; Computer security; Business; Artificial intelligence; Marketing","score_opus":0.5334999294272715,"score_gpt":0.49637163349274754,"score_spread":0.03712829593452399,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294497255","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":[0.0000068269705,0.00023318238,0.98684365,0.002977585,0.0015895213,0.0005582929,0.00076386944,0.000052568306,0.0069744964],"genre_scores_gemma":[0.033092454,0.00001926463,0.95402193,0.0038779073,0.0011350516,0.000011447201,0.00046037533,0.000044999848,0.0073365797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99255776,0.00014696099,0.0012721804,0.0021540166,0.0033592156,0.0005098822],"domain_scores_gemma":[0.9832718,0.0096479375,0.0007181931,0.005361851,0.0007691455,0.00023108546],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.022581391,0.0003726396,0.00068165176,0.00096373487,0.000302762,0.0010756181,0.008158239,0.00039701018,0.00013107057],"category_scores_gemma":[0.02060323,0.00029613732,0.00012592087,0.0010699712,0.00093632215,0.00092492515,0.0038404986,0.00077117747,0.00033834836],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022213118,0.00003122941,0.00022458646,0.000027904784,0.000015434716,0.0000069457597,0.0003062024,0.00986827,3.528709e-7,0.58642226,0.00987797,0.39319664],"study_design_scores_gemma":[0.00012249305,0.00003566964,0.00024555638,0.000073446136,0.000018082961,0.0000019392144,0.0000017844997,0.047298923,0.0000016531746,0.738375,0.2135164,0.0003090566],"about_ca_topic_score_codex":0.000024281519,"about_ca_topic_score_gemma":0.000523165,"teacher_disagreement_score":0.3928876,"about_ca_system_score_codex":0.00021840369,"about_ca_system_score_gemma":0.0007757735,"threshold_uncertainty_score":0.9999614},"labels":[],"label_agreement":null},{"id":"W2294768574","doi":"10.1109/icppw.2015.42","title":"Efficient Parallelization of the Google Trigram Method for Document Relatedness Computation","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Dalhousie University","funders":"","keywords":"Computer science; Trigram; Computation; Set (abstract data type); Construct (python library); Theoretical computer science; Word (group theory); Parallel computing; Artificial intelligence; Algorithm; Programming language","score_opus":0.26415966669649316,"score_gpt":0.4911128465630769,"score_spread":0.22695317986658375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294768574","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":[0.0079022525,0.000018499737,0.9836079,0.0023879532,0.00049952196,0.0005973406,0.000010803829,0.000019877776,0.004955847],"genre_scores_gemma":[0.8412213,0.0000018254916,0.14764167,0.00074363354,0.000032599928,0.0000504276,0.00003497472,0.000007825171,0.01026578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794275,0.0003534178,0.0005059591,0.0002189191,0.00087924744,0.00009971673],"domain_scores_gemma":[0.99835235,0.00062907237,0.00025616976,0.00035312868,0.00036211003,0.000047153768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006748628,0.00006003095,0.00013837001,0.00007392055,0.00006940807,0.000087193686,0.0004232349,0.000032518903,0.000038258688],"category_scores_gemma":[0.0015049861,0.000032042626,0.00007482933,0.00050253136,0.000033752163,0.00008198469,0.00015949758,0.000027710254,0.00003798548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000773596,0.00016697652,0.00009034558,0.000012079114,0.000022378088,1.3110389e-7,0.0017372506,0.537115,0.000030939067,0.2617287,0.10503719,0.09398165],"study_design_scores_gemma":[0.0012589274,0.000113421076,0.0008250686,0.0000109758,0.000031813124,6.5013666e-7,0.0034954413,0.6740208,0.00073587045,0.19642712,0.12297554,0.000104356666],"about_ca_topic_score_codex":0.0001013125,"about_ca_topic_score_gemma":0.000039232313,"teacher_disagreement_score":0.8359662,"about_ca_system_score_codex":0.000033855256,"about_ca_system_score_gemma":0.00004385196,"threshold_uncertainty_score":0.23389532},"labels":[],"label_agreement":null},{"id":"W2295201002","doi":"10.1109/ichi.2015.109","title":"What's to Learn from Unvalidated Sources of Health Information?","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Memorial University of Newfoundland","funders":"","keywords":"Identification (biology); Computer science; Risk analysis (engineering); Data science; Knowledge management; Management science; Engineering; Business","score_opus":0.28847573540003446,"score_gpt":0.44650085666489814,"score_spread":0.15802512126486368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295201002","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":[0.6215384,0.00021610846,0.23458394,0.09084141,0.0021524972,0.0007936627,0.0002064275,0.00016469196,0.049502853],"genre_scores_gemma":[0.96215284,0.000027467788,0.0073172622,0.020789886,0.000041668587,0.00000705387,0.00015812978,0.000004441201,0.009501242],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774,0.0002153077,0.0006960282,0.0001359668,0.0010893227,0.00012339652],"domain_scores_gemma":[0.9986603,0.00021788449,0.0002215216,0.000502304,0.00023770361,0.00016023639],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005243906,0.000054991393,0.00018647386,0.00018298598,0.000041114028,0.00061291404,0.0006008769,0.000019265102,0.00063326],"category_scores_gemma":[0.0013624995,0.000037726662,0.000026565553,0.00051059126,0.000027248585,0.0029440594,0.00031891788,0.000031408417,0.0032666144],"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":[0.00002540363,0.000044962333,0.0012938641,0.0000040213345,0.000014856561,2.869766e-7,0.0111220665,0.0006888234,0.0000019158495,0.012820155,0.6490506,0.32493308],"study_design_scores_gemma":[0.00022149037,0.00008390244,0.0032943615,0.00001034511,0.0000016479718,1.310035e-7,0.06914147,0.0002155639,0.00017717537,0.015277275,0.9115151,0.00006149869],"about_ca_topic_score_codex":0.0025474227,"about_ca_topic_score_gemma":0.00030757312,"teacher_disagreement_score":0.34061444,"about_ca_system_score_codex":0.000018188259,"about_ca_system_score_gemma":0.000081751634,"threshold_uncertainty_score":0.9975095},"labels":[],"label_agreement":null},{"id":"W2295468252","doi":"10.14778/2856318.2856325","title":"Combining quantitative and logical data cleaning","year":2015,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University; McMaster University; University of Toronto","funders":"","keywords":"Computer science; Metric (unit); Inference; Functional dependency; Set (abstract data type); Distortion (music); Statistical inference; Data mining; Algorithm; Theoretical computer science; Dependency (UML); Quality (philosophy); Data quality; Artificial intelligence; Relational database; Mathematics","score_opus":0.6149975953066957,"score_gpt":0.46831911800896336,"score_spread":0.14667847729773237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295468252","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":[0.8576558,0.000619131,0.0020347037,0.01634783,0.00095049787,0.0010692904,0.00014263696,0.00009417782,0.121085934],"genre_scores_gemma":[0.99297893,0.000018739227,0.0060202754,0.000415054,0.000023338138,0.000006020169,0.0000035215762,0.000005000513,0.0005291247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977972,0.000031881475,0.00043404335,0.00041970517,0.0011464946,0.00017070991],"domain_scores_gemma":[0.9986349,0.0003081137,0.00033326904,0.00037710302,0.00024603843,0.00010061237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059782444,0.00009779505,0.00021289579,0.000073743955,0.00010760045,0.0002372084,0.0018597412,0.000026016503,0.000018939967],"category_scores_gemma":[0.0047378363,0.00005502174,0.00003024039,0.0003319944,0.00018943092,0.0006538076,0.00362099,0.00010046949,0.000030717252],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012732235,0.00018007187,0.01047531,0.000032786473,0.00006513477,0.0000010813916,0.0058014565,0.000017464672,0.0013909802,0.8257729,0.1355931,0.020542407],"study_design_scores_gemma":[0.0026813566,0.0007681448,0.014293695,0.00020923157,0.00012735295,0.000021913154,0.10939527,0.00860213,0.0059854877,0.5873224,0.2700839,0.00050907466],"about_ca_topic_score_codex":0.000057334182,"about_ca_topic_score_gemma":0.000007735977,"teacher_disagreement_score":0.23845045,"about_ca_system_score_codex":0.000021559514,"about_ca_system_score_gemma":0.000018833302,"threshold_uncertainty_score":0.5671975},"labels":[],"label_agreement":null},{"id":"W2295659583","doi":"","title":"DataXFormer: Leveraging the Web for Semantic Transformations","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":18,"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; Transformation (genetics); Semantic Web; Data transformation; Code (set theory); Value (mathematics); Resource (disambiguation); Information retrieval; Data Web; Web application; Web service; Programming language; World Wide Web; Theoretical computer science; Database; Data warehouse; Set (abstract data type)","score_opus":0.46775781758491525,"score_gpt":0.4531624274002128,"score_spread":0.014595390184702461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295659583","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":[0.0036593196,0.00002668973,0.87236786,0.03586712,0.00040356218,0.0004766916,0.000118096126,0.00005032766,0.08703035],"genre_scores_gemma":[0.9739695,0.000014610804,0.004352335,0.0046549314,0.000073735435,0.000053744745,0.0000691799,0.000005201231,0.016806768],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986692,0.00006309932,0.0003289219,0.00015700041,0.0006308778,0.00015089344],"domain_scores_gemma":[0.9986892,0.00052366185,0.00005352736,0.000551816,0.00011816262,0.00006365666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056058816,0.000055186087,0.000088042936,0.000075130934,0.00019460257,0.0003690995,0.000812398,0.000013629292,0.00019887865],"category_scores_gemma":[0.0008141751,0.00002742403,0.000051509367,0.0002737529,0.000041299663,0.00085767516,0.00009760987,0.000037221096,0.0006340767],"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":[0.0000073591273,0.00001965538,0.000040295487,0.000003923212,0.000010263957,1.7528164e-7,0.0015631965,0.00010714357,0.000007965819,0.12577055,0.8285108,0.043958645],"study_design_scores_gemma":[0.00027084656,0.000015570151,0.0000748661,0.0000017945677,0.000009341313,0.0000012244615,0.008650146,0.019325908,0.00004092498,0.05873349,0.9128241,0.00005177757],"about_ca_topic_score_codex":0.000041930925,"about_ca_topic_score_gemma":0.00027073128,"teacher_disagreement_score":0.97031015,"about_ca_system_score_codex":0.000011648657,"about_ca_system_score_gemma":0.0000532574,"threshold_uncertainty_score":0.81499845},"labels":[],"label_agreement":null},{"id":"W2295712623","doi":"","title":"ualberta at TAC-KBP 2012: English and Cross-Lingual Entity Linking.","year":2012,"lang":"en","type":"article","venue":"Theory and applications of categories","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":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Entity linking; Knowledge base; Ambiguity; Information retrieval; Construct (python library); Task (project management); Information extraction; Pace; Natural language processing; Artificial intelligence; Programming language; Engineering","score_opus":0.0449615131411834,"score_gpt":0.3754842903132494,"score_spread":0.330522777172066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295712623","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":[0.9497654,0.0029776744,0.019720469,0.00021276357,0.00025554653,0.00043405255,0.0001473465,0.000055223318,0.026431538],"genre_scores_gemma":[0.9900098,0.0001474828,0.00020812015,0.00011455023,0.00020456503,0.00005270129,0.00004076865,0.0000058078417,0.009216212],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986556,0.00017675808,0.00038547,0.00026174443,0.00032842418,0.0001920133],"domain_scores_gemma":[0.997428,0.0014937121,0.00019408902,0.00058417534,0.00019095378,0.00010904529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005010619,0.000105946354,0.00019111641,0.000090731264,0.00037212647,0.00018445936,0.00038134962,0.00006017356,0.00030044053],"category_scores_gemma":[0.0008080063,0.00008403563,0.00003528261,0.0002422136,0.0007199414,0.00079790637,0.00051672204,0.00007298891,0.0000700098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042230513,0.00006564095,0.00813046,0.00002437375,0.0000152283565,5.5570684e-8,0.003497409,0.0000013851705,0.000067269706,0.9540112,0.0010311625,0.033113565],"study_design_scores_gemma":[0.00016744705,0.000019567613,0.008621433,0.0000037543618,0.000028315511,0.0000017852758,0.0026608382,0.0000023372359,0.002374243,0.49829,0.48770848,0.00012181478],"about_ca_topic_score_codex":0.000025746956,"about_ca_topic_score_gemma":0.000037035046,"teacher_disagreement_score":0.48667732,"about_ca_system_score_codex":0.000008113756,"about_ca_system_score_gemma":0.000013959449,"threshold_uncertainty_score":0.34268737},"labels":[],"label_agreement":null},{"id":"W2312243314","doi":"10.1177/2327857914031002","title":"User Perception of Data and Medical Record Personalities","year":2014,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Conestoga College","funders":"","keywords":"Data quality; Quality (philosophy); Computer science; Personality psychology; Personality; Data science; Perception; Psychology; Engineering; Social psychology","score_opus":0.12846512510153843,"score_gpt":0.40332280737459447,"score_spread":0.27485768227305607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312243314","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":[0.9939584,0.00002688703,0.000010993446,0.004068632,0.00028122717,0.00011298627,0.00014284323,0.0000042149295,0.0013938174],"genre_scores_gemma":[0.99882585,0.0001904405,0.00015005468,0.00056734093,0.00006858727,0.0000024747212,0.000025174231,0.000004847584,0.00016523583],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982316,0.000028244414,0.00061140297,0.0003295032,0.0006959487,0.00010332139],"domain_scores_gemma":[0.9989179,0.0002878112,0.00038924394,0.00018574539,0.00015266481,0.00006663426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002369489,0.00008837471,0.00021286345,0.000114626506,0.00009779246,0.00009128774,0.0011842935,0.000048997164,0.000059053964],"category_scores_gemma":[0.00061975984,0.000058852675,0.000031900003,0.00005975742,0.00014531348,0.0003219662,0.0008027297,0.00011823974,7.763694e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022303112,0.00010140163,0.77490896,0.00045032336,0.000035109606,6.312726e-8,0.01598299,0.000007889945,0.000271336,0.17559074,0.009248948,0.023179194],"study_design_scores_gemma":[0.0010749717,0.0004810135,0.75881535,0.0007681011,0.000014287661,0.0000026474397,0.06442826,0.0028141006,0.0002183965,0.011166234,0.15991078,0.00030585023],"about_ca_topic_score_codex":0.0010337086,"about_ca_topic_score_gemma":0.0005603624,"teacher_disagreement_score":0.16442451,"about_ca_system_score_codex":0.00008399959,"about_ca_system_score_gemma":0.000028085064,"threshold_uncertainty_score":0.23999423},"labels":[],"label_agreement":null},{"id":"W2328353948","doi":"10.2966/script.120215.154","title":"Reflections on the Concept of Open Data","year":2015,"lang":"en","type":"article","venue":"SCRIPTed A Journal of Law Technology & Society","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Computer science; Data science","score_opus":0.6257464399519292,"score_gpt":0.5407464510057203,"score_spread":0.08499998894620897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2328353948","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":[0.0663156,0.0037774886,0.043361835,0.6282549,0.0062989276,0.001861832,0.0011068025,0.00022546534,0.24879718],"genre_scores_gemma":[0.9816927,0.00006709605,0.010362251,0.0069565745,0.00007665156,0.0000036738486,0.000008548567,0.000008506673,0.0008240306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975782,0.00024635292,0.00081660686,0.00025561082,0.0009337029,0.00016949668],"domain_scores_gemma":[0.9962185,0.00037853964,0.0008619365,0.0017684464,0.0007040554,0.00006849106],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.009408119,0.00009397326,0.00033265701,0.000098559394,0.0002128684,0.00018988218,0.008039039,0.00012950829,0.00012456092],"category_scores_gemma":[0.0029129589,0.000052139672,0.00012213674,0.0010613224,0.0009827996,0.0007981142,0.0027903474,0.00050337747,0.000036564663],"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":[0.000018084354,0.00008357518,0.000018349989,5.481742e-7,0.00008759362,0.00000285977,0.00080852956,0.00000777482,0.00019296214,0.47011322,0.52579266,0.0028738442],"study_design_scores_gemma":[0.00045968225,0.00024704935,0.000023272729,0.00002320757,0.00003323807,0.000024241082,0.027390635,0.00004286924,0.0012261935,0.2199228,0.7505532,0.000053655884],"about_ca_topic_score_codex":0.00009804165,"about_ca_topic_score_gemma":0.00009781892,"teacher_disagreement_score":0.9153771,"about_ca_system_score_codex":0.0000502362,"about_ca_system_score_gemma":0.00017837873,"threshold_uncertainty_score":0.9973279},"labels":[],"label_agreement":null},{"id":"W233072892","doi":"","title":"Thoughts on a Design Framework for System Integration","year":2007,"lang":"en","type":"article","venue":"Defense Technical Information Center (DTIC)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interoperability; System integration; Computer science; Process (computing); Data integration; Software engineering; Knowledge management; Systems engineering; Data science; Engineering; World Wide Web; Database","score_opus":0.20244393454300066,"score_gpt":0.4178670335534149,"score_spread":0.21542309901041426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W233072892","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":[0.0005229049,0.0000041316334,0.9851958,0.000740421,0.00075594743,0.001093715,0.00009391926,0.00031161352,0.011281546],"genre_scores_gemma":[0.85754263,0.0000038009046,0.13811137,0.0037103044,0.00021746996,0.00009583195,0.00016422047,0.000010548941,0.0001438414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666977,0.00013984327,0.0013835737,0.00026817195,0.0011777773,0.00036086395],"domain_scores_gemma":[0.9956492,0.002604216,0.00044960462,0.00079912605,0.00035450814,0.00014334756],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008454921,0.00018334841,0.00026034587,0.00045126115,0.00021223692,0.00051526533,0.0006822731,0.00020433345,0.000030963456],"category_scores_gemma":[0.0046344907,0.00013108671,0.00016466867,0.0005982624,0.000065689994,0.0013592264,0.00013999068,0.00022876226,0.0012599448],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046034373,0.00011308161,0.000017029623,0.000034448756,0.0000136011095,0.0000023047226,0.000514765,0.0001327798,0.000018333609,0.8542552,0.060426645,0.084011465],"study_design_scores_gemma":[0.001758303,0.00075456646,0.001727342,0.00046364355,0.00004868134,0.000034441655,0.005446527,0.0120231,0.0033005911,0.15352109,0.82027745,0.0006442551],"about_ca_topic_score_codex":0.0000035169874,"about_ca_topic_score_gemma":0.000010373904,"teacher_disagreement_score":0.8570197,"about_ca_system_score_codex":0.00017998097,"about_ca_system_score_gemma":0.00002212697,"threshold_uncertainty_score":0.9995177},"labels":[],"label_agreement":null},{"id":"W2330924252","doi":"10.1097/ede.0b013e318210aca5","title":"The New World of Data Linkages in Clinical Epidemiology","year":2011,"lang":"en","type":"review","venue":"Epidemiology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Cancer Institute","keywords":"Epidemiology; Geography; Data science; Computational biology; Medicine; Computer science; Biology; Pathology","score_opus":0.9333179870764827,"score_gpt":0.6914807965745963,"score_spread":0.24183719050188646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2330924252","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.208806e-7,0.97938836,0.006209449,0.006656712,0.0025401455,0.0007014909,0.00024516217,0.000023422754,0.004235047],"genre_scores_gemma":[5.184928e-7,0.9781624,0.0071927,0.0027255553,0.00076076697,0.00003195628,0.00037757063,0.000024691266,0.010723862],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.86583084,0.102148734,0.02571178,0.0040214406,0.0005124272,0.0017747643],"domain_scores_gemma":[0.36440504,0.61241716,0.009971683,0.012643773,0.00012882441,0.00043354914],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30914587,0.0005117556,0.009570676,0.000668052,0.00010925736,0.000017395316,0.013484491,0.00086736423,0.00057278894],"category_scores_gemma":[0.42162368,0.00025987191,0.0010368945,0.0012838034,0.0014791172,0.00026549178,0.006352066,0.0017098921,0.0017810097],"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":[0.0000050929434,0.000026433698,0.0007517844,0.0001538618,0.00007034293,0.0000024907322,0.0000065500985,3.9433792e-7,1.2299704e-10,0.09536202,0.35129976,0.55232126],"study_design_scores_gemma":[0.0001023465,0.00005261846,0.0012318499,0.00068273424,0.00013430012,0.000005139421,0.00001607378,0.00002276348,1.2511017e-9,0.21615167,0.7814228,0.00017768318],"about_ca_topic_score_codex":0.00095481024,"about_ca_topic_score_gemma":0.0046000117,"teacher_disagreement_score":0.5521436,"about_ca_system_score_codex":0.0000469357,"about_ca_system_score_gemma":0.0006711531,"threshold_uncertainty_score":0.99998534},"labels":[],"label_agreement":null},{"id":"W2354815035","doi":"10.1117/12.2230236","title":"Toward unified query processing for ISR information needs and collection management","year":2016,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Data Quality and Management","field":"Decision Sciences","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":"Defence Research and Development Canada","funders":"","keywords":"Computer science; Data collection; Process (computing); Information management; Data science; Information integration; Information retrieval; Database","score_opus":0.040037764433041946,"score_gpt":0.28940851661955636,"score_spread":0.24937075218651442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2354815035","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":[0.9789837,0.00004130417,0.0056957235,0.00984247,0.0003288485,0.0009819588,0.00008406463,0.00007384996,0.0039680786],"genre_scores_gemma":[0.80703527,0.00036585878,0.18817277,0.00064687256,0.00044728513,0.0007104261,0.000023757855,0.00005984987,0.0025378803],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99729455,3.1078145e-8,0.0009737026,0.00029845943,0.0011120808,0.00032119395],"domain_scores_gemma":[0.99685127,0.00039940124,0.0005856113,0.00007343836,0.0019874435,0.000102851925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024498035,0.00023415331,0.0003374831,0.00032373928,0.00014718024,0.00041298647,0.00096553593,0.00012700069,0.0000105337285],"category_scores_gemma":[0.0017245194,0.00015424922,0.00032709143,0.00062805065,0.00019943135,0.002277371,0.00031281795,0.00010233466,0.0000031161962],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023175387,0.00007129115,0.00015777096,0.000743507,0.00024955848,2.4903182e-8,0.00078842713,0.000019100475,0.027457356,0.9192134,0.026938219,0.024129586],"study_design_scores_gemma":[0.011911474,0.0018669919,0.0072498806,0.0022582759,0.00089651044,0.00004029975,0.0740266,0.06433432,0.09928955,0.13723037,0.59881395,0.0020817833],"about_ca_topic_score_codex":0.0000061114956,"about_ca_topic_score_gemma":2.3679206e-7,"teacher_disagreement_score":0.781983,"about_ca_system_score_codex":0.00014180575,"about_ca_system_score_gemma":0.000025972598,"threshold_uncertainty_score":0.6290101},"labels":[],"label_agreement":null},{"id":"W2357632358","doi":"","title":"Data Backup and the Technical Plan for Recovery after Disaster for HIS in Our Hospital","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"CAE (Canada)","funders":"","keywords":"Backup; Data loss; Guard (computer science); Disaster recovery; Plan (archaeology); Computer security; Data security; Computer science; Measure (data warehouse); Data recovery; Medical emergency; Engineering; Database; Medicine; Encryption; Operating system; Geography","score_opus":0.24951215798059395,"score_gpt":0.4114673316661513,"score_spread":0.16195517368555734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2357632358","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":[0.26085502,0.00039313713,0.55822915,0.14967605,0.0017698873,0.0076434566,0.00866043,0.00010662342,0.012666245],"genre_scores_gemma":[0.9427836,0.00008808564,0.032137442,0.005764379,0.00019045343,0.00045033026,0.0002504971,0.000013884446,0.018321317],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99870497,0.000058859863,0.000352284,0.00041863768,0.0003032476,0.00016198673],"domain_scores_gemma":[0.9977464,0.0011799614,0.000056188986,0.0009541338,0.000028223632,0.000035099903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031671722,0.00007431614,0.00017319253,0.000059285016,0.00007213013,0.00014160393,0.0009037785,0.000037706603,0.000055915003],"category_scores_gemma":[0.0016181066,0.000037710466,0.00004697806,0.00010256578,0.00010054232,0.00059103523,0.00078261213,0.000044595294,0.00003731075],"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":[0.0008679595,0.00008960594,0.0011984955,0.00000830023,0.00001095419,0.0000033527697,0.0002940566,0.0000010362718,0.0000013382833,0.007403452,0.97040343,0.019718003],"study_design_scores_gemma":[0.0028980935,0.0002228032,0.014988747,0.000010935364,0.000016039006,0.000005666252,0.003255906,0.0012040979,0.000004291409,0.04153694,0.9356671,0.000189374],"about_ca_topic_score_codex":0.000030238687,"about_ca_topic_score_gemma":0.00083431037,"teacher_disagreement_score":0.6819286,"about_ca_system_score_codex":0.00000875696,"about_ca_system_score_gemma":0.000013800511,"threshold_uncertainty_score":0.19371417},"labels":[],"label_agreement":null},{"id":"W2361231636","doi":"","title":"The Design Of A Rule-based Interactive Data Cleaning Framework","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Interactivity; Scalability; Extension (predicate logic); Data flow diagram; Currency; Human–computer interaction; Data mining; Database; Programming language; Multimedia","score_opus":0.20660549661684052,"score_gpt":0.44074881239422037,"score_spread":0.23414331577737985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2361231636","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":[0.00011594851,0.000049615017,0.9941082,0.004561953,0.000020852238,0.0005592321,0.00006325575,0.00003403879,0.0004869318],"genre_scores_gemma":[0.09883847,0.000012492752,0.8978422,0.0028893317,0.00010893896,0.00007349375,0.00007443986,0.000006738196,0.0001538445],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983635,0.00018841062,0.000477416,0.0004354881,0.00038131975,0.00015387933],"domain_scores_gemma":[0.994644,0.0030057419,0.0002571798,0.0019046261,0.000145258,0.000043189902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002218801,0.000089341396,0.00013915426,0.00008726281,0.00028255454,0.00032350756,0.003168209,0.000034528806,0.000024731893],"category_scores_gemma":[0.000061350795,0.000059570222,0.000042767555,0.00055026775,0.000086481385,0.00024337506,0.00046910887,0.00013130961,0.00021334905],"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":[0.000020597667,0.00012971647,0.000013143771,0.0000017155307,0.000015329402,2.9554795e-7,0.00023297867,0.00081507716,0.00040546147,0.033325166,0.044537712,0.9205028],"study_design_scores_gemma":[0.00013420223,0.00003301652,0.0010650518,0.000018701929,0.0000133195545,9.132635e-7,0.00025330755,0.01905565,0.0008377895,0.122305736,0.85618484,0.00009746585],"about_ca_topic_score_codex":0.000007450057,"about_ca_topic_score_gemma":0.0000027891165,"teacher_disagreement_score":0.9204053,"about_ca_system_score_codex":0.00001668758,"about_ca_system_score_gemma":0.0000423652,"threshold_uncertainty_score":0.58873737},"labels":[],"label_agreement":null},{"id":"W2394807234","doi":"","title":"The UC3M team at the Knowledge Base Population task.","year":2009,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Spurious relationship; Computer science; Task (project management); Knowledge base; Entity linking; Baseline (sea); Population; Similarity (geometry); Information retrieval; Base (topology); Open source; Information extraction; Data mining; World Wide Web; Artificial intelligence; Machine learning; Software; Mathematics; Engineering; Programming language","score_opus":0.042355241823967514,"score_gpt":0.36662700195315157,"score_spread":0.3242717601291841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2394807234","genre_codex":"other","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":[0.20668292,0.019101636,0.23253441,0.042499933,0.0005396328,0.0046551665,0.00040317274,0.00029167155,0.49329144],"genre_scores_gemma":[0.9869356,0.00011777612,0.000036564354,0.0002257372,0.000054944452,0.000063547144,0.000027469552,0.000002499769,0.012535872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987873,0.00031347346,0.00032830788,0.00019121368,0.00026355716,0.00011618319],"domain_scores_gemma":[0.9968434,0.0020368707,0.00016387053,0.0008185807,0.00010192185,0.000035358837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056562666,0.00007327533,0.00010334685,0.000042612122,0.00088689727,0.00014050423,0.0005862519,0.00002470012,0.000055602857],"category_scores_gemma":[0.00046268743,0.000035394994,0.000038134807,0.0003601961,0.0003815438,0.00016670855,0.0001584328,0.000052536496,0.00010045616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029122331,0.000025995372,0.00004272175,0.0000017391159,0.0000046777873,1.7202492e-8,0.00036649226,0.0000067093,0.00005863277,0.8150169,0.0063284673,0.1781185],"study_design_scores_gemma":[0.00004700952,0.000014151505,0.0033988925,0.0000010839275,0.000012965033,6.780276e-7,0.001930322,0.000015894057,0.00027858894,0.66794986,0.3263147,0.000035905763],"about_ca_topic_score_codex":0.00001534133,"about_ca_topic_score_gemma":0.000086764194,"teacher_disagreement_score":0.7802527,"about_ca_system_score_codex":0.0000102089325,"about_ca_system_score_gemma":0.000015321055,"threshold_uncertainty_score":0.6821386},"labels":[],"label_agreement":null},{"id":"W2395059241","doi":"","title":"REACTION at the Entity Linking task in KBP 2011.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Task (project management); Computer science; Systems engineering; Engineering","score_opus":0.08199842474337567,"score_gpt":0.34680038930626156,"score_spread":0.2648019645628859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395059241","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":[0.7344839,0.0012451025,0.13554813,0.0013565061,0.00021466508,0.0011200999,0.000092083406,0.00006572765,0.12587382],"genre_scores_gemma":[0.9965177,0.000114581584,0.000099114215,0.00008602108,0.000022225742,0.000076896344,0.000013556259,0.000002462129,0.0030674252],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99903476,0.00020408517,0.00028661505,0.00018313063,0.0002110273,0.0000803723],"domain_scores_gemma":[0.99865776,0.0005684892,0.00015255089,0.00054101093,0.000059724687,0.000020446842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046642744,0.00005383797,0.000098695935,0.00008293814,0.00018511072,0.0000352815,0.00038047982,0.000028080565,0.00027496924],"category_scores_gemma":[0.00012634808,0.00003421093,0.00002440235,0.00021525944,0.00034230345,0.00024915102,0.00022238113,0.000059069138,0.00016733451],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004197834,0.000039500428,0.0009870603,0.0000058477754,0.000005111717,9.901517e-8,0.0018017322,8.3195687e-7,0.00033180945,0.94706565,0.0004787612,0.049241588],"study_design_scores_gemma":[0.00006292331,0.000009325458,0.014193752,0.000002181502,0.0000097052025,8.4491063e-7,0.0035125406,0.0000031357856,0.00212771,0.8955247,0.08450978,0.000043389577],"about_ca_topic_score_codex":0.00017791046,"about_ca_topic_score_gemma":0.00032385203,"teacher_disagreement_score":0.26203385,"about_ca_system_score_codex":0.000009184066,"about_ca_system_score_gemma":0.0000102733975,"threshold_uncertainty_score":0.30107203},"labels":[],"label_agreement":null},{"id":"W2395690085","doi":"10.5281/zenodo.3781776","title":"Data Rescue in Canada, a Case Study","year":2010,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Computer security; Business","score_opus":0.2674311170619187,"score_gpt":0.38603318131185566,"score_spread":0.11860206424993697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395690085","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":[0.941717,0.0000116212605,0.0009212555,0.0019893819,0.00039616585,0.0008659678,0.0017897211,0.0001894861,0.052119363],"genre_scores_gemma":[0.9979481,0.0000032130092,0.00013623625,0.0002086543,0.000059893424,2.3516067e-8,0.0006096964,0.0002610241,0.00077316246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966969,0.0007396592,0.00046886003,0.0006913571,0.0011015414,0.00030167666],"domain_scores_gemma":[0.9968912,0.00012608274,0.000091121634,0.0023779678,0.00033957002,0.00017408346],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006812656,0.00009857515,0.00015069098,0.00028569408,0.0011008385,0.0012675815,0.004194731,0.000025298508,0.01400578],"category_scores_gemma":[0.005931391,0.00008896618,0.000014510297,0.0010168542,0.00007824955,0.00059541245,0.00621945,0.0003677666,0.00385018],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003239802,0.0003285103,0.00015893462,0.0000081551225,0.000019379682,0.0022006442,0.0016662178,0.000038662718,0.0001620041,0.0020389594,0.72127664,0.27206945],"study_design_scores_gemma":[0.00039981017,0.00006345337,0.0030597956,0.0000029403861,0.0000050570984,0.00038940881,0.014842166,0.0011014948,0.0000073442297,0.00020003144,0.9798159,0.00011258039],"about_ca_topic_score_codex":0.4246643,"about_ca_topic_score_gemma":0.6657391,"teacher_disagreement_score":0.2719569,"about_ca_system_score_codex":0.00012017499,"about_ca_system_score_gemma":0.00003097992,"threshold_uncertainty_score":0.9997692},"labels":[],"label_agreement":null},{"id":"W2395959986","doi":"","title":"BUPTTeam Participation at TAC 2012 Knowledge Base Population","year":2012,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ranking (information retrieval); Node (physics); Computer science; Task (project management); Selection (genetic algorithm); Cluster analysis; Base (topology); Knowledge base; Population; Cluster (spacecraft); Data mining; Information retrieval; Artificial intelligence; Mathematics; Computer network; Engineering","score_opus":0.08896754430988418,"score_gpt":0.4073813255499505,"score_spread":0.3184137812400663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395959986","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":[0.67983127,0.0033985346,0.26553845,0.00065917784,0.00028465685,0.00097304565,0.00014786073,0.00010418888,0.049062807],"genre_scores_gemma":[0.9938439,0.000031954274,0.00020731759,0.000061829436,0.00010849202,0.0001487029,0.000094376555,0.000004905659,0.005498483],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99871063,0.00030129054,0.0003898635,0.00017643959,0.00025007717,0.00017166772],"domain_scores_gemma":[0.99819326,0.0009027174,0.0001956386,0.0005047985,0.00010593776,0.00009765309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049024406,0.00008120791,0.00014555879,0.00011145218,0.00023422719,0.000043697375,0.00022141148,0.000038631446,0.00042408344],"category_scores_gemma":[0.0003860369,0.00006391361,0.00003296199,0.00033659616,0.00017524377,0.00076751196,0.00018480475,0.000036831854,0.0002943488],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032280754,0.000115624534,0.0040552528,0.000013580935,0.0000072885196,1.2328647e-8,0.00088760833,0.0000061911696,0.00015394873,0.93434334,0.0024208012,0.057964087],"study_design_scores_gemma":[0.0001387127,0.000018555329,0.047152743,0.000003316712,0.000044002947,8.4142266e-7,0.0017290821,0.00002858638,0.0028415918,0.71921647,0.22870736,0.00011876577],"about_ca_topic_score_codex":0.000017245166,"about_ca_topic_score_gemma":0.00003391442,"teacher_disagreement_score":0.31401268,"about_ca_system_score_codex":0.000017511944,"about_ca_system_score_gemma":0.000008511249,"threshold_uncertainty_score":0.46434164},"labels":[],"label_agreement":null},{"id":"W2398314932","doi":"","title":"The MSR.KM System for Entity Linking at TAC 2013.","year":2013,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.04564384244977663,"score_gpt":0.34152763407518755,"score_spread":0.2958837916254109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398314932","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":[0.0913241,0.0027394143,0.87116015,0.005207945,0.00040722714,0.0037880235,0.00032655252,0.0001417662,0.024904845],"genre_scores_gemma":[0.99083245,0.00009908871,0.00032981668,0.00006600665,0.000072359515,0.00082652865,0.000028434277,0.0000048329716,0.007740497],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988846,0.0001567062,0.00036833857,0.00020600329,0.00025724474,0.00012708212],"domain_scores_gemma":[0.99624175,0.0026155289,0.00021475583,0.00065875036,0.00022898549,0.0000402403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044765873,0.000071147646,0.00013587107,0.00004525844,0.0007575312,0.00025026064,0.00060251035,0.00003118959,0.00005262729],"category_scores_gemma":[0.00023673888,0.00004231834,0.000047574555,0.00018466277,0.00035897276,0.00026082128,0.00026459445,0.000034946894,0.000168515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017597242,0.000011532138,0.00005377555,0.000033501285,0.000012502259,1.4889094e-8,0.00020226685,0.0000036437964,0.0001079749,0.94895065,0.0057541505,0.044852387],"study_design_scores_gemma":[0.00006723013,0.000010123181,0.00025553297,0.000003836853,0.000013030692,6.3120314e-7,0.004523472,0.000038021946,0.0010445879,0.6326414,0.36135802,0.000044153374],"about_ca_topic_score_codex":0.000049045455,"about_ca_topic_score_gemma":0.00004561056,"teacher_disagreement_score":0.89950836,"about_ca_system_score_codex":0.000012250446,"about_ca_system_score_gemma":0.0000126201785,"threshold_uncertainty_score":0.58263946},"labels":[],"label_agreement":null},{"id":"W2398442511","doi":"","title":"Machine Learning for Information Retrieval: TREC 2009 Web, Relevance Feedback and Legal Tracks.","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":27,"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":"Relevance feedback; Relevance (law); Computer science; Information retrieval; World Wide Web; Artificial intelligence; Image retrieval","score_opus":0.06583608472360887,"score_gpt":0.36169415369887564,"score_spread":0.2958580689752668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398442511","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":[0.10779464,0.0013480384,0.4328487,0.06740305,0.001234219,0.002771115,0.0003973062,0.00076711364,0.38543582],"genre_scores_gemma":[0.92913157,0.00036699796,0.008621317,0.0056640795,0.000084295716,0.000005135883,0.00012238568,0.0000064376104,0.055997804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830765,0.00007626349,0.00054662314,0.00023900004,0.00062881334,0.00020163962],"domain_scores_gemma":[0.99878246,0.00052576873,0.0001881278,0.0002826978,0.00014084835,0.00008009064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031736717,0.00010528127,0.00018149843,0.00017320663,0.00018030228,0.0006147524,0.00030925227,0.000049937367,0.00018356204],"category_scores_gemma":[0.003520231,0.000077163255,0.00005311215,0.00039881573,0.00003504058,0.0026798395,0.000059958806,0.00011402785,0.00022482128],"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":[0.00024212472,0.000037174053,0.00008000543,0.0000108947,0.000006842722,9.87466e-7,0.0002850381,0.00021576846,0.00008644323,0.056730412,0.085071884,0.85723245],"study_design_scores_gemma":[0.00070543995,0.00022617048,0.0026133521,0.0000064723363,0.0000073394226,0.0000031647364,0.00048908446,0.02156846,0.00015238908,0.008920125,0.9651879,0.00012006958],"about_ca_topic_score_codex":0.000030167352,"about_ca_topic_score_gemma":0.000056403707,"teacher_disagreement_score":0.88011605,"about_ca_system_score_codex":0.000018228024,"about_ca_system_score_gemma":0.000023140934,"threshold_uncertainty_score":0.5928072},"labels":[],"label_agreement":null},{"id":"W2399833365","doi":"","title":"Open Data in Vancouver: The Inspiration and the Vision.","year":2011,"lang":"en","type":"article","venue":"IASSIST Conference","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Computer graphics (images); Computer vision","score_opus":0.603460426186831,"score_gpt":0.4682804701029587,"score_spread":0.13517995608387234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2399833365","genre_codex":"other","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":[0.049018078,0.0004449695,0.07548285,0.04728276,0.0023122402,0.003452975,0.00035225006,0.00006885009,0.821585],"genre_scores_gemma":[0.99577206,0.000041575822,0.0005200066,0.0018549389,0.000014653212,0.00002404081,0.000009423962,0.0000023439973,0.001760953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980541,0.00052547164,0.0003815112,0.00042025326,0.00050257234,0.0001161025],"domain_scores_gemma":[0.996934,0.0007838681,0.00016382562,0.002005373,0.00008131842,0.000031624793],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008936161,0.0000737896,0.00015044866,0.000045089426,0.00019678038,0.0009941686,0.005585962,0.000024711993,0.00049398694],"category_scores_gemma":[0.0019120818,0.000032030235,0.0000130118115,0.00028469734,0.0003896581,0.0012688313,0.005540699,0.00010494761,0.00011225829],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015834808,0.000081270824,0.0028534555,0.0000033321833,0.000011419437,0.0000045260945,0.004233819,0.0000010298398,0.000003871146,0.48397094,0.09841421,0.41026378],"study_design_scores_gemma":[0.0013763377,0.00004496444,0.19725382,0.000028024122,0.000016373644,0.000001148406,0.0069712787,0.0056231907,0.000016536242,0.21171728,0.5768039,0.00014710765],"about_ca_topic_score_codex":0.0031348728,"about_ca_topic_score_gemma":0.047113586,"teacher_disagreement_score":0.946754,"about_ca_system_score_codex":0.000007240135,"about_ca_system_score_gemma":0.00006624896,"threshold_uncertainty_score":0.9997943},"labels":[{"model":"gemma","categories":["open_science"],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"commentary","about_ca_system":false,"about_ca_topic":true,"confidence":"high"}],"label_agreement":"split"},{"id":"W2400338427","doi":"","title":"Automatic Acquisition of isA Relationships from Web Tables.","year":2012,"lang":"en","type":"article","venue":"Software Engineering and Knowledge Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; World Wide Web; Information retrieval","score_opus":0.06541475244909939,"score_gpt":0.3047322870531124,"score_spread":0.239317534604013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400338427","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":[0.64813375,0.005148388,0.34420544,0.000039549966,0.0014696405,0.00017133832,0.00012999156,0.0004638368,0.00023804602],"genre_scores_gemma":[0.96969146,0.000028846787,0.029760582,0.000007275228,0.0002348982,0.000017229326,0.0000422481,0.000026312006,0.00019115387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840254,0.00005994564,0.0005604888,0.00026004718,0.0003802702,0.0003367223],"domain_scores_gemma":[0.99725556,0.0019228054,0.0000976891,0.00045363393,0.00008062846,0.00018969596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020851386,0.00019893916,0.00032280572,0.0003694343,0.00007735646,0.000084324085,0.00028879975,0.000102802456,0.00018080659],"category_scores_gemma":[0.0036424883,0.00018655923,0.00007425106,0.00058169494,0.000023754954,0.00064000196,0.00020590759,0.00021028795,0.00012796074],"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":[0.000053374228,0.0013585166,0.27330664,0.0032279023,0.0012035769,0.000021228818,0.037703555,0.17800988,0.018481933,0.13276869,0.043535624,0.31032908],"study_design_scores_gemma":[0.00086417346,0.000050486695,0.18276821,0.00056806323,0.00013125518,0.000010710829,0.0008437035,0.6724729,0.0017456199,0.00080128637,0.1388276,0.00091599114],"about_ca_topic_score_codex":0.000016147073,"about_ca_topic_score_gemma":0.000004757256,"teacher_disagreement_score":0.494463,"about_ca_system_score_codex":0.00004514296,"about_ca_system_score_gemma":0.000021563237,"threshold_uncertainty_score":0.7607665},"labels":[],"label_agreement":null},{"id":"W2400809607","doi":"","title":"ECNU: Brief System Description of Submission to Knowledge Base Population at TAC 2011.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Entity linking; Knowledge base; Computer science; Base (topology); Population; Information retrieval; Natural language processing; World Wide Web; Mathematics; Medicine","score_opus":0.10956786629703463,"score_gpt":0.3443977628546998,"score_spread":0.23482989655766517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400809607","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":[0.53514975,0.000599434,0.41783047,0.00016438177,0.00017915989,0.0011864555,0.0001839868,0.00008650272,0.044619855],"genre_scores_gemma":[0.99562794,0.000014945812,0.0007388777,0.00002731105,0.000025523419,0.00007803107,0.00004270394,0.0000055012856,0.0034391638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998552,0.00026731126,0.00053296273,0.00026945624,0.00026975406,0.000108491935],"domain_scores_gemma":[0.998474,0.00030641365,0.00026750797,0.00063238194,0.00022940054,0.00009027599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003754489,0.00008992492,0.00020921498,0.00019789717,0.0001669681,0.000027915768,0.00035097,0.000045601668,0.00023202297],"category_scores_gemma":[0.00017994062,0.00007018833,0.00004121524,0.0003141246,0.00014367684,0.00029966352,0.00023382112,0.000031089752,0.00013005454],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015146674,0.00007914338,0.00085309386,0.00007690127,0.000007906864,8.721995e-8,0.0015249556,0.000003790467,0.0013807907,0.972695,0.0016475485,0.021579344],"study_design_scores_gemma":[0.00031886125,0.0001316483,0.042827237,0.00004832471,0.00007847138,0.0000037136986,0.011295926,0.000070762755,0.035887774,0.8607071,0.048398703,0.00023144753],"about_ca_topic_score_codex":0.00019247674,"about_ca_topic_score_gemma":0.000065473236,"teacher_disagreement_score":0.4604782,"about_ca_system_score_codex":0.000025676489,"about_ca_system_score_gemma":0.00001536987,"threshold_uncertainty_score":0.28621972},"labels":[],"label_agreement":null},{"id":"W2401187431","doi":"10.3233/978-1-61499-203-5-189","title":"Clinician Variations in Data Trust and Use","year":2013,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 Victoria","funders":"","keywords":"Computer science; Data science","score_opus":0.5059977657776822,"score_gpt":0.5418432695702594,"score_spread":0.03584550379257723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401187431","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":[0.7979463,0.00651366,0.007986,0.17916422,0.0013952774,0.0029298828,0.00031589987,0.00021846057,0.0035303414],"genre_scores_gemma":[0.93691534,0.019758906,0.03395671,0.008819558,0.000018826246,0.00008783205,0.0000345981,0.0000055703927,0.00040265764],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99808115,0.00007812672,0.0012743322,0.00016379627,0.00017545045,0.00022715195],"domain_scores_gemma":[0.99791837,0.00094661175,0.00028127542,0.00075451285,0.000065156986,0.000034065375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042335615,0.00007752208,0.00030025854,0.0007543644,0.00017201954,0.00007473662,0.0004998957,0.00008827937,0.00001048135],"category_scores_gemma":[0.007132887,0.00005854155,0.0000052284627,0.00090995507,0.0004351386,0.0014067844,0.0016720693,0.0002197552,0.00003679017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006280724,0.00006997741,0.21907699,0.00024378386,0.000028151073,0.0000015534255,0.010949841,0.0000087352,4.176641e-8,0.28635868,0.05141447,0.4318415],"study_design_scores_gemma":[0.000848911,0.00016039544,0.20251279,0.00015021901,0.0000052689547,0.000006505756,0.13752832,0.020996924,3.3562458e-7,0.32310346,0.31449267,0.00019421702],"about_ca_topic_score_codex":0.0001706463,"about_ca_topic_score_gemma":0.0013114008,"teacher_disagreement_score":0.4316473,"about_ca_system_score_codex":0.000024950712,"about_ca_system_score_gemma":0.000033782366,"threshold_uncertainty_score":0.85392475},"labels":[],"label_agreement":null},{"id":"W2401451337","doi":"10.5281/zenodo.3781772","title":"Barriers to Data Sharing: New Evidence from a US Survey","year":2010,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Canadian Institute for Public Safety Research and Treatment","funders":"","keywords":"Computer science; Business; Data science","score_opus":0.44756446938417477,"score_gpt":0.42100436047184747,"score_spread":0.026560108912327296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401451337","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":[0.64933443,0.00016231416,0.17214678,0.027521461,0.002962768,0.002734151,0.017977316,0.002174955,0.12498585],"genre_scores_gemma":[0.9755064,0.000050458857,0.00435155,0.0025049187,0.0004984025,4.0934907e-8,0.0071811555,0.0010316256,0.008875416],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99596405,0.0006619002,0.00045867218,0.0012183496,0.0013353422,0.00036166923],"domain_scores_gemma":[0.9941738,0.00038502045,0.00014015564,0.0038633381,0.0005846915,0.00085295946],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.010973905,0.00013420994,0.00018063556,0.0002781002,0.0014656571,0.004212377,0.01127824,0.000055630066,0.08910342],"category_scores_gemma":[0.07424859,0.00012395522,0.00002961643,0.0012664946,0.00012077329,0.0012807625,0.014758706,0.0003260272,0.04780766],"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":[0.00006351784,0.000021678685,0.00027218356,0.000002959177,0.000017407985,0.0000061996884,0.0007516759,0.000015793648,0.0016042542,0.0009195305,0.89682144,0.09950335],"study_design_scores_gemma":[0.0001737912,0.00006217283,0.026263524,0.00001597066,0.0000072510293,0.0000046666173,0.00025693374,0.000742393,0.0001106024,0.0012322001,0.9709734,0.00015709783],"about_ca_topic_score_codex":0.0018493185,"about_ca_topic_score_gemma":0.00019878661,"teacher_disagreement_score":0.32617202,"about_ca_system_score_codex":0.000041435098,"about_ca_system_score_gemma":0.000016899363,"threshold_uncertainty_score":0.9998343},"labels":[],"label_agreement":null},{"id":"W2402612754","doi":"10.22215/etd/2013-07045","title":"Multidimensional contexts for data quality assessment","year":2013,"lang":"en","type":"dissertation","venue":"","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":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Computer science","score_opus":0.5229680496476575,"score_gpt":0.5862770038323718,"score_spread":0.06330895418471427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402612754","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042201024,0.0007859133,0.42153135,0.009367797,0.02315605,0.013615461,0.016484415,0.0005283545,0.47232965],"genre_scores_gemma":[0.013805021,0.0000368128,0.08400703,0.002050883,0.00025188233,0.00034846232,0.08962425,0.00004045026,0.8098352],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938535,0.00038131338,0.0015286362,0.0014497906,0.0024760673,0.0003107047],"domain_scores_gemma":[0.9911521,0.003530955,0.00081456685,0.003500269,0.0008572411,0.00014485948],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0109261805,0.00029083854,0.00065115624,0.00021281184,0.00022518745,0.0005610413,0.0029679907,0.00021753518,0.0060504703],"category_scores_gemma":[0.0044324235,0.00020395842,0.0001680505,0.0001909978,0.0000412741,0.00089438836,0.00068212097,0.0001915497,0.0016661],"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":[0.000043992663,0.00013628558,0.000033982404,0.000052944117,0.000067410285,5.4334157e-7,0.000076727294,0.0000013766357,0.00008436909,0.16662677,0.70280355,0.13007204],"study_design_scores_gemma":[0.00071128685,0.000050494786,0.017975856,0.00003588541,0.000056566645,1.8589847e-7,0.004259265,0.0036323697,0.00008987023,0.036452796,0.93630123,0.00043417615],"about_ca_topic_score_codex":0.0008834376,"about_ca_topic_score_gemma":0.0029671306,"teacher_disagreement_score":0.33752432,"about_ca_system_score_codex":0.00004647195,"about_ca_system_score_gemma":0.000271419,"threshold_uncertainty_score":0.99911124},"labels":[],"label_agreement":null},{"id":"W2402684910","doi":"","title":"BIT's Slot-Filling Method for TAC-KBP 2013.","year":2013,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Bit (key); Computer science; Algorithm; Arithmetic; Mathematics; Computer network","score_opus":0.06833038482035207,"score_gpt":0.3975507777021472,"score_spread":0.3292203928817951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2402684910","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":[0.0029888751,0.00028742073,0.98815066,0.001794874,0.00004411018,0.0007454114,0.000070697184,0.000030554995,0.005887411],"genre_scores_gemma":[0.8814233,0.0002317807,0.098584145,0.0008323152,0.00020295708,0.0022961616,0.00008941544,0.000020711142,0.016319204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99876505,0.00017492878,0.00040666916,0.0002791808,0.00023768125,0.00013647709],"domain_scores_gemma":[0.9961582,0.0027323244,0.00019188695,0.0005979486,0.0002613087,0.000058325502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004595829,0.000089325324,0.00019947023,0.00012020106,0.00022417039,0.00015947473,0.0005122701,0.00003949552,0.00031310032],"category_scores_gemma":[0.00045070256,0.00006551108,0.000053208638,0.00030014163,0.00022116586,0.00039534914,0.0001481626,0.000042497304,0.00013414415],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013357794,0.000023704262,0.000010292493,0.000016045728,0.000011996665,1.2155957e-8,0.00027279352,0.000017363982,0.0004165599,0.8144733,0.006799568,0.17794505],"study_design_scores_gemma":[0.000091629205,0.00002251362,0.00011076682,0.0000019141023,0.000016111651,4.5221233e-7,0.0032382773,0.00021547575,0.002628229,0.746482,0.24712692,0.00006569414],"about_ca_topic_score_codex":0.0000877931,"about_ca_topic_score_gemma":0.000009620376,"teacher_disagreement_score":0.8895665,"about_ca_system_score_codex":0.000003927038,"about_ca_system_score_gemma":0.000016310812,"threshold_uncertainty_score":0.3428229},"labels":[],"label_agreement":null},{"id":"W2403315168","doi":"","title":"On Axiomatization and Inference Complexity over a Hierarchy of Functional Dependencies.","year":2015,"lang":"en","type":"article","venue":"AMW","topic":"Data Quality and Management","field":"Decision Sciences","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 Waterloo; Ontario Tech University","funders":"","keywords":"Functional dependency; Inference; Hierarchy; Tuple; Mathematics; Dependency theory (database theory); Rule of inference; Theoretical computer science; Metric (unit); Antecedent (behavioral psychology); Focus (optics); Extension (predicate logic); Computer science; Algorithm; Discrete mathematics; Data mining; Artificial intelligence; Relational database; Programming language","score_opus":0.5096816871169793,"score_gpt":0.44880443507436196,"score_spread":0.06087725204261729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403315168","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":[0.80716914,0.000038124275,0.16526377,0.0013566188,0.00034238843,0.0001745112,0.00007653163,0.000028787204,0.02555015],"genre_scores_gemma":[0.9981209,0.0000026695507,0.00052336376,0.00044229953,0.000013641789,0.0000023296466,0.000017241506,0.0000015308409,0.000876006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986101,0.00009396756,0.00021504742,0.00016607625,0.000847779,0.00006704942],"domain_scores_gemma":[0.99901736,0.00044645712,0.00009830738,0.00024121914,0.0001367603,0.000059894384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013863886,0.00004551036,0.00009549293,0.00010478996,0.00003743698,0.00006443902,0.00016905472,0.00001983601,0.0003362256],"category_scores_gemma":[0.0020594683,0.00003399949,0.000015342759,0.00023060176,0.00008193972,0.00027293566,0.00015917812,0.000033244927,0.00011333529],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086351385,0.00009504585,0.0065367376,0.0000099313875,0.000012162672,0.0000014083915,0.00071537396,0.00024812977,0.00007464411,0.9065259,0.06323569,0.022458635],"study_design_scores_gemma":[0.00047353326,0.00014458231,0.15351021,0.000013405038,0.000004960712,0.0000010536951,0.00045381134,0.004484445,0.000107969194,0.8271801,0.01354484,0.00008111555],"about_ca_topic_score_codex":0.0001809764,"about_ca_topic_score_gemma":0.00022407985,"teacher_disagreement_score":0.19095181,"about_ca_system_score_codex":0.00002599013,"about_ca_system_score_gemma":0.000034181357,"threshold_uncertainty_score":0.36814347},"labels":[],"label_agreement":null},{"id":"W2404439713","doi":"","title":"Information Quality designed by ICT.","year":2013,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information and Communications Technology; Quality (philosophy); Business; Computer science; World Wide Web; Physics","score_opus":0.06755227543677714,"score_gpt":0.3359734485110747,"score_spread":0.2684211730742976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404439713","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":[0.21270266,0.000045223715,0.671156,0.0010626639,0.0007334199,0.0013683169,0.0002509741,0.00035482118,0.112325914],"genre_scores_gemma":[0.9932328,0.000015076703,0.0022889306,0.0028396791,0.0000331926,0.00016828417,0.00067549816,0.0000056372633,0.0007408962],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99566305,0.0003339566,0.001989712,0.000138483,0.0015039289,0.00037085207],"domain_scores_gemma":[0.9968282,0.00045058577,0.0009340746,0.0007395465,0.00088834,0.00015925987],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.0049560335,0.00020037344,0.0002934404,0.00043140544,0.00038598524,0.0026897562,0.0008380633,0.00012586993,0.0012955196],"category_scores_gemma":[0.0043765903,0.00016225924,0.00009865592,0.0008453294,0.00016236692,0.032651164,0.00023894916,0.00011869369,0.013999632],"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":[0.000027445138,0.000030037885,0.00086565845,0.00010022399,0.000025805373,1.2238542e-7,0.008060261,0.00010637899,0.000144293,0.026522383,0.35974002,0.6043774],"study_design_scores_gemma":[0.0011077777,0.00015918138,0.041576806,0.000058128746,0.00001833165,0.000007983812,0.027980804,0.0043102675,0.0014034088,0.11468075,0.8079779,0.00071864453],"about_ca_topic_score_codex":0.00080380955,"about_ca_topic_score_gemma":0.000015586487,"teacher_disagreement_score":0.78053015,"about_ca_system_score_codex":0.00019693548,"about_ca_system_score_gemma":0.000060741822,"threshold_uncertainty_score":0.99961746},"labels":[],"label_agreement":null},{"id":"W2404580422","doi":"","title":"Benchmarks for Enterprise Linking: Thomson Reuters R&D at TAC 2013.","year":2013,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Task (project management); Computer science; Domain (mathematical analysis); Named-entity recognition; Entity linking; Information retrieval; Artificial intelligence; Mathematics; Knowledge base; Management","score_opus":0.03887689956804048,"score_gpt":0.3441753447018895,"score_spread":0.305298445133849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404580422","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":[0.10426566,0.0011323891,0.8600539,0.005829807,0.00021210038,0.0028342088,0.0002668769,0.0000713235,0.025333717],"genre_scores_gemma":[0.9876438,0.00017485587,0.0021109069,0.00033798683,0.00007384282,0.0008718205,0.00016009045,0.00000759518,0.008619124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987828,0.00012413049,0.00040230065,0.00029472832,0.00025269872,0.00014331768],"domain_scores_gemma":[0.99729955,0.0015736998,0.00021378222,0.0006660011,0.00018218927,0.00006479405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025732014,0.000097031116,0.00018299873,0.000105215026,0.00024939442,0.00013784783,0.0005501721,0.000046571007,0.0004941479],"category_scores_gemma":[0.00023005914,0.00007242687,0.000058931844,0.00019948948,0.0003264344,0.00036577997,0.00028144,0.000042781885,0.00009700216],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048459555,0.0000421499,0.00019941432,0.000026204805,0.000015732172,3.334297e-8,0.00070935866,0.0000054219954,0.00026514087,0.9002951,0.028957414,0.06943559],"study_design_scores_gemma":[0.000108271364,0.000025411626,0.00036808912,0.0000042045854,0.000014115307,4.8811364e-7,0.0018922648,0.000032669388,0.0012571092,0.6684585,0.3277718,0.00006703791],"about_ca_topic_score_codex":0.00003048096,"about_ca_topic_score_gemma":0.000014623552,"teacher_disagreement_score":0.8833781,"about_ca_system_score_codex":0.00000989335,"about_ca_system_score_gemma":0.000012495633,"threshold_uncertainty_score":0.5410573},"labels":[],"label_agreement":null},{"id":"W2404833249","doi":"10.5281/zenodo.3781385","title":"Bringing them in: what 5 years of data can tell us about growing a data service","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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; Service (business); Data science; Business; Marketing","score_opus":0.3892335848361716,"score_gpt":0.3863174045296732,"score_spread":0.0029161803064983727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2404833249","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":[0.8171964,0.0014052746,0.012507912,0.008346786,0.0013467422,0.0018740793,0.0062874933,0.0009841244,0.15005116],"genre_scores_gemma":[0.99231,0.00028093104,0.0009497389,0.0008549612,0.00014611085,1.5746288e-8,0.004621264,0.0004240612,0.0004129335],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99712,0.00045312254,0.00047307945,0.00057611335,0.0009832956,0.00039435198],"domain_scores_gemma":[0.9962887,0.00014185638,0.00018171564,0.0029931741,0.0002461849,0.0001483477],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.007919067,0.00009791769,0.00018593349,0.00026846677,0.00042778742,0.0014984865,0.007215905,0.00003602015,0.005362443],"category_scores_gemma":[0.0023356543,0.00009909586,0.000018932096,0.0012979791,0.00008755129,0.0055394354,0.015305395,0.00017883927,0.005143669],"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":[0.000055415923,0.0002731457,0.00032409915,0.00009560798,0.000049417282,0.000014926097,0.005569161,0.00006806583,0.0006012841,0.0046773157,0.16331574,0.8249558],"study_design_scores_gemma":[0.00024060674,0.000015591593,0.00901703,0.000065866254,0.000010023301,0.000017425058,0.0034045333,0.0016250266,0.00006402423,0.00015570605,0.9852653,0.00011886641],"about_ca_topic_score_codex":0.0002470088,"about_ca_topic_score_gemma":0.00001248104,"teacher_disagreement_score":0.82483697,"about_ca_system_score_codex":0.000050886734,"about_ca_system_score_gemma":0.000005190534,"threshold_uncertainty_score":0.99953806},"labels":[],"label_agreement":null},{"id":"W2405050116","doi":"10.1016/j.jval.2016.03.1777","title":"PROBABILISTIC RECORD MATCHING USING MACHINE LEARNING TECHNIQUES","year":2016,"lang":"en","type":"article","venue":"Value in Health","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Matching (statistics); Data mining; Weighting; Confusion matrix; Set (abstract data type); Metric (unit); Probabilistic logic; Levenshtein distance; Artificial intelligence; Algorithm; Mathematics; Statistics","score_opus":0.31160901547951836,"score_gpt":0.45121663754216795,"score_spread":0.1396076220626496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405050116","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":[0.6702071,0.00046200067,0.30038032,0.022580396,0.0010181456,0.0016338809,0.000068669746,0.0004647977,0.0031847209],"genre_scores_gemma":[0.897252,0.00035696637,0.09778221,0.0016902538,0.0001766817,0.000032164266,0.00000604266,0.000034518034,0.0026691298],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965158,0.0011717742,0.0008705731,0.00044418278,0.0006529336,0.0003447385],"domain_scores_gemma":[0.99773747,0.001328517,0.00032686017,0.00046064137,0.000047705817,0.000098820325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012592945,0.000105221814,0.0002652371,0.00031610436,0.00016420738,0.000104502,0.0004748017,0.000039295344,0.00014412703],"category_scores_gemma":[0.0030731356,0.00006522894,0.00004156864,0.00048264329,0.000050354443,0.0003469094,0.00025714462,0.00015668564,0.00010648487],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052626114,0.00013816525,0.017080974,0.00017498319,0.000007138114,0.000017001634,0.001437368,0.0023101056,0.0006299536,0.055198282,0.0010371547,0.92191625],"study_design_scores_gemma":[0.00050749216,0.00033915756,0.0025633012,0.0011260139,0.0000046991245,0.0000131894685,0.00071468664,0.024809808,0.00026753274,0.6228152,0.34644002,0.0003989084],"about_ca_topic_score_codex":0.013650379,"about_ca_topic_score_gemma":0.0005602226,"teacher_disagreement_score":0.9215173,"about_ca_system_score_codex":0.000244161,"about_ca_system_score_gemma":0.00011723514,"threshold_uncertainty_score":0.99291784},"labels":[],"label_agreement":null},{"id":"W2405562871","doi":"10.3233/978-1-61499-289-9-861","title":"Development of a Public Health Reporting Data Warehouse: Lessons Learned","year":2013,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":17,"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 Victoria","funders":"","keywords":"Data warehouse; Formative assessment; Computer science; Process management; Scale (ratio); Data extraction; Knowledge management; Database; Engineering; MEDLINE","score_opus":0.8068837092946661,"score_gpt":0.5873405471340644,"score_spread":0.21954316216060177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405562871","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":[0.37085804,0.013861277,0.0621768,0.54556996,0.0011173218,0.0030452504,0.00011718862,0.0005106026,0.0027435666],"genre_scores_gemma":[0.7611048,0.008468524,0.22562389,0.0043693143,0.000013389356,0.00011208461,0.00005401312,0.00001073129,0.00024325511],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99339485,0.00014304007,0.005133649,0.0002658495,0.00053585746,0.000526734],"domain_scores_gemma":[0.99433804,0.0004049619,0.003681128,0.0012646714,0.0002230251,0.00008816342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023934947,0.00012137785,0.0006565116,0.00091146585,0.00043639497,0.000050630842,0.0010199144,0.000082864375,0.00001304944],"category_scores_gemma":[0.017524922,0.00009019523,0.00001369461,0.0013554526,0.0004954358,0.00084518536,0.0030553634,0.00026555828,0.00003334578],"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":[0.0000010994137,0.000042573294,0.0036534336,0.000516895,0.000033549193,4.6462037e-7,0.020143991,0.0000032475587,1.6808869e-7,0.02772375,0.012903071,0.93497777],"study_design_scores_gemma":[0.0003879756,0.00013320599,0.008118168,0.0002516308,0.000001877555,0.000010226267,0.36748806,0.0014944911,0.000006995595,0.038485847,0.5834502,0.00017131261],"about_ca_topic_score_codex":0.00006653023,"about_ca_topic_score_gemma":0.00045579512,"teacher_disagreement_score":0.93480647,"about_ca_system_score_codex":0.00009719079,"about_ca_system_score_gemma":0.00047235383,"threshold_uncertainty_score":0.9907509},"labels":[],"label_agreement":null},{"id":"W2405781509","doi":"","title":"Rich Data: Risks, Issues, Controversies & Hype.","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 Alberta","funders":"","keywords":"Big data; Government (linguistics); Promotion (chess); Business; State (computer science); Analytics; Marketing; Data science; Political science; Computer science; Politics; Law","score_opus":0.803639955861975,"score_gpt":0.5643870837347821,"score_spread":0.23925287212719293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405781509","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0084206285,0.0017189538,0.049592815,0.06858692,0.0029415581,0.0005339091,0.0007378431,0.00031341374,0.86715394],"genre_scores_gemma":[0.51122195,0.00023269701,0.020963827,0.018772388,0.00080799556,0.000011405846,0.00053040526,0.000022215232,0.44743714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973731,0.00019169081,0.00036083753,0.00048193338,0.0013958655,0.00019655733],"domain_scores_gemma":[0.99665904,0.0008339872,0.000101459686,0.002062605,0.0001871492,0.00015575418],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006873461,0.00008689096,0.00020022123,0.00009794334,0.000068815534,0.0004839731,0.002223572,0.000031629657,0.0010081433],"category_scores_gemma":[0.008653634,0.00005748628,0.000023636438,0.00035255385,0.00007788061,0.0013340242,0.0016342852,0.00005928683,0.008058259],"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":[0.000013514908,0.000033852302,0.00063170743,7.565692e-7,0.00001249286,0.0000050529748,0.00011790087,0.000007841313,0.0000016383216,0.038975466,0.9441045,0.016095262],"study_design_scores_gemma":[0.00038643245,0.000030568674,0.00066074147,0.0000011942146,0.000010999607,9.022261e-7,0.006227812,0.00058613764,0.000025374116,0.030556217,0.961424,0.00008960594],"about_ca_topic_score_codex":0.0016248722,"about_ca_topic_score_gemma":0.0005907968,"teacher_disagreement_score":0.5028013,"about_ca_system_score_codex":0.000023375416,"about_ca_system_score_gemma":0.000045975954,"threshold_uncertainty_score":0.99990505},"labels":[],"label_agreement":null},{"id":"W2405889505","doi":"10.5281/zenodo.3781572","title":"DataCite Canada: Canada's Data Registration Centre","year":2011,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Land registration; Computer science; Geography; Archaeology","score_opus":0.32616730933515403,"score_gpt":0.3245950437760552,"score_spread":0.00157226555909884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405889505","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074723326,0.000111088266,0.03810404,0.013522209,0.001136958,0.0011444405,0.01905761,0.00062185735,0.91882944],"genre_scores_gemma":[0.9359944,0.000059365848,0.0010769157,0.0023069174,0.00025284538,2.5535046e-8,0.03158813,0.00082556484,0.027895832],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965381,0.0004987317,0.00045304117,0.0006862567,0.0014893904,0.00033446477],"domain_scores_gemma":[0.996662,0.000064073494,0.00020894277,0.0022935807,0.00054613926,0.00022524489],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028062854,0.00011582136,0.00013772673,0.000110672074,0.0013901213,0.0012812176,0.004908338,0.00002811178,0.016372945],"category_scores_gemma":[0.0040077036,0.00010797563,0.000015208055,0.0006165428,0.0000907243,0.0011812347,0.0036845093,0.00015378225,0.0014209519],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019549841,0.00003328039,0.000007750259,0.000008024096,0.000016565333,0.000029395036,0.00022442765,0.0000044767276,0.00002266804,0.014125142,0.92282134,0.0626874],"study_design_scores_gemma":[0.00015530811,0.00002139955,0.0018453421,0.0000069611506,0.000008676509,0.000014710133,0.0013627997,0.00031139003,0.000049994298,0.00040599643,0.99568784,0.00012957912],"about_ca_topic_score_codex":0.877981,"about_ca_topic_score_gemma":0.878113,"teacher_disagreement_score":0.92852205,"about_ca_system_score_codex":0.00023758216,"about_ca_system_score_gemma":0.00009178445,"threshold_uncertainty_score":0.99990994},"labels":[],"label_agreement":null},{"id":"W2405922764","doi":"10.22215/etd/2017-11827","title":"Multidimensional Ontologies for Contextual Quality Data Specification and Extraction","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Datalog; Computer science; Ontology; Context (archaeology); Dimension (graph theory); Data model (GIS); Data mining; Information retrieval; Data quality; Web Ontology Language; Data modeling; Database; Theoretical computer science; Semantic Web; Artificial intelligence; Mathematics","score_opus":0.698625282896067,"score_gpt":0.6021789871339925,"score_spread":0.09644629576207442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405922764","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16433214,0.0037809145,0.264915,0.014711965,0.025387233,0.011095346,0.017626641,0.00073857507,0.4974122],"genre_scores_gemma":[0.21595713,0.000749684,0.031445008,0.0004397057,0.00064272975,0.00020288056,0.07184756,0.000045573863,0.67866975],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964478,0.0002049665,0.00092996494,0.0011833896,0.0010506789,0.00018320205],"domain_scores_gemma":[0.99285054,0.0027332786,0.0011689482,0.0027114283,0.00046708365,0.00006869615],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073674903,0.00021152661,0.00044850836,0.00016703978,0.0004955958,0.0006890628,0.0015719131,0.00023194402,0.00044035158],"category_scores_gemma":[0.013318368,0.0001600407,0.000072209616,0.000050862516,0.00010326654,0.0013750865,0.0002338789,0.0001466988,0.00015368126],"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":[0.00059267314,0.00010734799,0.00009461164,0.00006805873,0.00005686491,0.0000010300101,0.0003137439,5.616929e-7,0.0003832282,0.11615145,0.23367615,0.64855427],"study_design_scores_gemma":[0.0005604658,0.00005666353,0.080830075,0.000031397365,0.000057730795,0.0000010661357,0.013902275,0.0005982063,0.00028063232,0.021512877,0.8818443,0.0003243262],"about_ca_topic_score_codex":0.0006304997,"about_ca_topic_score_gemma":0.012196543,"teacher_disagreement_score":0.64822996,"about_ca_system_score_codex":0.000026636017,"about_ca_system_score_gemma":0.000090278256,"threshold_uncertainty_score":0.99499285},"labels":[],"label_agreement":null},{"id":"W2406968597","doi":"","title":"Breaking the Chains: On Declarative Analysis and Independence in the Big Data Era.","year":2014,"lang":"en","type":"article","venue":"GI-Jahrestagung","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Big data; Computer science; Data science; Data management; Scarcity; Database; Data mining","score_opus":0.34408772542810734,"score_gpt":0.4325429461399086,"score_spread":0.08845522071180129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406968597","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":[0.747606,0.00054790685,0.1858986,0.033173118,0.0008442705,0.001321395,0.00037122806,0.00007955692,0.030157937],"genre_scores_gemma":[0.9954957,0.0000496975,0.00016765969,0.0037254225,0.00010868105,0.000015681453,0.00003687157,0.000004856624,0.00039547213],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99557394,0.0013821754,0.00046412065,0.0007313696,0.0015712418,0.00027714772],"domain_scores_gemma":[0.99300784,0.0038990905,0.00022462764,0.0027530056,0.000064574524,0.000050875646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01628755,0.00015123672,0.0002614995,0.00037080428,0.0003608714,0.00080884463,0.0032117853,0.000056914185,0.000041942407],"category_scores_gemma":[0.0033758127,0.000073893134,0.000054200602,0.0019927372,0.00019688036,0.0004835637,0.0010874525,0.0003332435,0.00007813431],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076846445,0.00016459529,0.041827355,0.000010850467,0.00023876112,0.000037109723,0.010264744,0.00091059884,0.00003460574,0.12715198,0.012228192,0.80705434],"study_design_scores_gemma":[0.0005684398,0.00011980269,0.76174104,0.000043776527,0.00023085762,0.0000061388328,0.013837382,0.045850758,0.000037786394,0.029893074,0.14730364,0.0003672987],"about_ca_topic_score_codex":0.0013138317,"about_ca_topic_score_gemma":0.019114936,"teacher_disagreement_score":0.80668706,"about_ca_system_score_codex":0.000018068224,"about_ca_system_score_gemma":0.000033526325,"threshold_uncertainty_score":0.99878365},"labels":[],"label_agreement":null},{"id":"W2407048971","doi":"10.5281/zenodo.3781914","title":"Taking the Pulse of our Members: Creating a Healthy Data Environment","year":2009,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada; Carleton University","funders":"","keywords":"Computer science; Pulse (music); Telecommunications","score_opus":0.3024859585988458,"score_gpt":0.40018767354960405,"score_spread":0.09770171495075824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407048971","genre_codex":"other","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":[0.022996258,0.00050243543,0.08586779,0.059890993,0.00038292396,0.0021739055,0.0019485924,0.0007376203,0.8254995],"genre_scores_gemma":[0.99629515,0.000094557414,0.00094484014,0.0009202262,0.00010755877,1.4886441e-8,0.0007439968,0.00018362557,0.00071004435],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967461,0.000777454,0.0005116734,0.0005081402,0.0011848899,0.00027169907],"domain_scores_gemma":[0.9973614,0.000107089894,0.00037971133,0.0018706984,0.0001745565,0.00010653605],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0071238126,0.000096417236,0.00015417062,0.0001573452,0.0016117214,0.0009149497,0.0040248837,0.000027868798,0.013508002],"category_scores_gemma":[0.004491886,0.00007034579,0.000037161462,0.0005388157,0.000089503264,0.00053677615,0.0032287107,0.00016844942,0.0033743626],"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":[0.000058818925,0.00016055194,0.0000031087347,0.000012352834,0.00002003738,0.0000047954404,0.0016595391,0.0002490449,0.0003207292,0.01159,0.22348651,0.7624345],"study_design_scores_gemma":[0.000242041,0.00020041797,0.002219685,0.00001506058,0.000010848917,0.000012793018,0.0041145394,0.001815671,0.00005028786,0.0010276911,0.9902045,0.00008643886],"about_ca_topic_score_codex":0.00006997028,"about_ca_topic_score_gemma":8.7777346e-7,"teacher_disagreement_score":0.9732989,"about_ca_system_score_codex":0.00005626794,"about_ca_system_score_gemma":0.0000033048877,"threshold_uncertainty_score":0.999688},"labels":[],"label_agreement":null},{"id":"W2407371826","doi":"10.5281/zenodo.3781406","title":"Collaborative Data Management: Best Practices throughout the Data Life Cycle","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Council of University Libraries","funders":"","keywords":"Computer science; Data management; Product life-cycle management; Data science; Database; Business","score_opus":0.4229911267320463,"score_gpt":0.4652831398985137,"score_spread":0.04229201316646741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407371826","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016265919,0.0009916609,0.022989558,0.022784946,0.00075238675,0.0016445257,0.008583733,0.00060553773,0.94002104],"genre_scores_gemma":[0.9121482,0.0025825056,0.0064338944,0.0064035873,0.0019257723,3.8789955e-7,0.043812547,0.0020860115,0.02460709],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995022,0.0015801049,0.00049013423,0.0008406791,0.0015930238,0.00047403554],"domain_scores_gemma":[0.99258053,0.00037044217,0.00058957725,0.0056853765,0.0005313526,0.0002427439],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012807368,0.0001526475,0.00017327821,0.00017366467,0.0031322993,0.003836242,0.013035447,0.00004092785,0.0117893],"category_scores_gemma":[0.014084854,0.00010917822,0.000022502612,0.0016223049,0.00031493913,0.004844217,0.02596817,0.00024584736,0.044702455],"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":[0.000036724174,0.00022744748,0.0000071090703,0.000016913162,0.00009129617,0.0000039211673,0.0013628732,0.0000146447,0.0000109557795,0.028098421,0.804112,0.16601771],"study_design_scores_gemma":[0.0002577815,0.000042940203,0.00053422304,0.000009459904,0.000052938474,0.000010691104,0.013061121,0.0009979231,0.0000064417973,0.00066585897,0.9842187,0.00014189661],"about_ca_topic_score_codex":0.000056964254,"about_ca_topic_score_gemma":0.0000042619686,"teacher_disagreement_score":0.915414,"about_ca_system_score_codex":0.0000440049,"about_ca_system_score_gemma":0.0000068454838,"threshold_uncertainty_score":0.9981655},"labels":[],"label_agreement":null},{"id":"W2420813781","doi":"10.1145/2882903.2899397","title":"BART in Action","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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","keywords":"Computer science; Strengths and weaknesses; Set (abstract data type); Core (optical fiber); Action (physics); Data set; Data science; Artificial intelligence; Data mining; Programming language","score_opus":0.5820444491325807,"score_gpt":0.5371231260573351,"score_spread":0.044921323075245545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2420813781","genre_codex":"other","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":[0.23733924,0.0000064834708,0.20169288,0.038501013,0.00076598616,0.00015430615,0.0000085248475,0.000066829496,0.52146477],"genre_scores_gemma":[0.90598434,0.000007360513,0.00030879775,0.0006997319,0.00001724886,0.000002439465,2.7944844e-7,8.4444827e-7,0.092978954],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992766,0.00005590461,0.00015045279,0.0001324079,0.00031938995,0.0000652783],"domain_scores_gemma":[0.999436,0.00026463417,0.000020267911,0.00024346264,0.00001607988,0.000019556092],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017621169,0.00002071544,0.000041379248,0.00008978197,0.000012387312,0.00004166996,0.0002017686,0.000010912981,0.004068869],"category_scores_gemma":[0.0006432647,0.000009367846,0.000013113335,0.00016359871,0.000014208808,0.00036896046,0.0000757712,0.000010399032,0.0050201104],"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":[0.000005443515,0.000017947314,0.0027820342,3.2080249e-7,7.6675406e-7,0.000001154339,0.000029305236,5.521281e-7,0.0004945871,0.11051134,0.15711364,0.7290429],"study_design_scores_gemma":[0.00014065455,0.0000081658945,0.03933916,0.0000023956022,2.8810564e-7,1.7752996e-7,0.00025699325,0.000016720518,0.0006889094,0.06905545,0.890462,0.000029079501],"about_ca_topic_score_codex":0.000045218145,"about_ca_topic_score_gemma":0.00066120346,"teacher_disagreement_score":0.73334837,"about_ca_system_score_codex":0.000011814208,"about_ca_system_score_gemma":0.000004750704,"threshold_uncertainty_score":0.99684155},"labels":[],"label_agreement":null},{"id":"W2427822648","doi":"10.1109/icde.2016.7498319","title":"DataXFormer: A robust transformation discovery system","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":true,"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; Transformation (genetics); Data transformation; Representation (politics); External Data Representation; Knowledge base; Information retrieval; Base (topology); World Wide Web; Data mining; Theoretical computer science; Artificial intelligence; Data warehouse; Mathematics","score_opus":0.20874692386325125,"score_gpt":0.37243103055243876,"score_spread":0.1636841066891875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2427822648","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":[0.0076577277,0.0000053283384,0.8764841,0.0034480388,0.00027377234,0.00014686439,0.00015752093,0.00007201974,0.11175465],"genre_scores_gemma":[0.97652817,0.00001162829,0.00078253367,0.00030326235,0.000039520193,0.00001083903,0.000017291757,0.0000032791131,0.022303507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99821377,0.00008922201,0.00045944168,0.00024264789,0.0008402826,0.00015465847],"domain_scores_gemma":[0.99888176,0.0003011689,0.00008642875,0.00062992825,0.000048827602,0.000051915038],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027013666,0.000068871544,0.00012152432,0.00011844613,0.000082277445,0.00037179084,0.0006170991,0.000023996045,0.00048498512],"category_scores_gemma":[0.00023697819,0.000030190551,0.00005331533,0.00023055381,0.000037360187,0.004149607,0.00010560936,0.000019582616,0.0029682135],"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":[0.000020062189,0.000022742535,0.00011781065,0.00001617523,0.000010352484,0.0000015899894,0.00016262157,0.000013534884,0.0001811385,0.783845,0.06957199,0.14603695],"study_design_scores_gemma":[0.0007722301,0.000053226315,0.0022229073,0.000073016825,0.000015003693,0.000006993277,0.00829381,0.0009839215,0.0011778531,0.0077609355,0.9784109,0.0002292028],"about_ca_topic_score_codex":0.000050914732,"about_ca_topic_score_gemma":0.00012506088,"teacher_disagreement_score":0.9688704,"about_ca_system_score_codex":0.0000388401,"about_ca_system_score_gemma":0.000016151209,"threshold_uncertainty_score":0.9978081},"labels":[],"label_agreement":null},{"id":"W2435238507","doi":"","title":"Data Profiling","year":2018,"lang":"en","type":"book","venue":"","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":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Computer science; Metadata; Inference; Data mining; Data science; Artificial intelligence; World Wide Web; Programming language","score_opus":0.6744232901337949,"score_gpt":0.5236971452500062,"score_spread":0.15072614488378866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2435238507","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.876995e-7,0.000058772952,0.019707842,0.0004945909,0.0008942983,0.00021876818,0.0016147422,0.00006314506,0.97694755],"genre_scores_gemma":[0.0000011425157,0.000018101111,0.008696371,0.001359391,0.00064212317,0.000002176915,0.002622035,0.000011927198,0.9866467],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962528,0.000096175245,0.00062930345,0.0010277166,0.0018171278,0.0001769082],"domain_scores_gemma":[0.9931091,0.0006811096,0.0002658698,0.005704189,0.00016746148,0.00007224068],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008580113,0.00015300397,0.0002937454,0.0001931332,0.000082877115,0.00053957425,0.006521922,0.00013312751,0.011182332],"category_scores_gemma":[0.0023148886,0.00010057867,0.000051133888,0.00011521525,0.00013516417,0.00051168475,0.0055223955,0.0001428715,0.03466784],"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":[0.0000018260534,0.00000603077,8.6117063e-7,0.000006355228,0.000014079117,0.0000032776375,0.000006668135,6.246282e-8,1.3775075e-7,0.12545714,0.85308915,0.021414395],"study_design_scores_gemma":[0.000035331108,0.000012427349,0.0000017421659,0.0000130073495,0.0000135417,5.3578236e-7,0.0000461459,0.00014962917,0.0000029966302,0.20176026,0.79784757,0.00011678315],"about_ca_topic_score_codex":0.0000071033082,"about_ca_topic_score_gemma":0.0001464854,"teacher_disagreement_score":0.07630312,"about_ca_system_score_codex":0.00002932967,"about_ca_system_score_gemma":0.00025103294,"threshold_uncertainty_score":0.99885327},"labels":[],"label_agreement":null},{"id":"W2461005711","doi":"10.1145/2911451.2911456","title":"An Architecture for Privacy-Preserving and Replicable High-Recall Retrieval Experiments","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Waterloo","funders":"","keywords":"Computer science; Recall; Architecture; Precision and recall; Information retrieval; Order (exchange); Information privacy; Computer security","score_opus":0.15761016311109097,"score_gpt":0.429325468273088,"score_spread":0.27171530516199704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2461005711","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":[0.4832374,0.00005458421,0.48822162,0.021240763,0.00032453082,0.0008001126,0.0001377251,0.00013730345,0.005845986],"genre_scores_gemma":[0.92966926,0.000014415294,0.04487253,0.0016143937,0.0001294392,0.00003038378,0.000013423578,0.000015189513,0.023640938],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979517,0.00012710295,0.00036755748,0.0006696611,0.0006279057,0.00025605707],"domain_scores_gemma":[0.9973002,0.0008382893,0.00009974558,0.0015113384,0.00009395333,0.00015649127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026361726,0.000108194945,0.00018586544,0.00010332177,0.0001400549,0.00029728183,0.0011618008,0.000050848932,0.00086200377],"category_scores_gemma":[0.0026562742,0.000056076067,0.00004076747,0.0001641374,0.00006762958,0.00059163134,0.00076341233,0.000034895136,0.0000663388],"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":[0.0008495652,0.00028356942,0.0012022947,0.000028580516,0.000060773622,0.000004829407,0.0011925158,0.000012085864,0.12301067,0.09917888,0.39127132,0.3829049],"study_design_scores_gemma":[0.001272505,0.00032090626,0.003295359,0.000021362663,0.000009065504,0.0000018810412,0.00048819208,0.0002752116,0.034837738,0.31465256,0.6445895,0.00023572973],"about_ca_topic_score_codex":0.000083500316,"about_ca_topic_score_gemma":0.000037112153,"teacher_disagreement_score":0.4464319,"about_ca_system_score_codex":0.000016379427,"about_ca_system_score_gemma":0.000014072165,"threshold_uncertainty_score":0.9438337},"labels":[],"label_agreement":null},{"id":"W2463241984","doi":"10.29173/cais345","title":"Bringing Together Functional Classification and Business Process Analysis: Growing Trends in Records Management","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Economic rent; Point (geometry); Business process; Process (computing); Function (biology); Knowledge management; Humanities; Sociology; Computer science; Library science; Business; Economics; Marketing; Philosophy; Artificial intelligence; Mathematics; Work in process","score_opus":0.07733218206249626,"score_gpt":0.32065348876196675,"score_spread":0.2433213066994705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463241984","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":[0.95726323,0.0004965423,0.0006346238,0.015057305,0.0003660801,0.00046203783,0.00010866065,0.000026216012,0.025585305],"genre_scores_gemma":[0.987922,0.0003143637,0.00083341746,0.00030055572,0.00007725779,0.00008301712,0.000015797299,0.000018017583,0.010435557],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996245,0.0000884084,0.0011921754,0.00075798586,0.0011919318,0.0005244588],"domain_scores_gemma":[0.9722034,0.00023376939,0.0011753029,0.00034354374,0.025899928,0.00014410607],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0029507354,0.00034281466,0.000701084,0.0013306029,0.00017660011,0.0048798756,0.0017753157,0.00017933788,0.0004770332],"category_scores_gemma":[0.005174071,0.00028036218,0.00020410672,0.004575729,0.0005837045,0.02178022,0.0009855778,0.00028280492,0.00001308801],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015720536,0.00047107597,0.4207551,0.0011099556,0.000842941,0.0000022218167,0.022709372,0.0002038556,0.0005941493,0.06998182,0.0067362487,0.47643608],"study_design_scores_gemma":[0.0005430205,0.000065736924,0.9130938,0.00053404906,0.0005471934,0.000006564002,0.022642795,0.007361798,0.00028568238,0.018660313,0.03591137,0.00034765166],"about_ca_topic_score_codex":0.0013876008,"about_ca_topic_score_gemma":0.00014530598,"teacher_disagreement_score":0.49233875,"about_ca_system_score_codex":0.00009930811,"about_ca_system_score_gemma":0.00009783351,"threshold_uncertainty_score":0.99996483},"labels":[],"label_agreement":null},{"id":"W2465051419","doi":"","title":"Critical implementation factors in data warehouse implementations in canadian financial institutions: qualitative expanded study","year":2006,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data warehouse; Implementation; Quality (philosophy); Business; Data quality; Finance; Accounting; Qualitative property; Qualitative research; Knowledge management; Computer science; Database; Marketing; Sociology","score_opus":0.5690071729099726,"score_gpt":0.622903979228842,"score_spread":0.053896806318869395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2465051419","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":[0.9836371,0.000010961759,0.006347506,0.0032510066,0.00028404882,0.0012328018,0.0024713115,0.00003273676,0.0027325102],"genre_scores_gemma":[0.99724996,0.0000016034597,0.000785277,0.00035944697,0.000027071015,0.00008199506,0.001338636,0.0000055588716,0.00015045829],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958433,0.0008690505,0.0012342964,0.00068032934,0.0008623085,0.0005107418],"domain_scores_gemma":[0.99753755,0.0012442457,0.00008832171,0.0008634815,0.0001229201,0.00014346534],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0064979726,0.00014796581,0.00024098923,0.0010971257,0.0002488095,0.00035890343,0.0010123504,0.000038872502,0.0013214903],"category_scores_gemma":[0.003952484,0.00012718525,0.000027489954,0.0014326891,0.00009898634,0.002065462,0.00036073034,0.00012276853,0.00009215022],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024251112,0.0010264984,0.48304987,0.00000559939,0.000010543868,0.000053599022,0.034692157,0.00012793043,0.0000068826726,0.4168873,0.05987788,0.0042374716],"study_design_scores_gemma":[0.001182956,0.00007986646,0.5820714,0.0000046067757,0.000009577753,3.1391855e-7,0.36318904,0.000106265536,0.00001611897,0.03116416,0.021973222,0.00020246887],"about_ca_topic_score_codex":0.9054185,"about_ca_topic_score_gemma":0.9988978,"teacher_disagreement_score":0.38572314,"about_ca_system_score_codex":0.00034210458,"about_ca_system_score_gemma":0.0008417679,"threshold_uncertainty_score":0.9995914},"labels":[],"label_agreement":null},{"id":"W2469916400","doi":"","title":"Linking 2006 Census and hospital data in Canada.","year":2015,"lang":"en","type":"article","venue":"PubMed","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Geological Survey of Canada; Statistics Canada","funders":"","keywords":"Census; Record linkage; Demography; Linkage (software); Geography; Population; Matching (statistics); Database; Medicine; Computer science; Biology","score_opus":0.29811807224951903,"score_gpt":0.3500027166522466,"score_spread":0.05188464440272755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2469916400","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":[0.9071549,0.0016036812,0.0007934621,0.041065417,0.004010147,0.0015866961,0.0023633703,0.000053016276,0.041369304],"genre_scores_gemma":[0.99805546,0.000009746784,0.00018163932,0.0006074477,0.000053809126,0.000036994985,0.00008024388,0.0000030216488,0.00097162434],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983347,0.000080281476,0.0002558106,0.00033146952,0.0007602731,0.0002374581],"domain_scores_gemma":[0.9987776,0.00019737546,0.00006535206,0.0007629144,0.000040358056,0.00015634231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004206485,0.000052831383,0.00011068762,0.00006933141,0.000023903063,0.00016748371,0.0008863346,0.000015552863,0.0000048310676],"category_scores_gemma":[0.0024533737,0.000041836156,0.0000048093875,0.0002617261,0.000026628173,0.00039209236,0.0009690072,0.00005932052,0.000009679203],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005736833,0.00001759947,0.059945274,0.0000023845025,0.0000037460325,0.000030882456,0.00010095684,0.00000868941,2.0505919e-8,0.00080214435,0.33984178,0.5992408],"study_design_scores_gemma":[0.00020603598,0.0000018540107,0.3953286,0.0000014992069,0.0000020925934,5.884701e-7,0.0009522855,0.00024003742,9.2978036e-7,0.0032608584,0.59993947,0.000065763394],"about_ca_topic_score_codex":0.5711946,"about_ca_topic_score_gemma":0.94155425,"teacher_disagreement_score":0.59917504,"about_ca_system_score_codex":0.000091828566,"about_ca_system_score_gemma":0.00015004376,"threshold_uncertainty_score":0.43166083},"labels":[],"label_agreement":null},{"id":"W2471940872","doi":"10.3163/1536-5050.104.3.014","title":"De-duplication of database search results for systematic reviews in EndNote","year":2016,"lang":"en","type":"article","venue":"Journal of the Medical Library Association JMLA","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1874,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Computer science; World Wide Web; Information retrieval; Data science; Library science; Database","score_opus":0.16035700940096184,"score_gpt":0.4287371023629208,"score_spread":0.26838009296195897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471940872","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":[0.074178316,0.0016254006,0.16657749,0.74281263,0.0028669322,0.005496583,0.0012561934,0.000033285192,0.0051531736],"genre_scores_gemma":[0.9317532,0.0031903114,0.010024758,0.009438374,0.0014162752,0.00011628771,0.00004358677,0.00003621234,0.043980967],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928336,0.0024552601,0.0021486261,0.00012895679,0.0022841345,0.00014943471],"domain_scores_gemma":[0.9847605,0.011724626,0.0027192023,0.0004905218,0.00017412312,0.00013098572],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.049430564,0.000061008846,0.00043517235,0.00017143872,0.000040216935,0.00007131558,0.0013401711,0.00007508284,0.00012316073],"category_scores_gemma":[0.12979983,0.000025709553,0.00019657481,0.00047940735,0.000033632128,0.001046447,0.00023719088,0.00014565144,0.000025157304],"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":[0.0005142581,0.00046450426,0.01141685,0.0026384087,0.00012196978,0.0000082984825,0.0011514872,0.000020316813,0.00066230627,0.025360102,0.9091059,0.048535615],"study_design_scores_gemma":[0.009985187,0.00045230318,0.043978408,0.03919894,0.00019553959,0.000031853786,0.0012228396,0.0033693428,0.0052159806,0.08551436,0.8104419,0.00039331758],"about_ca_topic_score_codex":0.0000027107071,"about_ca_topic_score_gemma":0.0000037098791,"teacher_disagreement_score":0.85757494,"about_ca_system_score_codex":0.00010754485,"about_ca_system_score_gemma":0.00022587235,"threshold_uncertainty_score":0.97881126},"labels":[],"label_agreement":null},{"id":"W2474544103","doi":"10.18260/p.26272","title":"Architectural Evaluation of Master Data Management (MDM): Literature Review","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Ottawa","funders":"St. Jude Medical; American Society for Engineering Education","keywords":"Computer science; Notation; Master data; Process (computing); Qualitative property; Quantitative analysis (chemistry); Software engineering; Data science; Business process; Management science; Process management; Knowledge management; Engineering; Data mining; Work in process; Operations management; Programming language","score_opus":0.5556549298580707,"score_gpt":0.5130888725810021,"score_spread":0.042566057277068636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2474544103","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006099854,0.047050197,0.22941455,0.10051235,0.0019209845,0.0058701,0.0018350516,0.00016789495,0.60712904],"genre_scores_gemma":[0.62720525,0.041987706,0.050457526,0.031162718,0.0004749238,0.00023061983,0.0014334793,0.00005617274,0.24699162],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956298,0.0005502454,0.0006296258,0.0005303316,0.002516161,0.00014381965],"domain_scores_gemma":[0.9964472,0.00027392182,0.00019941045,0.0027320108,0.0003001917,0.00004726792],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.015136947,0.00009672887,0.00020417808,0.0001535671,0.000028870905,0.00011291915,0.0018762177,0.000020875892,0.004622241],"category_scores_gemma":[0.0012340659,0.00004349085,0.000053331492,0.00048961886,0.00005161776,0.00077741937,0.0013946862,0.000034465265,0.00058708055],"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":[0.0000065558856,0.000019644038,0.000028796632,0.00013693166,0.000021531172,0.0000015324752,0.00003326693,8.073332e-7,0.00001537826,0.010890652,0.17529328,0.8135516],"study_design_scores_gemma":[0.0008964294,0.000041599775,0.0048550772,0.0036136531,0.0002059934,0.0000069606695,0.00016694129,0.00049930974,0.00009197069,0.052744422,0.93667114,0.00020648305],"about_ca_topic_score_codex":0.0000025574486,"about_ca_topic_score_gemma":0.000025890786,"teacher_disagreement_score":0.81334513,"about_ca_system_score_codex":0.000016501572,"about_ca_system_score_gemma":0.000013876562,"threshold_uncertainty_score":0.99628764},"labels":[],"label_agreement":null},{"id":"W2481701410","doi":"10.2495/dne-v11-n3-370-375","title":"Developing a data map for opening public sector information","year":2016,"lang":"en","type":"article","venue":"International Journal of Design & Nature and Ecodynamics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Metadata; Process (computing); Computer science; Task (project management); Automation; Key (lock); Data mapping; Data science; Knowledge management; Public sector; Process management; World Wide Web; Engineering; Database; Systems engineering; Computer security; Political science","score_opus":0.19609341919696013,"score_gpt":0.4051800031778149,"score_spread":0.20908658398085475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481701410","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":[0.0027940632,0.00010478561,0.9714031,0.023582997,0.0016478865,0.00011750701,0.00022881386,0.0000058875544,0.0001149087],"genre_scores_gemma":[0.8142297,0.0003227954,0.18141717,0.0029958296,0.000548381,0.0000045262755,0.00013441526,0.000010263482,0.00033688016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808633,0.000077873,0.00070259674,0.0001462834,0.00086080766,0.00012609041],"domain_scores_gemma":[0.9967939,0.0011996768,0.00065243547,0.00024552253,0.0010435808,0.00006483059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049415776,0.00008274476,0.00015432909,0.0004402136,0.00007014629,0.00071119005,0.0018875297,0.00008759832,0.0000398731],"category_scores_gemma":[0.0041555846,0.00004895388,0.000046458536,0.00012032322,0.000029992405,0.005001504,0.00043466073,0.00013473965,0.00001733956],"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":[0.00041350228,0.00003866417,0.00075635704,0.000015758491,0.00034408565,0.000015480775,0.00032330165,0.000076692755,0.00020949934,0.20274349,0.06824918,0.726814],"study_design_scores_gemma":[0.0015589673,0.000088937624,0.0012603017,0.00014140701,0.000024332723,0.00010292093,0.0005035565,0.016947443,0.00008184856,0.14270897,0.83638906,0.0001922421],"about_ca_topic_score_codex":0.0000017452029,"about_ca_topic_score_gemma":0.00002277598,"teacher_disagreement_score":0.8114357,"about_ca_system_score_codex":0.00008798498,"about_ca_system_score_gemma":0.00016701366,"threshold_uncertainty_score":0.68580216},"labels":[],"label_agreement":null},{"id":"W2482322048","doi":"10.1177/2327857916051007","title":"A Method for Developing Data Quality Measures and Metrics for Primary Health Care","year":2016,"lang":"en","type":"article","venue":"Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"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":"Ontario Ministry of Health and Long-Term Care","keywords":"Quality (philosophy); Completeness (order theory); Computer science; Data quality; Quality management; Primary care; Exploratory research; Data science; Exploratory data analysis; Data mining; Knowledge management; Medicine; Metric (unit); Operations management; Engineering; Mathematics; Family medicine; Management system","score_opus":0.2942096064236911,"score_gpt":0.4812717803780066,"score_spread":0.1870621739543155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2482322048","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":[0.8951364,0.0017009466,0.019781306,0.06946291,0.0016483908,0.003523731,0.008033093,0.000043564916,0.00066962093],"genre_scores_gemma":[0.9663147,0.00060725317,0.028334811,0.0042102057,0.00015065173,0.00007856096,0.0001446001,0.000023677869,0.00013559389],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974948,0.000047351103,0.0010172465,0.0006416562,0.00056069944,0.0002382402],"domain_scores_gemma":[0.99677444,0.001474952,0.00085172965,0.00027178822,0.00054137234,0.00008569874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005504002,0.00015623908,0.0004060208,0.00023922499,0.00031353856,0.00018366908,0.0013816908,0.000054853863,0.0000013669465],"category_scores_gemma":[0.0015935241,0.00009310018,0.0000672884,0.0001353013,0.00006675314,0.00037966427,0.0008268783,0.00007712426,1.7401747e-7],"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":[0.0014230917,0.00013391009,0.10646288,0.0039738994,0.00018089535,5.7387197e-8,0.023079703,0.000017990698,0.0009473823,0.5907223,0.029153941,0.24390392],"study_design_scores_gemma":[0.0045498163,0.0010291288,0.21557416,0.0012616843,0.000034986857,0.0000020209511,0.036764536,0.00023404653,0.0031537446,0.039119996,0.6973875,0.0008883775],"about_ca_topic_score_codex":0.00059765595,"about_ca_topic_score_gemma":0.0008315807,"teacher_disagreement_score":0.6682336,"about_ca_system_score_codex":0.00072742475,"about_ca_system_score_gemma":0.0001913457,"threshold_uncertainty_score":0.3796515},"labels":[],"label_agreement":null},{"id":"W2483857718","doi":"10.1109/swste.2016.14","title":"The Problem of the Lack of Benefit of a Document to Its Producer (PotLoBoaDtiP)","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"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","keywords":"Computer science","score_opus":0.1952275378131951,"score_gpt":0.42424984729057674,"score_spread":0.22902230947738164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2483857718","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":[0.6495626,0.00021725132,0.005073948,0.19633122,0.0006372223,0.0038977594,0.00023423103,0.000034666446,0.14401112],"genre_scores_gemma":[0.92796487,0.00002792822,0.0010621186,0.00039557193,0.000015678983,0.000022966511,2.126935e-7,0.000003910825,0.07050677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975032,0.000116995034,0.0007331066,0.000251631,0.0012460639,0.00014900065],"domain_scores_gemma":[0.9974732,0.0006197526,0.0003446272,0.0011533999,0.00037093944,0.000038093975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043512876,0.000071371396,0.00018449732,0.00005486754,0.00005463056,0.000032701155,0.0014788897,0.000018990038,0.0005037742],"category_scores_gemma":[0.0007941727,0.00002253149,0.000087388624,0.000469113,0.00012500826,0.0001679249,0.0008468682,0.000022939414,0.0001339947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083540304,0.00013777814,0.000990616,0.00003642274,0.000052517735,1.07386775e-7,0.0009690695,0.00004973324,0.009405024,0.62985396,0.10663415,0.2517871],"study_design_scores_gemma":[0.00041462487,0.00019269732,0.014347186,0.000115289666,0.00001975522,3.198367e-7,0.0011134498,0.000006703218,0.20485178,0.1367225,0.6421094,0.00010630961],"about_ca_topic_score_codex":0.000091800364,"about_ca_topic_score_gemma":0.0003802491,"teacher_disagreement_score":0.53547525,"about_ca_system_score_codex":0.000012878379,"about_ca_system_score_gemma":0.00003495956,"threshold_uncertainty_score":0.5515974},"labels":[],"label_agreement":null},{"id":"W2489528053","doi":"","title":"Data Fusion for Mine Action Decision Support: An Example From Lebanon","year":2004,"lang":"en","type":"article","venue":"JMU Scholoraly Commons (James Madison University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mine action; Decision support system; Operations research; Action (physics); Sensor fusion; Computer science; Mining engineering; Engineering; Data mining; Political science; Artificial intelligence; Law","score_opus":0.3898994090914583,"score_gpt":0.4086261089501165,"score_spread":0.018726699858658158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489528053","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":[0.69966215,0.000056714656,0.28761262,0.0027493169,0.0008938121,0.00076766254,0.0031179576,0.00022237294,0.004917389],"genre_scores_gemma":[0.92314833,0.00017707222,0.05439884,0.0010495536,0.00036080976,0.0000053282024,0.010555321,0.000054330572,0.0102504045],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99631864,0.00029384342,0.0005634711,0.0013916154,0.001005955,0.00042647688],"domain_scores_gemma":[0.99456316,0.00089239836,0.00039680142,0.0036024167,0.00022192707,0.00032326824],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021452976,0.00027303922,0.00044567557,0.0008916908,0.0006352681,0.00058065203,0.0040797344,0.00018489062,0.00059887406],"category_scores_gemma":[0.0005052755,0.00025879752,0.00015148264,0.001346952,0.00015491922,0.0039898483,0.0019245988,0.00025579764,0.00037072506],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001959386,0.0010624984,0.0019131657,0.0000110480705,0.00012610517,0.00012358521,0.0011510614,0.00087143574,0.0008948689,0.021036023,0.32852548,0.64232534],"study_design_scores_gemma":[0.00301077,0.00038555101,0.00497082,0.000026041167,0.00010131713,0.0000023027021,0.006630703,0.0008394563,0.00022053694,0.019098625,0.96435726,0.00035661753],"about_ca_topic_score_codex":0.004572674,"about_ca_topic_score_gemma":0.020595867,"teacher_disagreement_score":0.6419687,"about_ca_system_score_codex":0.00020391721,"about_ca_system_score_gemma":0.00012023533,"threshold_uncertainty_score":0.9999864},"labels":[],"label_agreement":null},{"id":"W2492590231","doi":"10.14778/2983200.2983203","title":"Distributed data deduplication","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data deduplication; Tuple; Computer science; Blocking (statistics); Block (permutation group theory); Relation (database); Backup; Locality; Process (computing); Theoretical computer science; Data mining; Database; Mathematics","score_opus":0.27015668142943616,"score_gpt":0.4095847037039765,"score_spread":0.13942802227454032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492590231","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":[0.53420186,0.00044796744,0.06260016,0.31239685,0.002539681,0.004448726,0.006065222,0.0003774347,0.07692211],"genre_scores_gemma":[0.9969729,0.000034896664,0.0007136844,0.00032922538,0.000048093018,0.000023461926,0.000013878963,0.000004956632,0.0018588923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978591,0.000014057066,0.00046756526,0.00042803856,0.0010639259,0.00016730075],"domain_scores_gemma":[0.9981716,0.0002162236,0.00040090503,0.00091236766,0.0002468247,0.000052059524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028330449,0.00008521082,0.00013965889,0.00006043705,0.00009177444,0.000107490894,0.0036101257,0.000024283818,0.00013077073],"category_scores_gemma":[0.0027982353,0.000036720947,0.000050297233,0.0004182962,0.00011102656,0.0006597339,0.0023385265,0.00003541284,0.00015625088],"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":[0.000041050534,0.00017856839,0.0076983077,0.00002086533,0.000045253637,9.9132635e-8,0.00014281253,0.0000010380242,0.033738043,0.18160972,0.6230755,0.15344873],"study_design_scores_gemma":[0.00055827317,0.00003815815,0.022558033,0.00006807549,0.0000369814,0.0000021759029,0.0005607348,0.00011306024,0.056911714,0.1197099,0.7993017,0.0001411777],"about_ca_topic_score_codex":0.000025190955,"about_ca_topic_score_gemma":0.0000059905256,"teacher_disagreement_score":0.46277106,"about_ca_system_score_codex":0.000042893793,"about_ca_system_score_gemma":0.00001607763,"threshold_uncertainty_score":0.6708572},"labels":[],"label_agreement":null},{"id":"W2494687620","doi":"10.4018/978-1-61520-777-0.ch004","title":"A Framework for Privacy Assurance and Ubiquitous Knowledge Discovery in Health 2.0 Data Mashups","year":2010,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Ottawa","funders":"","keywords":"Context (archaeology); Internet privacy; Data discovery; Computer science; Health care; Information privacy; Interoperability; The Internet; Knowledge management; World Wide Web; Data science; Metadata","score_opus":0.19467658823010572,"score_gpt":0.4370473413932036,"score_spread":0.2423707531630979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494687620","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013695598,0.0030168563,0.089490786,0.00309049,0.0029972717,0.0026299704,0.012291126,0.00010370432,0.88624287],"genre_scores_gemma":[0.105961256,0.0006881415,0.142983,0.013658655,0.0036008584,0.00029542405,0.0007822472,0.00029147105,0.7317389],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954389,0.00011427131,0.0013222805,0.0016427347,0.00093602046,0.00054579665],"domain_scores_gemma":[0.99382603,0.0015535993,0.0007419591,0.0035255922,0.00011540521,0.00023740286],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0043894206,0.00045072648,0.00095633493,0.00018034283,0.00018816882,0.0008830143,0.003241441,0.00050213595,0.00003083015],"category_scores_gemma":[0.002380754,0.00038194412,0.00012983999,0.00006517996,0.00027270717,0.0004702347,0.0030959125,0.0006260858,0.00015077772],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007031786,0.000027193491,0.00002187274,0.00015341431,0.000029226634,0.000010712822,0.00016861573,3.7668235e-7,5.926269e-7,0.90394056,0.02450992,0.07106722],"study_design_scores_gemma":[0.000224713,0.000054577748,0.00010345866,0.00030888373,0.000011235914,0.000004117488,0.00003357155,0.00002136698,8.549065e-7,0.52789146,0.47113106,0.00021470354],"about_ca_topic_score_codex":0.0001987122,"about_ca_topic_score_gemma":0.0054572844,"teacher_disagreement_score":0.44662115,"about_ca_system_score_codex":0.00013861137,"about_ca_system_score_gemma":0.0005690931,"threshold_uncertainty_score":0.99986327},"labels":[],"label_agreement":null},{"id":"W2506390062","doi":"10.4018/978-1-59904-857-4.ch055","title":"Statistical Data and Metadata Quality Assessment","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardization; Quality (philosophy); Product (mathematics); Summary statistics; Metadata; Data quality; Business; Computer science; Statistics; Service (business); Operations research; Marketing; Engineering; Mathematics; World Wide Web","score_opus":0.3882986246822918,"score_gpt":0.48040005689706244,"score_spread":0.09210143221477063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2506390062","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012174503,0.00030053197,0.05461511,0.00039110967,0.00045057855,0.00038246464,0.03651388,0.00006139038,0.90727276],"genre_scores_gemma":[0.03178431,0.0003415259,0.055328306,0.0065544248,0.0007007817,0.000026425509,0.0032466839,0.00009865193,0.9019189],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99301773,0.0002836757,0.0014182224,0.0018211717,0.0030836486,0.00037556633],"domain_scores_gemma":[0.99290895,0.001053709,0.0005765526,0.0049541327,0.00016834385,0.00033829416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004826953,0.00045236194,0.00096221326,0.00009939075,0.00022177795,0.000990346,0.003363178,0.00025477103,0.0003914826],"category_scores_gemma":[0.0010450613,0.00036384398,0.00009447405,0.000032942444,0.00053958985,0.00051532895,0.0058654463,0.0003603264,0.00047171157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016833903,0.000013829713,0.000025601414,0.000014284214,0.00009854401,0.00008621785,0.000012103398,1.4425018e-7,1.9252754e-7,0.7160561,0.23040403,0.05327213],"study_design_scores_gemma":[0.00018156906,0.00003094669,0.0008277284,0.000017523385,0.00007473873,0.000017489376,0.00003355242,0.00003420085,1.6229225e-7,0.43664697,0.5618711,0.00026401354],"about_ca_topic_score_codex":0.0003529735,"about_ca_topic_score_gemma":0.0006673017,"teacher_disagreement_score":0.33146706,"about_ca_system_score_codex":0.00012219994,"about_ca_system_score_gemma":0.00034314176,"threshold_uncertainty_score":0.9998813},"labels":[],"label_agreement":null},{"id":"W2512595308","doi":"10.14778/3067421.3067422","title":"Effective and complete discovery of order dependencies via set-based axiomatization","year":2017,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","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; University of Waterloo; York University; Ontario Tech University","funders":"","keywords":"Computer science; Tuple; Completeness (order theory); Inference; Axiom; Rule of inference; Functional dependency; Set (abstract data type); Data mining; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Relational database; Discrete mathematics","score_opus":0.10627989270277285,"score_gpt":0.36554846528466095,"score_spread":0.25926857258188807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512595308","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":[0.92862576,0.0005723568,0.044241324,0.0048176064,0.0018971969,0.00620824,0.0012669788,0.00007313653,0.012297385],"genre_scores_gemma":[0.9976421,0.00004405493,0.0016117803,0.000101327976,0.000037904534,0.00012380512,0.000017444943,0.000013441772,0.00040815343],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99652123,0.000064020365,0.00081908697,0.00064141577,0.0017498058,0.00020444182],"domain_scores_gemma":[0.9958264,0.00045310255,0.0022152902,0.0006880905,0.00076772046,0.000049363105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033594456,0.00027509505,0.0006356508,0.00025058165,0.00022286916,0.0005649687,0.0020778584,0.00011836934,0.000019704748],"category_scores_gemma":[0.002580051,0.00017196836,0.00018238943,0.00021983782,0.00041099906,0.0005211645,0.003889347,0.00020965181,0.0000060249936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023546412,0.003064084,0.08989029,0.023661176,0.0037959192,0.0000075752273,0.030185876,0.007448188,0.24226977,0.26579016,0.05540025,0.27613208],"study_design_scores_gemma":[0.003221047,0.00052344747,0.1476767,0.003035057,0.00080556545,0.000007890549,0.0041645863,0.019071246,0.25606704,0.5560165,0.0080988165,0.0013120841],"about_ca_topic_score_codex":0.0004662753,"about_ca_topic_score_gemma":0.000050521336,"teacher_disagreement_score":0.29022634,"about_ca_system_score_codex":0.00007165452,"about_ca_system_score_gemma":0.00006601547,"threshold_uncertainty_score":0.70126665},"labels":[],"label_agreement":null},{"id":"W2513414733","doi":"10.1109/sai.2016.7556026","title":"A density-based data cleaning approach for deduplication with data consistency and accuracy","year":2016,"lang":"en","type":"article","venue":"2016 SAI Computing Conference (SAI)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"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":"Data deduplication; Computer science; Data mining; Correctness; Data warehouse; Data quality; Tuple; Data transformation; Consistency (knowledge bases); Scalability; Data consistency; Data modeling; Data set; Database; Data integrity; Set (abstract data type); Algorithm; Artificial intelligence; Mathematics","score_opus":0.4115022651312117,"score_gpt":0.4283854050917017,"score_spread":0.016883139960490012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2513414733","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":[0.014512392,0.000051923984,0.9797456,0.002861469,0.00008974913,0.0006836994,0.0004597144,0.00010292497,0.001492521],"genre_scores_gemma":[0.8668959,0.000018147057,0.13111609,0.00081696175,0.00010599929,0.000009748591,0.0007391997,0.000016938882,0.00028098424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630404,0.0002699591,0.00065473065,0.0016257945,0.00074120826,0.00040429668],"domain_scores_gemma":[0.9903907,0.0038616701,0.0005871859,0.0044879694,0.00051156036,0.00016086888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005960433,0.00023516567,0.0003900812,0.00016158274,0.00042244923,0.00079732994,0.0035720363,0.000073668176,0.000037452115],"category_scores_gemma":[0.005022718,0.00014115394,0.000027634747,0.00028746124,0.00032829717,0.001227319,0.0026701784,0.000105327046,0.000073141724],"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":[0.00015468837,0.00015675755,0.0046562385,0.00008053494,0.00006318272,0.0000028741856,0.00020136464,0.000025111278,0.0003346727,0.045883235,0.045697197,0.9027441],"study_design_scores_gemma":[0.003913671,0.00028568244,0.0142469965,0.0006521974,0.00019038019,0.000025058649,0.0017046818,0.70244884,0.00026438886,0.010362208,0.26487845,0.001027402],"about_ca_topic_score_codex":0.00012059732,"about_ca_topic_score_gemma":0.00008011714,"teacher_disagreement_score":0.90171677,"about_ca_system_score_codex":0.000027007862,"about_ca_system_score_gemma":0.0003694673,"threshold_uncertainty_score":0.76886714},"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,"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":"W2525564411","doi":"10.18438/b85g9j","title":"Academic Librarians’ Knowledge of Bibliometrics and Altmetrics","year":2016,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Altmetrics; Bibliometrics; Library science; Sociology; Computer science; Data science","score_opus":0.14592259151478693,"score_gpt":0.4024911142746871,"score_spread":0.25656852275990016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525564411","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":[0.025772272,0.018389402,0.407741,0.4797753,0.0012849747,0.0013323962,0.00041364782,0.00033305972,0.06495793],"genre_scores_gemma":[0.81659585,0.07547784,0.024510013,0.079697795,0.0001771427,0.000033469467,0.000037625632,0.00001994686,0.003450296],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99748325,0.00048042645,0.000931471,0.00021859645,0.0007287899,0.00015748559],"domain_scores_gemma":[0.97460544,0.023826705,0.00079527294,0.00044092006,0.0001631337,0.00016855521],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0053149927,0.00011305244,0.00018752975,0.005559206,0.00010627422,0.00061298924,0.00057460257,0.00010427311,0.000364494],"category_scores_gemma":[0.04508016,0.00007059272,0.00003224149,0.012014753,0.00015475808,0.3784156,0.000498289,0.00014540937,0.00018387983],"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":[0.00017600288,0.000030956162,0.0022740858,0.000079459576,0.000009893604,6.4564875e-7,0.0001822893,0.0000031564311,0.000039447394,0.4242262,0.03742211,0.5355558],"study_design_scores_gemma":[0.00037935402,0.00013770032,0.01733608,0.00017032136,0.000019658295,0.000005101254,0.00065534626,0.00053286355,0.001179593,0.0034513539,0.9760121,0.000120496756],"about_ca_topic_score_codex":0.0000023018445,"about_ca_topic_score_gemma":1.2481273e-8,"teacher_disagreement_score":0.93859005,"about_ca_system_score_codex":0.000004892497,"about_ca_system_score_gemma":0.00015267955,"threshold_uncertainty_score":0.9629635},"labels":[],"label_agreement":null},{"id":"W2528898284","doi":"","title":"Record linkage for web data","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Toronto","funders":"","keywords":"Computer science; Record linkage; Linkage (software); Linked data; Relational database; Task (project management); Information retrieval; Process (computing); Set (abstract data type); Matching (statistics); Data mining; Database; World Wide Web; Semantic Web; Data science; Engineering; Programming language","score_opus":0.5393046271116645,"score_gpt":0.5347174130476245,"score_spread":0.004587214064039946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528898284","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042619808,0.00065346214,0.029265724,0.0018286097,0.017237607,0.00209588,0.0069847107,0.000204371,0.93746763],"genre_scores_gemma":[0.005819385,0.00009009452,0.012352406,0.00078922015,0.0007343859,0.00007186036,0.046999346,0.000029240879,0.93311405],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972281,0.00009066706,0.0007075516,0.00074950943,0.00096596446,0.0002582038],"domain_scores_gemma":[0.995344,0.0010619223,0.00036463054,0.002947559,0.00018626124,0.00009565866],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0061575687,0.00016780556,0.00032346457,0.00022081604,0.00011230423,0.00040517456,0.0036086696,0.00018142807,0.0053513865],"category_scores_gemma":[0.0030120623,0.00011948576,0.00009500762,0.00023897899,0.000014421825,0.000837237,0.0004281212,0.00011860605,0.0030952883],"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":[0.000022879285,0.000030704803,0.000019911695,0.00003323094,0.000017401742,2.5578842e-7,0.00006958194,3.7936154e-8,0.000013992458,0.008610937,0.66469425,0.3264868],"study_design_scores_gemma":[0.00013617602,0.000018496747,0.0014611384,0.000016137743,0.000050066392,9.982813e-8,0.0020530312,0.00022275414,0.000020430378,0.01176174,0.9840824,0.00017755112],"about_ca_topic_score_codex":0.00010528579,"about_ca_topic_score_gemma":0.0067881946,"teacher_disagreement_score":0.32630923,"about_ca_system_score_codex":0.000012539079,"about_ca_system_score_gemma":0.00008475109,"threshold_uncertainty_score":0.9976809},"labels":[],"label_agreement":null},{"id":"W2530130430","doi":"","title":"Data quality through active constraint discovery and maintenance","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Constraint (computer-aided design); Data integrity; Data quality; Data mining; Relation (database); Quality (philosophy); Set (abstract data type); Domain (mathematical analysis); Machine learning; Engineering; Mathematics; Database","score_opus":0.4121116768603989,"score_gpt":0.5156160078328202,"score_spread":0.10350433097242134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530130430","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04458545,0.0008627187,0.04586496,0.00283488,0.004438496,0.0012631951,0.018770108,0.00012104856,0.88125914],"genre_scores_gemma":[0.5507504,0.0006827387,0.004276696,0.0021913298,0.0003630344,0.000042135372,0.024822146,0.000040463092,0.41683105],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959001,0.00036201187,0.00089936994,0.0011315984,0.001366562,0.0003403679],"domain_scores_gemma":[0.9952402,0.0013044041,0.00064017787,0.0025512774,0.00016725884,0.000096641605],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005149002,0.00026889966,0.00054945267,0.000088860055,0.00014900633,0.00074208196,0.0019575015,0.00017347299,0.0011016318],"category_scores_gemma":[0.0033266153,0.00018124365,0.00007207514,0.00023001243,0.00021591308,0.0040027793,0.0008881636,0.00026347354,0.000324936],"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":[0.00019822399,0.00014821607,0.00014858514,0.0001043207,0.00013838829,0.0000050136573,0.002334108,2.597372e-7,0.000052685235,0.5801761,0.20593591,0.21075818],"study_design_scores_gemma":[0.00039941148,0.000026428483,0.07073952,0.00008735451,0.00009386389,0.0000029813132,0.08929137,0.000019115869,0.00014983542,0.11734957,0.7212433,0.00059724663],"about_ca_topic_score_codex":0.0010554667,"about_ca_topic_score_gemma":0.008204427,"teacher_disagreement_score":0.51530737,"about_ca_system_score_codex":0.000032957298,"about_ca_system_score_gemma":0.000112788584,"threshold_uncertainty_score":0.9998115},"labels":[],"label_agreement":null},{"id":"W2533963320","doi":"10.1186/s12911-016-0375-3","title":"Describing the linkages of the immigration, refugees and citizenship Canada permanent resident data and vital statistics death registry to Ontario’s administrative health database","year":2016,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":204,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"College of Physicians and Surgeons of Ontario; Ottawa Hospital; Canadian Institute for Health Information; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Health informatics; Refugee; Citizenship; Immigration; Health statistics; Database; Health services research; Official statistics; Nationality; Data science; Medicine; Public health; Political science; Computer science; Nursing; Environmental health; Law; Population","score_opus":0.2748628273168988,"score_gpt":0.42740360635392416,"score_spread":0.15254077903702534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2533963320","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":[0.36332515,0.00022090822,0.6313368,0.0028947631,0.00021344767,0.00036518648,0.0014724106,0.0000056748045,0.00016565133],"genre_scores_gemma":[0.91771,0.0002260605,0.077702686,0.0040817545,0.000041508803,0.0000063545604,0.000044776778,0.0000062132185,0.00018066535],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99588037,0.0002049449,0.0012221687,0.0002699288,0.00220954,0.00021307908],"domain_scores_gemma":[0.9909324,0.0069243284,0.00052906544,0.0011527966,0.00013972337,0.00032168708],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0064369733,0.0001363654,0.0002632047,0.00006754996,0.0004044852,0.00032860372,0.000990583,0.00004338361,0.00005872155],"category_scores_gemma":[0.010625935,0.000059264414,0.000015744234,0.00015425362,0.00022483173,0.00030203885,0.0021767062,0.0001508739,0.0000015546825],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013357545,0.000031869415,0.026009358,0.00019697602,0.000052185038,0.000020311105,0.008844078,0.000019008268,0.000004709281,0.053425055,0.3518594,0.5594035],"study_design_scores_gemma":[0.0052976077,0.00096016406,0.3463129,0.014076194,0.00023613163,0.0005134228,0.15074311,0.10626336,0.00009785522,0.13379197,0.2399453,0.0017619486],"about_ca_topic_score_codex":0.031738937,"about_ca_topic_score_gemma":0.7942245,"teacher_disagreement_score":0.76248556,"about_ca_system_score_codex":0.00007247046,"about_ca_system_score_gemma":0.0017325045,"threshold_uncertainty_score":0.99770796},"labels":[],"label_agreement":null},{"id":"W2537494674","doi":"10.1109/fskd.2016.7603389","title":"Characteristics and classification of big data in health care sector","year":2016,"lang":"en","type":"article","venue":"","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":"Concordia University","funders":"","keywords":"Big data; Context (archaeology); Health care; Service (business); Human services; Business; Knowledge management; Service provider; Data science; Computer science; Internet privacy; Marketing; Data mining","score_opus":0.4701924603207224,"score_gpt":0.4564716473466358,"score_spread":0.013720812974086616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537494674","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":[0.71783864,0.0004171027,0.19988948,0.05507602,0.0014408771,0.00092657754,0.0049053454,0.00006382702,0.019442113],"genre_scores_gemma":[0.9981298,0.000111240384,0.0005025402,0.00028459172,0.000024522962,0.0000011932336,0.00005059208,0.000001545318,0.00089400524],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99887985,0.000109177454,0.0003930654,0.00024043205,0.00030581982,0.00007164632],"domain_scores_gemma":[0.99863005,0.00029708428,0.00015131004,0.0008393159,0.000047933434,0.00003430385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002000258,0.000032929955,0.00011178986,0.00009647355,0.000016917451,0.00003313713,0.00044648972,0.0000144803835,0.00009795164],"category_scores_gemma":[0.0009301383,0.000017774099,0.000005366724,0.00014616168,0.000042843712,0.0002039154,0.00031786106,0.000015265068,0.000042897856],"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":[0.000009105656,0.000021818738,0.024871401,0.000027303866,0.0000016858855,2.470822e-7,0.0003845893,9.496891e-9,0.00020890465,0.018315064,0.012414152,0.94374573],"study_design_scores_gemma":[0.00018516963,0.00002822039,0.70648974,0.000022532846,9.5011666e-7,1.5432099e-7,0.001473226,0.00006125629,0.000028353867,0.0012319555,0.29043773,0.00004074343],"about_ca_topic_score_codex":0.00014359446,"about_ca_topic_score_gemma":0.0011788266,"teacher_disagreement_score":0.94370496,"about_ca_system_score_codex":0.000015295376,"about_ca_system_score_gemma":0.000039095212,"threshold_uncertainty_score":0.111352965},"labels":[],"label_agreement":null},{"id":"W2538383174","doi":"10.1145/2983323.2983326","title":"PARC","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Computer science; Key (lock); Process (computing); Data quality; Set (abstract data type); Focus (optics); Information privacy; Visualization; Data anonymization; Data mining; Computer security; Engineering","score_opus":0.3665018902815535,"score_gpt":0.4727680972124533,"score_spread":0.10626620693089978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2538383174","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009081283,0.000005373083,0.29288533,0.034665965,0.00026524573,0.000050771938,0.000010073638,0.000051727144,0.66298425],"genre_scores_gemma":[0.7599065,0.0000054816655,0.0011325805,0.0019278381,0.000027812444,0.0000020369912,2.49564e-7,0.0000011305011,0.23699638],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991439,0.00004555449,0.00014093428,0.00014215564,0.00045254471,0.00007488653],"domain_scores_gemma":[0.9990895,0.00042638025,0.000022638462,0.00039685093,0.000030117471,0.000034526824],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016570042,0.00002259329,0.00004313651,0.000040286377,0.00002333214,0.00006181327,0.00039007838,0.000007856511,0.011371997],"category_scores_gemma":[0.0009828747,0.0000086344435,0.000020966667,0.000106889456,0.000028575865,0.00022060113,0.00015138018,0.000006444743,0.016455848],"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":[0.0000011440626,0.0000053903323,0.00039621704,8.605734e-8,9.731607e-7,5.892783e-7,0.000008910731,2.8555414e-8,0.000102400125,0.24019825,0.37626088,0.38302514],"study_design_scores_gemma":[0.000063145395,0.0000060718694,0.0033560554,8.2149813e-7,3.9984738e-7,1.5024793e-7,0.000077155266,0.000002847889,0.0003374461,0.17534402,0.8207899,0.000022020082],"about_ca_topic_score_codex":0.000011502553,"about_ca_topic_score_gemma":0.000036371184,"teacher_disagreement_score":0.7508252,"about_ca_system_score_codex":0.000003847678,"about_ca_system_score_gemma":0.0000043475984,"threshold_uncertainty_score":0.98953176},"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":"W2544442953","doi":"10.1017/s1743921316002702","title":"That over-used and much abused 4-letter word: DATA","year":2015,"lang":"en","type":"article","venue":"Proceedings of the International Astronomical Union","topic":"Data Quality and Management","field":"Decision Sciences","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":"Dominion Astrophysical Observatory","funders":"","keywords":"Objectivity (philosophy); Optimal distinctiveness theory; Noun; Linguistics; Verb; Plural; Subjectivity; The Internet; Computer science; Conversation; Epistemology; Sociology; Psychology; World Wide Web; Philosophy; Social psychology","score_opus":0.2334190913761537,"score_gpt":0.3747928134479398,"score_spread":0.1413737220717861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544442953","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":[0.97475857,0.000009054576,0.0006248965,0.021439897,0.00059017685,0.00012394977,0.00007842384,0.000013252296,0.0023617945],"genre_scores_gemma":[0.996478,0.0000020855516,0.0016923735,0.000497184,0.00017511714,0.0000030733079,0.00002202671,0.0000054108764,0.0011246996],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981173,0.000019934518,0.0003359673,0.0003650258,0.0010452764,0.00011646152],"domain_scores_gemma":[0.99903905,0.00017114753,0.00023425712,0.00029724336,0.00018196437,0.0000763312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029154094,0.0000878187,0.00013493022,0.00009970625,0.000037162932,0.00021907683,0.0027170894,0.000034510416,0.000079853606],"category_scores_gemma":[0.001115071,0.000056791963,0.000038625632,0.00010762862,0.000118726464,0.0009879078,0.0024332309,0.00010931343,0.000030550345],"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":[0.0002215139,0.00019603524,0.21849234,0.000010445119,0.000115541196,2.0924148e-7,0.0005092882,0.000053424406,0.0027586003,0.045239475,0.7060008,0.026402319],"study_design_scores_gemma":[0.0018980321,0.000057641537,0.19403909,0.00007224268,0.00003241588,0.0000029969085,0.0020563866,0.012281531,0.004938075,0.040056035,0.74431044,0.00025513294],"about_ca_topic_score_codex":0.0000689412,"about_ca_topic_score_gemma":0.000022006589,"teacher_disagreement_score":0.03830962,"about_ca_system_score_codex":0.00005014894,"about_ca_system_score_gemma":0.000024017463,"threshold_uncertainty_score":0.5049073},"labels":[],"label_agreement":null},{"id":"W2544486974","doi":"10.14778/2994509.2994518","title":"Detecting data errors","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":237,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of California Berkeley","keywords":"Computer science; Raw data; Outlier; Data mining; Set (abstract data type); Variety (cybernetics); Data quality; Ground truth; Anomaly detection; Quality (philosophy); Big data; Data science; Machine learning; Artificial intelligence; Engineering","score_opus":0.30976099780462824,"score_gpt":0.41262294928917714,"score_spread":0.10286195148454891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2544486974","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":[0.8245145,0.00020489054,0.003952549,0.058244314,0.0024263745,0.0016782933,0.000400624,0.00019917605,0.108379275],"genre_scores_gemma":[0.99439347,0.00001976695,0.0012644703,0.00030697422,0.0000648686,0.000011581206,6.5930794e-7,0.0000073253163,0.003930863],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973492,0.000019714142,0.0005474916,0.0004984864,0.001347826,0.00023725697],"domain_scores_gemma":[0.9980723,0.0003440704,0.000466794,0.00086386176,0.00019223653,0.000060700644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00496573,0.00010763893,0.00018001643,0.000102775724,0.00013860654,0.00012181615,0.0041889576,0.000027374881,0.00018562136],"category_scores_gemma":[0.00501184,0.000046149242,0.000071275084,0.00042631655,0.00012405789,0.00078664353,0.0036942144,0.00005910585,0.00015150444],"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":[0.00007913954,0.00019482571,0.013919795,0.00005613091,0.00010709281,6.834094e-7,0.0009899496,0.0000023793123,0.086810105,0.07285151,0.2312869,0.5937015],"study_design_scores_gemma":[0.001125774,0.00011145139,0.009615254,0.00023926575,0.000070922404,0.00000861578,0.004676851,0.0001844982,0.18276016,0.13835426,0.6625121,0.00034083013],"about_ca_topic_score_codex":0.000045145218,"about_ca_topic_score_gemma":0.000018741684,"teacher_disagreement_score":0.59336066,"about_ca_system_score_codex":0.000038518217,"about_ca_system_score_gemma":0.000016787368,"threshold_uncertainty_score":0.77841955},"labels":[],"label_agreement":null},{"id":"W2548323776","doi":"10.1109/jcpc.2009.5420215","title":"The study and application of IMS Learning Design specifications in a mobile context","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Standardization; Software portability; Computer science; Implementation; Context (archaeology); Multimedia; Human–computer interaction; World Wide Web; Data science; Knowledge management; Software engineering; Programming language","score_opus":0.2655955715190111,"score_gpt":0.43201500241200147,"score_spread":0.16641943089299038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548323776","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":[0.21509275,0.00030927028,0.76722884,0.002270154,0.000034107805,0.002310391,0.000002128499,0.00003023855,0.0127221085],"genre_scores_gemma":[0.99811804,0.00003395417,0.0004612132,0.00006370873,0.0000042476877,0.00004690179,7.2811076e-7,8.8682685e-7,0.0012703105],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99891824,0.00024538225,0.00031627546,0.00016818002,0.00028982238,0.000062124825],"domain_scores_gemma":[0.9985918,0.0009161954,0.00009543386,0.00032751815,0.0000523401,0.000016708607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004214024,0.00003351428,0.00007867437,0.00006408988,0.00010552886,0.00009636406,0.00028387413,0.000009468944,0.000023283867],"category_scores_gemma":[0.0003904414,0.000019359195,0.000010446036,0.00032971747,0.000041946227,0.00011324483,0.00004559972,0.000042207714,0.000039058286],"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":[0.000014083752,0.00017593855,0.0023048418,2.8905163e-7,0.000002383959,1.4135617e-7,0.0017588036,0.000335577,0.00012570867,0.035306826,0.0010944195,0.95888096],"study_design_scores_gemma":[0.00089500507,0.00084475067,0.4176073,0.0000045938336,0.000010962118,6.243205e-7,0.22738706,0.016245333,0.00034440242,0.076071106,0.26043537,0.00015350002],"about_ca_topic_score_codex":0.000060541497,"about_ca_topic_score_gemma":0.00025696884,"teacher_disagreement_score":0.9587275,"about_ca_system_score_codex":0.000006450784,"about_ca_system_score_gemma":0.0000064098886,"threshold_uncertainty_score":0.14605051},"labels":[],"label_agreement":null},{"id":"W2549035799","doi":"10.14778/3007263.3007320","title":"Qualitative data cleaning","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":40,"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; Scripting language; Data quality; Data science; Analytics; Big data; Data mining; Qualitative property; Taxonomy (biology); Human error; Data analysis; Machine learning; Engineering; Reliability engineering","score_opus":0.49719438527572407,"score_gpt":0.5118316654115125,"score_spread":0.01463728013578841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2549035799","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":[0.5305543,0.00037204282,0.012773984,0.14685042,0.0029572733,0.0028874537,0.0015612461,0.000282114,0.30176115],"genre_scores_gemma":[0.9906567,0.000029674975,0.0020621761,0.00046064003,0.00006355929,0.0000140252905,0.0000019123615,0.000008211407,0.0067030974],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707395,0.000054203138,0.0006099861,0.00051712495,0.0015164987,0.00022823692],"domain_scores_gemma":[0.9975797,0.00075669464,0.000523128,0.0007999892,0.00027780829,0.00006266577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007971959,0.00011361256,0.00021056649,0.000098657794,0.00012307406,0.00012943112,0.0039916974,0.000025975121,0.00022627517],"category_scores_gemma":[0.0053848857,0.000048753016,0.00007263375,0.0004165528,0.00019017141,0.0009519894,0.0033566512,0.00005801426,0.00020923244],"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":[0.000074246906,0.00015256497,0.0012404068,0.000032946264,0.00009278326,3.3275384e-7,0.010124757,7.2548795e-7,0.019982668,0.44760528,0.38279852,0.13789476],"study_design_scores_gemma":[0.0011057628,0.00012199723,0.0027024832,0.00023299074,0.000056074652,0.0000031928748,0.046988912,0.00007014482,0.044552885,0.39121953,0.5126522,0.00029379534],"about_ca_topic_score_codex":0.00004059124,"about_ca_topic_score_gemma":0.000009891659,"teacher_disagreement_score":0.4601024,"about_ca_system_score_codex":0.000041729014,"about_ca_system_score_gemma":0.000019799001,"threshold_uncertainty_score":0.74176335},"labels":[],"label_agreement":null},{"id":"W2550374641","doi":"10.48550/arxiv.1611.06951","title":"Enforcing Relational Matching Dependencies with Datalog for Entity Resolution","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Datalog; Computer science; Relational database; Matching (statistics); Conjunctive query; Programming language; Semantics (computer science); Task (project management); Resolution (logic); Dependency theory (database theory); Theoretical computer science; Database; Process (computing); Data mining; Functional dependency; Mathematics","score_opus":0.30729618089979704,"score_gpt":0.2671823725150406,"score_spread":0.04011380838475642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2550374641","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":[0.20239167,0.000003322314,0.79428816,0.00023579878,0.00009476918,0.00013933961,0.00010839821,0.000037678805,0.0027008778],"genre_scores_gemma":[0.98598385,0.000009222201,0.0023022208,0.00007798555,0.000031811665,6.864911e-7,0.000026260197,0.0000048488546,0.011563119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998786,0.000091684065,0.00018472875,0.0004928687,0.00024334296,0.00020141403],"domain_scores_gemma":[0.99829066,0.00081336725,0.00016147325,0.00051526976,0.00015005129,0.000069172114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016729704,0.0000894544,0.00011718665,0.00017270376,0.00029987292,0.0000822198,0.0005464433,0.00004255845,0.00017877213],"category_scores_gemma":[0.00047029136,0.000060287635,0.00005885184,0.00036537976,0.00010803139,0.0017597235,0.0002569915,0.00004755269,0.00022857776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001697764,0.000028457187,0.004787704,0.0000064769724,0.000027471395,0.000018690234,0.00009530201,0.006027126,0.00014678792,0.9839524,0.002786128,0.0019537013],"study_design_scores_gemma":[0.0029173233,0.00021894755,0.03410638,0.0001097261,0.00010990166,0.000010148457,0.0028302737,0.019061262,0.00027358302,0.81022614,0.12956068,0.00057560764],"about_ca_topic_score_codex":0.000103551574,"about_ca_topic_score_gemma":0.0006803505,"teacher_disagreement_score":0.7919859,"about_ca_system_score_codex":0.00008893909,"about_ca_system_score_gemma":0.00004744871,"threshold_uncertainty_score":0.2937981},"labels":[],"label_agreement":null},{"id":"W2557720241","doi":"10.15353/joci.v12i3.3276","title":"Data Literacy defined pro populo: To read this article, please provide a little information","year":2016,"lang":"en","type":"article","venue":"The Journal of Community Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Literacy; Context (archaeology); Information literacy; Data science; Computer science; Sociology; Public relations; Political science; World Wide Web; Geography; Pedagogy","score_opus":0.23660703003835448,"score_gpt":0.42837699405994095,"score_spread":0.19176996402158647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557720241","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":[0.7868678,0.000034729215,0.1573331,0.04292443,0.00045373588,0.0007491406,0.00072936877,0.00004641041,0.010861294],"genre_scores_gemma":[0.9776579,0.000098177115,0.009592902,0.011516826,0.00008263875,0.0000044270682,0.000057544203,0.000008525069,0.0009810275],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99493366,0.001090295,0.0021972994,0.000019976409,0.001519034,0.00023970602],"domain_scores_gemma":[0.99096596,0.0034135126,0.0015377401,0.0029885604,0.0009022576,0.00019196233],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0235543,0.00013123776,0.0002735161,0.00033441102,0.000427888,0.0006606888,0.005369297,0.00004190849,0.00023022511],"category_scores_gemma":[0.01849109,0.00005966127,0.00006222047,0.0006223833,0.00014164318,0.010697165,0.0023144993,0.00043512048,0.0012516084],"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":[0.0003454648,0.00013947414,0.00015101137,0.000049182614,0.000048591133,4.3182814e-7,0.110441834,0.00007021913,0.000021652399,0.0030860424,0.31312025,0.57252586],"study_design_scores_gemma":[0.00085757225,0.0003526767,0.0018055819,0.00018526164,0.00006112874,0.000061787476,0.061277356,0.00079559954,0.00012979748,0.016958468,0.91735876,0.00015601428],"about_ca_topic_score_codex":0.00016545231,"about_ca_topic_score_gemma":0.00011029803,"teacher_disagreement_score":0.6042385,"about_ca_system_score_codex":0.00006385246,"about_ca_system_score_gemma":0.00013654049,"threshold_uncertainty_score":0.999526},"labels":[],"label_agreement":null},{"id":"W2557723918","doi":"10.15353/joci.v12i3.3274","title":"Data Literacy - What is it and how can we make it happen?","year":2016,"lang":"en","type":"article","venue":"The Journal of Community Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Literacy; Context (archaeology); Information literacy; The Internet; Computer science; Data science; Internet privacy; Political science; World Wide Web; Sociology; Geography; Pedagogy","score_opus":0.31089620332430623,"score_gpt":0.43750529438792857,"score_spread":0.12660909106362234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2557723918","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":[0.25559843,0.0004546955,0.027393524,0.7111325,0.0005284476,0.00021838823,0.00060654624,0.000010723448,0.004056727],"genre_scores_gemma":[0.944942,0.015599467,0.0017124596,0.033444334,0.000083769395,5.403621e-7,0.000016301812,0.000008793257,0.004192309],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99664414,0.0010292986,0.0009508945,0.000020288691,0.0011778652,0.00017754301],"domain_scores_gemma":[0.9912884,0.004430473,0.0011582512,0.0026290428,0.0003738576,0.0001199683],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.020470047,0.000116878604,0.00027346346,0.00017597678,0.00045856257,0.0017156448,0.005324927,0.0000381127,0.00019605715],"category_scores_gemma":[0.0018852653,0.00005146019,0.000045750327,0.00022938242,0.00024286567,0.0067589614,0.0030154474,0.00046296534,0.000087286215],"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":[0.000031821415,0.000036159534,0.000031164036,0.00002406642,0.000049481605,5.349541e-7,0.12958726,0.0000020833475,0.0000043017644,0.00036252366,0.40323833,0.46663228],"study_design_scores_gemma":[0.00034843176,0.00008525853,0.00017886907,0.00021531669,0.000036142243,0.000067397326,0.2859264,0.00019761985,0.000017710194,0.011618487,0.7012393,0.000069065165],"about_ca_topic_score_codex":0.000026252988,"about_ca_topic_score_gemma":0.00024732476,"teacher_disagreement_score":0.6893436,"about_ca_system_score_codex":0.000023449067,"about_ca_system_score_gemma":0.00006187652,"threshold_uncertainty_score":0.9993207},"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":"W2560772377","doi":"10.5281/zenodo.1118394","title":"The Picasso Project","year":2016,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Metadata; Computer science; Metadata repository; Metadata management; Meta Data Services; RDF; Linked data; World Wide Web; Data dictionary; Data element; Data mapping; Database; Information retrieval; Semantic Web","score_opus":0.4956699751435978,"score_gpt":0.4794309033703781,"score_spread":0.016239071773219704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560772377","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036558203,0.00028204918,0.00020110334,0.03242635,0.0005672806,0.001015165,0.67523205,0.00020707757,0.28970334],"genre_scores_gemma":[0.39294574,0.000050596376,0.00037272868,0.006124979,0.0011065941,0.0012617916,0.018958377,0.000045325334,0.57913387],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987204,0.00011095217,0.00018786613,0.00020173514,0.000624602,0.00015442619],"domain_scores_gemma":[0.99705046,0.0020627184,0.00008427768,0.00067463017,0.00009819037,0.00002969034],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00072639994,0.000048538863,0.00005796582,0.000034434815,0.00017145358,0.00030814123,0.0010029366,0.000019462208,0.14779347],"category_scores_gemma":[0.018113313,0.000017373892,0.00004599751,0.00020976645,0.0000100662455,0.00023123485,0.00040017776,0.000027949312,0.06288557],"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":[0.0000020478444,0.0000034303544,0.000006397965,9.613783e-7,0.000002122313,0.0000015090245,0.000019042336,2.798316e-8,0.0000041333237,0.001036235,0.82848406,0.17044005],"study_design_scores_gemma":[0.000067897716,0.0000087702065,0.0014137714,0.00006041235,6.377084e-7,5.9658004e-7,0.00008894342,0.0000053044073,0.00007393327,0.004545852,0.9936918,0.00004209489],"about_ca_topic_score_codex":0.000002188911,"about_ca_topic_score_gemma":0.00003351905,"teacher_disagreement_score":0.65627366,"about_ca_system_score_codex":0.000012237755,"about_ca_system_score_gemma":0.000025198291,"threshold_uncertainty_score":0.99015754},"labels":[],"label_agreement":null},{"id":"W2564027179","doi":"10.1609/aaai.v30i1.9880","title":"Ontology Instance Linking: Towards Interlinked Knowledge Graphs","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Coreference; Identifier; Ontology; Information retrieval; Semantic Web; Linked data; Entity linking; Unique identifier; Data mining; Data science; Artificial intelligence; Resolution (logic); Knowledge base; Programming language","score_opus":0.33435980493086737,"score_gpt":0.424342706670221,"score_spread":0.08998290173935364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2564027179","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":[0.6130912,0.0002411726,0.041309487,0.053687487,0.0049477625,0.0016941164,0.00012265418,0.00030018628,0.28460595],"genre_scores_gemma":[0.9952952,0.00011788487,0.00049514166,0.0004423533,0.00007272774,0.000029437586,5.5815957e-7,0.000012589298,0.0035340916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99625427,0.000085075386,0.0012869474,0.0008221805,0.0010969711,0.0004545511],"domain_scores_gemma":[0.99640554,0.00058239786,0.0007626267,0.00065228844,0.001467608,0.00012953745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003403233,0.00027303214,0.00046902406,0.000339419,0.00021238868,0.00029542917,0.0039449385,0.00014020933,0.0006065754],"category_scores_gemma":[0.004784199,0.00014291599,0.00022946877,0.0010939527,0.00091946364,0.00058847794,0.00091201026,0.00025368755,0.0009550352],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096179545,0.00011822587,0.00020273529,0.000012083352,0.000012839349,2.992087e-7,0.00092349347,5.052157e-7,0.007129192,0.63792074,0.0010518255,0.3525319],"study_design_scores_gemma":[0.00005629063,0.00021186736,0.0005757938,0.00039880225,0.000014600143,0.0000020876823,0.0016737246,0.00054066227,0.13959004,0.84625286,0.01045547,0.00022782334],"about_ca_topic_score_codex":0.000037087608,"about_ca_topic_score_gemma":0.00020538311,"teacher_disagreement_score":0.38220406,"about_ca_system_score_codex":0.00006561022,"about_ca_system_score_gemma":0.0001303933,"threshold_uncertainty_score":0.99982285},"labels":[],"label_agreement":null},{"id":"W2565866388","doi":"10.1109/dsaa.2016.91","title":"Meeting Health Care Research Needs in a Kimball Integrated Data Warehouse","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Data warehouse; Business intelligence; Strengths and weaknesses; Data science; Computer science; Health care; Knowledge management; Process management; Business; Data mining; Psychology","score_opus":0.7122640670249207,"score_gpt":0.5932049366698655,"score_spread":0.11905913035505522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565866388","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":[0.15587868,0.0025883487,0.09416255,0.38096517,0.0019113772,0.0038534268,0.002745934,0.0008791997,0.3570153],"genre_scores_gemma":[0.97724396,0.00015279965,0.0033689805,0.0021206983,0.00005963139,0.000015057751,0.00010490243,0.000014276876,0.016919672],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99475694,0.0014453034,0.0007283906,0.0006684229,0.0018643927,0.0005365532],"domain_scores_gemma":[0.9947906,0.002102876,0.00009634515,0.0025235391,0.0003277571,0.00015884143],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.026422758,0.000096295276,0.00023075838,0.0009032372,0.00015538826,0.00031568465,0.003315451,0.00004415415,0.00069286925],"category_scores_gemma":[0.009325431,0.00004906701,0.000023289867,0.0022278614,0.00012651422,0.00080574653,0.0028184594,0.00017265376,0.0012721228],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000286233,0.0000705458,0.00174429,0.000011489345,0.0000054081206,0.0000083922,0.0036987136,0.000002687222,0.000032519543,0.013919577,0.57516104,0.40531674],"study_design_scores_gemma":[0.00045977562,0.000080325255,0.0012552241,0.00010794977,8.044841e-7,5.6465e-7,0.06761966,0.00017147086,0.00006446948,0.0030373975,0.9270949,0.000107476175],"about_ca_topic_score_codex":0.0074113808,"about_ca_topic_score_gemma":0.031066854,"teacher_disagreement_score":0.8213653,"about_ca_system_score_codex":0.0001812767,"about_ca_system_score_gemma":0.0002912934,"threshold_uncertainty_score":0.9995055},"labels":[],"label_agreement":null},{"id":"W2565966619","doi":"10.1109/cbi.2016.9","title":"ELM: An Extended Logic Matching Method on Record Linkage Analysis of Disparate Databases for Profiling Data Mining","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Data mining; Probabilistic logic; Profiling (computer programming); Data deduplication; Matching (statistics); Identifier; Artificial intelligence; Machine learning; Database; Mathematics; Statistics","score_opus":0.5979240502219576,"score_gpt":0.5597760552806768,"score_spread":0.03814799494128085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2565966619","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":[0.036212485,0.000013212014,0.95837545,0.0007335524,0.0001642766,0.00030938548,0.0027571663,0.0000460598,0.0013883797],"genre_scores_gemma":[0.07077489,0.000030271045,0.9236903,0.00077207555,0.000062028535,0.000025046764,0.0010931959,0.0000124951,0.0035396516],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962002,0.0005968623,0.0009622043,0.0011337203,0.00081820047,0.00028878296],"domain_scores_gemma":[0.99006927,0.005924895,0.00049594877,0.0032577142,0.00014586336,0.0001062944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014454034,0.0001632156,0.0005591598,0.0006234299,0.0001467001,0.00017226115,0.002116387,0.00003661717,0.00060267124],"category_scores_gemma":[0.0043384703,0.00008673939,0.00012700117,0.0010302941,0.000055146247,0.0015691471,0.0010116493,0.000047435296,0.000040329654],"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":[0.0002743911,0.0003254108,0.0011331545,0.00003301772,0.0006164503,0.000005295129,0.00022615318,0.00030258726,0.0050936677,0.092718646,0.007908868,0.89136237],"study_design_scores_gemma":[0.0043173325,0.0017794828,0.021051792,0.00048387752,0.004864139,0.0000029770338,0.03032524,0.5078593,0.035291906,0.20585075,0.18562132,0.002551902],"about_ca_topic_score_codex":0.00016849276,"about_ca_topic_score_gemma":0.0010007722,"teacher_disagreement_score":0.88881046,"about_ca_system_score_codex":0.000015545374,"about_ca_system_score_gemma":0.000030452946,"threshold_uncertainty_score":0.6598828},"labels":[],"label_agreement":null},{"id":"W257370745","doi":"10.1007/978-3-642-38457-8_4","title":"Move Pruning and Duplicate Detection","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Pruning; Computer science; Heuristic; Conjunction (astronomy); Simple (philosophy); State (computer science); Artificial intelligence; Machine learning; Data mining; Algorithm","score_opus":0.07483745370710014,"score_gpt":0.329650977274377,"score_spread":0.2548135235672768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W257370745","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":[0.00048339178,0.00017016112,0.9858318,0.0008211545,0.00084897724,0.00034560502,0.0000064638575,0.00004699149,0.011445428],"genre_scores_gemma":[0.8216088,0.00019899156,0.1511018,0.0076909866,0.0009879187,0.00003823767,0.00001222757,0.00006871874,0.018292328],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963361,0.000044842727,0.00054210855,0.0013082272,0.0014226654,0.0003460631],"domain_scores_gemma":[0.9973851,0.0008908618,0.0003104945,0.001079661,0.0002050491,0.00012886872],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030550242,0.00027339158,0.00035787807,0.0007604025,0.00024946185,0.0011651516,0.0015929688,0.00017240323,0.00015869232],"category_scores_gemma":[0.0005740618,0.00020957139,0.000058341866,0.0004377422,0.00070445536,0.00066610717,0.0015123237,0.00041826203,0.00036733373],"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":[0.000002592218,0.000004983262,0.000013993133,0.000007639911,0.0000034911357,0.000006211754,0.00023364325,0.0014691707,0.00010041675,0.0058882926,0.00009440849,0.99217516],"study_design_scores_gemma":[0.00018332704,0.000109933055,0.0010452975,0.00012830934,0.0000099348135,0.00002382101,0.0000018376526,0.15834357,0.00089990534,0.77422065,0.06450952,0.00052390574],"about_ca_topic_score_codex":0.000066767214,"about_ca_topic_score_gemma":0.00015421928,"teacher_disagreement_score":0.99165124,"about_ca_system_score_codex":0.00008816569,"about_ca_system_score_gemma":0.00006822636,"threshold_uncertainty_score":0.99987173},"labels":[],"label_agreement":null},{"id":"W2574540012","doi":"10.1101/094888","title":"DataMed: Finding useful data across multiple biomedical data repositories","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; University of California, San Diego; National Institute of Environmental Health Sciences; University of California, Los Angeles; University of Manchester; Yale University; European Bioinformatics Institute; Arizona State University; McGill University; National Institute of Diabetes and Digestive and Kidney Diseases; Johns Hopkins University; Purdue University; School of Medicine, New York University; National Institutes of Health; Universitair Medisch Centrum Groningen; GlaxoSmithKline","keywords":"Metadata; Interoperability; Computer science; Big data; Data science; Data discovery; World Wide Web; Knowledge extraction; Service (business); Reusability; Information retrieval; Data mining; Software","score_opus":0.23407611614065013,"score_gpt":0.4000028326354582,"score_spread":0.16592671649480809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574540012","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":[0.43101677,0.002528868,0.18015842,0.009702867,0.040861417,0.0037135074,0.32969165,0.0022355926,0.00009090672],"genre_scores_gemma":[0.9771331,0.0003494918,0.017738776,0.00062128756,0.0035329007,0.00010053671,0.00022038732,0.00018167915,0.00012186467],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98574513,0.00084206014,0.0024021089,0.0056634643,0.003980102,0.0013671207],"domain_scores_gemma":[0.9608285,0.0022120741,0.0017214146,0.03377285,0.00071394315,0.00075126183],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.018756185,0.00089481816,0.001287861,0.00049083406,0.0007540468,0.0034189117,0.026201155,0.000810073,0.00014596149],"category_scores_gemma":[0.02756528,0.00070723443,0.00014198742,0.0013505563,0.00088942965,0.0033304694,0.06736136,0.0011009924,0.0011296],"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":[0.00032983095,0.0014766718,0.06605769,0.0010281821,0.0016263401,0.0012514496,0.00018697158,0.0000075362063,0.13687977,0.0040787198,0.7865837,0.00049309264],"study_design_scores_gemma":[0.0009275402,0.00003676572,0.04116811,0.00058661454,0.0001532872,6.5739975e-8,0.000068912,0.0014024937,0.0052606734,0.000057596608,0.9490032,0.0013347056],"about_ca_topic_score_codex":0.00023769069,"about_ca_topic_score_gemma":0.00006326786,"teacher_disagreement_score":0.5461163,"about_ca_system_score_codex":0.00024031044,"about_ca_system_score_gemma":0.00094562926,"threshold_uncertainty_score":0.99964815},"labels":[],"label_agreement":null},{"id":"W2579288502","doi":"","title":"Record linkage procedures to detect cardiovascular endpoints in follow-up studies","year":2002,"lang":"en","type":"article","venue":"BOA (University of Milano-Bicocca)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linkage (software); Record linkage; Medicine; Internal medicine; Biology; Genetics; Environmental health","score_opus":0.18828756166085972,"score_gpt":0.3266984085877627,"score_spread":0.138410846926903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579288502","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":[0.9666566,0.0034999487,0.006284011,0.0034509208,0.00080001494,0.0009548446,0.00012986764,0.000115262956,0.018108506],"genre_scores_gemma":[0.971207,0.0015506085,0.006291889,0.00042225866,0.00005605752,0.0000024073813,0.0000066242565,0.000015419546,0.020447694],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708176,0.00031128083,0.0003617881,0.0007060521,0.0011863173,0.0003528219],"domain_scores_gemma":[0.9980604,0.00038366756,0.00016002405,0.0010306534,0.00021753508,0.00014772663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024379634,0.00018807498,0.0006598011,0.0006457108,0.00020210168,0.000049806295,0.0013007781,0.00009307129,0.0005329698],"category_scores_gemma":[0.0017519111,0.00019265137,0.0004036728,0.0010791671,0.0001406519,0.00046907488,0.0008183435,0.0001418972,0.00077452516],"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":[0.00036902778,0.00030581825,0.0070314296,0.000303297,0.0012507455,0.00057657924,0.02590278,0.00044227275,0.00069357554,0.001110802,0.49038357,0.47163013],"study_design_scores_gemma":[0.0031301351,0.00039735602,0.04149347,0.00026124818,0.00021381085,0.0000072915063,0.058369763,0.00033154158,0.00037534168,0.006354359,0.888352,0.0007137056],"about_ca_topic_score_codex":0.000543216,"about_ca_topic_score_gemma":0.007923968,"teacher_disagreement_score":0.47091642,"about_ca_system_score_codex":0.000092894035,"about_ca_system_score_gemma":0.000028302582,"threshold_uncertainty_score":0.99552125},"labels":[],"label_agreement":null},{"id":"W2583699183","doi":"","title":"Data Ingestion for the Connected World.","year":2017,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ingestion; Medicine","score_opus":0.9484017230905639,"score_gpt":0.6713623530691826,"score_spread":0.27703937002138135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2583699183","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":[0.005522109,0.0006263262,0.45330533,0.1717604,0.010070287,0.016485639,0.1798762,0.00026783245,0.16208589],"genre_scores_gemma":[0.9747884,0.000066857734,0.00028932886,0.00016640042,0.00048526344,0.0002847146,0.00710516,0.000018046507,0.01679582],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99250394,0.0013980637,0.00087368884,0.0015515607,0.003095837,0.000576882],"domain_scores_gemma":[0.94324183,0.0155006265,0.0010446927,0.03154089,0.008521804,0.0001501352],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.060575463,0.00018046139,0.0003630426,0.0006285084,0.0026699193,0.007006608,0.02731622,0.00007358223,0.0002100638],"category_scores_gemma":[0.07575348,0.00010639686,0.000017336664,0.0016988615,0.0010721635,0.0024670889,0.0123276105,0.000597105,0.00078612217],"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":[0.00010513038,0.000038574115,0.00013999092,0.000021646012,0.000040798033,0.0000025329525,0.00006615131,0.0000017330412,0.00003463729,0.43471894,0.48719916,0.07763071],"study_design_scores_gemma":[0.00047053254,0.000094809686,0.0040212222,0.00017026968,0.000006161026,0.0000012349255,0.0036828965,0.06365814,0.00003278553,0.011803441,0.91589785,0.00016064102],"about_ca_topic_score_codex":0.0010904167,"about_ca_topic_score_gemma":0.0021297482,"teacher_disagreement_score":0.9692663,"about_ca_system_score_codex":0.0000614393,"about_ca_system_score_gemma":0.00044243576,"threshold_uncertainty_score":0.9999919},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2591159053","doi":"10.1515/jos-2017-0006","title":"Three Methods for Occupation Coding Based on Statistical Learning","year":2017,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":51,"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":"Social Sciences and Humanities Research Council of Canada","keywords":"Coding (social sciences); Computer science; Respondent; Statistical learning; German; Artificial intelligence; Machine learning; Data mining; Statistics; Mathematics; Geography","score_opus":0.35728536526680754,"score_gpt":0.5651666475921359,"score_spread":0.20788128232532832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591159053","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":[0.00026066467,0.0000053977856,0.99676955,0.00060897943,0.00111511,0.00013524278,0.00036793255,0.0000054044194,0.0007317331],"genre_scores_gemma":[0.10454293,0.0000060605453,0.89470845,0.00023265662,0.00037022363,0.0000018842442,0.000021231785,0.000011078139,0.00010544701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742734,0.00030253208,0.00089888886,0.00017937704,0.0010037246,0.00018811226],"domain_scores_gemma":[0.98932046,0.007918413,0.0016032831,0.00035131804,0.00069189334,0.00011463132],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01040329,0.00010481091,0.00034222947,0.00018565689,0.00068196753,0.0007745995,0.00076760934,0.000049952916,0.00017359667],"category_scores_gemma":[0.06395116,0.00008033809,0.000081656224,0.00006545061,0.00011166413,0.0002428289,0.00008340097,0.00023155897,0.000023678806],"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":[0.00052951474,0.0000975878,0.0007651415,0.000014502037,0.00002205814,0.00001952762,0.00006392911,0.003454657,0.000023446906,0.19653015,0.04512209,0.7533574],"study_design_scores_gemma":[0.001402793,0.0014546851,0.040389832,0.000057896435,0.000111047244,0.0000033936578,0.00022193548,0.5142961,0.00010839626,0.26150846,0.18023211,0.0002133708],"about_ca_topic_score_codex":0.00002211103,"about_ca_topic_score_gemma":0.00009711389,"teacher_disagreement_score":0.753144,"about_ca_system_score_codex":0.000056434557,"about_ca_system_score_gemma":0.00014970679,"threshold_uncertainty_score":0.9439336},"labels":[],"label_agreement":null},{"id":"W2591700809","doi":"10.14778/3137628.3137631","title":"HoloClean","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":454,"is_retracted":false,"has_abstract":true,"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; Defense Advanced Research Projects Agency","keywords":"Leverage (statistics); Computer science; Probabilistic logic; Inference; Tuple; Data mining; Statistical model; Machine learning; Artificial intelligence; Mathematics","score_opus":0.22842113719041443,"score_gpt":0.4286142488382545,"score_spread":0.20019311164784007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2591700809","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":[0.581025,0.00004108088,0.000087839646,0.024449741,0.0010436918,0.00057143305,0.000028283312,0.000039192495,0.39271373],"genre_scores_gemma":[0.9901442,0.000014291614,0.0004617177,0.0003847261,0.000059751605,0.000012974079,2.2077373e-7,0.000005049163,0.008917073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979413,0.000008699308,0.00038580198,0.00029643648,0.0011827187,0.00018502654],"domain_scores_gemma":[0.99826056,0.000067055895,0.0006783588,0.00073050876,0.00020838475,0.000055133634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028892548,0.00009153604,0.00017483621,0.00006363964,0.00048777726,0.00057495205,0.0038197737,0.000025606552,0.00013652032],"category_scores_gemma":[0.0026008012,0.00005030314,0.00012403652,0.0001049913,0.00022738478,0.0005424615,0.0018964281,0.00007774967,0.00016891785],"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":[0.000058013004,0.00023263598,0.03047157,0.000045969504,0.000069661015,9.3672304e-7,0.0012200383,0.000004676824,0.008127528,0.49477202,0.33836237,0.12663458],"study_design_scores_gemma":[0.0007907638,0.00009693258,0.1417979,0.00007219232,0.000042830896,0.000004126095,0.0026405826,0.000100045116,0.08212352,0.28274205,0.48936182,0.00022724316],"about_ca_topic_score_codex":0.000084885505,"about_ca_topic_score_gemma":0.000009997489,"teacher_disagreement_score":0.4091192,"about_ca_system_score_codex":0.000022835353,"about_ca_system_score_gemma":0.000010587316,"threshold_uncertainty_score":0.7098153},"labels":[],"label_agreement":null},{"id":"W2603227181","doi":"10.35502/jcswb.39","title":"Data opportunities and risks: the dynamic of public, personal, and commercial interest","year":2017,"lang":"en","type":"article","venue":"Journal of Community Safety and Well-Being","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Government of Saskatchewan","funders":"","keywords":"Public interest; Business; Internet privacy; Risk analysis (engineering); Computer science; Political science","score_opus":0.5241872281998107,"score_gpt":0.4611656499565048,"score_spread":0.0630215782433059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603227181","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":[0.9272322,0.0007070919,0.0032304928,0.059298642,0.0002486921,0.000097760996,0.00011971858,0.000004145686,0.009061234],"genre_scores_gemma":[0.9915111,0.007534705,0.00014319697,0.00060277263,0.000041856416,1.9422734e-7,0.000011614376,0.0000046673167,0.00014987985],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99712473,0.001431697,0.00072552817,0.00009826575,0.00047712796,0.00014266798],"domain_scores_gemma":[0.9946916,0.0025878632,0.0010693704,0.0013191752,0.00020615537,0.0001258502],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.018850144,0.000113330745,0.00036090522,0.00014378804,0.0020474414,0.00096245884,0.0025661672,0.000047793837,0.000043811004],"category_scores_gemma":[0.0024909268,0.000071149356,0.000047014768,0.00005176859,0.0010529801,0.0018770617,0.0036411632,0.0006253728,0.0000010989351],"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":[0.0003078849,0.00018061133,0.012804761,0.00009157302,0.00027462663,0.000018500026,0.018527534,0.0000016279605,0.00001938809,0.035237625,0.007732424,0.92480344],"study_design_scores_gemma":[0.0012088206,0.00028820828,0.45213246,0.00024696757,0.00015885125,0.00016804422,0.11400769,0.0016038931,0.0000071113404,0.06841421,0.36156228,0.00020146114],"about_ca_topic_score_codex":0.00042520274,"about_ca_topic_score_gemma":0.0022492635,"teacher_disagreement_score":0.924602,"about_ca_system_score_codex":0.000010443171,"about_ca_system_score_gemma":0.000045615616,"threshold_uncertainty_score":0.9992518},"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":"W2606005405","doi":"10.23889/ijpds.v1i1.101","title":"Privacy-Preserving Record Linkage: An international collaboration between Canada, Australia and Wales","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Record linkage; Linkage (software); Bloom filter; Computer science; Quality (philosophy); General partnership; Probabilistic logic; Data quality; Scale (ratio); Data mining; Data science; Business; Environmental health; Medicine; Geography; Marketing; Artificial intelligence","score_opus":0.4574532106082225,"score_gpt":0.5592249468859519,"score_spread":0.1017717362777294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606005405","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":[0.947947,0.0000071965796,0.018423684,0.020073842,0.0099173905,0.0002891076,0.002872268,0.000015951546,0.000453563],"genre_scores_gemma":[0.98512787,0.000024589906,0.011446783,0.00020623204,0.0010513338,0.000004182325,0.00077336293,0.0000064333726,0.0013592303],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9950315,0.000090418005,0.000833656,0.0007099393,0.0030871779,0.00024733163],"domain_scores_gemma":[0.995011,0.00030383762,0.0011203722,0.0016617996,0.0016469425,0.00025608754],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.007205537,0.00013105755,0.00017207827,0.00037773073,0.0016032786,0.0083158575,0.012490058,0.00004428569,0.00019734514],"category_scores_gemma":[0.016199194,0.00011273362,0.00002818234,0.00018200783,0.0002251203,0.018277362,0.0027867204,0.00016005803,0.000012534822],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084813226,0.000052707488,0.72801757,0.000005408912,0.00007465884,0.000018042972,0.00022961701,0.00022609945,0.0002584015,0.020990886,0.05343196,0.19660984],"study_design_scores_gemma":[0.00037540734,0.000029112192,0.7426515,0.000027072148,0.000012172812,0.000012874874,0.00026947758,0.015035237,0.00004297481,0.016793024,0.22459845,0.00015269143],"about_ca_topic_score_codex":0.084571175,"about_ca_topic_score_gemma":0.23820555,"teacher_disagreement_score":0.19645715,"about_ca_system_score_codex":0.00024755095,"about_ca_system_score_gemma":0.000364012,"threshold_uncertainty_score":0.9996965},"labels":[],"label_agreement":null},{"id":"W2606083779","doi":"10.23889/ijpds.v1i1.165","title":"A review of a standards-based set of information security practices applied in Data Linkage Centers","year":2017,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linkage (software); Record linkage; Confidentiality; Business; Standardization; Population; Public relations; Knowledge management; Internet privacy; Computer security; Computer science; Political science; Medicine; Environmental health; Law","score_opus":0.657427594685601,"score_gpt":0.6472529292939032,"score_spread":0.010174665391697757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606083779","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000045139345,0.8737138,0.023270985,0.0015824116,0.003428091,0.0021124505,0.09513119,0.000011553596,0.0007450272],"genre_scores_gemma":[0.00021541986,0.9802835,0.0032787146,0.00023242722,0.00012838322,0.000013912458,0.015829334,0.000006944603,0.000011368841],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990047,0.0002968235,0.003429453,0.00066978246,0.0053333547,0.00022362759],"domain_scores_gemma":[0.97831327,0.0011284127,0.014814632,0.0035937026,0.0020437932,0.00010616496],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051425226,0.00021802833,0.0010841534,0.0015082839,0.0001999941,0.001081229,0.020139633,0.00008479919,0.000081151935],"category_scores_gemma":[0.061502397,0.00016231633,0.00016292812,0.00079773983,0.00028838837,0.012435411,0.003313103,0.00032204084,0.00000998492],"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":[0.000045580662,0.000057092053,0.00003370227,0.009835576,0.000049844504,0.0000017210378,0.000046211346,0.0000156479,1.267416e-7,0.0026058482,0.021284528,0.9660241],"study_design_scores_gemma":[0.00032429452,0.000019013318,0.000060726223,0.029577306,0.00011399667,0.000011470631,0.000056645258,0.0024213253,3.248441e-7,0.0011125669,0.96615976,0.00014258131],"about_ca_topic_score_codex":0.00023450339,"about_ca_topic_score_gemma":0.00022125315,"teacher_disagreement_score":0.9658815,"about_ca_system_score_codex":0.0002543085,"about_ca_system_score_gemma":0.0019399184,"threshold_uncertainty_score":0.9999558},"labels":[],"label_agreement":null},{"id":"W2606367575","doi":"10.7939/r3183481s","title":"University of Alberta Service and Academic Unit Responses to Panel Discussion on Coordinating Research Data Practices and Infrastructure","year":2012,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Unit (ring theory); Business; Service (business); Public relations; Operations management; Engineering management; Marketing; Political science; Engineering; Psychology; Mathematics education","score_opus":0.329703113892229,"score_gpt":0.4142972109465452,"score_spread":0.0845940970543162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606367575","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":[0.9632353,0.00005050289,0.000066033324,0.027348453,0.000047479694,0.0002098032,0.00010339659,0.000009072656,0.008929938],"genre_scores_gemma":[0.97136426,0.00019887251,0.0023212717,0.00036143383,0.000027675338,2.8042349e-8,0.00009583976,0.000008367968,0.025622271],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99748844,0.00092039065,0.00018800712,0.00047985325,0.0006728705,0.00025041224],"domain_scores_gemma":[0.99207956,0.0062840674,0.00037202062,0.0009188772,0.00009063543,0.00025484615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021949164,0.00011139494,0.00023359095,0.00044187348,0.00035063503,0.000056592922,0.0018052105,0.000118639175,0.00046776395],"category_scores_gemma":[0.002952835,0.00009064949,0.000019609668,0.0009358381,0.00027096109,0.004749281,0.005411924,0.0003222756,0.00004232786],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050820666,0.000321367,0.53522635,0.00034317447,0.00017368373,0.000022113452,0.11017713,0.000042479645,0.000859485,0.030204948,0.2690635,0.048483722],"study_design_scores_gemma":[0.0005283205,0.00013925982,0.27453715,0.00015101366,0.000042450018,0.0000035661553,0.0997824,0.0004119434,0.00012794121,0.0011083029,0.62299436,0.00017329934],"about_ca_topic_score_codex":0.006928859,"about_ca_topic_score_gemma":0.0019312686,"teacher_disagreement_score":0.35393086,"about_ca_system_score_codex":0.000010567683,"about_ca_system_score_gemma":0.00008845091,"threshold_uncertainty_score":0.9996841},"labels":[],"label_agreement":null},{"id":"W2606372922","doi":"10.23889/ijpds.v1i1.388","title":"A Federated Data Linkage Strategy to Support Population Health Research in Canada","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Partnership Against Cancer","funders":"","keywords":"Cohort; Custodians; Biobank; Medicine; Data quality; Cohort study; Government (linguistics); Family medicine; Health care; Gerontology; Business; Geography; Political science; Marketing","score_opus":0.7997039661952389,"score_gpt":0.6484931996867838,"score_spread":0.1512107665084551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606372922","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":[0.74512565,0.00006436416,0.070085704,0.14353618,0.019024866,0.0028652481,0.01691315,0.000046213532,0.0023386355],"genre_scores_gemma":[0.9928065,0.00002124555,0.0025343723,0.0010507766,0.0003109405,0.0000058511737,0.0028793064,0.0000074169893,0.0003835773],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9908847,0.00028588984,0.0012755326,0.0010652874,0.005934508,0.0005540469],"domain_scores_gemma":[0.9942905,0.0004715559,0.000827544,0.002696949,0.001325409,0.00038808657],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.040605534,0.00011747554,0.00022330903,0.0009623219,0.0021715995,0.006612808,0.016638158,0.000029035744,0.00012651585],"category_scores_gemma":[0.014900006,0.000100647834,0.00002020223,0.0006891058,0.000114736846,0.010000882,0.0045144167,0.0003049215,0.000044926328],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012008201,0.00008624342,0.13090374,0.0000071249033,0.000016823911,0.00004759506,0.000092572576,0.0021790105,0.00003099335,0.0089425715,0.17148416,0.6860891],"study_design_scores_gemma":[0.0005193102,0.00010414002,0.81363565,0.00007040915,0.0000020482485,0.000026102,0.000695856,0.08832281,0.0000053438926,0.011961986,0.08448881,0.00016751373],"about_ca_topic_score_codex":0.82347137,"about_ca_topic_score_gemma":0.95942444,"teacher_disagreement_score":0.68592155,"about_ca_system_score_codex":0.0012350902,"about_ca_system_score_gemma":0.0036415989,"threshold_uncertainty_score":0.99912745},"labels":[],"label_agreement":null},{"id":"W2606501131","doi":"10.23889/ijpds.v1i1.76","title":"Social Data Linkage Environment","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Identifier; Record linkage; Computer science; Index (typography); Personally identifiable information; Internet privacy; Unique identifier; Database; World Wide Web; Computer security; Sociology; Demography","score_opus":0.6447609076066653,"score_gpt":0.5948565105111473,"score_spread":0.04990439709551797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606501131","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":[0.0686361,0.00008947932,0.75465643,0.12021157,0.02845367,0.0010815688,0.017803043,0.0000806437,0.0089874705],"genre_scores_gemma":[0.98170173,0.000050927243,0.01261764,0.00055342447,0.0015636353,0.0000031787486,0.0016762404,0.000007821719,0.0018254175],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99439365,0.000061738654,0.00070402917,0.0008211129,0.0037719067,0.00024759164],"domain_scores_gemma":[0.9946865,0.00021020012,0.0010406863,0.0035748777,0.00035827735,0.00012948828],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.015294448,0.0001006736,0.00014019987,0.00029013483,0.0027492808,0.0064321063,0.030217176,0.000033285272,0.00027872773],"category_scores_gemma":[0.010137336,0.00008004458,0.00004608919,0.0000947729,0.0004193577,0.013843622,0.009070815,0.0001391163,0.00019996049],"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":[0.00008495343,0.00016854006,0.017014695,0.0000029901912,0.00006492607,0.000021924205,0.00020701939,0.00020713276,0.00024557766,0.09025483,0.23300697,0.65872043],"study_design_scores_gemma":[0.00043465526,0.000016160377,0.1680013,0.00000936597,0.000012986348,0.000018951234,0.00012934791,0.036161862,0.000015023571,0.045548853,0.74951345,0.0001380514],"about_ca_topic_score_codex":0.00013396963,"about_ca_topic_score_gemma":0.000083854946,"teacher_disagreement_score":0.9130656,"about_ca_system_score_codex":0.00010213881,"about_ca_system_score_gemma":0.00010720678,"threshold_uncertainty_score":0.9999492},"labels":[],"label_agreement":null},{"id":"W2606743718","doi":"10.23889/ijpds.v1i1.77","title":"Record Linkage Project Process Model","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Record linkage; Linkage (software); Linked data; Process (computing); Computer science; Session (web analytics); Information retrieval; Data science; World Wide Web; Sociology; Demography; Population","score_opus":0.5924316145985103,"score_gpt":0.6150809603045536,"score_spread":0.022649345706043267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606743718","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":[0.17847781,0.000019819594,0.7775746,0.016666738,0.0146773355,0.00091974024,0.0026834363,0.00006785558,0.008912673],"genre_scores_gemma":[0.97147584,0.000028125969,0.024507722,0.0004779174,0.00056180975,0.000010945385,0.00020895104,0.000007956995,0.0027207613],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99495625,0.00003968858,0.0007442303,0.00067537813,0.0033272943,0.00025715627],"domain_scores_gemma":[0.9952112,0.00016721568,0.0011269776,0.0018566457,0.0015191286,0.0001188322],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01135714,0.000106860374,0.00014635966,0.0005224733,0.0018193842,0.0066603194,0.015555424,0.00003343205,0.000056832905],"category_scores_gemma":[0.017981676,0.00008035814,0.00006165093,0.00021250593,0.00026607353,0.013894221,0.0017894333,0.0001473989,0.000050298782],"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":[0.00024458912,0.0002326289,0.03467113,0.0000126857785,0.00006067905,0.000021246695,0.0006382818,0.0067950366,0.0002689573,0.087668866,0.095427476,0.77395844],"study_design_scores_gemma":[0.0005165318,0.000034982142,0.025744136,0.00004005649,0.000011037892,0.000028771115,0.00025561298,0.708342,0.000046506742,0.17493929,0.08984951,0.0001915207],"about_ca_topic_score_codex":0.00018015908,"about_ca_topic_score_gemma":0.00022470261,"teacher_disagreement_score":0.792998,"about_ca_system_score_codex":0.00008861575,"about_ca_system_score_gemma":0.00033985247,"threshold_uncertainty_score":0.99989796},"labels":[],"label_agreement":null},{"id":"W2606772694","doi":"10.23889/ijpds.v1i1.307","title":"Information Management at a Health Services Research Organization in Toronto, Ontario, Canada: Moving from Identifiable Data to Coded Data","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Identifier; Computer science; Population; Confidentiality; Data sharing; Data quality; Data collection; Business; Data science; Internet privacy; Knowledge management; Computer security; Medicine; Environmental health; Service (business)","score_opus":0.3377112444792492,"score_gpt":0.528678948045083,"score_spread":0.19096770356583376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606772694","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":[0.5165605,0.00021807523,0.30161253,0.052608274,0.035612047,0.0054004956,0.08231876,0.00009836282,0.005570969],"genre_scores_gemma":[0.9311269,0.0000890073,0.02059636,0.0018421513,0.0003164405,0.000008774106,0.04438577,0.000012420197,0.0016221558],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9918384,0.00014132679,0.0012234141,0.0008795239,0.0054964568,0.00042086904],"domain_scores_gemma":[0.99086004,0.0002631424,0.001014975,0.0060089505,0.0015982949,0.00025459903],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.01983506,0.0001229078,0.00019521076,0.00049183227,0.00222174,0.007076413,0.030902933,0.000029627883,0.0006054833],"category_scores_gemma":[0.004844438,0.00011203123,0.000009615434,0.00056703924,0.00008294446,0.038020194,0.024607388,0.00015765599,0.00006315676],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029608712,0.00019170756,0.16428673,0.000047756996,0.0001276171,0.000028226788,0.0042305524,0.0027122933,0.000102261656,0.013885882,0.56244814,0.25164273],"study_design_scores_gemma":[0.0005180527,0.000014133216,0.60067356,0.00014128746,0.000006532882,0.0000056620324,0.0037294847,0.053326786,0.000009082264,0.0021443276,0.33928314,0.00014792186],"about_ca_topic_score_codex":0.9797177,"about_ca_topic_score_gemma":0.9981719,"teacher_disagreement_score":0.43638685,"about_ca_system_score_codex":0.003999388,"about_ca_system_score_gemma":0.001340077,"threshold_uncertainty_score":0.9998241},"labels":[],"label_agreement":null},{"id":"W2606808438","doi":"10.23889/ijpds.v1i1.49","title":"Record Linkage Methodology for the Social Data Linkage Environment at Statistics Canada","year":2017,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Record linkage; Probabilistic logic; Linkage (software); Statistic; Computer science; Population; Data science; Data mining; Statistics; Artificial intelligence; Mathematics","score_opus":0.6885121311704627,"score_gpt":0.5782337375018265,"score_spread":0.11027839366863623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606808438","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":[0.0031240406,0.000027882998,0.92535585,0.023205759,0.009652668,0.00041308563,0.03812001,0.0000062683257,0.00009443123],"genre_scores_gemma":[0.399483,0.00046808666,0.55940354,0.005472804,0.005795038,0.000060524882,0.017749289,0.00004483543,0.011522882],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953352,0.00016206737,0.0008274852,0.00074036804,0.0026291832,0.00030567244],"domain_scores_gemma":[0.99225146,0.0031266932,0.0013314175,0.0026756476,0.00049859745,0.000116216885],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.019863296,0.000120445045,0.00018587998,0.00013126784,0.004261568,0.0022066596,0.019788513,0.00003855733,0.00023214993],"category_scores_gemma":[0.024552397,0.0000822382,0.000037983868,0.000081620456,0.0004185512,0.0031026592,0.0062759416,0.00015298424,0.000018124456],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011556269,0.000033225042,0.0038829206,0.0000039217734,0.00007218737,0.000008347694,0.00010987888,0.00027363273,0.00007185533,0.02878278,0.5398387,0.42680702],"study_design_scores_gemma":[0.00039825268,0.000021301457,0.07674168,0.0000058496103,0.00003194342,0.00001401387,0.00022185966,0.061006244,0.0000136218505,0.020937415,0.84048766,0.000120177014],"about_ca_topic_score_codex":0.039649785,"about_ca_topic_score_gemma":0.24440314,"teacher_disagreement_score":0.42668682,"about_ca_system_score_codex":0.00032949806,"about_ca_system_score_gemma":0.00042749342,"threshold_uncertainty_score":0.9988291},"labels":[],"label_agreement":null},{"id":"W2611926229","doi":"","title":"Beyond the Dataset: Understanding Sociotechnical Aspects of the Knowledge Discovery Process Among Modern Data Professionals","year":2017,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Simon Fraser University","keywords":"Sociotechnical system; Data science; Process (computing); Knowledge management; Computer science","score_opus":0.15589358735361483,"score_gpt":0.3803340841839857,"score_spread":0.22444049683037084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611926229","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":[0.921321,0.00054719124,0.0017545343,0.019156484,0.0028522883,0.0030015565,0.025873046,0.000070607915,0.025423327],"genre_scores_gemma":[0.6975551,0.000055032957,0.000050560517,0.000039353978,0.00004796183,9.318571e-7,0.0059092646,0.000018396253,0.29632336],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99661016,0.00039107577,0.0003567615,0.0007855097,0.001592213,0.00026426688],"domain_scores_gemma":[0.99383813,0.0005172441,0.0014280728,0.003962664,0.0001907863,0.0000630828],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0031445718,0.00024039605,0.0005227636,0.00018643108,0.0011847806,0.00023400773,0.009488006,0.00027685735,0.00014107896],"category_scores_gemma":[0.000580921,0.00014626031,0.00017182935,0.00029180825,0.0008242002,0.0020147406,0.0022758383,0.00047578465,0.000027053487],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006535186,0.001149785,0.0010374292,0.0016549473,0.0009122986,0.00003939406,0.31435847,0.00011008045,0.00057976093,0.09240181,0.57524973,0.0118527785],"study_design_scores_gemma":[0.00070566114,0.00005524851,0.012541131,0.0009042231,0.00052110874,0.0000011082365,0.80183935,0.0014656497,0.00045006353,0.17562705,0.005396112,0.00049326854],"about_ca_topic_score_codex":0.004145317,"about_ca_topic_score_gemma":0.13215883,"teacher_disagreement_score":0.5698536,"about_ca_system_score_codex":0.000085552485,"about_ca_system_score_gemma":0.00038924126,"threshold_uncertainty_score":0.9958711},"labels":[],"label_agreement":null},{"id":"W261503754","doi":"10.20982/tqmp.02.1.p020","title":"Formatting data files for repeated-measures analyses in SPSS: Using the Aggregate and Restructure procedures","year":2006,"lang":"en","type":"article","venue":"Tutorials in Quantitative Methods for Psychology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Concordia University; Université du Québec à Montréal","funders":"","keywords":"Disk formatting; Aggregate (composite); Computer science; Restructuring; Database; Operating system; Business; Materials science","score_opus":0.7403271780089065,"score_gpt":0.6902018180616303,"score_spread":0.05012535994727618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261503754","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":[0.07288555,0.0030120714,0.91782653,0.0014528388,0.0021826923,0.0017141327,0.0005853069,0.000029781555,0.0003111149],"genre_scores_gemma":[0.028422043,0.00009523276,0.9703192,0.00042994582,0.0003590405,0.00014485035,0.00012441246,0.000022779013,0.00008248593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9936023,0.0030991985,0.0014509988,0.0010117219,0.00038551274,0.00045027555],"domain_scores_gemma":[0.98235875,0.015277236,0.0008068878,0.001233739,0.00028720158,0.00003617076],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033562977,0.00022775793,0.0006720399,0.00060194015,0.00024755026,0.00027702897,0.0014066335,0.00014445663,0.000010840168],"category_scores_gemma":[0.0390842,0.00014482222,0.00008020998,0.00095913967,0.000370885,0.0006298092,0.00036176978,0.00016757644,0.0000011759761],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004111872,0.0003950661,0.005597607,0.00044758793,0.0003749655,0.000016967491,0.009276353,0.0045111873,0.0753184,0.538705,0.05285827,0.3083867],"study_design_scores_gemma":[0.0017979537,0.00020191084,0.0076386062,0.00009941379,0.000087534914,0.000009042186,0.0050227,0.0110542495,0.0013550903,0.8726474,0.09977085,0.0003152395],"about_ca_topic_score_codex":0.00050461484,"about_ca_topic_score_gemma":0.0018376516,"teacher_disagreement_score":0.3339424,"about_ca_system_score_codex":0.000030423196,"about_ca_system_score_gemma":0.00006486325,"threshold_uncertainty_score":0.99515027},"labels":[],"label_agreement":null},{"id":"W2615642425","doi":"10.1109/icde.2017.39","title":"SEDEX: Scalable Entity Preserving Data Exchange","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Schema (genetic algorithms); Ambiguity; Scalability; Data exchange; Star schema; Database schema; Tuple; Schema migration; Data mining; Information retrieval; Theoretical computer science; Semi-structured model; Database; Programming language; Database design","score_opus":0.6898325825479652,"score_gpt":0.5363748586287157,"score_spread":0.1534577239192495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615642425","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007127219,0.00008254433,0.034229264,0.022418164,0.0016449257,0.0002847877,0.0003169887,0.0000749215,0.9338212],"genre_scores_gemma":[0.26637644,0.00008589004,0.0070682405,0.0032776294,0.0004116082,0.000010255596,0.000088108114,0.000011070468,0.7226708],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977339,0.00010541528,0.00028830057,0.0005947309,0.0010556761,0.00022196407],"domain_scores_gemma":[0.9914098,0.00022624577,0.0001927007,0.007990825,0.00008764444,0.00009280678],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0073018945,0.00007596591,0.00014769832,0.00006793536,0.0006889339,0.0026693447,0.008834496,0.00003198418,0.01680732],"category_scores_gemma":[0.005189275,0.00005372929,0.000030059124,0.00008674235,0.000094072646,0.0052497806,0.0116790375,0.000059895243,0.004362905],"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":[0.0000033331194,0.00003459863,0.0017882423,0.000007991933,0.00000775836,0.000005101458,0.000044038006,6.609324e-7,0.000013495048,0.0104058795,0.964567,0.023121877],"study_design_scores_gemma":[0.00014082949,0.0000070370675,0.0109193865,0.0000046073424,0.000005861465,4.4516526e-7,0.00019246654,0.0024443245,0.000091324524,0.02687356,0.95923644,0.000083697756],"about_ca_topic_score_codex":0.0024415217,"about_ca_topic_score_gemma":0.0035604548,"teacher_disagreement_score":0.2592492,"about_ca_system_score_codex":0.000008921499,"about_ca_system_score_gemma":0.000018231782,"threshold_uncertainty_score":0.998366},"labels":[],"label_agreement":null},{"id":"W2616147950","doi":"10.14778/3115404.3115409","title":"Auto-join","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Joins; Join (topology); Computer science; Transformation (genetics); Domain (mathematical analysis); String (physics); Database; Data mining; Theoretical computer science; Programming language; Mathematics","score_opus":0.19962649177423786,"score_gpt":0.4134582450415684,"score_spread":0.21383175326733056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616147950","genre_codex":"other","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":[0.3593015,0.0000888122,0.00025488046,0.04407267,0.0019231034,0.0010338206,0.000057418318,0.00007551115,0.5931923],"genre_scores_gemma":[0.9845093,0.000016093094,0.0007370529,0.00042024293,0.00006947974,0.00002097857,3.231767e-7,0.0000058122955,0.014220709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976644,0.0000105407835,0.00045332251,0.00032973324,0.0013317786,0.0002102305],"domain_scores_gemma":[0.9981151,0.000082763654,0.00075638824,0.000758498,0.00022520404,0.000062045314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032645203,0.000105961655,0.00020365432,0.00007488864,0.00050972303,0.0006620825,0.0037798367,0.000030618357,0.00019230042],"category_scores_gemma":[0.002977339,0.000058914313,0.00014040794,0.00012143654,0.0002163719,0.0006064652,0.0020014464,0.00008723116,0.00019545775],"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":[0.00004967026,0.00023604221,0.01742536,0.0000561211,0.00007307003,8.7720787e-7,0.0011789707,0.0000049124883,0.012397085,0.49123296,0.384108,0.09323694],"study_design_scores_gemma":[0.00066539604,0.000072268034,0.08386739,0.0000710882,0.00003837509,0.0000032514204,0.0015339248,0.00022891264,0.05437285,0.24218534,0.61676323,0.00019797371],"about_ca_topic_score_codex":0.000115769944,"about_ca_topic_score_gemma":0.000013101016,"teacher_disagreement_score":0.6252078,"about_ca_system_score_codex":0.000031349173,"about_ca_system_score_gemma":0.000016739512,"threshold_uncertainty_score":0.702394},"labels":[],"label_agreement":null},{"id":"W2626925008","doi":"10.1145/3106426.3106484","title":"Preference-driven similarity join","year":2017,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Web Intelligence","topic":"Data Quality and Management","field":"Decision Sciences","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":"Simon Fraser University","funders":"","keywords":"Similarity (geometry); Join (topology); Set (abstract data type); Object (grammar); Variety (cybernetics); Similitude","score_opus":0.4629911135755076,"score_gpt":0.44031049862763233,"score_spread":0.022680614947875266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626925008","genre_codex":"other","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":[0.3042265,0.000007593053,0.0010248921,0.031684205,0.0019375888,0.00043448815,0.00016361725,0.000045815377,0.6604753],"genre_scores_gemma":[0.9913488,0.000084230014,0.0006286705,0.0005037063,0.000084383304,0.00001782373,0.0000015748324,0.000006772791,0.0073240297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962781,0.00002063821,0.0006961185,0.00056510314,0.0022230148,0.00021702336],"domain_scores_gemma":[0.99618936,0.00020953092,0.0011191636,0.00079553,0.0016040931,0.00008235624],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020553384,0.00017994539,0.00025128067,0.00016404496,0.00040619218,0.0013919742,0.01010172,0.00007433012,0.0013338351],"category_scores_gemma":[0.007898115,0.00011570513,0.0001629923,0.00013864573,0.00048765974,0.0009340014,0.002063349,0.0002898818,0.00034075655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007340548,0.0001114215,0.010142065,0.00001042363,0.00003718145,5.442178e-7,0.00023398487,0.000021554604,0.0046439716,0.95103633,0.010179218,0.023509914],"study_design_scores_gemma":[0.00022575221,0.00016147098,0.028082706,0.0004556451,0.00002490556,0.0000050721073,0.0021131597,0.03226092,0.10365051,0.7953193,0.037305743,0.0003948269],"about_ca_topic_score_codex":0.00008610991,"about_ca_topic_score_gemma":0.00009761292,"teacher_disagreement_score":0.68712234,"about_ca_system_score_codex":0.00005560424,"about_ca_system_score_gemma":0.000102352824,"threshold_uncertainty_score":0.9996447},"labels":[],"label_agreement":null},{"id":"W2631182992","doi":"10.1109/ccece.2017.7946661","title":"A content-based data masking technique for a built-in framework in Business Intelligence platform","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Masking (illustration); Computer science; Data warehouse; Business intelligence; Database; Knowledge management; Data science; World Wide Web","score_opus":0.6792248335221864,"score_gpt":0.521441100059523,"score_spread":0.1577837334626634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2631182992","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":[0.0022898668,0.000014317295,0.98961174,0.004623524,0.00023958116,0.0009632624,0.000096470016,0.000025523354,0.002135683],"genre_scores_gemma":[0.82142365,0.000014943354,0.17653824,0.0011272592,0.00003848973,0.00019547458,0.00005467631,0.0000104068795,0.0005968308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765474,0.00004428286,0.00070972065,0.00069754425,0.0005806499,0.000313043],"domain_scores_gemma":[0.9940263,0.0015865603,0.0002907738,0.0038964811,0.00014727096,0.00005258709],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.00848429,0.00013061581,0.00029214655,0.00033886026,0.00017541976,0.00083769666,0.0055801133,0.000107924054,0.00016248913],"category_scores_gemma":[0.020255893,0.000097783966,0.00003608723,0.00042034575,0.00012882453,0.0014316932,0.0016596534,0.00015130902,0.000057916714],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004907658,0.0005933262,0.021794438,0.00014726828,0.00001828569,0.00008272867,0.00035259614,0.00040482156,0.00053910294,0.5120745,0.008553976,0.45494822],"study_design_scores_gemma":[0.0013300125,0.00010926125,0.054701537,0.0011224031,0.000016227172,0.0000032433004,0.006257368,0.07259576,0.009553937,0.72792065,0.1255151,0.00087448495],"about_ca_topic_score_codex":0.0021277638,"about_ca_topic_score_gemma":0.011299778,"teacher_disagreement_score":0.8191338,"about_ca_system_score_codex":0.000040225492,"about_ca_system_score_gemma":0.000080358914,"threshold_uncertainty_score":0.99980015},"labels":[],"label_agreement":null},{"id":"W2725122689","doi":"10.29173/cais912","title":"An Analysis of Seasonal and Topical Queries in a Large Public Library to Support User Engagement","year":2016,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Analytics; Overtime; Identifier; Library science; Political science; Humanities; Computer science; Art; Data science","score_opus":0.07657643030396424,"score_gpt":0.3375330674694285,"score_spread":0.26095663716546424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725122689","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":[0.9580912,0.000160312,0.00034519698,0.03641031,0.00019075123,0.00038907785,0.0021115658,0.000016878146,0.0022847361],"genre_scores_gemma":[0.99374443,0.00029991122,0.0009690329,0.00078730297,0.000057744084,0.000026421669,0.000012714214,0.000013912942,0.004088552],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99626166,0.00020582983,0.0011505074,0.0006463798,0.0011536747,0.0005819316],"domain_scores_gemma":[0.98593384,0.0006408419,0.0008170374,0.00047338364,0.01178667,0.0003482017],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0039331145,0.00028817257,0.00090907415,0.0008025704,0.000102652324,0.002901962,0.0026704178,0.00017317278,0.0010246593],"category_scores_gemma":[0.022887846,0.00019063495,0.000237213,0.001842066,0.0007523453,0.021850258,0.002361156,0.00020019746,0.000006453738],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019809858,0.0005071274,0.727813,0.0001949355,0.00032244905,0.0000025306563,0.018790467,0.0000014282907,0.001159211,0.20476049,0.0072424226,0.03900785],"study_design_scores_gemma":[0.00054372376,0.00056917703,0.6115859,0.00023240542,0.00027071146,0.0000022766712,0.008366024,0.00019017282,0.0027260524,0.0050753206,0.37019995,0.00023825897],"about_ca_topic_score_codex":0.00025421582,"about_ca_topic_score_gemma":0.0003761168,"teacher_disagreement_score":0.36295754,"about_ca_system_score_codex":0.00004656428,"about_ca_system_score_gemma":0.00040926918,"threshold_uncertainty_score":0.99988854},"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":"W2729808627","doi":"10.1371/journal.pone.0178731","title":"A conceptual framework for quality assessment and management of biodiversity data","year":2017,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Universidade de São Paulo; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Conceptual framework; Data science; Variety (cybernetics); Data management; Quality (philosophy); Data quality; Proof of concept; Management science; Data mining; Engineering; Artificial intelligence","score_opus":0.7553622666505247,"score_gpt":0.514162342283249,"score_spread":0.24119992436727578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2729808627","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":[0.7876779,0.00014629944,0.18081222,0.013169311,0.0003005558,0.0020075256,0.007296635,0.000052136613,0.0085374275],"genre_scores_gemma":[0.74293035,0.0002769175,0.25545797,0.00040768186,0.000042530566,0.000020716447,0.00014497197,0.0000039922065,0.00071486103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9976998,0.000117489086,0.00039528657,0.00053308374,0.0010985507,0.00015580503],"domain_scores_gemma":[0.99549454,0.00070893974,0.0004810166,0.003106501,0.00013523725,0.000073768904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048953984,0.0000852454,0.00031545517,0.00004838679,0.00038441323,0.00030695158,0.0024139953,0.00004484358,0.00013001476],"category_scores_gemma":[0.0012882609,0.00007233448,0.000034133136,0.000055737175,0.0003897246,0.0005960361,0.0034368928,0.00006652819,0.000035658322],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011811218,0.001735326,0.04752873,0.00032892526,0.00078520115,0.000004666091,0.00047921462,4.403166e-7,0.00006517029,0.906591,0.016112247,0.026250996],"study_design_scores_gemma":[0.0021098389,0.0002559364,0.70546186,0.00034803516,0.0005840379,1.2781923e-7,0.009627688,0.0005610278,0.0005533379,0.24830101,0.031778805,0.0004182776],"about_ca_topic_score_codex":0.00009428323,"about_ca_topic_score_gemma":0.000038137627,"teacher_disagreement_score":0.65828997,"about_ca_system_score_codex":0.000015476791,"about_ca_system_score_gemma":0.000016038757,"threshold_uncertainty_score":0.44858444},"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":"W2736616122","doi":"10.1016/j.dib.2017.07.038","title":"Dataset of anomalies and malicious acts in a cyber-physical subsystem","year":2017,"lang":"en","type":"article","venue":"Data in Brief","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Thales Group; Department of Clinical Neurosciences, University of Calgary","keywords":"Computer science; Cyber-physical system; Computer security; Research article; Data science; Operating system","score_opus":0.30719743047038894,"score_gpt":0.47648082064911546,"score_spread":0.1692833901787265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736616122","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":[0.9490263,0.000058362137,0.00011133361,0.0009748822,0.00013522046,0.00023663267,0.047671836,0.0000057776647,0.001779657],"genre_scores_gemma":[0.9955818,0.000023188784,0.00024101314,0.00017577193,0.000030853294,0.0000046140062,0.00384939,0.0000038776407,0.000089476736],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99806464,0.00017130557,0.0004924737,0.00053248444,0.00056201644,0.00017708122],"domain_scores_gemma":[0.9951486,0.00042331443,0.00028865828,0.0040658824,0.000022432436,0.00005112263],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038893006,0.00009030367,0.00031747104,0.00014458856,0.00007247378,0.00040043693,0.003018348,0.000033060194,0.000025367828],"category_scores_gemma":[0.0026699423,0.00007242835,0.000011991035,0.00013892504,0.00022946128,0.0015766164,0.0033217496,0.00008021888,0.00005496193],"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":[0.0002604887,0.0010749495,0.24991013,0.00026233093,0.00005710112,0.0004886442,0.0031739722,0.000014766046,0.0004529452,0.09318833,0.5326036,0.11851274],"study_design_scores_gemma":[0.0007110023,0.00003591709,0.49397117,0.00006604662,0.000008345874,0.0000048947986,0.0007351005,0.0012449952,0.00008223444,0.0036123358,0.49938163,0.00014631539],"about_ca_topic_score_codex":0.0037549075,"about_ca_topic_score_gemma":0.009342701,"teacher_disagreement_score":0.24406102,"about_ca_system_score_codex":0.000009528226,"about_ca_system_score_gemma":0.000020693451,"threshold_uncertainty_score":0.5676322},"labels":[],"label_agreement":null},{"id":"W2737275827","doi":"","title":"SUMMA at TAC Knowledge Base Population Task 2017.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Task (project management); Base (topology); Knowledge base; Computer science; Population; Artificial intelligence; Mathematics; Medicine; Engineering; Environmental health; Systems engineering","score_opus":0.09041987003507082,"score_gpt":0.4039581842127519,"score_spread":0.3135383141776811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737275827","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":[0.4418089,0.0027180118,0.20011583,0.0039633415,0.0005643281,0.001925689,0.0008634776,0.0001661236,0.34787428],"genre_scores_gemma":[0.9864659,0.00006956023,0.00015817599,0.000044176297,0.00006519366,0.000073736664,0.00006833312,0.0000044438752,0.013050529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885124,0.00016537456,0.00033805252,0.00028034256,0.0002455012,0.00011949398],"domain_scores_gemma":[0.99740416,0.0006694505,0.0003484331,0.0013946109,0.00011785807,0.000065491855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00395212,0.00008671941,0.0001752307,0.00009147429,0.0009002957,0.00021558547,0.0007773498,0.000040288596,0.00016584012],"category_scores_gemma":[0.00079213415,0.000067435736,0.000042064075,0.00010393257,0.00046115922,0.0004938453,0.00049511535,0.000041787156,0.00021101776],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038803442,0.000041892516,0.0013587956,0.000013728065,0.000008301852,1.5365032e-7,0.00027551164,0.000002076761,0.00013807621,0.93780094,0.0050884527,0.05523329],"study_design_scores_gemma":[0.0001164815,0.000011699419,0.019135974,0.000003759546,0.000018163752,8.6565467e-7,0.0006836267,0.000017932543,0.00080385664,0.7766241,0.20250563,0.00007792009],"about_ca_topic_score_codex":0.000075994176,"about_ca_topic_score_gemma":0.00016184,"teacher_disagreement_score":0.54465693,"about_ca_system_score_codex":0.00001187073,"about_ca_system_score_gemma":0.000016210177,"threshold_uncertainty_score":0.6924437},"labels":[],"label_agreement":null},{"id":"W2737719817","doi":"10.23974/ijol.2017.vol2.1.38","title":"Editorial: Introducing this Special Issue on Data Librarianship","year":2017,"lang":"en","type":"editorial","venue":"International Journal of Librarianship","topic":"Data Quality and Management","field":"Decision Sciences","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":"Library science; Computer science; Engineering ethics; Data science; Political science; Engineering","score_opus":0.188426744847238,"score_gpt":0.4376218285475843,"score_spread":0.2491950837003463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737719817","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":[0.000001976894,0.00011758498,0.00055582874,0.017398825,0.8817957,0.0001886045,0.0034325663,0.00003546279,0.09647343],"genre_scores_gemma":[0.000031223226,0.0003302924,0.0012085543,0.00063957,0.9648579,0.0000033853485,0.0015569682,0.00008736834,0.031284776],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97721684,0.0012518414,0.0033135603,0.0015059544,0.016174404,0.000537402],"domain_scores_gemma":[0.97047716,0.013685275,0.006976388,0.0056421165,0.0027353747,0.00048365546],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.019233668,0.0006615357,0.0013786616,0.0017580233,0.00035141245,0.012257349,0.036822945,0.0011942812,0.010744472],"category_scores_gemma":[0.11920656,0.00052422035,0.00053227093,0.0003230104,0.00030649803,0.010419619,0.004548155,0.0033673781,0.0023964045],"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":[0.0011462567,0.00020401453,0.000030200395,0.000017496026,0.00054838246,0.00030588458,0.00029338006,0.000020041272,0.0000016478388,0.0029541317,0.939376,0.05510255],"study_design_scores_gemma":[0.0013780848,0.00025790953,0.000052650947,0.0005009117,0.00011821931,0.000012340075,0.0001656131,0.00002241683,0.000020366542,0.029105332,0.9678897,0.00047643427],"about_ca_topic_score_codex":0.00007738261,"about_ca_topic_score_gemma":0.000044106175,"teacher_disagreement_score":0.0999729,"about_ca_system_score_codex":0.00023139462,"about_ca_system_score_gemma":0.0025869475,"threshold_uncertainty_score":0.99972093},"labels":[],"label_agreement":null},{"id":"W2737857854","doi":"10.23974/ijol.2017.vol2.1.35","title":"Lives in Data: Prominent Data Librarians, Archivists and Educators Share Their Thoughts","year":2017,"lang":"en","type":"article","venue":"International Journal of Librarianship","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"China; Library science; Field (mathematics); Political science; Public relations; Key (lock); Sociology; Law; Computer science","score_opus":0.4638614143762922,"score_gpt":0.47245123330095407,"score_spread":0.008589818924661874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737857854","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":[0.5326401,0.0035552515,0.013394227,0.3736882,0.022205444,0.0011997418,0.010606234,0.00010620401,0.042604625],"genre_scores_gemma":[0.9918352,0.0002812956,0.004170928,0.0007277941,0.0017581371,0.000001967798,0.00021858074,0.000019481022,0.0009866117],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9965801,0.00031822344,0.0010546442,0.0005535634,0.0013024134,0.00019104927],"domain_scores_gemma":[0.994712,0.0011224716,0.001164911,0.002688402,0.00013082802,0.00018136798],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0046041314,0.0001610728,0.0003189279,0.00049762585,0.000146281,0.004480181,0.016262293,0.00004297215,0.00017090555],"category_scores_gemma":[0.006219518,0.000110969704,0.000052486073,0.00010433035,0.00019370666,0.013090908,0.006055971,0.00031431305,0.0000341373],"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":[0.0007305715,0.00068910595,0.1820209,0.00004183483,0.0005268892,0.0009763489,0.006005087,0.000010857161,0.00007836943,0.05127866,0.3927172,0.36492413],"study_design_scores_gemma":[0.0012040556,0.00006194606,0.43420047,0.00037652167,0.00002111652,0.00015255468,0.003023424,0.0010944393,0.00011418283,0.1481317,0.4113671,0.00025250716],"about_ca_topic_score_codex":0.00003738025,"about_ca_topic_score_gemma":0.00016696462,"teacher_disagreement_score":0.4591951,"about_ca_system_score_codex":0.00001826758,"about_ca_system_score_gemma":0.00030952628,"threshold_uncertainty_score":0.99655324},"labels":[],"label_agreement":null},{"id":"W2742025582","doi":"10.1145/3077136.3080812","title":"Navigating Imprecision in Relevance Assessments on the Road to Total Recall","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"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":"Recall; Relevance (law); Computer science; Precision and recall; Ground truth; Relevance feedback; Information retrieval; Data curation; Data mining; Artificial intelligence; Image retrieval; Cognitive psychology; Psychology; Image (mathematics)","score_opus":0.27943193789252796,"score_gpt":0.534968558435086,"score_spread":0.255536620542558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742025582","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":[0.8819772,0.0000041229446,0.0047228085,0.020718463,0.0005956476,0.00037092122,0.000011335158,0.00001974449,0.09157976],"genre_scores_gemma":[0.9857993,0.0000054595994,0.0027760782,0.0025616959,0.00004253072,0.000021197666,0.0000015556067,0.0000047700487,0.008787408],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9974,0.00021257161,0.00045382473,0.0004673026,0.0012467043,0.0002196045],"domain_scores_gemma":[0.9964469,0.0013167042,0.00020107462,0.0018984718,0.00006576088,0.00007107608],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0074158562,0.00009468706,0.00015029626,0.000036864625,0.00041456462,0.0010665249,0.0018852965,0.00003413441,0.00040722467],"category_scores_gemma":[0.010387505,0.000050885592,0.000045751305,0.00017354608,0.000042903717,0.0005775288,0.0010387029,0.00021406765,0.0016831609],"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":[0.000028883258,0.00004585322,0.00078655465,7.766238e-7,0.00000260061,0.0000057761936,0.00020026516,0.00008941829,0.0001414415,0.010906006,0.019245088,0.96854734],"study_design_scores_gemma":[0.0010960593,0.0006023718,0.64502156,0.0004955743,0.0000067142614,0.0000029218704,0.005556049,0.012703517,0.0021473656,0.104086936,0.22765411,0.00062684825],"about_ca_topic_score_codex":0.0006156237,"about_ca_topic_score_gemma":0.0005964389,"teacher_disagreement_score":0.9679205,"about_ca_system_score_codex":0.00004173539,"about_ca_system_score_gemma":0.000013824012,"threshold_uncertainty_score":0.99997044},"labels":[],"label_agreement":null},{"id":"W2743149664","doi":"10.2139/ssrn.3008736","title":"A Data Commons for Food Security","year":2017,"lang":"pl","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Food security; Business; Commons; Computer security; Internet privacy; Computer science; Political science; Law; Biology; Agriculture; Ecology","score_opus":0.23726940871807647,"score_gpt":0.44386986300763326,"score_spread":0.20660045428955678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743149664","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":[0.07302607,0.03127118,0.6477969,0.16721012,0.014665355,0.0041868645,0.03142197,0.00014961053,0.030271908],"genre_scores_gemma":[0.98390174,0.005872804,0.00032610833,0.00044276734,0.0011143098,0.000010787551,0.00015333571,0.00003185689,0.008146276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99230456,0.00042212495,0.0010467938,0.0009137236,0.0013986934,0.003914075],"domain_scores_gemma":[0.9916484,0.0007325452,0.0015004599,0.0055361507,0.00030209238,0.00028037297],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.035773087,0.00032066778,0.0005613132,0.00019834883,0.003854363,0.004061112,0.013505231,0.0001647117,0.00016807999],"category_scores_gemma":[0.0056632455,0.00026785437,0.00028779908,0.00014457102,0.00035218796,0.002851574,0.0033748194,0.0024242376,0.0003306394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021600831,0.00030151085,0.00035433492,0.00002232336,0.00060993974,0.000005238243,0.00030062962,0.000002096211,0.000002888286,0.7628312,0.07661711,0.1587367],"study_design_scores_gemma":[0.0010637254,0.00076501723,0.00021432925,0.000030990705,0.00013499027,0.000073260526,0.0029437754,0.0008714253,0.0000041026346,0.5607557,0.43292862,0.00021401451],"about_ca_topic_score_codex":0.00017580866,"about_ca_topic_score_gemma":0.0650464,"teacher_disagreement_score":0.9108757,"about_ca_system_score_codex":0.0004841512,"about_ca_system_score_gemma":0.0037430509,"threshold_uncertainty_score":0.99997735},"labels":[],"label_agreement":null},{"id":"W2748020237","doi":"10.1007/978-3-319-56994-9_78","title":"Corroborating Quality of Data Through Density Information","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Data deduplication; Tuple; Data quality; Computer science; Master data; Data mining; Data integration; Process (computing); Quality (philosophy); Data integrity; Data pre-processing; Database; Data science; Engineering","score_opus":0.30176257184093275,"score_gpt":0.4222852155345378,"score_spread":0.12052264369360505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2748020237","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":[0.00007339572,0.0031554978,0.90783924,0.00021517165,0.0016406943,0.00065031264,0.00048313334,0.000021817175,0.08592074],"genre_scores_gemma":[0.9860928,0.0010912303,0.0015204223,0.00063346943,0.0008814512,0.000008801914,0.0019392194,0.000028527136,0.007804048],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99638283,0.00023214227,0.0016597153,0.0005228286,0.0010021724,0.00020032874],"domain_scores_gemma":[0.99303323,0.0018899231,0.0021411076,0.0026381717,0.00025144647,0.000046106423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007996664,0.00025753156,0.0009173933,0.00011971802,0.00018958366,0.00070813764,0.0015063279,0.0004344388,0.000026111346],"category_scores_gemma":[0.0024474056,0.00019122005,0.00006404887,0.000052903986,0.0001790852,0.001414701,0.0011658785,0.0004146702,0.000015450687],"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":[0.00016903298,0.000031026164,0.002446462,0.00097230443,0.00018901599,0.000017022465,0.0022341288,0.06088384,0.000002251857,0.3624769,0.022667991,0.54791003],"study_design_scores_gemma":[0.00077970885,0.00009065656,0.0013088399,0.0017200605,0.000086653985,0.000012581731,0.00022054015,0.16638152,0.0000018606152,0.1773915,0.65109086,0.00091520214],"about_ca_topic_score_codex":0.0013637228,"about_ca_topic_score_gemma":0.0028845589,"teacher_disagreement_score":0.98601943,"about_ca_system_score_codex":0.000027856937,"about_ca_system_score_gemma":0.000045399556,"threshold_uncertainty_score":0.7797727},"labels":[],"label_agreement":null},{"id":"W2750213807","doi":"10.31937/ijnmt.v4i1.534","title":"Designing Information Product (IP) Maps On the Process of Data Processing and Academic Information","year":2017,"lang":"en","type":"article","venue":"IJNMT (International Journal of New Media Technology)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ryerson University","keywords":"Computer science; Data management; Quality (philosophy); Information management; Information system; Data quality; Product (mathematics); Process (computing); Data science; Knowledge management; Database; Engineering; Operations management","score_opus":0.2337570832177952,"score_gpt":0.4385282002339322,"score_spread":0.20477111701613698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750213807","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":[0.58809274,0.00061680406,0.11991867,0.2834017,0.003207326,0.0009878826,0.00036453226,0.000098259035,0.0033120662],"genre_scores_gemma":[0.99377257,0.00020515975,0.005249529,0.0004995247,0.0002005435,0.0000029915702,0.000035502155,0.0000035301557,0.000030682004],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968997,0.00003893334,0.0010658493,0.00013594043,0.0017346613,0.00012488755],"domain_scores_gemma":[0.9951984,0.00026358134,0.0027963808,0.0007181559,0.00097006385,0.00005337632],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004656765,0.00010323891,0.0001965408,0.00082237745,0.00018861347,0.00051050464,0.005139925,0.00009275729,0.000018067407],"category_scores_gemma":[0.018565549,0.00006333796,0.00002841047,0.00022515288,0.00026700564,0.0098721655,0.00076297944,0.00043367234,0.000027522938],"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":[0.00010085567,0.000017356626,0.0017191212,0.00001533363,0.000043051517,0.0000029027844,0.0018737867,0.00003308102,0.00015166635,0.0063435454,0.01931338,0.9703859],"study_design_scores_gemma":[0.004397467,0.0004062613,0.052762832,0.0018837169,0.00015319938,0.00040914983,0.0274525,0.0038832352,0.035852805,0.4276867,0.4445101,0.0006020402],"about_ca_topic_score_codex":0.0000101477235,"about_ca_topic_score_gemma":0.0000067602605,"teacher_disagreement_score":0.9697839,"about_ca_system_score_codex":0.000030419415,"about_ca_system_score_gemma":0.00021777449,"threshold_uncertainty_score":0.9897015},"labels":[],"label_agreement":null},{"id":"W2754893762","doi":"10.26789/jsc.2017.01.001","title":"Achieving interoperability of smart city data: An analysis of 311 data","year":2017,"lang":"en","type":"article","venue":"Journal of Smart Cities","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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 Toronto","funders":"","keywords":"Ontology; Interoperability; Computer science; Semantics (computer science); Smart city; Construct (python library); Semantic interoperability; Service (business); Data science; World Wide Web; Linked data; Upper ontology; Information retrieval; Semantic Web; Internet of Things","score_opus":0.4986911969215018,"score_gpt":0.48408684875006247,"score_spread":0.014604348171439352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754893762","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":[0.98968446,0.000105272426,0.005594489,0.0010083069,0.000613128,0.00006717344,0.0016061411,0.0000042214774,0.0013167873],"genre_scores_gemma":[0.99762255,0.000095484655,0.0016217928,0.00010148392,0.00010820105,2.7132802e-7,0.00006864159,0.000004825145,0.0003767371],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99537677,0.0004958357,0.001853238,0.0004353594,0.0016639617,0.00017481305],"domain_scores_gemma":[0.9888425,0.000724924,0.0026922526,0.0069104675,0.0007064265,0.00012346193],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.021684494,0.0001342216,0.00094874034,0.0005873611,0.00024435064,0.0005450053,0.009408133,0.00005037073,0.0007198896],"category_scores_gemma":[0.008953086,0.00009269155,0.00020241413,0.00033138893,0.00061812444,0.005648054,0.004373066,0.00021346333,0.0000059808212],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042932515,0.0005071332,0.9343305,0.000078677076,0.0017992264,0.00001620543,0.0019518144,0.000103569335,0.00024873656,0.0010665773,0.02663518,0.032833014],"study_design_scores_gemma":[0.00040298398,0.00035383584,0.9422096,0.00009626106,0.0010421828,0.0000053171075,0.008734539,0.0030542896,0.00024181159,0.0016966399,0.042002194,0.00016031871],"about_ca_topic_score_codex":0.0008079212,"about_ca_topic_score_gemma":0.0044749756,"teacher_disagreement_score":0.032672696,"about_ca_system_score_codex":0.00002640378,"about_ca_system_score_gemma":0.00010622302,"threshold_uncertainty_score":0.9993949},"labels":[],"label_agreement":null},{"id":"W2766870458","doi":"10.1002/asi.23972","title":"<i>JASIST</i> special issue on biomedical information retrieval","year":2017,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Library science; Columbia university; Computer science; Information science; Health informatics; Health care; Sociology; Media studies; Political science","score_opus":0.045010136248981716,"score_gpt":0.3755419098705108,"score_spread":0.3305317736215291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766870458","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":[0.18827745,0.000016803007,0.0076002255,0.60035366,0.02314412,0.0017094311,0.00034959675,0.00008977565,0.17845893],"genre_scores_gemma":[0.9932192,0.00004545951,0.00077310187,0.0036706591,0.0011078861,0.000004457702,0.0000047823282,0.0000025443117,0.0011719285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961433,0.000031013362,0.00090960925,0.00007623585,0.0026540826,0.00018576303],"domain_scores_gemma":[0.99311256,0.00027906158,0.003489515,0.0004840138,0.0025742329,0.000060631115],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.015493191,0.000067135974,0.00017452698,0.0010355626,0.0013183388,0.001480343,0.0021244572,0.00012383562,0.000019200694],"category_scores_gemma":[0.06528114,0.000039954062,0.00006710912,0.0009911428,0.00046916527,0.009362763,0.0003857747,0.00018864682,0.00012285345],"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":[0.0001202646,0.000041490828,0.0030194125,0.000009434285,0.000025310928,2.1380531e-7,0.0010149655,0.000011818339,0.00008771775,0.16996406,0.36464307,0.46106222],"study_design_scores_gemma":[0.00058353896,0.00014170777,0.009227945,0.0000107426185,0.000010108493,0.000005611781,0.0010746982,0.00017929805,0.00087814947,0.022319041,0.9655189,0.000050295803],"about_ca_topic_score_codex":0.0000021322994,"about_ca_topic_score_gemma":0.0000024934097,"teacher_disagreement_score":0.8049417,"about_ca_system_score_codex":0.00023846517,"about_ca_system_score_gemma":0.0002354515,"threshold_uncertainty_score":0.9999818},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2768756899","doi":"","title":"Multidimensional User Manual (MUM): A Tool to Manage and Communicate Data Quality Information","year":2004,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Université Laval","funders":"","keywords":"Computer science; Quality (philosophy); Human–computer interaction; Data quality; Engineering","score_opus":0.10053683324435912,"score_gpt":0.36463029976508593,"score_spread":0.2640934665207268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768756899","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":[0.2191273,0.0005148126,0.6561625,0.077476054,0.0006936064,0.0025156925,0.00378297,0.00045047302,0.039276615],"genre_scores_gemma":[0.5722582,0.0008802934,0.39381158,0.0043257307,0.000050251103,0.00018783007,0.012171661,0.0000707457,0.01624372],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98482597,0.009051757,0.0019706034,0.0014597027,0.0021924675,0.0004995293],"domain_scores_gemma":[0.9804068,0.0040996536,0.001182092,0.011630311,0.0023315167,0.00034960447],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.045770966,0.00047099133,0.00069522497,0.00057186896,0.0005606439,0.0021234967,0.0068707746,0.0003088694,0.00026557976],"category_scores_gemma":[0.01354015,0.00044903846,0.00016129078,0.00070996693,0.00038597724,0.0017378868,0.02986574,0.000809675,0.00073118083],"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":[0.00012548834,0.00098294,0.0010034918,0.00040151217,0.00023858974,0.000010186034,0.023578983,0.00074007,0.00018512878,0.6062247,0.036523167,0.32998574],"study_design_scores_gemma":[0.0014740777,0.0000012628076,0.036288764,0.0013077854,0.000087426626,0.000008493267,0.0014556053,0.011687708,0.00087003387,0.042263255,0.9034095,0.0011460953],"about_ca_topic_score_codex":0.0050346954,"about_ca_topic_score_gemma":0.004830885,"teacher_disagreement_score":0.8668863,"about_ca_system_score_codex":0.00016454559,"about_ca_system_score_gemma":0.0002552107,"threshold_uncertainty_score":0.99979615},"labels":[],"label_agreement":null},{"id":"W2768921330","doi":"10.5220/0006582703100319","title":"Integrating a Survey Ontology into an Upper Level Ontology - Using the Data Collection Ontology (DCO) as the Basis for a Survey Ontology","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Ontology; Ontology-based data integration; Computer science; Upper ontology; Process ontology; Information retrieval; Suggested Upper Merged Ontology; Ontology alignment; Semantic Web","score_opus":0.7661720941383888,"score_gpt":0.5633738214982361,"score_spread":0.2027982726401527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768921330","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":[0.31682438,0.00026186917,0.62431955,0.031701762,0.005586634,0.0032770955,0.0017890815,0.00015187748,0.016087713],"genre_scores_gemma":[0.97160155,0.00003330949,0.015606158,0.005790621,0.00020581186,0.00014213775,0.0007039063,0.000039154118,0.0058773803],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.984825,0.009698953,0.0016351715,0.0019655116,0.000867282,0.0010080818],"domain_scores_gemma":[0.971113,0.01861931,0.0013700039,0.007638562,0.0010735601,0.00018554875],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04630525,0.00046924132,0.0011048313,0.0003334039,0.0042437147,0.0013932968,0.0101046255,0.00045796626,0.00077703665],"category_scores_gemma":[0.08015772,0.0002560888,0.00017391186,0.0005271731,0.0015601747,0.001667507,0.003109478,0.00053916353,0.00011716841],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003073393,0.0009211159,0.40574175,0.000029004595,0.00093318534,0.00003420222,0.01047604,0.00005610009,0.00030538274,0.22399727,0.17012364,0.18430892],"study_design_scores_gemma":[0.0014216078,0.0007256165,0.8262429,0.000017626571,0.00014959175,0.00016207548,0.009519104,0.04124623,0.000054565775,0.06263397,0.05720771,0.00061899016],"about_ca_topic_score_codex":0.49785203,"about_ca_topic_score_gemma":0.9761762,"teacher_disagreement_score":0.6547771,"about_ca_system_score_codex":0.00019530575,"about_ca_system_score_gemma":0.0006740724,"threshold_uncertainty_score":0.99998915},"labels":[],"label_agreement":null},{"id":"W2770448539","doi":"10.1177/0961000617742465","title":"Data science in data librarianship: Core competencies of a data librarian","year":2017,"lang":"en","type":"article","venue":"Journal of Librarianship and Information Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data curation; Computer science; Data management; Metadata; Data science; World Wide Web; Library science; Database","score_opus":0.6056634588857582,"score_gpt":0.47246913967965815,"score_spread":0.1331943192061001,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770448539","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":[0.45278817,0.0015077045,0.10127295,0.10950895,0.012743524,0.002619591,0.022334628,0.00015009029,0.29707438],"genre_scores_gemma":[0.9663391,0.00038927724,0.031756528,0.0010655327,0.00014269237,6.584871e-7,0.00019603314,0.0000063089874,0.00010385421],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9918983,0.00014178111,0.0024775018,0.00073447684,0.0042809783,0.00046696272],"domain_scores_gemma":[0.98285264,0.0010000601,0.0037554111,0.011360758,0.00060288125,0.00042823027],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.043919627,0.00019019085,0.0005286026,0.002097925,0.001086042,0.010158893,0.054271508,0.00007147681,0.00011046506],"category_scores_gemma":[0.03076707,0.00013668778,0.000029939685,0.0027159362,0.0044203415,0.4350524,0.025202278,0.0003817633,0.00002671035],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036925325,0.0002726261,0.09727208,0.00016163482,0.000036559613,0.000037447244,0.006460982,0.00006164095,0.00072022,0.5059407,0.06204803,0.32661885],"study_design_scores_gemma":[0.001467256,0.0001602205,0.5025309,0.00028264057,0.0000316793,0.00008942857,0.009965533,0.060971122,0.00019710803,0.021315897,0.40261498,0.00037323724],"about_ca_topic_score_codex":0.00006561949,"about_ca_topic_score_gemma":0.000051105584,"teacher_disagreement_score":0.51355094,"about_ca_system_score_codex":0.000024127414,"about_ca_system_score_gemma":0.003123035,"threshold_uncertainty_score":0.99828905},"labels":[],"label_agreement":null},{"id":"W2770828134","doi":"10.1145/3110025.3120958","title":"datumPIPE","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"McMaster University","funders":"","keywords":"Computer science; Data quality; Data mining; Quality (philosophy); Data integrity; Set (abstract data type); Data set; Database; Artificial intelligence; Engineering","score_opus":0.644200694101546,"score_gpt":0.5830364078440127,"score_spread":0.06116428625753334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770828134","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067698704,0.0000038713465,0.017595261,0.009830878,0.00045204567,0.0000409638,0.00000767318,0.000021907035,0.96527755],"genre_scores_gemma":[0.8126388,0.0000031744994,0.0014286473,0.0012889341,0.000045981742,0.0000013462077,0.0000017034187,0.0000013020543,0.1845901],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99906945,0.000026391444,0.00014045693,0.00017772775,0.00050569983,0.00008028369],"domain_scores_gemma":[0.9979441,0.00010636722,0.00008484661,0.0017892133,0.000036287485,0.000039160084],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0022318326,0.000028805514,0.000060071707,0.000031939748,0.0003155788,0.0011235985,0.0017526938,0.000011118403,0.00337024],"category_scores_gemma":[0.0025179354,0.00001759397,0.000025098545,0.000025992582,0.00006204714,0.00061865506,0.0006397177,0.000022572693,0.007440115],"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":[0.0000015341161,0.000010117565,0.0013610194,3.0822918e-7,0.0000019958065,0.0000026504435,0.000022323191,2.8798826e-7,0.000010489679,0.28543332,0.5360342,0.1771217],"study_design_scores_gemma":[0.000058005062,0.0000045366105,0.04449322,5.6776116e-7,9.008312e-7,2.0974197e-7,0.00012961209,0.000084499196,0.00009067847,0.08979462,0.86531246,0.000030664803],"about_ca_topic_score_codex":0.000109113935,"about_ca_topic_score_gemma":0.00017475872,"teacher_disagreement_score":0.8058689,"about_ca_system_score_codex":0.000002429436,"about_ca_system_score_gemma":0.000006022173,"threshold_uncertainty_score":0.99991333},"labels":[],"label_agreement":null},{"id":"W2773765147","doi":"10.1155/2017/6120820","title":"Using Distributed Data over HBase in Big Data Analytics Platform for Clinical Services","year":2017,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"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 Victoria; Island Health","funders":"Western Canada Research Grid","keywords":"Computer science; NoSQL; Big data; Metadata; Usability; SPARK (programming language); Database; Analytics; Distributed File System; Cloud computing; Distributed data store; Data mining; World Wide Web; Operating system","score_opus":0.9139543871601463,"score_gpt":0.7032738511653618,"score_spread":0.21068053599478453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2773765147","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":[0.007286176,0.00010112541,0.98822117,0.0028748433,0.0003369297,0.00029413632,0.00064409926,0.0000073526826,0.00023415784],"genre_scores_gemma":[0.014612581,0.00004317569,0.98317933,0.0008820527,0.00028424265,0.000004732394,0.0009466129,0.00000734962,0.00003989505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967998,0.00031510057,0.0013436608,0.0006750036,0.00067741045,0.00018898287],"domain_scores_gemma":[0.9831841,0.014157322,0.000420726,0.002011758,0.00010273632,0.00012333471],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030988261,0.00012647569,0.00060882105,0.00016684308,0.00016028971,0.00018390002,0.0024679443,0.00007124758,0.00005824294],"category_scores_gemma":[0.029706728,0.00008287484,0.000024376452,0.00020260685,0.000427545,0.00061997847,0.0027390586,0.00015620826,0.000004048463],"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":[0.00019857286,0.0006145722,0.009170651,0.00066205027,0.000096575495,0.0000381169,0.00043287346,0.00074177387,0.000007814221,0.16179542,0.010925973,0.8153156],"study_design_scores_gemma":[0.00078472163,0.000021172304,0.012398449,0.00012928646,0.000028536055,0.000002179266,0.00027822025,0.5220956,2.56186e-7,0.45805395,0.0061498494,0.000057743066],"about_ca_topic_score_codex":0.000058517748,"about_ca_topic_score_gemma":0.000101715545,"teacher_disagreement_score":0.81525785,"about_ca_system_score_codex":0.000015058049,"about_ca_system_score_gemma":0.00004919613,"threshold_uncertainty_score":0.9978015},"labels":[],"label_agreement":null},{"id":"W2775078427","doi":"10.1177/2053951717745678","title":"Challenges in administrative data linkage for research","year":2017,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":356,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Economic and Social Research Council; Wellcome Trust","keywords":"Linkage (software); Record linkage; Computer science; Data quality; Data science; Data collection; Confidentiality; Data mining; Sample (material); Population; Computer security; Engineering; Statistics; Sociology","score_opus":0.9805021151538041,"score_gpt":0.681924870153455,"score_spread":0.2985772450003491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775078427","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":[0.02054836,0.01685871,0.056675423,0.4947101,0.008716423,0.010453798,0.18591082,0.00032732333,0.20579906],"genre_scores_gemma":[0.9244187,0.019760638,0.031172777,0.0013382344,0.0023792582,0.00018348428,0.012218664,0.00004949484,0.008478783],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99560934,0.00036895066,0.00049364823,0.0015490326,0.0015135409,0.00046548835],"domain_scores_gemma":[0.98190695,0.0026410192,0.00023717608,0.014890411,0.00021302435,0.0001114057],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.043281335,0.0001217356,0.00026117873,0.000056613997,0.0008379799,0.001330097,0.017246831,0.0001122376,0.000042092364],"category_scores_gemma":[0.017427856,0.00009554727,0.00005861652,0.00017658819,0.00048061064,0.002232797,0.014980306,0.00029884785,0.00020948189],"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":[0.00001755518,0.00011708596,0.00012636418,0.000027941005,0.000024636245,0.0000044367735,0.0013596436,1.0215941e-7,0.000008770851,0.007451819,0.6041026,0.38675904],"study_design_scores_gemma":[0.00047704368,0.000053241467,0.013985453,0.000030463236,0.0000067875812,4.708933e-7,0.016254015,0.0015982552,0.000016281761,0.017350942,0.95009947,0.00012757762],"about_ca_topic_score_codex":0.00024212286,"about_ca_topic_score_gemma":0.007538258,"teacher_disagreement_score":0.9038703,"about_ca_system_score_codex":0.000034576737,"about_ca_system_score_gemma":0.00022248088,"threshold_uncertainty_score":0.9997066},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W2782105765","doi":"10.24251/hicss.2018.096","title":"Data Quality Challenges in Twitter Content Analysis for Informing Policy Making in Health Care","year":2018,"lang":"en","type":"article","venue":"Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Social media; Microblogging; Computer science; Variety (cybernetics); Process (computing); Profiling (computer programming); Reliability (semiconductor); Content analysis; Set (abstract data type); Data science; Quality (philosophy); World Wide Web; Sociology; Artificial intelligence","score_opus":0.48591597449744817,"score_gpt":0.4817864261405992,"score_spread":0.004129548356848978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782105765","genre_codex":"other","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":[0.05299052,0.00008922962,0.00017738288,0.035885382,0.0026058285,0.001832338,0.0028862308,0.0000798939,0.9034532],"genre_scores_gemma":[0.99735826,0.000055778164,0.0007074539,0.0005318781,0.00040399656,0.0001264881,0.000015369002,0.00001987492,0.00078089134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9854631,0.00018166548,0.0038813832,0.002337095,0.0071198223,0.0010169578],"domain_scores_gemma":[0.98416305,0.0007280979,0.0053022336,0.00084056717,0.008757576,0.0002084828],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.023191418,0.00066334946,0.0014200166,0.0032345096,0.00091746496,0.001466142,0.019351725,0.00022433249,0.000052380863],"category_scores_gemma":[0.0013575351,0.0004209233,0.00050694775,0.0046734004,0.0023861134,0.004122646,0.0036785717,0.0004827571,0.0000269807],"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":[0.00026545936,0.00014566298,0.01541323,0.00032790442,0.00014173343,4.3638593e-7,0.009523423,0.000090217065,0.000065807704,0.97057706,0.0010204883,0.0024286048],"study_design_scores_gemma":[0.0008517168,0.0006436309,0.018834636,0.0031600983,0.00003868625,0.000017715087,0.9668316,0.0014290315,0.00013667456,0.0044338345,0.0031207092,0.0005016407],"about_ca_topic_score_codex":0.0018772843,"about_ca_topic_score_gemma":0.0012360063,"teacher_disagreement_score":0.9661432,"about_ca_system_score_codex":0.0010057754,"about_ca_system_score_gemma":0.0010126593,"threshold_uncertainty_score":0.9998243},"labels":[],"label_agreement":null},{"id":"W2783287373","doi":"","title":"Quantifying duplication to improve data quality.","year":2017,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data deduplication; Quality (philosophy); Gene duplication; Database","score_opus":0.8003330727568276,"score_gpt":0.6486310263808803,"score_spread":0.1517020463759473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783287373","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":[0.27095932,0.001706497,0.032770183,0.61073804,0.00876677,0.02556598,0.022413487,0.00012599892,0.026953714],"genre_scores_gemma":[0.9879181,0.00028586827,0.0026257269,0.0001459885,0.00007133011,0.0001761056,0.0000223788,0.000011578275,0.008742941],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949221,0.0008526142,0.0007330593,0.0009991754,0.0020432486,0.00044982185],"domain_scores_gemma":[0.97642314,0.005693792,0.0009244687,0.0070293886,0.009792272,0.00013693955],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0140631655,0.00016320549,0.00047387637,0.0001678403,0.002026575,0.00062682567,0.0066760634,0.000041857445,0.00001852687],"category_scores_gemma":[0.12682173,0.00010001215,0.000063796106,0.00078431197,0.0007972142,0.0007992816,0.0053444365,0.00019666612,0.00008098473],"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":[0.0011485266,0.00030248793,0.0009725575,0.00019228237,0.00026436575,7.7373085e-7,0.006637512,0.0002118593,0.016533773,0.62265795,0.10217025,0.24890766],"study_design_scores_gemma":[0.0019619402,0.00061463495,0.0092317,0.00051285763,0.00002851211,5.5823744e-8,0.14251678,0.0012374235,0.045579575,0.09258925,0.70526785,0.00045945472],"about_ca_topic_score_codex":0.000031985157,"about_ca_topic_score_gemma":0.0025332083,"teacher_disagreement_score":0.71695876,"about_ca_system_score_codex":0.000114567716,"about_ca_system_score_gemma":0.0002963987,"threshold_uncertainty_score":0.99927264},"labels":[],"label_agreement":null},{"id":"W2783291455","doi":"10.1109/bigdata.2017.8258218","title":"Identifying and mitigating risks to the quality of open data in the post-truth era","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Open data; Big data; Data science; Transparency (behavior); Data quality; Computer science; Analytics; Quality (philosophy); Ground truth; Open government; Data analysis; Computer security; Data mining; World Wide Web; Business","score_opus":0.7811195203369069,"score_gpt":0.6219168215022497,"score_spread":0.1592026988346572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783291455","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":[0.901267,0.00003642471,0.0035877358,0.0459471,0.00024953712,0.00077210856,0.00033040592,0.0000062947506,0.04780339],"genre_scores_gemma":[0.99480194,0.000007161921,0.002258038,0.0023816419,0.000022160802,0.000007061384,0.000014089561,0.0000020561627,0.0005058633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99731433,0.00069413584,0.0005681882,0.00041425944,0.0008755143,0.00013356813],"domain_scores_gemma":[0.99261487,0.0023279667,0.00036729735,0.0045728986,0.00008069791,0.000036284873],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.039203677,0.00006246542,0.00017246035,0.000046375404,0.00053542707,0.0036274246,0.011933473,0.00001690277,0.00012128461],"category_scores_gemma":[0.017641861,0.000028170274,0.00001863766,0.0001427226,0.0001310835,0.0016080044,0.012093373,0.00009947277,0.00005325972],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006594879,0.00012610352,0.07537943,0.000037146357,0.000038344628,0.0000057796633,0.017668,0.00000842843,0.00020867217,0.32286772,0.04948779,0.5341067],"study_design_scores_gemma":[0.00020993841,0.000014714372,0.9161479,0.000021129346,0.000005856883,5.6745665e-7,0.03856423,0.00017576605,0.000056205972,0.028260434,0.016471935,0.00007132733],"about_ca_topic_score_codex":0.025132485,"about_ca_topic_score_gemma":0.025397781,"teacher_disagreement_score":0.84076846,"about_ca_system_score_codex":0.0000039604583,"about_ca_system_score_gemma":0.000021979986,"threshold_uncertainty_score":0.9974069},"labels":[],"label_agreement":null},{"id":"W2786093037","doi":"10.1109/hpcc-smartcity-dss.2017.35","title":"An Efficient Type-Agnostic Approach for Finding Sub-sequences in Data","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 Toronto","funders":"","keywords":"Computer science; Search engine indexing; Data mining; Data deduplication; Inverted index; Normalization (sociology); Semantics (computer science); Index (typography); Raw data; Data type; Data structure; Theoretical computer science; Information retrieval; Database","score_opus":0.5830582344166529,"score_gpt":0.5204564048528669,"score_spread":0.06260182956378602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786093037","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":[0.30181468,0.000083577295,0.6463284,0.0026446555,0.0017405704,0.0015107165,0.00047060856,0.0000828486,0.045323968],"genre_scores_gemma":[0.9824299,0.000007665324,0.015961206,0.00015789896,0.000052238833,0.000013851237,0.00016586602,0.000004597688,0.0012067249],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800396,0.0000963063,0.00036515278,0.00068494893,0.0006108652,0.00023874619],"domain_scores_gemma":[0.9958396,0.0006719064,0.0001755591,0.0031716346,0.00006964165,0.00007163994],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0076650986,0.00008677381,0.00017390183,0.00014589838,0.00036450353,0.0011252484,0.0046538496,0.00003763859,0.00008920904],"category_scores_gemma":[0.007428887,0.00005980523,0.000022358423,0.00015714628,0.00012014066,0.0008837686,0.00091740297,0.000054867487,0.000114809736],"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":[0.00029024426,0.0021512858,0.028985793,0.00013306277,0.000064601845,0.000042579497,0.002263976,0.036175344,0.0010800639,0.36646673,0.26977006,0.29257628],"study_design_scores_gemma":[0.0008950809,0.0001575201,0.029665144,0.000026576838,0.000023262384,0.0000021629103,0.0042962763,0.882825,0.0005229975,0.018781627,0.062374722,0.00042958796],"about_ca_topic_score_codex":0.00026381007,"about_ca_topic_score_gemma":0.00062311965,"teacher_disagreement_score":0.8466497,"about_ca_system_score_codex":0.000016005051,"about_ca_system_score_gemma":0.000041397834,"threshold_uncertainty_score":0.99991167},"labels":[],"label_agreement":null},{"id":"W2787120925","doi":"10.3233/978-1-61499-830-3-1138","title":"Mapping the Electronic Health Record: A Method to Study Display Fragmentation","year":2017,"lang":"en","type":"article","venue":"Studies in health technology and informatics","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 Victoria","funders":"Agency for Healthcare Research and Quality","keywords":"Fragmentation (computing); Computer science; Electronic health record; Computer graphics (images); Health care; Political science; Operating system","score_opus":0.2764781090987098,"score_gpt":0.5452845495756286,"score_spread":0.26880644047691876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787120925","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":[0.5082333,0.003174359,0.18989222,0.29105136,0.0012003258,0.0048564663,0.000026937978,0.00014414302,0.0014208751],"genre_scores_gemma":[0.963572,0.0027775357,0.023046132,0.010150528,0.000022214792,0.0002436113,0.0000020054924,0.0000047791314,0.00018118443],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99728525,0.00031341368,0.0013416447,0.00020391303,0.00038889423,0.0004668835],"domain_scores_gemma":[0.99747264,0.0005318518,0.00087849074,0.0009901994,0.00007824931,0.00004858556],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.016926948,0.000119658296,0.0004196261,0.00058108475,0.0019736385,0.00012647579,0.0009945295,0.00004642703,0.0000046575437],"category_scores_gemma":[0.0028075997,0.000073981435,0.000018839084,0.000679211,0.00023345188,0.00039954166,0.0012697378,0.00032511752,0.000028727167],"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":[0.000013154268,0.000056923152,0.015939709,0.00010172958,0.000051257506,6.480093e-7,0.05458928,0.000018883582,6.199606e-8,0.07317117,0.0048212823,0.8512359],"study_design_scores_gemma":[0.0006576653,0.0010715753,0.048073202,0.00010549362,0.000004228509,0.0000048986662,0.6149849,0.000930128,0.000002019136,0.12775353,0.20627168,0.00014066242],"about_ca_topic_score_codex":0.00020985317,"about_ca_topic_score_gemma":0.0016056497,"teacher_disagreement_score":0.85109526,"about_ca_system_score_codex":0.000146282,"about_ca_system_score_gemma":0.00008571961,"threshold_uncertainty_score":0.99932563},"labels":[],"label_agreement":null},{"id":"W2789351899","doi":"10.3389/frobt.2018.00008","title":"Bridging Weighted Rules and Graph Random Walks for Statistical Relational Models","year":2018,"lang":"en","type":"article","venue":"Frontiers in Robotics and AI","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistical relational learning; Computer science; Random walk; Relational database; Theoretical computer science; Ranking (information retrieval); Artificial intelligence; Machine learning; Data mining; Mathematics; Statistics","score_opus":0.07816044410258924,"score_gpt":0.34746207764412407,"score_spread":0.2693016335415348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789351899","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":[0.002460448,0.00021440077,0.99392015,0.0020178237,0.00048538888,0.00019427185,0.00013382593,0.000008806041,0.0005648681],"genre_scores_gemma":[0.28020585,0.00016101189,0.717473,0.0010084183,0.00014428729,0.0000138669675,0.00009008232,0.000010614147,0.0008929292],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987958,0.000070068345,0.00033275786,0.00030598184,0.00032499275,0.00017040767],"domain_scores_gemma":[0.9992729,0.00034973232,0.000062905696,0.00015614486,0.00008650101,0.00007185155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014261709,0.000081936654,0.00020733183,0.0001826882,0.00016592917,0.00018562624,0.0001339948,0.000045559584,0.000015742215],"category_scores_gemma":[0.000320355,0.00006516818,0.000023660295,0.0001258194,0.00025190698,0.0002868352,0.00010324415,0.00006578403,0.000003512434],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020561276,0.000043000433,0.003008583,0.000016338978,0.000032565444,0.0000031915124,0.00040739583,0.00235742,0.0000014908176,0.6921349,0.18748729,0.114302196],"study_design_scores_gemma":[0.0007741308,0.00002654619,0.0018459733,0.000008867092,0.000009975538,5.282957e-7,0.00011596129,0.47477427,0.0000012840902,0.51635706,0.006022894,0.00006252373],"about_ca_topic_score_codex":0.000013191428,"about_ca_topic_score_gemma":0.000016572765,"teacher_disagreement_score":0.47241685,"about_ca_system_score_codex":0.000009363254,"about_ca_system_score_gemma":0.000015669697,"threshold_uncertainty_score":0.2657481},"labels":[],"label_agreement":null},{"id":"W2789515120","doi":"10.1016/j.websem.2018.02.001","title":"Publishing privacy logs to facilitate transparency and accountability","year":2018,"lang":"en","type":"article","venue":"Journal of Web Semantics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Accountability; Audit; Privacy policy; Information privacy; Transparency (behavior); SPARQL; Implementation; Computer security; World Wide Web; Semantic Web; Accounting; RDF; Business; Software engineering","score_opus":0.3420801518467736,"score_gpt":0.4188652556274554,"score_spread":0.07678510378068182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789515120","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":[0.9303081,0.00007586975,0.044882964,0.021311218,0.00085051724,0.00012566205,0.00005095264,0.000010456653,0.0023842624],"genre_scores_gemma":[0.99298435,0.00005297402,0.005158712,0.0011164547,0.0002337894,4.343346e-7,8.083585e-7,0.000004797418,0.00044769005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968368,0.00019562786,0.0010805725,0.00025726616,0.0014027434,0.00022701155],"domain_scores_gemma":[0.9973604,0.0005697923,0.0004166307,0.0005304368,0.00089388795,0.00022886111],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010207718,0.000110378845,0.00032775477,0.0003151211,0.00013027931,0.0013342154,0.001161212,0.0000542791,0.00021255367],"category_scores_gemma":[0.0065612034,0.00007657648,0.000087056746,0.000528318,0.00015682138,0.0025833363,0.00030325894,0.00020638121,0.00010160732],"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":[0.00053254835,0.00064932776,0.083699726,0.00017272335,0.00021370841,0.00009221992,0.046658877,0.00007853105,0.0039376603,0.011294883,0.56325203,0.28941777],"study_design_scores_gemma":[0.0007333356,0.0005707419,0.06675513,0.00007611506,0.00005161368,0.000045174867,0.0049621775,0.00044680227,0.00028059402,0.04925467,0.8766105,0.00021312949],"about_ca_topic_score_codex":0.000032576812,"about_ca_topic_score_gemma":0.00019934855,"teacher_disagreement_score":0.3133585,"about_ca_system_score_codex":0.000032030097,"about_ca_system_score_gemma":0.00008922023,"threshold_uncertainty_score":0.9997025},"labels":[],"label_agreement":null},{"id":"W2789592939","doi":"10.5441/002/edbt.2018.87","title":"FastOFD: Contextual Data Cleaning with Ontology Functional Dependencies","year":2018,"lang":"en","type":"article","venue":"Movebank","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"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":"Computer science; Ontology; Functional dependency; Dependency theory (database theory); Information retrieval; Data mining; Relational database","score_opus":0.4593973220632835,"score_gpt":0.4301787023006636,"score_spread":0.029218619762619913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789592939","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":[0.2443273,0.00014157352,0.5556008,0.003989126,0.0022415493,0.0003862065,0.00051211903,0.00021495826,0.19258635],"genre_scores_gemma":[0.98011374,0.00000222315,0.0024263216,0.002869073,0.00036008644,0.000005428137,0.00012561468,0.000008833915,0.0140886605],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973751,0.00015593429,0.0003719344,0.0006895432,0.0011327164,0.00027477543],"domain_scores_gemma":[0.99736935,0.0005640788,0.00015488408,0.001579377,0.0002526273,0.000079691],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026873585,0.00011981436,0.0001966298,0.00012829843,0.0002590996,0.00030271118,0.0015668151,0.000051588722,0.0034310753],"category_scores_gemma":[0.0013863908,0.00008120228,0.00002640444,0.0002979303,0.00042047337,0.0009491522,0.0010297737,0.00011064636,0.0024605282],"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":[0.0006205366,0.00017042313,0.024684293,0.000008419848,0.00014853536,0.00005914456,0.0011765748,0.00005820047,0.00020201114,0.18389708,0.56709296,0.22188182],"study_design_scores_gemma":[0.0008790408,0.00036293326,0.10904405,0.0000143851485,0.0000252111,0.00003659034,0.0034279027,0.0017518026,0.00017951573,0.012189239,0.87182206,0.00026727654],"about_ca_topic_score_codex":0.00022199714,"about_ca_topic_score_gemma":0.0058354256,"teacher_disagreement_score":0.73578644,"about_ca_system_score_codex":0.000024228999,"about_ca_system_score_gemma":0.00006711101,"threshold_uncertainty_score":0.99831617},"labels":[],"label_agreement":null},{"id":"W2792505333","doi":"10.47622/978-1-928331-56-8","title":"The Social Dynamics of Open Data","year":2017,"lang":"en","type":"book","venue":"African Minds eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Comisión Nacional de Investigación Científica y Tecnológica; International Development Research Centre","keywords":"Open data; Data collection; Data science; Dynamics (music); Computer science; Open science; Open research; Open source; Management science; World Wide Web; Sociology; Social science; Engineering; Statistics; Mathematics","score_opus":0.412274993420936,"score_gpt":0.4866937168620067,"score_spread":0.0744187234410707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792505333","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000042761567,0.000036920417,0.00033775595,0.0015213643,0.0004878107,0.00053137203,0.004480064,0.000009103432,0.9925913],"genre_scores_gemma":[0.0017536137,0.0000074979125,0.00019227425,0.00013944144,0.00023933047,0.000017003409,0.00065383717,0.000024680041,0.9969723],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99587345,0.00025259762,0.0009320966,0.00085214333,0.001780787,0.00030893766],"domain_scores_gemma":[0.98980576,0.0013888744,0.0017995121,0.0067063505,0.00022054961,0.00007894388],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.009052572,0.00024557786,0.00064202637,0.00013385083,0.001117386,0.0023803262,0.035884455,0.00018521912,0.0001404625],"category_scores_gemma":[0.0014436287,0.00015654636,0.00013679975,0.000040372277,0.0012638986,0.00029880283,0.023040615,0.00031275392,0.00022473744],"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":[0.000016499838,0.0000068547174,7.389218e-7,0.00000450185,0.000055335735,0.000004433602,0.00030618985,2.046688e-8,1.1713708e-7,0.19139907,0.4944133,0.31379297],"study_design_scores_gemma":[0.00013266805,0.000025701698,0.000025708086,0.0000209553,0.00006052331,6.845275e-7,0.0010884104,0.000063838226,0.0000010185338,0.20217094,0.79625237,0.00015719504],"about_ca_topic_score_codex":0.00026661798,"about_ca_topic_score_gemma":0.00553647,"teacher_disagreement_score":0.31363577,"about_ca_system_score_codex":0.0001016116,"about_ca_system_score_gemma":0.00089596125,"threshold_uncertainty_score":0.9986553},"labels":[{"model":"gemma","categories":["open_science","sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["scholarly_communication","open_science"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2792572948","doi":"10.1145/3186549.3186559","title":"Data Quality","year":2018,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":32,"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 Toronto; University of Waterloo","funders":"","keywords":"Computer science; Scope (computer science); Quality (philosophy); Data quality; Empiricism; Data science; Action (physics); Data mining; Epistemology; Programming language; Engineering","score_opus":0.6848192121373361,"score_gpt":0.55904053398058,"score_spread":0.12577867815675614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792572948","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":[0.4250788,0.00018925531,0.21887101,0.05202212,0.012401808,0.001081529,0.0025327324,0.00060209946,0.28722063],"genre_scores_gemma":[0.89865524,0.00005338884,0.045093898,0.0081806835,0.001891306,0.000015029494,0.00034858132,0.000027138585,0.045734715],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99666893,0.00042643203,0.00067723804,0.00085369206,0.0011031732,0.00027053876],"domain_scores_gemma":[0.9894873,0.001685167,0.00024193196,0.008265403,0.00020206535,0.0001181657],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009842128,0.000111867506,0.00023540446,0.000115982395,0.00019032326,0.00032120335,0.0071133245,0.000054924927,0.0034401536],"category_scores_gemma":[0.019623693,0.000081814134,0.000049498925,0.000543984,0.00021269398,0.00094504183,0.0050032553,0.00009706799,0.008168026],"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":[0.000022609218,0.000039125796,0.0016710487,0.0000021133073,0.000011581835,0.0000017328605,0.00009111282,8.5897916e-8,0.000048970454,0.005743865,0.52502155,0.46734622],"study_design_scores_gemma":[0.00015041696,0.00006110441,0.008588974,0.0000038028631,0.000006493947,7.0167914e-7,0.00035230495,0.00020512336,0.000076564764,0.1165323,0.8738972,0.00012499624],"about_ca_topic_score_codex":0.00043266453,"about_ca_topic_score_gemma":0.0021389693,"teacher_disagreement_score":0.47357646,"about_ca_system_score_codex":0.000015726251,"about_ca_system_score_gemma":0.000040299135,"threshold_uncertainty_score":0.99825865},"labels":[],"label_agreement":null},{"id":"W2793476072","doi":"10.1515/jos-2018-0003","title":"Design-Based Estimation with Record-Linked Administrative Files and a Clerical Review Sample","year":2018,"lang":"en","type":"review","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimator; Sample (material); Statistics; Record linkage; Estimation; Linkage (software); Population; Econometrics; Regression analysis; Computer science; Missing data; Regression; Mathematics; Demography; Sociology; Engineering","score_opus":0.49991367302203166,"score_gpt":0.5189310698110305,"score_spread":0.019017396788998886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793476072","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.00300866e-7,0.41526237,0.5832051,0.000065911016,0.00019324027,0.0003844906,0.00085557933,0.0000044837802,0.000028738543],"genre_scores_gemma":[4.774076e-7,0.64266986,0.35684144,0.00018343331,0.00017863272,0.0000060262373,0.00007899581,0.000013335187,0.000027827735],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99453074,0.0012088551,0.002267866,0.00032721565,0.0014689668,0.00019635582],"domain_scores_gemma":[0.9847565,0.009841784,0.003754211,0.00034964242,0.0011098093,0.0001880057],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005265758,0.00030947023,0.0019505094,0.0002499511,0.00013570677,0.00031171629,0.0006343974,0.0001164896,0.00034745247],"category_scores_gemma":[0.019001905,0.00018451698,0.00016202025,0.00057050964,0.00025647724,0.00017595166,0.00007878456,0.00034561753,0.000042235624],"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":[0.000071089926,0.00007531152,4.414461e-7,0.003467249,0.00007440508,0.00005985954,0.000037327878,0.0000123141135,2.2583588e-9,0.0005700364,0.10242252,0.89320946],"study_design_scores_gemma":[0.00019026901,0.0014591631,0.0000064507326,0.018003386,0.0010350212,0.00003778264,0.000035564815,0.0009291022,5.8703552e-8,0.0031867719,0.9748866,0.00022981751],"about_ca_topic_score_codex":0.000012442977,"about_ca_topic_score_gemma":0.000047514983,"teacher_disagreement_score":0.8929796,"about_ca_system_score_codex":0.00008696061,"about_ca_system_score_gemma":0.0013092386,"threshold_uncertainty_score":0.98926145},"labels":[],"label_agreement":null},{"id":"W2795302121","doi":"10.1109/icde.2018.00093","title":"Seeping Semantics: Linking Datasets Using Word Embeddings for Data Discovery","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"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; Schema (genetic algorithms); Knowledge graph; Semantics (computer science); Linked data; Information retrieval; Semantic Web; Word (group theory); RDF; Distributional semantics; Natural language processing; Semantic similarity; Programming language","score_opus":0.49323168033993964,"score_gpt":0.519707133187662,"score_spread":0.026475452847722403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795302121","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":[0.01744589,0.000022354652,0.9766752,0.0010229704,0.00088816753,0.00031912953,0.002067088,0.000055659588,0.001503556],"genre_scores_gemma":[0.6047588,0.000024751494,0.37391815,0.008209795,0.0019275179,0.000011227342,0.0053598178,0.00004993685,0.005740017],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970962,0.00009177249,0.0006427289,0.00092027435,0.0008759178,0.0003731115],"domain_scores_gemma":[0.99576837,0.0010035377,0.00024476054,0.0027783962,0.000127052,0.000077868965],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0058664903,0.00014101829,0.0002499748,0.00019397853,0.00042134372,0.001793432,0.002906196,0.000048406288,0.0002087417],"category_scores_gemma":[0.0025378172,0.000107015854,0.000051861327,0.00044836572,0.00015628217,0.004182257,0.0035921242,0.0000696452,0.00025934007],"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":[0.000099686964,0.00016148498,0.002218245,0.00010600447,0.00014592342,0.000012453418,0.00091126346,0.00007543709,0.0009314037,0.07507817,0.7434011,0.17685884],"study_design_scores_gemma":[0.00031014343,0.00003484496,0.00026891704,0.00008589038,0.000048947157,0.0000034243872,0.0015515866,0.19762781,0.00047552463,0.025307236,0.7740192,0.0002665028],"about_ca_topic_score_codex":0.00013310344,"about_ca_topic_score_gemma":0.0004124949,"teacher_disagreement_score":0.60275704,"about_ca_system_score_codex":0.00002378588,"about_ca_system_score_gemma":0.000047921174,"threshold_uncertainty_score":0.9992428},"labels":[],"label_agreement":null},{"id":"W2795335174","doi":"10.5539/cis.v11n2p34","title":"Constructing Metadata Schema of Scientific and Technical Report Based on FRBR","year":2018,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Nanjing University of Aeronautics and Astronautics; Nanjing University; Government of Jiangsu Province","keywords":"Computer science; Metadata; Schema (genetic algorithms); Information retrieval; Metadata modeling; Resource (disambiguation); Scientific literature; Data science; World Wide Web; Metadata repository","score_opus":0.11854589095090393,"score_gpt":0.3938698230366426,"score_spread":0.2753239320857387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795335174","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":[0.1594581,0.0000042711704,0.8141837,0.000668756,0.0007091999,0.00016651912,0.000026936643,0.000030295312,0.02475219],"genre_scores_gemma":[0.9508633,7.980546e-7,0.04845924,0.00060092297,0.00002327256,0.0000012021717,0.000010326116,7.221923e-7,0.000040228966],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774593,0.000029395458,0.0005771769,0.0002860325,0.0012295517,0.0001319085],"domain_scores_gemma":[0.9982222,0.00023145077,0.00029582655,0.0006269383,0.0005368185,0.000086764856],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009080639,0.00006173787,0.00012671082,0.0005411693,0.00038923358,0.0015906905,0.0005921882,0.000020148336,0.000024217066],"category_scores_gemma":[0.001643513,0.000043896438,0.000016535838,0.0012350613,0.00244724,0.008136811,0.000609737,0.00004769509,0.000025877502],"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":[0.000023863078,0.000039009123,0.0049432404,0.000031930856,0.000004000257,0.000002406272,0.00056518463,0.000033944325,0.0004534127,0.31267294,0.011370908,0.6698592],"study_design_scores_gemma":[0.0010673932,0.0005407976,0.09337237,0.00014125029,0.000017581857,0.00025674063,0.001420997,0.5527157,0.013382484,0.00889846,0.32769707,0.00048914383],"about_ca_topic_score_codex":0.000004410878,"about_ca_topic_score_gemma":0.000002139836,"teacher_disagreement_score":0.7914052,"about_ca_system_score_codex":0.000011724623,"about_ca_system_score_gemma":0.000100428166,"threshold_uncertainty_score":0.99944574},"labels":[],"label_agreement":null},{"id":"W2798581322","doi":"10.3233/978-1-61499-852-5-6","title":"Exploring Semantic Data Federation to Enable Malaria Surveillance Queries","year":2018,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of New Brunswick","funders":"","keywords":"Computer science; Malaria; Software deployment; Semantic Web; World Wide Web; Globe; Data science; Coding (social sciences); Medicine; Software engineering","score_opus":0.6290201994302058,"score_gpt":0.5107365077585378,"score_spread":0.11828369167166797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798581322","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":[0.6938786,0.0042611654,0.07902192,0.20323299,0.0059441393,0.0027452502,0.00023391632,0.00066519115,0.010016812],"genre_scores_gemma":[0.9780073,0.0036482073,0.01504277,0.002966017,0.000058473866,0.000056752073,0.000015409481,0.00000462088,0.00020042129],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99804014,0.000080080456,0.0010377117,0.00022126437,0.00030368386,0.00031709834],"domain_scores_gemma":[0.99826545,0.00032879872,0.00023735469,0.0009596477,0.0001667025,0.00004205562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006299848,0.00010215966,0.00033097932,0.00059881335,0.0005614765,0.00009708706,0.00069004786,0.000050846957,0.0000085080865],"category_scores_gemma":[0.005744244,0.00008010812,0.000006909022,0.001182677,0.0004294326,0.0013023992,0.0020654416,0.0001350561,0.00010635385],"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":[0.00006674489,0.00006116055,0.029069949,0.0009145233,0.0000768905,0.0000041343214,0.04016879,0.00004781701,0.0000022768882,0.48289192,0.09661835,0.35007745],"study_design_scores_gemma":[0.00039583843,0.00054981164,0.009873336,0.00022346704,0.0000032412104,0.000009931154,0.17235093,0.004051548,0.00006871441,0.060220994,0.75198495,0.00026725317],"about_ca_topic_score_codex":0.000058422935,"about_ca_topic_score_gemma":0.0017838158,"teacher_disagreement_score":0.6553666,"about_ca_system_score_codex":0.000043650252,"about_ca_system_score_gemma":0.000043726974,"threshold_uncertainty_score":0.68768114},"labels":[],"label_agreement":null},{"id":"W2798653217","doi":"10.1145/3209978.3210021","title":"Automated Comparative Table Generation for Facilitating Human Intervention in Multi-Entity Resolution","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Toronto; National Natural Science Foundation of China","keywords":"Computer science; Automatic summarization; Crowdsourcing; Pairwise comparison; Table (database); Human-in-the-loop; Machine learning; Data mining; Graph; Set (abstract data type); Process (computing); Information retrieval; Artificial intelligence; Theoretical computer science; World Wide Web","score_opus":0.5955459466693872,"score_gpt":0.5512337355109547,"score_spread":0.044312211158432535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798653217","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":[0.36447263,0.000009557706,0.6327113,0.00009871675,0.00024293347,0.00046612014,0.00005045047,0.00010678021,0.0018415272],"genre_scores_gemma":[0.96795094,2.9888108e-7,0.026273705,0.00007976149,0.000043231263,0.00004946731,0.00018173219,0.0000023782059,0.005418497],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981923,0.0003127345,0.0006177648,0.00036215695,0.00035270315,0.00016231224],"domain_scores_gemma":[0.99904025,0.0001741776,0.00016889995,0.00026693472,0.00032110247,0.000028618646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050597643,0.00007332944,0.00015211638,0.00020499749,0.00027433533,0.00026427998,0.0002452143,0.000036953075,0.00032200292],"category_scores_gemma":[0.00096666015,0.00006109893,0.000048613867,0.00040769312,0.00007625478,0.0008079602,0.0001204042,0.000038501206,0.00023015373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019100963,0.0018889308,0.004531633,0.000088802495,0.00008109736,0.0000015459703,0.017385984,0.0036377513,0.06574914,0.1578913,0.7066289,0.0419239],"study_design_scores_gemma":[0.00093465176,0.00017116686,0.0076211817,0.000014304592,0.000004081533,1.1168724e-7,0.0044121253,0.9686497,0.002672356,0.0031802377,0.01224129,0.00009881325],"about_ca_topic_score_codex":0.0010347062,"about_ca_topic_score_gemma":0.024984118,"teacher_disagreement_score":0.96501195,"about_ca_system_score_codex":0.00006947233,"about_ca_system_score_gemma":0.000009426861,"threshold_uncertainty_score":0.9928074},"labels":[],"label_agreement":null},{"id":"W2798664493","doi":"10.14778/3192965.3192973","title":"Table union search on open data","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":193,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Table (database); Computer science; Benchmark (surveying); Data mining; Set (abstract data type); Semantic search; Domain (mathematical analysis); Ontology; Decision table; Probabilistic logic; Information retrieval; Search engine; Artificial intelligence; Mathematics; Programming language","score_opus":0.48054255452095584,"score_gpt":0.4884253644300699,"score_spread":0.007882809909114052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2798664493","genre_codex":"other","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":[0.14392589,0.000053706885,0.0005731527,0.06921851,0.0016684515,0.002985392,0.0004888851,0.000073652496,0.78101236],"genre_scores_gemma":[0.9754143,0.00002897564,0.0017305071,0.003336686,0.00013562753,0.000023069544,0.00001300143,0.000011988765,0.019305864],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969523,0.000043248896,0.0004378641,0.000614234,0.0016927511,0.00025959374],"domain_scores_gemma":[0.9979764,0.00015689502,0.0002506188,0.0011581137,0.00038716942,0.00007080311],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.010258411,0.000108462635,0.00019549599,0.00011024985,0.00026476663,0.0006400906,0.010241611,0.000025533533,0.0004610213],"category_scores_gemma":[0.0013318779,0.00006089952,0.000033590495,0.0007900212,0.00020266307,0.0010107273,0.012952176,0.00010497614,0.00044534542],"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":[0.000075199125,0.00020598088,0.0009332173,0.000012908748,0.000028405233,1.5634785e-7,0.00040697042,0.0000033356066,0.0023794074,0.10444706,0.8579091,0.033598304],"study_design_scores_gemma":[0.000430178,0.00023024277,0.0018608792,0.00006300217,0.000013084304,0.0000011404599,0.0017424794,0.00041701316,0.048950367,0.023500832,0.92268395,0.00010681401],"about_ca_topic_score_codex":0.0004345713,"about_ca_topic_score_gemma":0.00004147274,"teacher_disagreement_score":0.8314884,"about_ca_system_score_codex":0.000034097906,"about_ca_system_score_gemma":0.000040924526,"threshold_uncertainty_score":0.99511343},"labels":[],"label_agreement":null},{"id":"W2801222526","doi":"10.4095/288849","title":"L'Infrastructure canadienne de données : De meilleures connaissances pour de meilleures décisions","year":2005,"lang":"fr","type":"report","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.16920314612412135,"score_gpt":0.3944777780384163,"score_spread":0.22527463191429498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801222526","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085337855,0.02578446,0.07024383,0.056190338,0.008201915,0.0021033192,0.0039919917,0.00059238815,0.7475539],"genre_scores_gemma":[0.26062268,0.031992927,0.05861734,0.013626247,0.004759418,0.0001995163,0.0004006294,0.00021199757,0.62956923],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9865867,0.001616601,0.0027795054,0.0023411354,0.003055393,0.0036206464],"domain_scores_gemma":[0.98857343,0.004002061,0.00143069,0.0027159906,0.0010173398,0.0022604903],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.015474225,0.0013359939,0.0019193236,0.0011538516,0.0014236992,0.0016269891,0.0051215747,0.001262823,0.039766066],"category_scores_gemma":[0.014950084,0.0010555593,0.00089480425,0.0012956355,0.0013326886,0.00093335897,0.0016320089,0.0014725209,0.0007681383],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059257734,0.00019502809,0.005310092,0.00019792512,0.00043358814,0.00083595316,0.002382771,0.004134918,0.00011365327,0.050075337,0.67417514,0.26208636],"study_design_scores_gemma":[0.0006177835,0.00012271381,0.035431698,0.00040436146,0.0003797916,0.00094725145,0.014337707,0.001810387,0.00018934034,0.047427915,0.8971725,0.0011585179],"about_ca_topic_score_codex":0.088926375,"about_ca_topic_score_gemma":0.38118392,"teacher_disagreement_score":0.29225755,"about_ca_system_score_codex":0.0026155238,"about_ca_system_score_gemma":0.010192971,"threshold_uncertainty_score":0.99993914},"labels":[],"label_agreement":null},{"id":"W2802214269","doi":"10.20381/ruor-21830","title":"Tri-Agency Data Management Policy Initiative","year":2017,"lang":"en","type":"article","venue":"uO Research (University of Ottawa)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Agency (philosophy); Business; Public administration; Data management; Process management; Political science; Computer science; Data mining; Sociology","score_opus":0.7321984042348094,"score_gpt":0.5575252311577853,"score_spread":0.17467317307702412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802214269","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010300383,0.000016235283,0.0087452615,0.024454297,0.00015584443,0.0005626785,0.0009110076,0.00003036171,0.9548239],"genre_scores_gemma":[0.8730543,0.00054624834,0.0057217237,0.0001681728,0.00012807791,8.598655e-7,0.00013517487,0.000011902264,0.120233506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99494183,0.00068111543,0.00024869572,0.0007606294,0.0028968232,0.00047089122],"domain_scores_gemma":[0.9930444,0.0006319068,0.00031386453,0.0053109303,0.00048450436,0.0002144092],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012984283,0.00010296376,0.00025614997,0.0011256976,0.0017627387,0.0004138573,0.011962915,0.00005951138,0.0013903772],"category_scores_gemma":[0.003953195,0.00010391847,0.000079583944,0.0007747316,0.0010310658,0.002322176,0.011154719,0.00025403014,0.0016072665],"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":[0.000015920947,0.00017853003,0.0037595222,0.00003778112,0.000104172614,0.00020616378,0.0008997367,0.000002285246,0.000013976794,0.4528176,0.3207437,0.22122058],"study_design_scores_gemma":[0.00064741896,0.000074281794,0.17100841,0.000019034096,0.000012632396,5.9629446e-7,0.00776212,0.00035155597,0.000015080943,0.04326483,0.7767356,0.000108438115],"about_ca_topic_score_codex":0.000945568,"about_ca_topic_score_gemma":0.0014862011,"teacher_disagreement_score":0.8627539,"about_ca_system_score_codex":0.00008623156,"about_ca_system_score_gemma":0.00015937752,"threshold_uncertainty_score":0.9995368},"labels":[],"label_agreement":null},{"id":"W2804792234","doi":"10.23889/ijpds.v3i1.450","title":"Unlocking First Nations health information through data linkage","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Laurentian University; Institute for Work & Health; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Indigenous; Linkage (software); Sovereignty; Context (archaeology); Linked data; Population; Record linkage; Geography; Metis; Economic growth; Database; Political science; Medicine; Environmental health; Biology; Law; Genetics; Ecology; World Wide Web; Computer science; Economics; Politics","score_opus":0.47246174585891115,"score_gpt":0.5651324642231068,"score_spread":0.09267071836419566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804792234","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":[0.0024377913,0.000037911774,0.946075,0.032021414,0.010508704,0.00045371012,0.005367042,0.00005769749,0.003040721],"genre_scores_gemma":[0.9155758,0.00018388356,0.06947912,0.0046719294,0.0018238648,0.000007279039,0.0078686895,0.000009990669,0.00037944363],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99393785,0.00008994499,0.0013254663,0.0006144062,0.0037026221,0.00032969675],"domain_scores_gemma":[0.99366176,0.0007339417,0.0011836615,0.0021994838,0.0020582657,0.00016286003],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0150215225,0.00012217536,0.00016151438,0.00090945355,0.0025226143,0.0036161377,0.012534098,0.000034943125,0.00022361148],"category_scores_gemma":[0.022064902,0.000100208425,0.0000395053,0.0013584323,0.00031683038,0.03518074,0.0034437547,0.00014513293,0.00028703728],"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":[0.000080475234,0.00014537982,0.004913412,0.00001760362,0.0000661957,0.0000023008588,0.0021338537,0.0010273585,0.0000133874455,0.29390606,0.39314875,0.30454522],"study_design_scores_gemma":[0.00035729885,0.000053033127,0.0108972,0.000055100936,0.0000060181865,0.000030320267,0.0005465501,0.08033777,0.000010471292,0.021300597,0.8862786,0.0001270181],"about_ca_topic_score_codex":0.0005746934,"about_ca_topic_score_gemma":0.0030173354,"teacher_disagreement_score":0.91313803,"about_ca_system_score_codex":0.00022939575,"about_ca_system_score_gemma":0.0004263196,"threshold_uncertainty_score":0.99877596},"labels":[],"label_agreement":null},{"id":"W2805138799","doi":"","title":"The IBM Systems for Entity Discovery and Linking at TAC 2017.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"IBM; Computer science; Operating system; Database; Nanotechnology; Materials science","score_opus":0.07877614834923444,"score_gpt":0.38673919880046786,"score_spread":0.3079630504512334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805138799","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":[0.19494428,0.009949951,0.765132,0.0038216065,0.00062217587,0.0025279815,0.0006993928,0.000047315585,0.022255316],"genre_scores_gemma":[0.9875858,0.00070934533,0.000054030923,0.000025838686,0.00007309322,0.00020392399,0.000013279445,0.0000031008599,0.011331617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991615,0.00009378365,0.00025214435,0.00020103264,0.0001956139,0.00009592145],"domain_scores_gemma":[0.99674237,0.0019086375,0.00031208442,0.0009250892,0.000082764134,0.000029048184],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.005034649,0.00006192165,0.00013004772,0.0000274781,0.0020011459,0.0010193707,0.00065323384,0.000026109534,0.0000027529377],"category_scores_gemma":[0.00059873355,0.00003695487,0.000029012372,0.000038109225,0.0007564854,0.00052087713,0.0004528782,0.00003026937,0.000006681649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004235811,0.000009304278,0.00030630126,0.000028262284,0.000013118053,4.2918e-8,0.00017749851,0.0000021735566,0.000043704058,0.9796886,0.0012838269,0.018404838],"study_design_scores_gemma":[0.00008610619,0.0000106175585,0.0016028368,0.000005225499,0.000016928008,9.051301e-7,0.001842585,0.000028364158,0.00021328997,0.68678,0.30936912,0.000044025335],"about_ca_topic_score_codex":0.000036443627,"about_ca_topic_score_gemma":0.000057664158,"teacher_disagreement_score":0.7926415,"about_ca_system_score_codex":0.0000050530302,"about_ca_system_score_gemma":0.000011619642,"threshold_uncertainty_score":0.9992981},"labels":[],"label_agreement":null},{"id":"W2805217704","doi":"","title":"FOFE-based Deep Neural Networks for Entity Discovery and Linking.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial neural network; Deep neural networks; Artificial intelligence","score_opus":0.05583899060996958,"score_gpt":0.3677476582644973,"score_spread":0.31190866765452774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805217704","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":[0.030016996,0.0003596514,0.9673897,0.00068435865,0.00006755204,0.00038261243,0.00007124162,0.000013264739,0.0010146176],"genre_scores_gemma":[0.998488,0.000032210424,0.0005073941,0.0001422635,0.000070655915,0.00012737872,0.00004034755,0.000003856019,0.00058791065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991829,0.000075687465,0.0002441418,0.00023684085,0.00015759542,0.00010283775],"domain_scores_gemma":[0.9976986,0.0011613572,0.00025741305,0.0007538562,0.00009057526,0.000038167855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002601142,0.000073257375,0.00015453812,0.000048091195,0.00069737254,0.000596083,0.00052028097,0.000034703906,0.000009230223],"category_scores_gemma":[0.0004318564,0.00005580447,0.000039061295,0.00005809129,0.00064152654,0.0005657607,0.00021687885,0.000042692554,0.0000013668083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071987415,0.000024672658,0.00068636314,0.000021327745,0.000008271685,7.6729016e-8,0.000072482755,0.00010001815,0.000014939724,0.87800443,0.00009201878,0.12090343],"study_design_scores_gemma":[0.0002477355,0.000031391377,0.0034745338,0.000003688924,0.00003173816,4.3999114e-7,0.0005893356,0.0044715796,0.00023607757,0.9657413,0.025087949,0.000084224506],"about_ca_topic_score_codex":0.00001852214,"about_ca_topic_score_gemma":0.00005246251,"teacher_disagreement_score":0.968471,"about_ca_system_score_codex":0.0000024774847,"about_ca_system_score_gemma":0.000008663261,"threshold_uncertainty_score":0.57480425},"labels":[],"label_agreement":null},{"id":"W2805327586","doi":"","title":"CMU System for Entity Discovery and Linking at TAC-KBP 2016.","year":2016,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.04356788796697616,"score_gpt":0.339607856484424,"score_spread":0.29603996851744785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805327586","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":[0.11720513,0.0006012179,0.87708443,0.00068537844,0.00008769852,0.0005899899,0.00040368547,0.000036965783,0.003305526],"genre_scores_gemma":[0.9898533,0.00012355669,0.00028625273,0.000037310725,0.00005787268,0.00016864143,0.0000140355605,0.0000043998866,0.009454595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899966,0.000109868204,0.00031480967,0.0002706175,0.00019927237,0.00010576139],"domain_scores_gemma":[0.9973046,0.0019133938,0.00018199247,0.00046551888,0.000093686605,0.00004080327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032355601,0.00007542502,0.00016858822,0.00007138753,0.0002709804,0.000127416,0.00029057136,0.00003316486,0.000018294277],"category_scores_gemma":[0.00023615966,0.000044214958,0.000035138866,0.000118453216,0.0003711576,0.00050049945,0.00027930067,0.000018154782,0.000022765858],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006185338,0.000014417574,0.00028923704,0.0000655276,0.000012661703,6.060248e-8,0.00016399147,3.7705232e-7,0.0008401561,0.94155043,0.00064396154,0.05635735],"study_design_scores_gemma":[0.0002479239,0.000029783689,0.00064334745,0.00002999797,0.000025540594,0.000001946582,0.0023102637,0.0000036114802,0.005821231,0.85674596,0.13405189,0.0000885096],"about_ca_topic_score_codex":0.000009016237,"about_ca_topic_score_gemma":0.000015576721,"teacher_disagreement_score":0.87679815,"about_ca_system_score_codex":0.000013195286,"about_ca_system_score_gemma":0.000015378755,"threshold_uncertainty_score":0.20841897},"labels":[],"label_agreement":null},{"id":"W2805545340","doi":"","title":"Illinois CCG TAC 2015 Event Nugget, Entity Discovery and Linking, and Slot Filler Validation Systems","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Filler (materials); Event (particle physics); Computer science; Materials science; Composite material; Physics","score_opus":0.06286482228217304,"score_gpt":0.36153977177700314,"score_spread":0.2986749494948301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805545340","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":[0.44065312,0.007005903,0.5418545,0.0012736559,0.00031019375,0.0012333709,0.0003832447,0.00006782823,0.0072181653],"genre_scores_gemma":[0.9955921,0.00036972994,0.0001565756,0.000050130246,0.00006780533,0.000093066774,0.00007422944,0.000005311777,0.0035910518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99849284,0.00027019624,0.0004145749,0.00031419774,0.00040064793,0.00010752571],"domain_scores_gemma":[0.9984656,0.0005491165,0.00023725846,0.00046132636,0.00019166652,0.00009505885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047204695,0.00010588258,0.00021437813,0.000112044785,0.0001745989,0.0003711117,0.0002386428,0.000048911945,0.000013062515],"category_scores_gemma":[0.00030665647,0.00008020605,0.00002184894,0.00021425083,0.00039191474,0.0007487121,0.00026892862,0.00005663151,0.000016082296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003972219,0.00004884726,0.0007217268,0.00004696903,0.000019162268,1.5328081e-7,0.0010211726,0.00004257247,0.00005367463,0.98449016,0.00292352,0.010592317],"study_design_scores_gemma":[0.000299221,0.00005278981,0.0016339788,0.000016128128,0.00004756838,0.0000040206637,0.00892074,0.00012977052,0.0005861619,0.7754589,0.21270631,0.00014441465],"about_ca_topic_score_codex":0.00009872471,"about_ca_topic_score_gemma":0.000017688992,"teacher_disagreement_score":0.554939,"about_ca_system_score_codex":0.000009807717,"about_ca_system_score_gemma":0.000029853109,"threshold_uncertainty_score":0.35786387},"labels":[],"label_agreement":null},{"id":"W2805831109","doi":"","title":"The ZJU-EDL System for Entity Discovery and Linking at TAC KBP 2015.","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.07136923357888218,"score_gpt":0.37166902919747385,"score_spread":0.30029979561859166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805831109","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":[0.15278888,0.0063237273,0.8138707,0.0033789754,0.00046195512,0.0021773756,0.0004994942,0.00009706921,0.020401785],"genre_scores_gemma":[0.9937827,0.00009588782,0.00017417615,0.00004309203,0.000069848254,0.00019753285,0.000025132898,0.00000419428,0.0056074527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99894714,0.00014007547,0.00031080737,0.00021689873,0.00027625432,0.00010880207],"domain_scores_gemma":[0.99737173,0.0017081542,0.00018789437,0.00052112,0.00015532333,0.00005579332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065870737,0.00007274531,0.0001458301,0.000042970918,0.00050142634,0.00031327756,0.0003926781,0.000029563354,0.0000020641505],"category_scores_gemma":[0.00034064057,0.000043897046,0.000030522395,0.00015023176,0.00044666277,0.0003780413,0.00033987232,0.000033387612,0.00001332511],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007971691,0.000012196793,0.00014186895,0.000034719433,0.000013518707,5.328369e-8,0.00044239612,0.000004052965,0.00003617443,0.98075974,0.0019734644,0.016502079],"study_design_scores_gemma":[0.00015326893,0.000026108637,0.0002018318,0.000006073735,0.000025144756,0.0000018127639,0.011030684,0.000023995513,0.0007496284,0.7160674,0.27165636,0.000057683417],"about_ca_topic_score_codex":0.000016909678,"about_ca_topic_score_gemma":0.000045962417,"teacher_disagreement_score":0.8409938,"about_ca_system_score_codex":0.00001489158,"about_ca_system_score_gemma":0.000025480798,"threshold_uncertainty_score":0.38566166},"labels":[],"label_agreement":null},{"id":"W2806382634","doi":"","title":"The lilian Cold Start System for TAC 2016.","year":2016,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.04819693834677411,"score_gpt":0.34347019672230644,"score_spread":0.2952732583755323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806382634","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":[0.0044668554,0.0009353825,0.97389686,0.0060897316,0.00016170001,0.0013258031,0.00048806507,0.00006516073,0.012570466],"genre_scores_gemma":[0.9840705,0.00009919731,0.00020073919,0.00006281766,0.00005976009,0.00050621416,0.0000040815617,0.000004401766,0.0149923265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990082,0.0001407662,0.00032807497,0.0001877569,0.00022134656,0.000113850794],"domain_scores_gemma":[0.9949723,0.0039869403,0.00016503959,0.0006631929,0.00017282103,0.00003969799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005208546,0.00006205475,0.000120543955,0.000040737654,0.0004020325,0.0001001809,0.00054346153,0.000023556637,0.000018025064],"category_scores_gemma":[0.000397049,0.000028185492,0.000037811256,0.00015188125,0.00044645468,0.000150888,0.00011156014,0.00001717547,0.000059619306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051858853,0.000008633787,0.000012242383,0.000014002835,0.000010604659,1.8431658e-8,0.00009072661,2.98985e-7,0.00036341813,0.9135815,0.006634439,0.07923227],"study_design_scores_gemma":[0.00008972845,0.000016037902,0.000040446303,0.0000051150632,0.000008616103,2.1016133e-7,0.0030866126,0.0000013933454,0.00333301,0.49757427,0.49581328,0.000031266078],"about_ca_topic_score_codex":0.0000056102076,"about_ca_topic_score_gemma":0.000013481793,"teacher_disagreement_score":0.9796036,"about_ca_system_score_codex":0.000008251393,"about_ca_system_score_gemma":0.000026921569,"threshold_uncertainty_score":0.30921498},"labels":[],"label_agreement":null},{"id":"W2806493583","doi":"","title":"The ijk System for EAL at TAC KBP 2016 Event Track.","year":2016,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Track (disk drive); Event (particle physics); Computer science; Environmental science; Operating system; Physics","score_opus":0.043996545623482534,"score_gpt":0.3575506512461208,"score_spread":0.31355410562263825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806493583","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":[0.018848898,0.0011707603,0.96030843,0.0058182357,0.00022325915,0.0014770761,0.00056038465,0.00007272916,0.011520235],"genre_scores_gemma":[0.9828626,0.00015208208,0.00010061689,0.000044044365,0.00007416586,0.0005224893,0.000007757069,0.00000514439,0.016231097],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874836,0.00018302117,0.00041601236,0.00023615356,0.00027754044,0.000138919],"domain_scores_gemma":[0.9946973,0.0041827126,0.00022293215,0.00069982104,0.00014969087,0.000047550944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056336243,0.00007840703,0.0001443449,0.000042957185,0.0005239134,0.000075665725,0.00058776035,0.000030046482,0.000034529956],"category_scores_gemma":[0.00035576595,0.00003534193,0.000059295868,0.00013589961,0.00045192265,0.00016934953,0.00017795464,0.000019343426,0.000106064406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009263275,0.000014066382,0.000012879331,0.000013720857,0.000012512433,2.8538276e-8,0.00013311706,6.850521e-7,0.00027697446,0.81701857,0.0052442276,0.1771806],"study_design_scores_gemma":[0.00014208058,0.000024512263,0.00012582302,0.000007012885,0.0000138488895,8.915171e-7,0.0024914294,0.0000027694985,0.0032041853,0.56759495,0.42634812,0.000044406766],"about_ca_topic_score_codex":0.000005672027,"about_ca_topic_score_gemma":0.00001926099,"teacher_disagreement_score":0.9640137,"about_ca_system_score_codex":0.000019708523,"about_ca_system_score_gemma":0.000024392068,"threshold_uncertainty_score":0.40295714},"labels":[],"label_agreement":null},{"id":"W2806702131","doi":"","title":"UFV in the TAC 2015 Cold Start Knowledge Base Population Track.","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Track (disk drive); Cold start (automotive); Base (topology); Population; Knowledge base; Computer science; Artificial intelligence; Mathematics; Demography; Engineering; Operating system; Sociology; Aerospace engineering","score_opus":0.11575770991222244,"score_gpt":0.402875549658632,"score_spread":0.28711783974640953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806702131","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":[0.6001896,0.006091711,0.22120808,0.010866534,0.00040683214,0.0040812045,0.0004996874,0.0001538488,0.15650247],"genre_scores_gemma":[0.9979006,0.000021241856,0.0001434061,0.00015133504,0.000042932857,0.00012927053,0.000039402512,0.0000031238953,0.0015687086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985151,0.00048776998,0.00036461937,0.0001942767,0.00033412807,0.00010405709],"domain_scores_gemma":[0.99806964,0.0010291522,0.0001269336,0.00058327685,0.00013991217,0.00005106397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0101185795,0.00007103146,0.00013825606,0.00011994669,0.00009964997,0.00009647869,0.00049550127,0.000031012,0.000037535498],"category_scores_gemma":[0.0005277492,0.000045475914,0.000023009516,0.0005503127,0.00020256198,0.00032438218,0.00009330065,0.00006120162,0.00006903306],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034415603,0.000094815354,0.0004201482,0.0000069744615,0.0000030055894,1.4879726e-7,0.0021547119,0.000019912475,0.000017759276,0.97794074,0.007553352,0.01175403],"study_design_scores_gemma":[0.00015854946,0.00002327866,0.002112547,0.0000022514616,0.000009716604,6.0568186e-7,0.013902716,0.000028072436,0.00017768312,0.8041779,0.17935295,0.000053771906],"about_ca_topic_score_codex":0.00007352069,"about_ca_topic_score_gemma":0.00019475758,"teacher_disagreement_score":0.39771095,"about_ca_system_score_codex":0.000011296705,"about_ca_system_score_gemma":0.00003486532,"threshold_uncertainty_score":0.35069177},"labels":[],"label_agreement":null},{"id":"W2807617704","doi":"","title":"CMU System for Entity Discovery and Linking at TAC-KBP 2015.","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.07956800820654318,"score_gpt":0.3750757211903893,"score_spread":0.2955077129838461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807617704","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":[0.16525914,0.0016542652,0.82308334,0.00071430166,0.00017214687,0.00095298165,0.00037460699,0.000057179303,0.007732021],"genre_scores_gemma":[0.994766,0.000036832047,0.00050345814,0.000045628258,0.00006464319,0.0001517545,0.00004411753,0.0000044205367,0.0043831565],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895346,0.00012638656,0.00031069614,0.00024860442,0.00026104916,0.0000997831],"domain_scores_gemma":[0.99823123,0.0009296532,0.00017672263,0.0004442827,0.00015113867,0.00006695321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047260453,0.000075742835,0.00018017393,0.00007360596,0.00021785726,0.0001916311,0.00029330287,0.00003435111,0.0000058874616],"category_scores_gemma":[0.00028541006,0.00005673791,0.00002939106,0.00015892618,0.00030026547,0.0004782567,0.00030859926,0.000029198965,0.000016766551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007612325,0.000019421697,0.00032655956,0.00006981269,0.00001264309,9.232561e-8,0.000514173,0.0000055284577,0.00007219721,0.9857328,0.0017672406,0.011403438],"study_design_scores_gemma":[0.00024833993,0.00003870724,0.00028455406,0.000010283302,0.000030141491,0.0000028051818,0.009713984,0.000028676002,0.0015192991,0.8375856,0.15045094,0.00008661961],"about_ca_topic_score_codex":0.00001926985,"about_ca_topic_score_gemma":0.000025387078,"teacher_disagreement_score":0.8295069,"about_ca_system_score_codex":0.00001564652,"about_ca_system_score_gemma":0.000023711134,"threshold_uncertainty_score":0.23137048},"labels":[],"label_agreement":null},{"id":"W2807916905","doi":"10.18438/eblip29416","title":"European Academic Libraries Offer or Plan to Offer Research Data Services","year":2018,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Staffing; Demographics; Library science; Plan (archaeology); Computer science; Political science; Sociology; Geography","score_opus":0.44345729700962516,"score_gpt":0.4875060085835866,"score_spread":0.04404871157396145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807916905","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02089144,0.0007653146,0.025205314,0.80170816,0.0012024415,0.0019227572,0.00081611954,0.00054048427,0.14694798],"genre_scores_gemma":[0.26610115,0.002077102,0.03566911,0.6819543,0.001288019,0.00004679916,0.0011466594,0.000044024368,0.011672837],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941276,0.00226659,0.0009173403,0.0004969946,0.001849236,0.00034224847],"domain_scores_gemma":[0.9870618,0.010168606,0.0003773594,0.0018439494,0.00025581097,0.0002924705],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.015729493,0.00015361693,0.00017319206,0.0006240465,0.0005887664,0.003993097,0.0035042958,0.00007593178,0.0021585205],"category_scores_gemma":[0.01866243,0.000105308354,0.000018033135,0.0018102665,0.000250485,0.4596892,0.004008917,0.00044408528,0.006148973],"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":[0.0025443973,0.000043672888,0.00062336586,0.00017176733,0.00002121893,0.000012372499,0.0028434303,0.0000137034,0.000028087588,0.16231719,0.73215544,0.09922538],"study_design_scores_gemma":[0.00018388632,0.00028148075,0.008251153,0.0002767866,0.000011914907,0.00000717218,0.0057178093,0.0023220473,0.00035366925,0.00090259715,0.98153204,0.00015943943],"about_ca_topic_score_codex":0.000018510744,"about_ca_topic_score_gemma":7.445294e-7,"teacher_disagreement_score":0.4556961,"about_ca_system_score_codex":0.0000061763462,"about_ca_system_score_gemma":0.00023861702,"threshold_uncertainty_score":0.99875367},"labels":[],"label_agreement":null},{"id":"W2807917947","doi":"10.18438/eblip29415","title":"Social Scientists’ Data Reuse Principally Influenced by Disciplinary Norms, Attitude, and Perceived Effort","year":2018,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reuse; Normative; Technology acceptance model; Survey data collection; Psychology; Social psychology; Computer science; Usability; Engineering; Political science; Mathematics; Statistics","score_opus":0.12229839151762797,"score_gpt":0.4236701941639364,"score_spread":0.3013718026463085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807917947","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":[0.47731283,0.0006752212,0.015857002,0.4765583,0.00092553033,0.0017394728,0.0009697256,0.0004070117,0.025554929],"genre_scores_gemma":[0.8235765,0.0014390968,0.033987887,0.13590436,0.00040870116,0.000048696562,0.0015070766,0.000022623508,0.0031050784],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968878,0.0003328899,0.00082359643,0.00049708434,0.0012080255,0.0002506109],"domain_scores_gemma":[0.9952294,0.0019288837,0.00062834617,0.001856198,0.00017290645,0.0001842245],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0050919876,0.00016780359,0.00019579465,0.0002443548,0.00093391223,0.002862419,0.0026098457,0.00008156905,0.00038382056],"category_scores_gemma":[0.013276465,0.00013194085,0.000024157904,0.00078483875,0.0005598854,0.34973523,0.004888167,0.00018638787,0.00031393176],"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":[0.001439693,0.00020193557,0.008709148,0.00021726845,0.000057885463,0.000011150958,0.0045518023,0.000013650645,0.00024652423,0.10959606,0.8219326,0.053022284],"study_design_scores_gemma":[0.0003682669,0.0001650375,0.11554382,0.00008453496,0.000029769788,0.000008626495,0.0013709852,0.003474504,0.00006659292,0.0010462533,0.87763935,0.00020228018],"about_ca_topic_score_codex":0.000012678999,"about_ca_topic_score_gemma":7.488464e-7,"teacher_disagreement_score":0.3468728,"about_ca_system_score_codex":0.000010316963,"about_ca_system_score_gemma":0.0001931215,"threshold_uncertainty_score":0.9981727},"labels":[],"label_agreement":null},{"id":"W2810994727","doi":"10.4000/terminal.1964","title":"Du statut d’objet technique à celui d’objet social dans le contexte de la production automatisée d’informations journalistiques","year":2018,"lang":"fr","type":"article","venue":"Terminal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"World Federation of Science Journalists","funders":"","keywords":"Humanities; Philosophy","score_opus":0.045377497070914104,"score_gpt":0.38709924338014934,"score_spread":0.34172174630923524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810994727","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":[0.2084448,0.00022020818,0.6275837,0.04103639,0.0034556186,0.0014116819,0.0010471428,0.0004879544,0.11631252],"genre_scores_gemma":[0.9497004,0.0001506194,0.019263955,0.0011061227,0.0024190105,0.00012675718,0.00008131808,0.00003069758,0.02712109],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99551016,0.001489642,0.0010519947,0.00044154646,0.00092862523,0.0005780433],"domain_scores_gemma":[0.9978419,0.00035261604,0.0006126588,0.000558775,0.00044549265,0.00018858304],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009958798,0.00027740048,0.00036412416,0.0003049474,0.0017541494,0.0011312467,0.0009277365,0.0002417655,0.0009499213],"category_scores_gemma":[0.0014789806,0.0002674938,0.00016005391,0.0005476293,0.0022215056,0.00251084,0.0003795817,0.0004245423,0.00060010736],"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":[0.00009485975,0.00047831133,0.00040663773,0.00015252242,0.00007172479,0.00011545855,0.04376764,0.000013373678,0.0013989721,0.180575,0.5233476,0.24957788],"study_design_scores_gemma":[0.00046649037,0.00029496502,0.020894667,0.00022814404,0.00009328035,0.00088363857,0.01286057,0.0015751887,0.0060895607,0.046036847,0.910123,0.00045363553],"about_ca_topic_score_codex":0.0016325649,"about_ca_topic_score_gemma":0.00076211675,"teacher_disagreement_score":0.74125564,"about_ca_system_score_codex":0.0002750539,"about_ca_system_score_gemma":0.00075828243,"threshold_uncertainty_score":0.9999777},"labels":[],"label_agreement":null},{"id":"W286555265","doi":"","title":"A New Method for Database Data Quality Evaluation at the Canadian Institute for Health Information (CIHI).","year":2002,"lang":"en","type":"article","venue":"ICIQ","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data quality; Health information; Quality (philosophy); Information quality; Quality management; Health care; Information system; Computer science; Database; Medicine; Operations management; Engineering","score_opus":0.7377534273204825,"score_gpt":0.6092499060943046,"score_spread":0.12850352122617792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W286555265","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":[0.0001323778,0.00012560035,0.89722556,0.08320918,0.00073759625,0.0024637037,0.013288782,0.000019152196,0.0027980758],"genre_scores_gemma":[0.02885621,0.00013526704,0.7294132,0.14094944,0.0010884113,0.0009804177,0.071543604,0.000038443322,0.026994972],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99712,0.00042151686,0.00072176603,0.0003446772,0.0011031507,0.00028884198],"domain_scores_gemma":[0.99615854,0.0010143336,0.00036447265,0.0019953179,0.00025117834,0.00021616208],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03152491,0.000091468246,0.00017005998,0.00015294376,0.0007604181,0.000428182,0.0013480835,0.000036588677,0.00065855886],"category_scores_gemma":[0.008630294,0.00006186987,0.00004617307,0.00032868775,0.00003581484,0.002629002,0.00034723562,0.00005545644,0.00040746352],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012027819,0.000005541634,0.000006707761,0.000011782277,0.0000066365224,2.424619e-8,0.00040433812,0.000109301225,7.386923e-7,0.012750255,0.61300653,0.37368613],"study_design_scores_gemma":[0.0005395127,0.00002730297,0.0003589631,0.000005912103,0.00001885622,5.428449e-7,0.0003201851,0.10465666,0.0000075678668,0.00682336,0.8871656,0.000075554664],"about_ca_topic_score_codex":0.30253905,"about_ca_topic_score_gemma":0.93069726,"teacher_disagreement_score":0.6281582,"about_ca_system_score_codex":0.0002927066,"about_ca_system_score_gemma":0.0005594377,"threshold_uncertainty_score":0.99972045},"labels":[],"label_agreement":null},{"id":"W2884960754","doi":"","title":"2006-4 Nested Pseudo-likelihood Estimation and Bootstrap-based Inference for Structural Discrete Markov Decision Models","year":2006,"lang":"en","type":"article","venue":"Econstor (Econstor)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Inference; Econometrics; Markov chain; Mathematics; Statistics; Computer science; Maximum likelihood; Artificial intelligence","score_opus":0.052838607905845325,"score_gpt":0.34667005567276027,"score_spread":0.29383144776691494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884960754","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":[0.6690991,0.00019188403,0.3256257,0.00047199483,0.0007185417,0.0007344875,0.00072524475,0.000099576304,0.0023334834],"genre_scores_gemma":[0.95593774,0.000010092366,0.042590313,0.00035740278,0.000121928475,0.00008477952,0.00021565238,0.000025356592,0.0006567592],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99590003,0.00020455162,0.0013407009,0.0010623774,0.0009022411,0.0005901167],"domain_scores_gemma":[0.99513096,0.0027699848,0.0005818159,0.0009874442,0.00028829536,0.00024149929],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0024419138,0.00040149677,0.00058625336,0.0005143501,0.00048257905,0.00076400855,0.0007881157,0.000186727,0.00039677336],"category_scores_gemma":[0.0011675172,0.00034085737,0.00020390861,0.00041455828,0.0004220462,0.0017785265,0.00021305218,0.00018070808,0.00010698601],"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":[0.0008891313,0.00029352502,0.47416,0.00018342886,0.00013061635,0.00003306062,0.0004279012,0.039846506,0.00044552193,0.098241776,0.122604534,0.26274404],"study_design_scores_gemma":[0.0023596317,0.00017206525,0.11975661,0.00009075876,0.00007459746,0.000018283705,0.00023787748,0.5860937,0.00022725924,0.28479743,0.005469004,0.0007027484],"about_ca_topic_score_codex":0.00032052994,"about_ca_topic_score_gemma":0.0013235159,"teacher_disagreement_score":0.54624724,"about_ca_system_score_codex":0.00012132151,"about_ca_system_score_gemma":0.0002475434,"threshold_uncertainty_score":0.99990433},"labels":[],"label_agreement":null},{"id":"W2889191855","doi":"10.23889/ijpds.v3i1.697","title":"The International Population Data Linkage Network – Banff and Beyond","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Calgary","funders":"","keywords":"Context (archaeology); Population; NOMINATE; Public relations; Library science; Computer science; Political science; Sociology; Geography","score_opus":0.29041916002824336,"score_gpt":0.5082813043779627,"score_spread":0.21786214434971934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889191855","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":[0.18229854,0.00073419727,0.51363754,0.14157549,0.13624991,0.0022121451,0.010168823,0.00023239342,0.012890946],"genre_scores_gemma":[0.9638779,0.0002471759,0.022553233,0.0023720565,0.0055786995,0.0000068423433,0.003661908,0.000016155418,0.0016859922],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938445,0.00012351527,0.0010504577,0.00093639235,0.003687006,0.00035812173],"domain_scores_gemma":[0.99455684,0.001048,0.000806346,0.0020393217,0.0013738703,0.00017562143],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.020140694,0.00014681245,0.00015201903,0.00034032768,0.0019856,0.0055129654,0.014395122,0.00004721017,0.00014361783],"category_scores_gemma":[0.011167107,0.00009935734,0.00004037863,0.00059321075,0.00052282633,0.008836553,0.0055916724,0.00018295737,0.00006691282],"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":[0.00020425075,0.000060081973,0.040249657,0.0000019038482,0.00009636379,0.000005542727,0.00015713582,0.0003535382,0.000072975214,0.16600674,0.29818517,0.49460664],"study_design_scores_gemma":[0.0003788135,0.00004016032,0.121639766,0.000019235713,0.00001518727,0.000046111778,0.00021302729,0.15693551,0.000005044609,0.0919166,0.6286447,0.00014582336],"about_ca_topic_score_codex":0.0002591896,"about_ca_topic_score_gemma":0.0013568628,"teacher_disagreement_score":0.7815794,"about_ca_system_score_codex":0.00011579977,"about_ca_system_score_gemma":0.000107319545,"threshold_uncertainty_score":0.99931365},"labels":[],"label_agreement":null},{"id":"W2889743896","doi":"10.23889/ijpds.v3i4.991","title":"Linking primary care EMR data and administrative data in Alberta, Canada: experiences, challenges, and potential solutions","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Calgary","funders":"","keywords":"Custodians; Analytics; Health care; Data collection; Medical record; Medical emergency; Medicine; Computer science; Data science; Political science","score_opus":0.37580310792389104,"score_gpt":0.4723326321179541,"score_spread":0.09652952419406308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889743896","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":[0.71553254,0.009405453,0.12930231,0.054867405,0.03223701,0.0026838817,0.04843877,0.00006943218,0.007463193],"genre_scores_gemma":[0.9879991,0.00034990988,0.0057918527,0.00029408865,0.00043881274,0.0000041828807,0.005024033,0.0000048247953,0.00009321016],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956817,0.00010343865,0.00069362216,0.0010943124,0.0021436538,0.00028328513],"domain_scores_gemma":[0.996697,0.00039743373,0.00038426116,0.0017944471,0.00056169415,0.00016513547],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005818332,0.0001194629,0.00016286407,0.00031354,0.0006969533,0.0011231692,0.00824764,0.000034200668,0.0000304322],"category_scores_gemma":[0.0032578814,0.00010071312,0.00000929659,0.00027491827,0.0005024687,0.008080422,0.007384073,0.00013676481,0.0000025848833],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022119601,0.00014776134,0.01322474,0.00003955949,0.00007452416,0.00008227353,0.012487652,0.000052165295,0.00005646049,0.03213261,0.01686907,0.924612],"study_design_scores_gemma":[0.0015976826,0.00018883358,0.3254832,0.00032130285,0.000047486556,0.00058486516,0.052431036,0.15859367,0.000013387966,0.013523433,0.44654644,0.000668688],"about_ca_topic_score_codex":0.057222184,"about_ca_topic_score_gemma":0.658116,"teacher_disagreement_score":0.9239433,"about_ca_system_score_codex":0.00016790372,"about_ca_system_score_gemma":0.0009895929,"threshold_uncertainty_score":0.99991375},"labels":[],"label_agreement":null},{"id":"W2889869750","doi":"10.23889/ijpds.v3i4.959","title":"Public views and recommendations on the use of linked data for research: preliminary results from a public deliberation engagement","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Guelph; University of British Columbia","funders":"","keywords":"Deliberation; Public relations; Public engagement; Harm; Data sharing; Political science; Secrecy; Internet privacy; Sociology; Psychology; Social psychology; Computer science; Medicine; Law","score_opus":0.9500920201003664,"score_gpt":0.617412246931546,"score_spread":0.33267977316882047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889869750","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":[0.06128535,0.000050360803,0.5110234,0.37223488,0.0060440125,0.002462499,0.046494935,0.000034251287,0.00037031723],"genre_scores_gemma":[0.9103077,0.0001381592,0.07337853,0.0017686631,0.00091798045,0.000043895347,0.012922271,0.000011750503,0.00051106303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940707,0.0006748513,0.0012439656,0.00087494997,0.0028534436,0.0002820963],"domain_scores_gemma":[0.9828424,0.009170649,0.0009462187,0.0027514114,0.004129331,0.00015998066],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046921905,0.000103185484,0.0001415409,0.000777735,0.0016207651,0.0040068887,0.007312706,0.000037481695,0.00010345839],"category_scores_gemma":[0.10674263,0.000067816276,0.000034794626,0.000795406,0.00053361506,0.010102543,0.0033162988,0.00020754845,0.000018586901],"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":[0.00050547125,0.00018370568,0.00025023063,0.0000020243099,0.00005221155,4.5411716e-7,0.00047023993,0.000041231426,0.00014952125,0.11440784,0.52045095,0.36348614],"study_design_scores_gemma":[0.00052458595,0.00023578898,0.007232054,0.000041132556,0.000009620609,0.0000028394275,0.00047227505,0.15677999,0.00002540947,0.03472262,0.7998736,0.00008007495],"about_ca_topic_score_codex":0.00017989328,"about_ca_topic_score_gemma":0.00074408174,"teacher_disagreement_score":0.8490223,"about_ca_system_score_codex":0.000096399555,"about_ca_system_score_gemma":0.0002433888,"threshold_uncertainty_score":0.99967897},"labels":[],"label_agreement":null},{"id":"W2890164357","doi":"10.23889/ijpds.v3i4.683","title":"Extending follow up of randomised clinical trials by linkage to routinely collected data – results of a scoping review of the published literature","year":2018,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Manitoba; Ontario Council of University Libraries; University of Toronto","funders":"","keywords":"Linkage (software); Medicine; Record linkage; Data extraction; Protocol (science); Family medicine; MEDLINE; Data mining; Alternative medicine; Computer science; Population; Environmental health; Pathology","score_opus":0.7130505119794814,"score_gpt":0.6578263544840742,"score_spread":0.05522415749540721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890164357","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016098917,0.9040352,0.016931932,0.0016490809,0.012697184,0.005380107,0.0591117,0.000010037998,0.00016867193],"genre_scores_gemma":[0.000056033234,0.98530626,0.0049856096,0.00025567645,0.0005239748,0.000021365753,0.008193376,0.000014529994,0.00064315234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97782403,0.003417325,0.0117543535,0.0013747064,0.005352889,0.0002766891],"domain_scores_gemma":[0.9504332,0.014804444,0.022135898,0.006266248,0.006081692,0.00027853608],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19478796,0.00027763494,0.0028324085,0.00097373076,0.00025493823,0.001147516,0.023959046,0.00015217077,0.000099471385],"category_scores_gemma":[0.51064634,0.00015433376,0.0007767383,0.0036656163,0.00035823352,0.0038582676,0.0055816215,0.00037362133,0.000004325271],"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":[0.0009214435,0.0001311962,0.00002030359,0.0075529628,0.00028338545,0.0000012589243,0.00007132835,0.000002892013,0.0000051830816,0.0004802888,0.4760178,0.51451194],"study_design_scores_gemma":[0.0039058377,0.00007096185,0.00003946376,0.28961495,0.0004085668,0.000016989303,0.000018141602,0.00048986,0.000004668429,0.00044651795,0.70480424,0.00017978775],"about_ca_topic_score_codex":0.000044202832,"about_ca_topic_score_gemma":0.000048660655,"teacher_disagreement_score":0.5143322,"about_ca_system_score_codex":0.000091110465,"about_ca_system_score_gemma":0.0015462901,"threshold_uncertainty_score":0.9998894},"labels":[],"label_agreement":null},{"id":"W2890268673","doi":"10.23889/ijpds.v3i4.1034","title":"A New Standards-based Grammar for Linking Aggregate Datasets","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Government (linguistics); Interoperability; Aggregate data; Computer science; Human immunodeficiency virus (HIV); Data science; World Wide Web; Medicine; Family medicine","score_opus":0.2856651451075076,"score_gpt":0.5436897848150035,"score_spread":0.2580246397074959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890268673","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":[0.0024063468,0.000019969119,0.97086686,0.005157493,0.006368364,0.0003566308,0.01466355,0.000025342844,0.00013545806],"genre_scores_gemma":[0.5209284,0.000026058038,0.45420304,0.004531107,0.0054747406,0.000022544438,0.013343772,0.00003281255,0.0014375041],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99383974,0.000059983005,0.00085789134,0.0007237566,0.004183513,0.00033513783],"domain_scores_gemma":[0.994937,0.00060616387,0.00073113217,0.0011261159,0.0023544908,0.000245076],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.016817402,0.00012652889,0.00016277762,0.00066408777,0.0008986755,0.003042957,0.0072095604,0.000035120214,0.00023615472],"category_scores_gemma":[0.013590655,0.00009981559,0.00008018828,0.00061123684,0.0002352058,0.005360054,0.00088546175,0.000096131174,0.00004193466],"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":[0.0004034147,0.000052634678,0.0014439702,0.0000052316545,0.000034644534,0.000004382603,0.000094023504,0.00039314057,0.00023821979,0.044060286,0.37669912,0.5765709],"study_design_scores_gemma":[0.00091715856,0.000112139816,0.0018440813,0.00005280456,0.000014351323,0.0000135051905,0.000058804908,0.071492694,0.00025042694,0.07436355,0.8507395,0.00014098325],"about_ca_topic_score_codex":0.00015981257,"about_ca_topic_score_gemma":0.00050958537,"teacher_disagreement_score":0.57642996,"about_ca_system_score_codex":0.00020193972,"about_ca_system_score_gemma":0.000727983,"threshold_uncertainty_score":0.9981619},"labels":[],"label_agreement":null},{"id":"W2890622483","doi":"10.23889/ijpds.v3i4.835","title":"Establishing an International Data Linkage Repository Workgroup Toward a Benchmarking Repository","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Guelph","funders":"","keywords":"Workgroup; Benchmarking; Computer science; Record linkage; Linkage (software); Data science; Metadata; Field (mathematics); Custodians; Information repository; Data mining; World Wide Web; Computer data storage; Business","score_opus":0.40029979659605125,"score_gpt":0.5237836597062985,"score_spread":0.12348386311024723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890622483","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":[0.21213359,0.000094578085,0.6520772,0.006568337,0.111201406,0.0007887345,0.0029834895,0.0002100583,0.0139426105],"genre_scores_gemma":[0.93607724,0.000028386688,0.051103868,0.0007719413,0.008440174,0.0000058363103,0.0025277762,0.000017091945,0.0010277134],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99095744,0.00023238335,0.0015212129,0.0016031269,0.005276224,0.0004095967],"domain_scores_gemma":[0.9920226,0.0006548192,0.0012474771,0.003403968,0.002354161,0.000317009],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.018585568,0.0001968708,0.00021867454,0.00094456674,0.0014170788,0.009656461,0.025263684,0.00007588558,0.00016974578],"category_scores_gemma":[0.010372453,0.00016883342,0.00006958714,0.0007760925,0.0004997102,0.034311652,0.0059788083,0.00029930755,0.00003891655],"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":[0.000671382,0.00071513624,0.11449294,0.000014224281,0.00031509373,0.0002175942,0.0026757834,0.001054542,0.004411707,0.051840838,0.14513107,0.6784597],"study_design_scores_gemma":[0.0008178101,0.00018729623,0.10740252,0.00015087024,0.000043511263,0.00049676176,0.0013462601,0.39453432,0.00025584837,0.012615853,0.4816495,0.00049944996],"about_ca_topic_score_codex":0.0004699212,"about_ca_topic_score_gemma":0.00018893105,"teacher_disagreement_score":0.72394365,"about_ca_system_score_codex":0.00028123936,"about_ca_system_score_gemma":0.00031697963,"threshold_uncertainty_score":0.99988294},"labels":[],"label_agreement":null},{"id":"W2890629418","doi":"10.23889/ijpds.v3i4.872","title":"Leveraging best practices in data governance: An organization-wide data inventory and mapping project to support a five year data strategy","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"College of Physicians and Surgeons of Ontario","funders":"","keywords":"Data governance; Data quality; Data warehouse; Computer science; Enterprise data management; Data management; Workflow; Metadata; Data dictionary; Data element; Data virtualization; Information governance; Data science; Database; World Wide Web; Business; Information system; Engineering; Management information systems; Marketing","score_opus":0.6289315489095745,"score_gpt":0.5585743379486544,"score_spread":0.07035721096092007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890629418","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":[0.6255275,0.0001420787,0.2684773,0.026619272,0.01195593,0.0027640038,0.06250773,0.00011636862,0.0018898302],"genre_scores_gemma":[0.92136294,0.0001720303,0.043995775,0.001636655,0.0012537014,0.0000040029,0.030601712,0.000024963738,0.00094825355],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941772,0.00017233417,0.0009574836,0.0017132555,0.0026699866,0.00030974663],"domain_scores_gemma":[0.99165857,0.00048074374,0.0013139705,0.0052657686,0.0010829361,0.00019803956],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.018566955,0.00014594833,0.00018474771,0.0006010346,0.0005112174,0.0036981825,0.023369517,0.000037536574,0.0001685616],"category_scores_gemma":[0.04225088,0.00012879282,0.000007608485,0.0014004098,0.0002271643,0.036069535,0.015676292,0.00018058492,0.00006658001],"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":[0.00021666187,0.00051213545,0.28479153,0.000027735605,0.000105332765,0.00006103391,0.003127293,0.00043291075,0.00028211207,0.008885178,0.45681468,0.2447434],"study_design_scores_gemma":[0.0009094501,0.00016234469,0.13263927,0.00014903447,0.000032691503,0.00010622966,0.007944775,0.28939858,0.000011555231,0.0035781786,0.56464934,0.0004185213],"about_ca_topic_score_codex":0.0026783647,"about_ca_topic_score_gemma":0.0065397792,"teacher_disagreement_score":0.2958354,"about_ca_system_score_codex":0.00012703617,"about_ca_system_score_gemma":0.00077411224,"threshold_uncertainty_score":0.9973361},"labels":[],"label_agreement":null},{"id":"W2890912884","doi":"10.23889/ijpds.v3i4.918","title":"Population Data Science: The science of data about people","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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 British Columbia","funders":"Economic and Social Research Council; Medical Research Council","keywords":"Population; Data science; Computer science; Informatics; Field (mathematics); Knowledge management; Political science; Sociology","score_opus":0.455399970034002,"score_gpt":0.5671411276653473,"score_spread":0.11174115763134529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890912884","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":[0.6802779,0.00017332142,0.23936515,0.020759583,0.03466048,0.0018161725,0.01900093,0.000107456035,0.003839048],"genre_scores_gemma":[0.9796689,0.00004121655,0.017247017,0.0003497965,0.00091324956,0.0000026400787,0.0015886262,0.000008610822,0.00017994209],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98524475,0.00012372588,0.001531387,0.0019014389,0.010614837,0.0005838763],"domain_scores_gemma":[0.9838299,0.0007521082,0.0016339084,0.008837012,0.004662163,0.00028486512],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","sts","scholarly_communication","open_science"],"category_scores_codex":[0.0662136,0.00017906488,0.000259587,0.0015180921,0.0031661368,0.0047003576,0.0679948,0.000036411187,0.00021545339],"category_scores_gemma":[0.035693772,0.00011793438,0.00004102695,0.005103541,0.004420639,0.044927873,0.020411199,0.00020691346,0.00007745716],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003061172,0.00045360686,0.066424474,0.00001751153,0.0000782916,0.000005041649,0.0015042115,0.0009628322,0.007895897,0.33701327,0.08182114,0.5035176],"study_design_scores_gemma":[0.0005081555,0.000086084365,0.5213321,0.00006551794,0.000036724865,0.00006572954,0.00093797996,0.3769083,0.00027517384,0.030144688,0.06936083,0.00027874712],"about_ca_topic_score_codex":0.0016693666,"about_ca_topic_score_gemma":0.0016888636,"teacher_disagreement_score":0.50323886,"about_ca_system_score_codex":0.00022619346,"about_ca_system_score_gemma":0.0012992116,"threshold_uncertainty_score":0.99828875},"labels":[],"label_agreement":null},{"id":"W2891156194","doi":"10.23889/ijpds.v3i4.675","title":"Governance Challenges to Promoting Data Readiness and Data Linkage for Not-for-Profit Organizational Service Data","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Alberta Health Services","funders":"","keywords":"Business; Data governance; Public relations; Corporate governance; Data sharing; Information governance; Service (business); Internet privacy; Political science; Marketing; Information system; Data quality; Law","score_opus":0.5205717022128199,"score_gpt":0.5341023824725832,"score_spread":0.013530680259763339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891156194","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":[0.018094022,0.00014716465,0.7422874,0.09195503,0.0063521555,0.0016695275,0.13932045,0.000053529846,0.00012072865],"genre_scores_gemma":[0.5442293,0.00039101663,0.35924354,0.0066046435,0.0067539886,0.000041911768,0.081634976,0.00006880587,0.0010317566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9935308,0.00007230905,0.0010699073,0.0022292603,0.0027075382,0.00039018155],"domain_scores_gemma":[0.9879971,0.0012418905,0.00092732674,0.0063342624,0.0032645378,0.00023485387],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.022004062,0.00019285557,0.00025007885,0.0003024803,0.0010000524,0.0030130874,0.032738637,0.000056758203,0.000051349423],"category_scores_gemma":[0.039858814,0.00016297176,0.000016801216,0.0007857283,0.00020039905,0.019910464,0.019166233,0.00011464035,0.000032027514],"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":[0.00067446317,0.00013316495,0.009570045,0.00015132257,0.00020693465,0.000005488898,0.0011567497,0.00014254704,0.001436921,0.19675414,0.24009693,0.5496713],"study_design_scores_gemma":[0.0009955085,0.000097297,0.045754973,0.00015505607,0.000051464893,0.00005715485,0.00046810744,0.52161115,0.000097752265,0.017896073,0.41243985,0.00037558918],"about_ca_topic_score_codex":0.00012720465,"about_ca_topic_score_gemma":0.0017155508,"teacher_disagreement_score":0.5492957,"about_ca_system_score_codex":0.00008230914,"about_ca_system_score_gemma":0.00033548023,"threshold_uncertainty_score":0.9980219},"labels":[],"label_agreement":null},{"id":"W2891521002","doi":"10.23889/ijpds.v3i4.942","title":"Data Linkage Methods in Manitoba","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Manitoba Health","funders":"","keywords":"Linkage (software); Computer science; Record linkage; Linked data; Data quality; Population; Data mining; Process (computing); Data science; Information retrieval; Engineering; Medicine","score_opus":0.6645466192572466,"score_gpt":0.6439882190382802,"score_spread":0.020558400218966377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891521002","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":[0.019570952,0.00003188883,0.95660466,0.006056309,0.012693381,0.00030517127,0.0027872748,0.000026689275,0.0019236808],"genre_scores_gemma":[0.44365615,0.00005367993,0.54883873,0.0019924208,0.0024093932,0.0000059508343,0.0021113534,0.000014152693,0.000918191],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99494386,0.00022445882,0.0010192628,0.0008845409,0.0026463016,0.00028159932],"domain_scores_gemma":[0.9950602,0.00077886536,0.00053385034,0.0024548373,0.0010367021,0.00013554942],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.035995662,0.00010131513,0.00015463275,0.0009385216,0.00041187712,0.0020717562,0.017893728,0.00003482069,0.00026793563],"category_scores_gemma":[0.020748938,0.000079724836,0.00003058222,0.0010037804,0.00032952937,0.010158585,0.0048686434,0.00015824789,0.00015192274],"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":[0.00008785813,0.00012963923,0.021011217,0.0000024793592,0.000025295722,0.000014231434,0.00018019663,0.000114252056,0.0006028654,0.03899502,0.07518413,0.8636528],"study_design_scores_gemma":[0.00046077304,0.000043609954,0.11673082,0.000030076348,0.000007741967,0.000044946726,0.00053167716,0.14896795,0.00008239586,0.07559175,0.6573492,0.00015903173],"about_ca_topic_score_codex":0.00036373505,"about_ca_topic_score_gemma":0.0036317029,"teacher_disagreement_score":0.8634938,"about_ca_system_score_codex":0.00013339466,"about_ca_system_score_gemma":0.00016223347,"threshold_uncertainty_score":0.9989642},"labels":[],"label_agreement":null},{"id":"W2891566313","doi":"10.23889/ijpds.v3i4.749","title":"Ligo: An Open Source Application for the Management and Execution of Administrative Data Linkage","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of British Columbia","funders":"","keywords":"Computer science; Python (programming language); Probabilistic logic; Population; Plug-in; Cloud computing; Interface (matter); Data science; Data mining; Software engineering; Programming language; Artificial intelligence; Operating system","score_opus":0.5482114767746085,"score_gpt":0.5869358928333936,"score_spread":0.03872441605878518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891566313","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":[0.010324895,0.000024192748,0.9814712,0.0034568012,0.0011489815,0.0011216017,0.002103249,0.000009262646,0.00033984956],"genre_scores_gemma":[0.9460676,0.00005021004,0.050721638,0.00045302272,0.00046770246,0.000035628873,0.0015536112,0.000006916757,0.00064370886],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969812,0.000066600725,0.00067164685,0.00067866244,0.0014519218,0.00014995097],"domain_scores_gemma":[0.99592507,0.0004894604,0.0007206667,0.0017814897,0.0009963817,0.00008693464],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.013581698,0.00008447292,0.00011711746,0.00022636124,0.0007726824,0.0017512917,0.013022207,0.000023124698,0.000025575648],"category_scores_gemma":[0.0017841994,0.000056724497,0.000017927723,0.00037256454,0.00041183844,0.006958404,0.004108595,0.00005764216,0.000006142339],"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":[0.0003345218,0.00016796443,0.0014660647,0.000009551729,0.00009520943,5.1345097e-7,0.00046655745,0.00014295852,0.00040445087,0.20476663,0.018260675,0.7738849],"study_design_scores_gemma":[0.0007922654,0.0002694346,0.048441637,0.00003466881,0.00006075424,0.000019844183,0.002196851,0.3438808,0.00021227643,0.0657056,0.53823304,0.00015283287],"about_ca_topic_score_codex":0.0001653313,"about_ca_topic_score_gemma":0.00035166895,"teacher_disagreement_score":0.9357427,"about_ca_system_score_codex":0.000040015933,"about_ca_system_score_gemma":0.00008484885,"threshold_uncertainty_score":0.999285},"labels":[],"label_agreement":null},{"id":"W2892008580","doi":"10.23889/ijpds.v3i4.947","title":"Meeting the challenge of data linkage for special populations","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of British Columbia","funders":"","keywords":"Linkage (software); Record linkage; Population; Christian ministry; Medical record; Identifier; Unique identifier; Medicine; Data set; Demography; Computer science; Statistics; Biology; Environmental health; Genetics; Surgery; Mathematics; Political science; Law","score_opus":0.6449232329171355,"score_gpt":0.5775271401239062,"score_spread":0.06739609279322933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892008580","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":[0.016464533,0.00009113625,0.8920241,0.044141978,0.026244864,0.0013490496,0.013782689,0.000035912577,0.005865751],"genre_scores_gemma":[0.9260364,0.000034676577,0.061757237,0.0004965177,0.009182427,0.000009221651,0.0019085417,0.000011427532,0.0005635387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953919,0.00008908627,0.0010874572,0.0006441752,0.002553699,0.00023365265],"domain_scores_gemma":[0.99396497,0.00090526673,0.0009911216,0.0020791604,0.0019736784,0.00008578714],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.019703625,0.00009674588,0.00015480333,0.00039490496,0.0010225803,0.0010029987,0.013505157,0.000031218766,0.00018775719],"category_scores_gemma":[0.017103497,0.000063390704,0.0000621308,0.000542002,0.00044545857,0.0059825196,0.0026723598,0.000098420045,0.000024522396],"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":[0.00015582374,0.0001998475,0.002926586,0.000007515595,0.00006222331,0.0000011786399,0.00082020694,0.00032933833,0.00014273796,0.46603444,0.17247264,0.35684747],"study_design_scores_gemma":[0.00051509927,0.000097464435,0.01682417,0.000044034205,0.00003026495,0.000011574461,0.00068073545,0.123702444,0.000037983144,0.20240961,0.65550596,0.00014067454],"about_ca_topic_score_codex":0.00013049401,"about_ca_topic_score_gemma":0.0010888949,"teacher_disagreement_score":0.9095719,"about_ca_system_score_codex":0.000054852797,"about_ca_system_score_gemma":0.00014765309,"threshold_uncertainty_score":0.99183226},"labels":[],"label_agreement":null},{"id":"W2892138780","doi":"10.23889/ijpds.v3i4.999","title":"Perspectives on Linkage Involving Indigenous data","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University nuhelot'ine thaiyots'i nistameyimâkanak Blue Quills; Providence Health Care; Laurentian University","funders":"","keywords":"Indigenous; Sovereignty; Population; Metis; Political science; Sociology; Geography; Public relations; Law; Politics; Database","score_opus":0.46462911489124337,"score_gpt":0.5578686461454321,"score_spread":0.09323953125418871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892138780","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":[0.4659334,0.00036422446,0.46121588,0.019009322,0.033506203,0.0013475588,0.011367992,0.00017392085,0.007081481],"genre_scores_gemma":[0.97941643,0.00007464351,0.015740056,0.0010105233,0.002048389,0.0000025063505,0.00092062517,0.000009442165,0.0007773726],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994228,0.00009974058,0.00071321207,0.0010158432,0.0036471914,0.0002959886],"domain_scores_gemma":[0.9945628,0.0005482194,0.00057725987,0.0025243151,0.0016270188,0.00016040125],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.014770442,0.000117667514,0.0001394222,0.00081864203,0.001090636,0.0028769954,0.016121648,0.000033821045,0.00027382124],"category_scores_gemma":[0.017519932,0.000090278714,0.000037625683,0.0007125098,0.00042339964,0.008805948,0.0034405973,0.00016815141,0.00026867137],"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":[0.00039640674,0.00065137574,0.018122258,0.000006377504,0.00016241566,0.000038245627,0.010247961,0.00039813077,0.0008695862,0.26379633,0.18237679,0.52293414],"study_design_scores_gemma":[0.0011503472,0.000427871,0.105182394,0.00011620075,0.00003191921,0.00011424159,0.011960764,0.10811634,0.00015654862,0.10448974,0.6677022,0.0005513984],"about_ca_topic_score_codex":0.00016859727,"about_ca_topic_score_gemma":0.00026357576,"teacher_disagreement_score":0.52238274,"about_ca_system_score_codex":0.00017465542,"about_ca_system_score_gemma":0.00022261798,"threshold_uncertainty_score":0.9981581},"labels":[],"label_agreement":null},{"id":"W2894874337","doi":"10.1145/3209280.3232788","title":"The Quest for Total Recall","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Waterloo","funders":"","keywords":"Due diligence; Recall; Computer science; Categorization; Precision and recall; Haystack; Information retrieval; Government (linguistics); Enforcement; Data science; Knowledge management; Business; Psychology; Political science; World Wide Web; Finance; Artificial intelligence","score_opus":0.316517329864422,"score_gpt":0.5082093572738737,"score_spread":0.19169202740945174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894874337","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008079203,0.0000330808,0.26194295,0.039291527,0.0022787645,0.0004997203,0.00003549724,0.00007603997,0.6877632],"genre_scores_gemma":[0.4138443,0.000010618161,0.008253607,0.0054697488,0.0007212573,0.00004369085,0.0000062008585,0.000006334121,0.57164425],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99910676,0.000051937586,0.00019429465,0.00017110824,0.00035462136,0.00012130268],"domain_scores_gemma":[0.99820644,0.0011159122,0.00003969696,0.0004719685,0.00013464232,0.00003135299],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00415833,0.00003270739,0.00004892385,0.000019529118,0.0002657209,0.00034296003,0.0005320133,0.0000135033315,0.00044681987],"category_scores_gemma":[0.0020270771,0.000014800994,0.000035844034,0.00011450171,0.000118913194,0.00014234195,0.00016837704,0.000016089129,0.0017273442],"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":[0.000009602077,0.000006049787,0.0000097428965,2.2777124e-7,0.0000022699192,6.0819474e-8,0.00004578713,1.15788936e-7,0.000006534371,0.31555057,0.5609186,0.12345038],"study_design_scores_gemma":[0.00006355399,0.00006094447,0.0005210438,5.7918913e-7,0.0000013060675,2.9570313e-7,0.00042715415,0.0003749707,0.00014766328,0.096965455,0.9014091,0.000027926862],"about_ca_topic_score_codex":0.00003288318,"about_ca_topic_score_gemma":0.0006506301,"teacher_disagreement_score":0.4057651,"about_ca_system_score_codex":0.0000051491975,"about_ca_system_score_gemma":0.0000102529375,"threshold_uncertainty_score":0.9990499},"labels":[],"label_agreement":null},{"id":"W2894983428","doi":"10.1109/tkde.2018.2874004","title":"Precise and Fast Cryptanalysis for Bloom Filter Based Privacy-Preserving Record Linkage","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Australian Research Council; Engineering and Physical Sciences Research Council; Simons Foundation","keywords":"Bloom filter; Computer science; Cryptanalysis; Encoding (memory); Scalability; Data mining; Filter (signal processing); Information retrieval; Algorithm; Database; Cryptography; Artificial intelligence","score_opus":0.1370625278578638,"score_gpt":0.37971452956261115,"score_spread":0.24265200170474735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894983428","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":[0.008671869,0.00013832583,0.9888781,0.00027736774,0.0005128523,0.00025500573,0.0008922806,0.00007159388,0.0003026408],"genre_scores_gemma":[0.93603486,0.00016543701,0.06076394,0.00015330031,0.0003241334,0.000084471314,0.00011199194,0.00004107708,0.0023207935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828416,0.000055036526,0.00042596183,0.0007207556,0.00026620913,0.00024786507],"domain_scores_gemma":[0.99699545,0.0010530564,0.00006252074,0.0016079806,0.00013251322,0.00014847206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015251181,0.00018291181,0.00026672706,0.00040035925,0.00026099946,0.0003488799,0.00097805,0.00007015829,0.00025815767],"category_scores_gemma":[0.0002989434,0.00015787329,0.00006376469,0.00046415167,0.000059621078,0.00080034725,0.00006468348,0.00012731263,0.000061958744],"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":[0.00018535274,0.00037970082,0.00007094775,0.0002937481,0.0002929227,0.000004459372,0.0012649567,0.0035420908,0.0021193437,0.00014924143,0.0328073,0.95888996],"study_design_scores_gemma":[0.0006101198,0.00012284087,0.00016702455,0.00007932181,0.00013787835,0.0000012727509,0.00012227512,0.7403471,0.0027603114,0.00020670252,0.25520077,0.00024439336],"about_ca_topic_score_codex":0.000022244483,"about_ca_topic_score_gemma":0.0002727275,"teacher_disagreement_score":0.9586455,"about_ca_system_score_codex":0.000015836551,"about_ca_system_score_gemma":0.000021519008,"threshold_uncertainty_score":0.6437886},"labels":[],"label_agreement":null},{"id":"W2895460691","doi":"10.32920/24132891","title":"Integrity Proofs for RDF Graphs","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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; RDF; Merkle tree; Mathematical proof; Data integrity; Hash function; Construct (python library); SPARQL; Theoretical computer science; Data mining; Information retrieval; Semantic Web; Database; Programming language; Cryptographic hash function; Mathematics","score_opus":0.660765239254517,"score_gpt":0.5361311141273202,"score_spread":0.12463412512719685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895460691","genre_codex":"methods","genre_gemma":"other","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":[0.0033616729,0.000086430155,0.87053007,0.035536516,0.010287711,0.004501631,0.0022459577,0.0009790958,0.0724709],"genre_scores_gemma":[0.10721208,0.00020968457,0.09281871,0.006285324,0.0007444348,0.0026722467,0.0017240959,0.0001108967,0.78822255],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962247,0.00018278824,0.00085355307,0.0011286965,0.0013163569,0.0002938886],"domain_scores_gemma":[0.99578494,0.0015667935,0.00029399522,0.0018927293,0.000359249,0.00010228362],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010742836,0.00021453178,0.0004465547,0.00044781875,0.00011440264,0.0008535793,0.0025876,0.0002342958,0.0006887483],"category_scores_gemma":[0.0058284206,0.00014526024,0.0003835145,0.00042814587,0.00008796168,0.00016427568,0.0042178268,0.0004665651,0.0019202689],"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":[0.000014156867,0.000045320958,0.00012707563,0.00007096891,0.0000389849,0.0000017659747,0.00012280527,0.000030194278,9.94728e-7,0.25481063,0.69560707,0.049130026],"study_design_scores_gemma":[0.00008949544,0.000019655743,0.00090138667,0.000021586597,0.000014199917,1.1312876e-7,0.00050380826,0.0007904826,0.000030527895,0.6678297,0.32965297,0.0001460779],"about_ca_topic_score_codex":0.00043808736,"about_ca_topic_score_gemma":0.0012422075,"teacher_disagreement_score":0.7777114,"about_ca_system_score_codex":0.00003255473,"about_ca_system_score_gemma":0.00011054823,"threshold_uncertainty_score":0.99885684},"labels":[],"label_agreement":null},{"id":"W2897914812","doi":"10.48550/arxiv.1810.04361","title":"Semi-supervised clustering for de-duplication","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Waterloo","funders":"","keywords":"Cluster analysis; Oracle; Correlation clustering; Computer science; Graph; Cluster (spacecraft); Combinatorics; Complete-linkage clustering; Data mining; Mathematics; Theoretical computer science; Pattern recognition (psychology); CURE data clustering algorithm; Artificial intelligence","score_opus":0.3552284649169554,"score_gpt":0.3098680257081865,"score_spread":0.04536043920876892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897914812","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":[0.14690098,0.000013223383,0.8459634,0.00035638025,0.00053183956,0.00059522537,0.00015983364,0.000102262944,0.005376829],"genre_scores_gemma":[0.9867409,0.00005990901,0.0022714974,0.00042589483,0.00020770247,0.0000057778147,0.00011067874,0.000017928658,0.010159745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977063,0.00020403793,0.0003623427,0.0011939715,0.00020625492,0.00032706998],"domain_scores_gemma":[0.99688417,0.00052166,0.0003401246,0.0017410254,0.00036282494,0.00015020017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028004628,0.00021412894,0.0003100798,0.00030938545,0.00021842048,0.0002895956,0.0021660195,0.00023565139,0.0002690794],"category_scores_gemma":[0.00067987276,0.00022415478,0.00024213851,0.00043660795,0.00013148302,0.00032391556,0.0023457902,0.0001930601,0.00043547817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009164715,0.0005738093,0.006517736,0.00073163275,0.00053029606,0.00008913401,0.0025603569,0.46169493,0.00033377996,0.26097524,0.22504301,0.040033605],"study_design_scores_gemma":[0.00049939554,0.000051660034,0.0010091859,0.000052606207,0.00009212558,7.9243455e-7,0.00063439674,0.7045326,0.00009763027,0.22317344,0.06950891,0.00034721577],"about_ca_topic_score_codex":0.00013094099,"about_ca_topic_score_gemma":0.00019695007,"teacher_disagreement_score":0.84369195,"about_ca_system_score_codex":0.00020039955,"about_ca_system_score_gemma":0.00012020378,"threshold_uncertainty_score":0.9140766},"labels":[],"label_agreement":null},{"id":"W2899051575","doi":"10.1109/pst.2018.8514187","title":"Managing Publicly Known Security Vulnerabilities in Software Systems","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 British Columbia","funders":"","keywords":"Secure coding; Computer science; Vulnerability management; Security bug; Computer security; NIST; Software security assurance; Vulnerability (computing); Software system; Software; Context (archaeology); Backporting; Software development; Software engineering; Component-based software engineering; Vulnerability assessment; Information security; Security service; Operating system","score_opus":0.12740275896242967,"score_gpt":0.39009731930467745,"score_spread":0.2626945603422478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899051575","genre_codex":"other","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":[0.24424925,0.00043960536,0.12570803,0.011361765,0.004396381,0.0010573651,0.00010315727,0.00059408665,0.61209035],"genre_scores_gemma":[0.9769129,0.000008316374,0.0007506973,0.00070760946,0.00018051108,0.00002333257,0.000007336568,0.0000064906217,0.021402806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970807,0.00040438847,0.0006391501,0.0005478377,0.0010021855,0.00032578164],"domain_scores_gemma":[0.9977796,0.0007964371,0.000102710124,0.0009970362,0.00023605836,0.000088147455],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008000529,0.000114508715,0.00023676544,0.00038770595,0.0001489799,0.0010165705,0.0010191735,0.00004802478,0.001778471],"category_scores_gemma":[0.0027354618,0.000082397964,0.000048864877,0.00080954103,0.00019170415,0.0011130533,0.0005945797,0.00010552289,0.0016564698],"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":[0.00002482773,0.00015058384,0.018429274,0.000064640924,0.000018229359,0.000012325558,0.004025589,0.00010368604,0.0000025798638,0.51116097,0.4021162,0.06389111],"study_design_scores_gemma":[0.00026436543,0.00007216517,0.0022957772,0.000027526492,0.0000031093296,0.0000023906853,0.019450573,0.006098988,0.000032500848,0.24895921,0.7225821,0.00021129196],"about_ca_topic_score_codex":0.0032835559,"about_ca_topic_score_gemma":0.0049751126,"teacher_disagreement_score":0.73266363,"about_ca_system_score_codex":0.000054764532,"about_ca_system_score_gemma":0.000029453126,"threshold_uncertainty_score":0.99913406},"labels":[],"label_agreement":null},{"id":"W2899225985","doi":"10.5267/j.uscm.2018.7.004","title":"Integration between open records and target cost to effectively manage supply chain costs","year":2018,"lang":"en","type":"article","venue":"Uncertain Supply Chain Management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Supply chain; Business; Chain (unit); Supply chain risk management; Computer science; Risk analysis (engineering); Operations management; Supply chain management; Process management; Marketing; Service management; Economics","score_opus":0.08179337785974011,"score_gpt":0.3845704567543373,"score_spread":0.3027770788945972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2899225985","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":[0.06575077,0.00013115721,0.638426,0.04186423,0.0026632857,0.02072044,0.0014814213,0.00043823873,0.22852442],"genre_scores_gemma":[0.91374713,0.00009586903,0.034265425,0.0085315155,0.0006097574,0.0011546346,0.0005839718,0.00007656876,0.040935114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928496,0.0011814452,0.0012084293,0.0019518678,0.0018682656,0.0009403943],"domain_scores_gemma":[0.9958409,0.0011088513,0.0003851694,0.0018307118,0.0003355719,0.0004987876],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013501167,0.000567556,0.0008017863,0.0011774155,0.00067476486,0.0021303326,0.0034621502,0.00013690087,0.0013934724],"category_scores_gemma":[0.0011128663,0.00047781167,0.00012587997,0.0020376907,0.0003276312,0.0011148079,0.0046050646,0.00025245408,0.0017368372],"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":[0.00027713095,0.00015196888,0.009113611,0.000053534743,0.00019537708,0.00005927213,0.0019553516,0.000057119418,0.000041840347,0.06485281,0.28552133,0.63772064],"study_design_scores_gemma":[0.0017108396,0.0007983238,0.08958219,0.00021143701,0.00008792211,0.0000021945973,0.006591822,0.002013156,0.00033998117,0.037310738,0.8605563,0.0007951129],"about_ca_topic_score_codex":0.0021433278,"about_ca_topic_score_gemma":0.0023827297,"teacher_disagreement_score":0.84799635,"about_ca_system_score_codex":0.00049943867,"about_ca_system_score_gemma":0.000032146207,"threshold_uncertainty_score":0.99976736},"labels":[],"label_agreement":null},{"id":"W2900691829","doi":"10.1109/tkde.2019.2893175","title":"Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Join (topology); Nearest neighbor search; Sublinear function; Range (aeronautics); Unary operation; Range query (database)","score_opus":0.0592414764365441,"score_gpt":0.3250866367617011,"score_spread":0.265845160325157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900691829","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":[0.25384632,0.0002644247,0.74363446,0.00029839686,0.00041482906,0.0005004491,0.0005214073,0.000106888074,0.00041281444],"genre_scores_gemma":[0.99140227,0.0002026136,0.008068964,0.000046830944,0.000014699832,0.000013562765,0.000028466684,0.000012131092,0.00021044962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982984,0.00008094188,0.00041774882,0.0006526922,0.00033054125,0.00021969082],"domain_scores_gemma":[0.9979545,0.0009304636,0.000052638286,0.0009423762,0.000015946101,0.000104066385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017209367,0.00017942024,0.00025737,0.00023762217,0.00009240413,0.0001761454,0.00038556414,0.0000811863,0.00012929972],"category_scores_gemma":[0.00010198143,0.00016935867,0.000027878285,0.00026213107,0.00002557398,0.0009398963,0.000047762715,0.0002486491,0.00011649519],"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":[0.00014129966,0.0021606265,0.0023203203,0.0007675231,0.00023536444,0.000034617675,0.005454815,0.22842643,0.0023817054,0.001429478,0.0021089786,0.75453883],"study_design_scores_gemma":[0.00086850143,0.0000803062,0.010018683,0.00007869355,0.00004257946,0.0000065059075,0.00032750107,0.96983176,0.0005538113,0.00030863765,0.01756609,0.00031692936],"about_ca_topic_score_codex":0.00004516713,"about_ca_topic_score_gemma":0.00015462279,"teacher_disagreement_score":0.7542219,"about_ca_system_score_codex":0.000056009325,"about_ca_system_score_gemma":0.000018753506,"threshold_uncertainty_score":0.6906246},"labels":[],"label_agreement":null},{"id":"W2901302597","doi":"10.23889/ijpds.v3i5.1045","title":"Administrative Data Format Standardization for Efficient Analytics","year":2018,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Computer science; Standardization; Data quality; Data management; Data science; Data pre-processing; Metadata; Data governance; Data processing; Data warehouse; Database; Data mining; World Wide Web; Engineering","score_opus":0.5881116757594165,"score_gpt":0.5992713194419055,"score_spread":0.011159643682489007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901302597","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":[0.0048251413,0.00001119596,0.9750781,0.0028904085,0.0051462078,0.00044137295,0.01106358,0.000019851988,0.0005241592],"genre_scores_gemma":[0.930027,0.000015456231,0.06265778,0.0006246463,0.0012961915,0.000008096834,0.0048630815,0.000010304932,0.00049742206],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99453473,0.00006322112,0.0010145657,0.00078873575,0.003303351,0.00029538648],"domain_scores_gemma":[0.99317694,0.00062206975,0.00081450853,0.0017902819,0.0034298196,0.00016638922],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.015996872,0.00012286426,0.0001691149,0.00057239266,0.0009868543,0.0025987641,0.00973547,0.00003439567,0.00011727203],"category_scores_gemma":[0.016983759,0.00009507621,0.000052658863,0.00073065906,0.00037321102,0.0061626183,0.0019895148,0.000080061174,0.000039386956],"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":[0.00095185015,0.00036887362,0.0035817006,0.0000143718335,0.00019438384,0.0000054849,0.0008959461,0.008862997,0.0002892292,0.26321554,0.43718728,0.28443232],"study_design_scores_gemma":[0.0005114861,0.00011731129,0.002886443,0.000018004417,0.000022327875,0.00001802284,0.00047328093,0.5718463,0.00010158524,0.018225687,0.405654,0.0001255464],"about_ca_topic_score_codex":0.000023259301,"about_ca_topic_score_gemma":0.00019468369,"teacher_disagreement_score":0.9252019,"about_ca_system_score_codex":0.00017288029,"about_ca_system_score_gemma":0.00037074092,"threshold_uncertainty_score":0.9984366},"labels":[],"label_agreement":null},{"id":"W2901674170","doi":"10.1186/s40965-018-0058-3","title":"The conceptual schema in geospatial data standard design with application to GroundWaterML2","year":2018,"lang":"en","type":"article","venue":"Open Geospatial Data Software and Standards","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Geological Survey of Canada","funders":"Bureau de Recherches Géologiques et Minières; U.S. Geological Survey; Natural Resources Canada; Muséum National d'Histoire Naturelle; Universität Salzburg; Institut Français de Recherche pour l'Exploitation de la Mer","keywords":"Geospatial analysis; Conceptual schema; Schema (genetic algorithms); Computer science; Data mining; Data science; Database; Information retrieval; Geography; Remote sensing","score_opus":0.21380253530369708,"score_gpt":0.4468257726292829,"score_spread":0.23302323732558583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901674170","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":[0.003130689,0.00008934328,0.9656855,0.002167432,0.00023117135,0.0018291358,0.026351213,0.000041479605,0.00047407075],"genre_scores_gemma":[0.7014062,0.00039567158,0.27890745,0.004082477,0.001144446,0.00048416905,0.011310996,0.00012690274,0.0021416768],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99329555,0.00055570167,0.0008338396,0.0016864227,0.003092387,0.00053607597],"domain_scores_gemma":[0.9912215,0.0011965472,0.00029000692,0.006112278,0.0009341346,0.00024555225],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.021093352,0.0002826065,0.0004819985,0.00010975726,0.0009839663,0.0032761472,0.009529063,0.000088237546,0.00026709866],"category_scores_gemma":[0.00587811,0.00017075357,0.000016259935,0.0007119382,0.00071496796,0.0028798308,0.012128064,0.0001914737,0.00010003221],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022508644,0.00005034133,0.001752019,0.000006871361,0.00004249586,0.000011810711,0.0010731935,0.00001574549,0.000004282581,0.0022529585,0.24982812,0.7427113],"study_design_scores_gemma":[0.0013529074,0.00083593116,0.0030076099,0.000048293103,0.000030751016,0.0000043669393,0.0017762139,0.0019498839,0.000052410465,0.0037502155,0.98685247,0.00033894356],"about_ca_topic_score_codex":0.005753792,"about_ca_topic_score_gemma":0.09383145,"teacher_disagreement_score":0.74237233,"about_ca_system_score_codex":0.000119893666,"about_ca_system_score_gemma":0.00072264444,"threshold_uncertainty_score":0.99775857},"labels":[],"label_agreement":null},{"id":"W2905047743","doi":"10.18438/eblip29478","title":"Research Support Priorities of and Relationships among Librarians and Research Administrators: A Content Analysis of the Professional Literature","year":2018,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Canadian Association of Research Libraries; Association of Research Libraries","keywords":"Content analysis; Thematic analysis; Library science; Coding (social sciences); Sociology; Psychology; Qualitative research; Computer science; Social science","score_opus":0.38705307610005246,"score_gpt":0.48127285290946137,"score_spread":0.0942197768094089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905047743","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":[0.85217756,0.0010655483,0.0006827395,0.12729123,0.00021474747,0.0012553158,0.0003874671,0.000031098167,0.016894277],"genre_scores_gemma":[0.99540937,0.00041710548,0.0010482164,0.0018010114,0.000029582632,0.000017445644,0.00003179842,0.0000026258338,0.0012428209],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9939775,0.003176809,0.00080041855,0.0002142559,0.0016679354,0.00016312141],"domain_scores_gemma":[0.98204803,0.015995452,0.0004982021,0.00053949887,0.0008092756,0.000109555185],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.017791651,0.00007863597,0.00019046682,0.0010246627,0.00058941735,0.001021044,0.00045200821,0.00009791415,0.00018968813],"category_scores_gemma":[0.022930196,0.000049249044,0.000039380386,0.0039291615,0.0012607421,0.10697744,0.00065269996,0.0004894667,0.0000050744065],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088223536,0.00008925913,0.10231067,0.00026053848,0.00013430459,0.000002341392,0.010846744,0.0000047022045,0.00004490122,0.8603586,0.017738588,0.007327123],"study_design_scores_gemma":[0.00025309913,0.00041330402,0.79281974,0.00060440134,0.0000981306,0.0000049025957,0.041220225,0.002320971,0.0007574624,0.00377501,0.15763544,0.00009732324],"about_ca_topic_score_codex":0.000019455501,"about_ca_topic_score_gemma":0.000001932398,"teacher_disagreement_score":0.8565836,"about_ca_system_score_codex":0.000004760789,"about_ca_system_score_gemma":0.00037752953,"threshold_uncertainty_score":0.98530006},"labels":[],"label_agreement":null},{"id":"W2905078980","doi":"10.2196/10436","title":"Where No Universal Health Care Identifier Exists: Comparison and Determination of the Utility of Score-Based Persons Matching Algorithms Using Demographic Data","year":2018,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Matching (statistics); Computer science; Health care; Identifier; Data mining; Statistics; Medicine; Algorithm; Mathematics","score_opus":0.23936289667713462,"score_gpt":0.4463407364047887,"score_spread":0.2069778397276541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905078980","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":[0.91188055,0.0026406806,0.073490135,0.008145634,0.00066406437,0.0011115543,0.0016160923,0.000034819564,0.00041643716],"genre_scores_gemma":[0.9966029,0.00006790344,0.0026180346,0.00056866906,0.00003646802,0.0000023750783,0.000076324264,0.000005559555,0.0000217954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964829,0.0011503095,0.0007538386,0.0005190534,0.0007759232,0.00031795554],"domain_scores_gemma":[0.9971538,0.0003997309,0.00075627613,0.0010553338,0.00039711953,0.00023769503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007065982,0.00011712214,0.00040840014,0.00018707932,0.0004677333,0.0001659698,0.0007561782,0.000050073446,0.000026143183],"category_scores_gemma":[0.0005866504,0.00008628044,0.00003903073,0.00070718705,0.00051227986,0.0004886999,0.0004645261,0.000121106146,9.344372e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006404846,0.00012753085,0.70341754,0.0010836554,0.000014498498,4.9209353e-7,0.007842184,9.2745e-7,0.000007090008,0.0004741843,0.008197316,0.27877054],"study_design_scores_gemma":[0.0011526828,0.0003424551,0.77941513,0.00018880119,0.0000027520473,0.00000375186,0.028223997,0.10901137,0.0000034914574,0.0004334799,0.08096104,0.00026103194],"about_ca_topic_score_codex":0.002064371,"about_ca_topic_score_gemma":0.0104627535,"teacher_disagreement_score":0.2785095,"about_ca_system_score_codex":0.000044131433,"about_ca_system_score_gemma":0.0006885291,"threshold_uncertainty_score":0.5838462},"labels":[],"label_agreement":null},{"id":"W2911562225","doi":"","title":"Proceedings of third international workshop on MapReduce and its Applications Date","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Variety (cybernetics); Computer science; Data science; Cover (algebra); Pleasure; World Wide Web; Software engineering; Engineering; Artificial intelligence","score_opus":0.20678318828991238,"score_gpt":0.43681681384126736,"score_spread":0.23003362555135498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911562225","genre_codex":"other","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":[0.15557104,0.00008892259,0.008589403,0.008416285,0.00031287115,0.00044666586,0.000060029048,0.000046706067,0.82646805],"genre_scores_gemma":[0.9803722,0.000035298803,0.0014057338,0.0005750471,0.00007748666,0.000028400227,0.0000063027096,0.0000022371728,0.01749731],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99902153,0.000006836564,0.00022364013,0.00016308675,0.00049462833,0.00009026949],"domain_scores_gemma":[0.9993833,0.00021933348,0.00009573387,0.00012177802,0.00012271854,0.000057178593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001342103,0.000044575776,0.000070559596,0.000104487684,0.000036168232,0.00009148589,0.00042792442,0.000019633691,0.00035063043],"category_scores_gemma":[0.00041144044,0.000031206047,0.000016439855,0.00019434393,0.000027737382,0.00059196586,0.0002536989,0.000037413178,0.00031020612],"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":[0.00000913222,0.000097538235,0.0007040574,0.0000043846308,0.000010002969,1.802566e-8,0.00026369235,0.0000010195503,0.00045546924,0.9016627,0.053400703,0.043391302],"study_design_scores_gemma":[0.00012673375,0.000010821208,0.010485018,0.000010850077,0.0000065073637,9.253919e-7,0.0019424286,0.00020898503,0.0032764298,0.010806772,0.97304755,0.00007699791],"about_ca_topic_score_codex":0.0000028591683,"about_ca_topic_score_gemma":0.0000013960403,"teacher_disagreement_score":0.9196468,"about_ca_system_score_codex":0.0000043793166,"about_ca_system_score_gemma":0.0000033916008,"threshold_uncertainty_score":0.39871755},"labels":[],"label_agreement":null},{"id":"W2913052408","doi":"","title":"Proceedings of the 10th IEEE international conference on Information Reuse & Integration","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reuse; Computer science; Engineering","score_opus":0.21812931853070847,"score_gpt":0.4171971717500172,"score_spread":0.19906785321930873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913052408","genre_codex":"other","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":[0.1329063,4.5938285e-7,0.007749007,0.03195759,0.0005841412,0.00025294127,0.000019690664,0.000026370559,0.8265035],"genre_scores_gemma":[0.99412155,0.0000047197163,0.00072671246,0.0025986074,0.000019050362,0.000002082735,0.000007142223,5.3001617e-7,0.0025196003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985996,0.000012497017,0.00036058907,0.00009420248,0.0008787192,0.000054430544],"domain_scores_gemma":[0.9990665,0.000045529203,0.000216957,0.00024570053,0.00040811716,0.000017215572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001124699,0.000047068363,0.00006347495,0.00011456948,0.000041259602,0.00025398776,0.0011158349,0.00002200299,0.000446482],"category_scores_gemma":[0.0013669482,0.00002430522,0.000034224864,0.00024723742,0.000030481964,0.001385166,0.000087898836,0.000055193417,0.00013347103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020113974,0.000029527797,0.00005869262,7.5945627e-7,0.0000022825009,1.515248e-8,0.00077289506,0.00000875068,0.0005893663,0.779892,0.15044507,0.06818052],"study_design_scores_gemma":[0.000719053,0.00036737093,0.059615064,0.00009960887,0.000011941326,0.0000018376344,0.012855478,0.016590314,0.040552672,0.6426237,0.2263296,0.00023333966],"about_ca_topic_score_codex":0.000013956502,"about_ca_topic_score_gemma":0.000010426429,"teacher_disagreement_score":0.86121523,"about_ca_system_score_codex":0.000018429377,"about_ca_system_score_gemma":0.000014231103,"threshold_uncertainty_score":0.48886648},"labels":[],"label_agreement":null},{"id":"W2913421376","doi":"","title":"Proceedings of the 4th workshop on Workshop for Ph.D. students in information & knowledge management","year":2011,"lang":"en","type":"article","venue":"Conference on Information and Knowledge Management","topic":"Data Quality and Management","field":"Decision Sciences","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":"Systems, Applications & Products in Data Processing (Canada)","funders":"","keywords":"Computer science; Viewpoints; Presentation (obstetrics); Point (geometry); Resource (disambiguation); Citation; World Wide Web; Library science; Data science","score_opus":0.1676516052721033,"score_gpt":0.38694816375382723,"score_spread":0.21929655848172394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913421376","genre_codex":"other","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":[0.01455005,0.000026873175,0.004511657,0.0004317614,0.0007321705,0.0028779544,0.000030484749,0.000051468527,0.97678757],"genre_scores_gemma":[0.98798615,0.00031237307,0.0006796339,0.000849364,0.000022415623,0.0005028531,0.000030759245,0.0000083416535,0.009608128],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970158,0.00005981972,0.0013348684,0.00030697044,0.00093926745,0.00034328105],"domain_scores_gemma":[0.9981222,0.00016339855,0.00060488,0.00054248306,0.00047050772,0.00009650334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003254144,0.00027540038,0.0003193438,0.0010371301,0.00021404716,0.00058788137,0.0015657588,0.00009251547,0.000104302264],"category_scores_gemma":[0.0002469301,0.00019215372,0.0001070149,0.0010776717,0.00012854012,0.0022397419,0.0011333065,0.00017202717,0.0005108162],"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":[0.00017515713,0.00027419184,0.00034580953,0.00027654806,0.000042002015,1.3576654e-7,0.010146946,0.000005760229,2.416008e-7,0.6386652,0.018044515,0.3320235],"study_design_scores_gemma":[0.004793396,0.0003060792,0.07024065,0.0014570432,0.00010183035,6.648767e-7,0.12660034,0.00404574,0.00012947334,0.031245627,0.76041883,0.00066030794],"about_ca_topic_score_codex":0.0000038647436,"about_ca_topic_score_gemma":0.000048147096,"teacher_disagreement_score":0.97343606,"about_ca_system_score_codex":0.00010003407,"about_ca_system_score_gemma":0.00002538274,"threshold_uncertainty_score":0.7835801},"labels":[],"label_agreement":null},{"id":"W2916773830","doi":"10.1007/s12652-019-01252-y","title":"A configurable identity matching algorithm for community care management","year":2019,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Computational intelligence; Identity (music); Identity management; Matching (statistics); Algorithm; Artificial intelligence; Mathematics; Computer security","score_opus":0.12942504875229946,"score_gpt":0.4084695099433377,"score_spread":0.2790444611910382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916773830","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":[0.27916685,0.00028683004,0.7172923,0.00008023644,0.00085086236,0.00037300412,0.000009609571,0.000013037244,0.0019272373],"genre_scores_gemma":[0.95835614,0.00008970419,0.040366042,0.00048304675,0.00010678136,0.0000016315441,0.0000059403546,0.000010641203,0.0005800708],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99705267,0.0002999311,0.001168184,0.00023623527,0.0009748857,0.00026810297],"domain_scores_gemma":[0.99701756,0.00091807474,0.000869858,0.00043239447,0.00066362624,0.00009846835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007605568,0.0001514783,0.00044369273,0.00033662157,0.0005710956,0.0008354479,0.0012288913,0.000040483013,0.00012047813],"category_scores_gemma":[0.00015226353,0.00012160522,0.00019001405,0.00026058385,0.00006363043,0.0008419312,0.0005714279,0.00035067694,0.00006029274],"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":[0.00007075139,0.00018318111,0.00026860303,0.0002293692,0.00016401923,0.000016971562,0.01674422,0.0014832267,0.00011158216,0.080725886,0.0009915244,0.89901066],"study_design_scores_gemma":[0.002371367,0.0016767747,0.0032767355,0.0010610231,0.00024187333,0.00010110691,0.45839974,0.030776821,0.0020805653,0.42857212,0.070657566,0.0007843245],"about_ca_topic_score_codex":0.00008482551,"about_ca_topic_score_gemma":0.000030409507,"teacher_disagreement_score":0.8982263,"about_ca_system_score_codex":0.00006787374,"about_ca_system_score_gemma":0.000022855142,"threshold_uncertainty_score":0.80562437},"labels":[],"label_agreement":null},{"id":"W2920914950","doi":"10.18438/eblip29516","title":"Data Librarians’ Skills and Competencies Are Heterogeneous and Cluster into Those for Generalists and Specialists","year":2019,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Medical education; Psychology; Subject (documents); Interpersonal communication; Work (physics); Computer science; Library science; Medicine; Social psychology; Engineering","score_opus":0.09420204864177724,"score_gpt":0.3646789076947657,"score_spread":0.27047685905298846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920914950","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4705562,0.010277204,0.045126315,0.4585476,0.0017537259,0.005342015,0.003087442,0.00032567285,0.0049838456],"genre_scores_gemma":[0.40196973,0.01671374,0.13983189,0.4359042,0.00055254303,0.00010066721,0.0020177164,0.000046942558,0.0028625787],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979594,0.000359895,0.0006155823,0.00043083847,0.00046489775,0.00016941766],"domain_scores_gemma":[0.9930054,0.005461211,0.00053561764,0.00076253107,0.00007566996,0.00015958554],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002394321,0.00016648215,0.00024245665,0.0001986351,0.00024593092,0.0029949849,0.0005121786,0.00007309117,0.00014153346],"category_scores_gemma":[0.004384868,0.00013183562,0.00001943383,0.00022552157,0.0001527217,0.21370831,0.0011810042,0.00010251421,0.000039147566],"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":[0.0024505835,0.00025483637,0.024645254,0.0020519316,0.00015549568,0.000020208465,0.0053082574,0.0003235404,0.000116982665,0.4929037,0.12851885,0.34325036],"study_design_scores_gemma":[0.0006545389,0.00013831166,0.01643862,0.00017090279,0.000032641023,0.00003062758,0.0014181025,0.012324228,0.00010253934,0.0024201768,0.96605057,0.00021877502],"about_ca_topic_score_codex":0.000010195395,"about_ca_topic_score_gemma":0.0000017571285,"teacher_disagreement_score":0.8375317,"about_ca_system_score_codex":0.0000040047853,"about_ca_system_score_gemma":0.00006312422,"threshold_uncertainty_score":0.99804},"labels":[],"label_agreement":null},{"id":"W2921690166","doi":"10.48550/arxiv.1903.05228","title":"Distributed Dependency Discovery","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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":"University of Waterloo","funders":"","keywords":"Computer science; Pruning; Dependency (UML); Focus (optics); Distributed computing; Implementation; Space (punctuation); Big data; Computation; Theoretical computer science; Distributed Computing Environment; Data mining; Algorithm; Artificial intelligence; Programming language","score_opus":0.27525841916614996,"score_gpt":0.27968798770166714,"score_spread":0.004429568535517181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921690166","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":[0.24575004,0.000056943107,0.72580373,0.00035962203,0.0021520169,0.00056799786,0.0018234935,0.00013969526,0.023346456],"genre_scores_gemma":[0.96519035,0.00012728016,0.00006836592,0.000192688,0.00007606456,7.140532e-7,0.00035108617,0.000015308045,0.033978116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99619883,0.00042990834,0.0005015431,0.0017626071,0.0006951752,0.0004119254],"domain_scores_gemma":[0.99528134,0.0006337654,0.00054644124,0.003021703,0.0003477227,0.00016901872],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002464528,0.00034278905,0.0005513875,0.00038454987,0.0001502421,0.0007197832,0.003603922,0.00030475095,0.0005782843],"category_scores_gemma":[0.0010981504,0.0003232017,0.00040376597,0.0008392242,0.00015380172,0.0010899922,0.0058140233,0.000585037,0.0033131083],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018861625,0.0003582081,0.01707388,0.00012580075,0.00029033626,0.00060480915,0.00017526392,0.32520336,0.00000927559,0.5701006,0.083431356,0.0024385122],"study_design_scores_gemma":[0.0010178454,0.00008009384,0.014930612,0.00012509468,0.00026173843,0.0000029283542,0.0019143756,0.058292516,0.000045346253,0.8055064,0.11662295,0.0012000673],"about_ca_topic_score_codex":0.00033390886,"about_ca_topic_score_gemma":0.00027306544,"teacher_disagreement_score":0.72573537,"about_ca_system_score_codex":0.00028212657,"about_ca_system_score_gemma":0.00026216457,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W2922217177","doi":"10.13016/m231pw-vd2z","title":"RESTORE: Automated Regression Testing for Datasets","year":2019,"lang":"en","type":"preprint","venue":"Maryland Shared Open Access Repository (USMAI Consortium)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Set (abstract data type); Data mining; Process (computing); Scale (ratio); Quality (philosophy); Data set; Data quality; Artificial intelligence","score_opus":0.36935616054139486,"score_gpt":0.5077334092430275,"score_spread":0.1383772487016326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922217177","genre_codex":"other","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":[0.2915374,0.0051937536,0.021637265,0.016000215,0.066885866,0.06992038,0.14175487,0.0066773454,0.3803929],"genre_scores_gemma":[0.7199289,0.00016243254,0.04021418,0.009304158,0.002995356,0.007038997,0.085671514,0.00064393814,0.1340405],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98927325,0.0012097469,0.0029070072,0.003389917,0.002359834,0.00086024875],"domain_scores_gemma":[0.98520505,0.0039988584,0.0031659857,0.0062169023,0.0009933402,0.00041987567],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007178848,0.0008664907,0.0017427624,0.0006833816,0.0010311053,0.024638213,0.01978722,0.000643882,0.0005610415],"category_scores_gemma":[0.008431799,0.00066355744,0.00034442588,0.0008904537,0.00020014461,0.0040871147,0.038724784,0.0008610364,0.00031093688],"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":[0.0005026866,0.00019240132,0.017212793,0.0004664462,0.00017425524,0.00017234801,0.000110776586,0.0010055932,0.00030746436,0.00015353812,0.97163767,0.008064053],"study_design_scores_gemma":[0.0032140804,0.0002548491,0.07625815,0.0023164942,0.00039581774,0.00007145351,0.00028049643,0.05629149,0.0014773918,0.009772042,0.84735966,0.0023080858],"about_ca_topic_score_codex":0.0028388093,"about_ca_topic_score_gemma":0.00018567019,"teacher_disagreement_score":0.42839152,"about_ca_system_score_codex":0.00025942866,"about_ca_system_score_gemma":0.0011106347,"threshold_uncertainty_score":0.9999206},"labels":[],"label_agreement":null},{"id":"W2934046129","doi":"10.2478/jos-2019-0007","title":"An Evolutionary Schema for Using “it-is-what-it-is” Data in Official Statistics","year":2019,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"","keywords":"Data science; Schema (genetic algorithms); Computer science; Set (abstract data type); Big data; Agency (philosophy); Process (computing); Data mining; Information retrieval; Sociology; Social science","score_opus":0.33696849945233176,"score_gpt":0.4966412882000322,"score_spread":0.15967278874770047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2934046129","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":[0.011483361,0.0001333379,0.9682086,0.0018387107,0.0026195382,0.0004382275,0.015124715,0.000007211541,0.00014628067],"genre_scores_gemma":[0.09019985,0.00027292917,0.8973669,0.008431269,0.0018686241,0.0000027176307,0.0010183573,0.000073521245,0.000765849],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99397725,0.00031227103,0.0022535902,0.0005497779,0.0024373701,0.00046973588],"domain_scores_gemma":[0.99385136,0.0021596244,0.0014963086,0.0011158109,0.0011489337,0.00022796888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006157867,0.0002464796,0.0006951622,0.00047227647,0.00019193994,0.0007018609,0.0021894332,0.00013923927,0.0009098162],"category_scores_gemma":[0.0041536763,0.00022088287,0.000081779646,0.0005337969,0.00014705694,0.0020680255,0.0004614216,0.00035916799,0.00012403181],"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":[0.00092266,0.0009422553,0.0009819509,0.00009058269,0.000104797735,0.00011836451,0.0013598157,0.003834347,0.000114893046,0.042906225,0.88247424,0.06614987],"study_design_scores_gemma":[0.002490888,0.0011697888,0.0033423195,0.00024115384,0.00019792652,0.000043971308,0.010802235,0.43748865,0.000055314144,0.09223348,0.4513006,0.0006336812],"about_ca_topic_score_codex":0.000110316534,"about_ca_topic_score_gemma":0.0005898482,"teacher_disagreement_score":0.4336543,"about_ca_system_score_codex":0.00018756544,"about_ca_system_score_gemma":0.0009848382,"threshold_uncertainty_score":0.9961849},"labels":[],"label_agreement":null},{"id":"W2936904543","doi":"","title":"Working Across Boundaries - Follow-Up Survey","year":2017,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Survey data collection; Dimension (graph theory); Work (physics); Agency (philosophy); USable; Argument (complex analysis); Public relations; Plan (archaeology); Order (exchange); Dissemination; Political science; Sociology; Computer science; World Wide Web; Business; Engineering; Geography; Social science; Law","score_opus":0.4935244230268321,"score_gpt":0.5068713704100264,"score_spread":0.013346947383194308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936904543","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":[0.5376588,0.00008256356,0.058321465,0.0077426448,0.015169148,0.00035196924,0.0001859764,0.00017466203,0.38031277],"genre_scores_gemma":[0.87026477,0.0000042838237,0.00040218994,0.0005793428,0.000054709693,0.0000030522426,0.000011554413,0.0000041993076,0.12867588],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99773544,0.0001935647,0.0003659379,0.00040462537,0.0009978061,0.00030261406],"domain_scores_gemma":[0.99688184,0.0006569883,0.00023760165,0.0020162757,0.00012892165,0.00007838],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013194422,0.00009193037,0.00019528292,0.000037668393,0.002740716,0.014141729,0.0023844715,0.00004091256,0.00093749753],"category_scores_gemma":[0.010289429,0.000063160165,0.0000718049,0.000115432886,0.00050748064,0.00091611233,0.0014694007,0.0000706842,0.0019387718],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054585587,0.000028259208,0.21591637,0.0000016146079,0.00002828133,0.000008149825,0.0011867995,0.00000124001,0.000004920892,0.061482377,0.45997795,0.26130944],"study_design_scores_gemma":[0.00019784278,0.000007656632,0.325203,0.0000032000742,0.0000015500848,2.4851798e-7,0.0006716349,0.000029969584,0.000033624674,0.01743615,0.6563357,0.00007941468],"about_ca_topic_score_codex":0.0037593935,"about_ca_topic_score_gemma":0.06944929,"teacher_disagreement_score":0.332606,"about_ca_system_score_codex":0.000012870687,"about_ca_system_score_gemma":0.000041469575,"threshold_uncertainty_score":0.9999758},"labels":[],"label_agreement":null},{"id":"W2938471675","doi":"10.5683/sp/e6lsvq","title":"Research Data Management Survey of Queen's University, 2018","year":2018,"lang":"en","type":"dataset","venue":"QSpace (Queen's University Library)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Ontario Council of University Libraries; Queen's University","funders":"","keywords":"Queen (butterfly); RDM; Library science; Data management plan; Survey research; Data management; Research data; Sociology; Engineering; Management; Computer science; Database; Pedagogy","score_opus":0.1725551812751804,"score_gpt":0.3636516977416655,"score_spread":0.1910965164664851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938471675","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007430071,0.0000103820485,0.00032683936,0.019367468,0.0007432473,0.0008539557,0.96816236,0.00011319981,0.010348237],"genre_scores_gemma":[0.000086113796,0.0021686626,0.0012527435,0.00015702062,0.00011020199,2.9046953e-7,0.75618684,0.000032370026,0.24000575],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98514515,0.005756264,0.0007527084,0.002766454,0.0045101116,0.0010693114],"domain_scores_gemma":[0.98466665,0.0028098337,0.0009539223,0.01032159,0.0006886535,0.0005593451],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.007409691,0.0006226221,0.001131003,0.0038602988,0.0007587081,0.0006160795,0.021185307,0.00059919665,0.005875261],"category_scores_gemma":[0.0008975153,0.0006531711,0.00023105144,0.006110613,0.0016392162,0.0051172185,0.037163805,0.0010721902,0.0026015914],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044862123,0.00035489377,0.00037409263,0.00020823532,0.00035938315,0.0006402613,0.000038241542,0.0000050080184,2.5471838e-8,0.0023808787,0.99484843,0.00034190842],"study_design_scores_gemma":[0.0006920515,0.00022344559,0.0061909826,0.0001730297,0.0001748204,2.0453618e-7,0.0027764793,0.0000039571473,0.0000070871847,0.00058914424,0.9885338,0.0006350001],"about_ca_topic_score_codex":0.17107868,"about_ca_topic_score_gemma":0.0050462927,"teacher_disagreement_score":0.22965752,"about_ca_system_score_codex":0.00026908866,"about_ca_system_score_gemma":0.0006756036,"threshold_uncertainty_score":0.99959195},"labels":[],"label_agreement":null},{"id":"W2941717757","doi":"10.3390/info10050156","title":"Exploring Whether Data Can be Represented as a Composite Unit in Form Processing Using the Manufacturing of Information Approach","year":2019,"lang":"en","type":"article","venue":"Information","topic":"Data Quality and Management","field":"Decision Sciences","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Relevance (law); Computer science; Representation (politics); Block (permutation group theory); Unit (ring theory); Quality (philosophy); Data mining; Simple (philosophy); Data quality; Information retrieval; Artificial intelligence; Mathematics; Engineering; Operations management","score_opus":0.49072795230219474,"score_gpt":0.41395952453904594,"score_spread":0.0767684277631488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941717757","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":[0.9442771,0.0000051711067,0.03839349,0.00045459942,0.00012942735,0.0006159501,0.0000630562,0.00002709391,0.016034132],"genre_scores_gemma":[0.99727184,0.000006378242,0.0017940891,0.00041613265,0.000010621185,0.000011901993,0.00044956582,0.0000030499812,0.000036414953],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977091,0.000085146785,0.00092878856,0.00012324372,0.000986554,0.00016716919],"domain_scores_gemma":[0.9981091,0.00013201503,0.00060151325,0.000998282,0.00013149992,0.000027613736],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0034825979,0.000094830764,0.00015665827,0.00043763686,0.00010851053,0.0004898797,0.0010589017,0.00003428564,0.000028329276],"category_scores_gemma":[0.00032181173,0.00006469404,0.00002455279,0.00054411456,0.000035430592,0.020699456,0.0006925653,0.00013036342,0.000062233754],"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":[0.0002946145,0.00010556939,0.009661552,0.00078738393,0.000058174253,6.913593e-7,0.11708996,0.08668273,0.00025780598,0.0076730526,0.00074125174,0.7766472],"study_design_scores_gemma":[0.0013196531,0.000040683746,0.031373482,0.00023421629,0.000024693109,0.000013493294,0.10980339,0.75717527,0.004096613,0.0025474485,0.093026906,0.00034416077],"about_ca_topic_score_codex":0.001147872,"about_ca_topic_score_gemma":0.000075789656,"teacher_disagreement_score":0.77630305,"about_ca_system_score_codex":0.000037889407,"about_ca_system_score_gemma":0.000051454663,"threshold_uncertainty_score":0.9929975},"labels":[],"label_agreement":null},{"id":"W2944628792","doi":"10.5479/10088/96518","title":"Data Standards for BARCODE Records in INSDC (BRIs)","year":2012,"lang":"en","type":"report","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Barcode; Computer science; Database; Operating system","score_opus":0.7631249978993779,"score_gpt":0.585327695359493,"score_spread":0.1777973025398849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944628792","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040080402,0.0013380437,0.1332103,0.0018913705,0.006382698,0.0013928087,0.06169764,0.000078756435,0.7939683],"genre_scores_gemma":[0.0037309863,0.009511258,0.04300617,0.0029173254,0.003901916,0.00035956615,0.023407549,0.00016422439,0.913001],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9897978,0.00027822432,0.001801758,0.001346549,0.0062044514,0.0005712521],"domain_scores_gemma":[0.9913478,0.0016373346,0.00063576497,0.005168565,0.0010301359,0.00018042921],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05598116,0.00030113375,0.00086206425,0.00065994746,0.00009112286,0.0005289796,0.004843406,0.00029489605,0.005112586],"category_scores_gemma":[0.025118748,0.00021618864,0.00014366607,0.00060012005,0.000082859224,0.0012784092,0.0035321752,0.00031628335,0.00030629252],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002077673,0.00005691593,0.00020851058,0.00006629972,0.000023540624,0.000003848842,0.000026715628,9.2473505e-7,1.7658857e-7,0.0013480504,0.74339056,0.2548537],"study_design_scores_gemma":[0.00027874584,0.000036603746,0.0006879079,0.00006872036,0.000039222236,0.0000034511434,0.00041063136,0.00014687818,0.0000026382972,0.008316095,0.9897015,0.0003075723],"about_ca_topic_score_codex":0.0025893915,"about_ca_topic_score_gemma":0.02621042,"teacher_disagreement_score":0.2545461,"about_ca_system_score_codex":0.00038732536,"about_ca_system_score_gemma":0.0022142762,"threshold_uncertainty_score":0.99579686},"labels":[],"label_agreement":null},{"id":"W2945741697","doi":"","title":"Enhancing Data Quality Using Data Management Strategies, Performance Measures, and Technology to Support Evidence-Based Practice","year":2019,"lang":"en","type":"article","venue":"Sigma's 30th International Nursing Research Congress","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Registered Nurses' Association of Ontario","funders":"","keywords":"Computer science; Data quality; Quality (philosophy); Quality management; Data governance; Data science; Process management; Risk analysis (engineering); Data mining; Business; Operations management; Management system; Engineering; Marketing","score_opus":0.6182450282767503,"score_gpt":0.609395430094628,"score_spread":0.008849598182122276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945741697","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":[0.3796612,0.0025659828,0.29261118,0.22195166,0.015429993,0.008265186,0.003143636,0.00054320955,0.07582796],"genre_scores_gemma":[0.9779317,0.00022079104,0.018091295,0.00060372683,0.00016793954,0.000023425871,0.00039725428,0.000025709884,0.0025382047],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9884267,0.0012212716,0.001051979,0.0020346385,0.006521759,0.0007436827],"domain_scores_gemma":[0.98844695,0.0035836536,0.0003688481,0.0051020915,0.0022583054,0.00024014727],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04634246,0.0002318467,0.00035939578,0.0015314458,0.00041960843,0.002309492,0.009031193,0.00011433764,0.00034293678],"category_scores_gemma":[0.01739475,0.00020956209,0.000024897052,0.0017019036,0.0005364407,0.007005088,0.0057585286,0.0005912714,0.0003376978],"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":[0.0015829222,0.0006506856,0.0066791335,0.00029203927,0.00031281039,0.00013977177,0.0005750767,0.0013413561,0.0033502523,0.05917259,0.08002867,0.84587467],"study_design_scores_gemma":[0.0018775241,0.0006815268,0.004615917,0.00452065,0.00009299997,0.000054150107,0.029380366,0.08891733,0.0016114056,0.01294807,0.85437036,0.00092971645],"about_ca_topic_score_codex":0.00032596296,"about_ca_topic_score_gemma":0.00020362876,"teacher_disagreement_score":0.84494495,"about_ca_system_score_codex":0.00043049792,"about_ca_system_score_gemma":0.0006731904,"threshold_uncertainty_score":0.9987262},"labels":[],"label_agreement":null},{"id":"W2946207881","doi":"10.1007/978-3-030-18305-9_52","title":"Name2Vec: Personal Names Embeddings","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Task (project management); Word (group theory); Information retrieval; Proper noun; Linkage (software); Natural language processing; Embedding; Artificial intelligence; Linguistics","score_opus":0.07252391469650568,"score_gpt":0.35107711140850406,"score_spread":0.2785531967119984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946207881","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":[0.00026441546,0.0003120445,0.9557235,0.002378362,0.0034013968,0.00041319843,0.000054412267,0.000070268194,0.037382398],"genre_scores_gemma":[0.5168906,0.00023449825,0.26139972,0.040489156,0.003808636,0.000026302561,0.000115371484,0.00021869285,0.17681703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925148,0.000066847904,0.0008283183,0.0020640832,0.0038870561,0.00063888065],"domain_scores_gemma":[0.9955687,0.0018217647,0.00046857912,0.001611205,0.0003542227,0.00017551625],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005286808,0.0004781779,0.000705975,0.0011902364,0.00025164097,0.0014193704,0.004439349,0.0002810566,0.00104634],"category_scores_gemma":[0.0010220683,0.00036850956,0.000230239,0.0006717867,0.0011080182,0.00077751745,0.0023251956,0.00073586276,0.0019104971],"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":[0.000013966231,0.00002476852,0.000117277086,0.000026997435,0.000014912284,0.00005090774,0.0016593648,0.0032410026,0.000019741985,0.032672815,0.0027687256,0.9593895],"study_design_scores_gemma":[0.00039172862,0.000229544,0.00037449616,0.00038647722,0.000019318966,0.000041178748,0.0000077346,0.13932736,0.00012812074,0.5166838,0.34130517,0.001105081],"about_ca_topic_score_codex":0.00002951597,"about_ca_topic_score_gemma":0.0001153187,"teacher_disagreement_score":0.95828444,"about_ca_system_score_codex":0.00022540608,"about_ca_system_score_gemma":0.00050370157,"threshold_uncertainty_score":0.9998767},"labels":[],"label_agreement":null},{"id":"W2949244208","doi":"10.48550/arxiv.1702.00820","title":"HoloClean: Holistic Data Repairs with Probabilistic Inference","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":57,"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":"Inference; Leverage (statistics); Probabilistic logic; Tuple; Computer science; Data mining; Statistical model; Machine learning; Artificial intelligence; Mathematics","score_opus":0.631797409494457,"score_gpt":0.3557862297306885,"score_spread":0.27601117976376843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949244208","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":[0.33081812,0.00012925749,0.54819983,0.0012171441,0.0037882433,0.0028824916,0.0042092744,0.00084326195,0.10791236],"genre_scores_gemma":[0.98617953,0.00009982791,0.0006055864,0.00012663913,0.00012150412,0.0000015937924,0.00039642677,0.000021563234,0.012447307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99505776,0.00044153119,0.00049256784,0.0029464588,0.00060712587,0.00045457398],"domain_scores_gemma":[0.9839115,0.0010262125,0.0010205678,0.013107098,0.0006644822,0.0002701536],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.003680598,0.00041943463,0.0006528821,0.00035801705,0.0004591253,0.0010266798,0.011666864,0.0002443909,0.00028107697],"category_scores_gemma":[0.010594192,0.0003541278,0.00012428648,0.00046816905,0.00084590475,0.0011396952,0.014741553,0.0006920684,0.00089497416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000753959,0.0007956108,0.0211414,0.0005729541,0.00062107306,0.0033439286,0.0007362921,0.24024527,0.0000012560436,0.63084185,0.08788745,0.013058928],"study_design_scores_gemma":[0.001268173,0.00024207459,0.018104862,0.0005265116,0.00072371674,0.0000071817826,0.0013884393,0.22935304,0.0000029803102,0.6227182,0.12399937,0.0016654395],"about_ca_topic_score_codex":0.00073809223,"about_ca_topic_score_gemma":0.0014449763,"teacher_disagreement_score":0.6553614,"about_ca_system_score_codex":0.00013749364,"about_ca_system_score_gemma":0.0004647076,"threshold_uncertainty_score":0.99989104},"labels":[],"label_agreement":null},{"id":"W2949348411","doi":"10.48550/arxiv.1008.4627","title":"Matching Dependencies with Arbitrary Attribute Values: Semantics, Query Answering and Integrity Constraints","year":2010,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Carleton University; University of Ottawa","funders":"","keywords":"Tuple; Computer science; Matching (statistics); Functional dependency; Data integrity; Semantics (computer science); Data mining; Generalization; Invariant (physics); Theoretical computer science; Relational database; Database; Mathematics; Programming language; Discrete mathematics","score_opus":0.2250640965752461,"score_gpt":0.2770791278655393,"score_spread":0.052015031290293195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949348411","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":[0.7613217,0.000036355326,0.2347462,0.00024809805,0.0005073474,0.00030960998,0.00022353702,0.00011669903,0.0024904218],"genre_scores_gemma":[0.99533564,0.00019035935,0.002753224,0.00021996612,0.00006948882,7.705554e-7,0.000049916907,0.000019133953,0.0013615092],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967156,0.00035047453,0.00046706144,0.0015564767,0.0004802265,0.0004301322],"domain_scores_gemma":[0.9966813,0.0007955552,0.00048353293,0.001483638,0.00029363576,0.00026238628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032566271,0.00041698912,0.0006289028,0.00044637517,0.00033846355,0.0006515033,0.0016899279,0.0004010589,0.0001816255],"category_scores_gemma":[0.00038323872,0.00036654796,0.0001578739,0.00043369905,0.0009821355,0.0008276183,0.0031492198,0.0018804722,0.00008604176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005199101,0.00061117555,0.109045036,0.0010108941,0.0012348564,0.0046633296,0.0075082583,0.0299677,0.00028089117,0.8313876,0.0030219627,0.010748417],"study_design_scores_gemma":[0.0014199021,0.00014594322,0.023836745,0.00077922555,0.00048298205,0.00007824189,0.031833425,0.0177225,0.00033837662,0.9180623,0.0034418995,0.0018584051],"about_ca_topic_score_codex":0.0009130561,"about_ca_topic_score_gemma":0.001892566,"teacher_disagreement_score":0.2340139,"about_ca_system_score_codex":0.00008011831,"about_ca_system_score_gemma":0.000246637,"threshold_uncertainty_score":0.99987864},"labels":[],"label_agreement":null},{"id":"W2949999477","doi":"10.48550/arxiv.1312.7373","title":"Extending Contexts with Ontologies for Multidimensional Data Quality Assessment","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Datalog; Context (archaeology); Quality (philosophy); Data quality; Quality assessment; Database; Information retrieval; Data mining; Data science; Evaluation methods; Engineering","score_opus":0.6427823544612737,"score_gpt":0.39728055478711893,"score_spread":0.2455017996741548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949999477","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":[0.19314674,0.00007697746,0.7980647,0.00083080796,0.00086940697,0.0015323486,0.0025342144,0.00016383344,0.0027809697],"genre_scores_gemma":[0.9673164,0.00006406779,0.022755578,0.00028316455,0.00007228192,0.000009271948,0.00096022134,0.000020756497,0.008518292],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950079,0.0006796899,0.0006887612,0.0025440885,0.00060866267,0.00047092218],"domain_scores_gemma":[0.99056596,0.0029737188,0.0009612338,0.004676195,0.0006236804,0.0001991929],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0058493516,0.00040433402,0.00077323505,0.00032070305,0.0003488511,0.0003606577,0.0040894817,0.0002399811,0.0003360845],"category_scores_gemma":[0.0014109066,0.00032364976,0.00018702641,0.00035247527,0.0003543229,0.001117447,0.0078650825,0.00045262263,0.0001683068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034278937,0.00039588806,0.0071271798,0.0001480071,0.0004454871,0.000097017844,0.00014428148,0.026588527,0.000019993531,0.90413046,0.04829963,0.012260749],"study_design_scores_gemma":[0.0042442614,0.00034516957,0.07914578,0.00033878558,0.00053463416,0.000005012434,0.0072567817,0.3106357,0.0000370555,0.37254643,0.22283787,0.0020725413],"about_ca_topic_score_codex":0.0008617088,"about_ca_topic_score_gemma":0.0015701321,"teacher_disagreement_score":0.77530915,"about_ca_system_score_codex":0.00020983898,"about_ca_system_score_gemma":0.00031969408,"threshold_uncertainty_score":0.99992156},"labels":[],"label_agreement":null},{"id":"W2950110688","doi":"","title":"Leveraging Technology to Promote Evidence-Based Practice and Enhance Data Quality","year":2019,"lang":"en","type":"article","venue":"Sigma's 30th International Nursing Research Congress","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Registered Nurses' Association of Ontario","funders":"","keywords":"Quality (philosophy); Computer science; Business; Data quality; Risk analysis (engineering); Data science; Process management; Marketing","score_opus":0.41006287526702284,"score_gpt":0.613996217070361,"score_spread":0.20393334180333816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950110688","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":[0.33838162,0.0010163417,0.040772043,0.591194,0.0049846163,0.0022668801,0.00028983058,0.0001854053,0.020909326],"genre_scores_gemma":[0.98354477,0.00005241278,0.008930968,0.0012822318,0.00014421041,0.00003586051,0.00004939706,0.000016223865,0.005943926],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910745,0.0012316066,0.0007260812,0.0015168316,0.004887336,0.00056367],"domain_scores_gemma":[0.98776,0.0068080854,0.00027718482,0.002440276,0.0025016163,0.00021280158],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03160992,0.00016456994,0.00028586533,0.001196083,0.00028451538,0.0014057783,0.0046813227,0.0000967024,0.00039387133],"category_scores_gemma":[0.07171563,0.00014425152,0.00003301309,0.00139595,0.00050680456,0.0026767333,0.0020768994,0.0005751608,0.0007288093],"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":[0.0010323303,0.0004646613,0.005935651,0.00005916773,0.00008967526,0.000054431384,0.001211531,0.00021279983,0.0040482352,0.041618925,0.10170323,0.8435694],"study_design_scores_gemma":[0.0009842511,0.00043505954,0.007206566,0.0030582629,0.000018183307,0.000020907435,0.007650713,0.0175809,0.0056608706,0.06679347,0.8900427,0.00054808595],"about_ca_topic_score_codex":0.00017430514,"about_ca_topic_score_gemma":0.000033624714,"teacher_disagreement_score":0.8430213,"about_ca_system_score_codex":0.00029210848,"about_ca_system_score_gemma":0.00028313484,"threshold_uncertainty_score":0.99963087},"labels":[],"label_agreement":null},{"id":"W2950296358","doi":"10.1088/1742-6596/1213/2/022021","title":"Research on data cleaning technology based on instance level","year":2019,"lang":"en","type":"article","venue":"Journal of Physics Conference Series","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Process (computing); Data quality; Quality (philosophy); Data mining; Engineering; Programming language","score_opus":0.6678248949701602,"score_gpt":0.519995239498033,"score_spread":0.14782965547212723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950296358","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":[0.4876683,0.00009496064,0.3028069,0.059517227,0.0037132066,0.00097174186,0.0008339059,0.00010034696,0.14429338],"genre_scores_gemma":[0.995544,0.000023737884,0.0025674992,0.00040778564,0.000113092814,0.0000011036452,0.000008044078,0.000007741782,0.0013269607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99620247,0.0002958406,0.00056770036,0.00037516849,0.0022919956,0.00026682712],"domain_scores_gemma":[0.9958493,0.00088437024,0.000474194,0.0016806693,0.0010451048,0.00006632495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064302697,0.00011750782,0.000331845,0.000497672,0.00014392567,0.00039850347,0.003150779,0.00006227967,0.00022755763],"category_scores_gemma":[0.0015780061,0.00008426394,0.000050584655,0.0010642001,0.0002494645,0.0013948055,0.0006177066,0.0006674427,0.00054293504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029999795,0.00015466801,0.00035890745,0.000012838184,0.0000183612,0.00001771573,0.00016974242,0.0006760538,0.00066143234,0.6249907,0.011472643,0.36116695],"study_design_scores_gemma":[0.0013032976,0.003104542,0.0038275942,0.0006773618,0.000015600657,0.000008092149,0.021314126,0.004263201,0.028660456,0.665093,0.27135414,0.00037858335],"about_ca_topic_score_codex":0.0000059988356,"about_ca_topic_score_gemma":0.000024298135,"teacher_disagreement_score":0.50787574,"about_ca_system_score_codex":0.00004333242,"about_ca_system_score_gemma":0.0003305591,"threshold_uncertainty_score":0.69785124},"labels":[],"label_agreement":null},{"id":"W2950545869","doi":"10.22215/etd/2018-13359","title":"Pairwise Estimating Equations for the Analysis of Linked Data","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Carleton University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Pairwise comparison; Record linkage; Computer science; Covariate; Linkage (software); Independence (probability theory); Data mining; Statistics; Econometrics; Mathematics; Machine learning; Sociology","score_opus":0.5450385659262785,"score_gpt":0.5499591261972531,"score_spread":0.004920560270974539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950545869","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":[0.0005245311,0.00006419639,0.98752886,0.00061639264,0.00090126845,0.00058659667,0.0020719015,0.000024072242,0.00768218],"genre_scores_gemma":[0.093670964,0.000057735117,0.4695937,0.0011261143,0.00080696907,0.00034385873,0.14892669,0.00005539984,0.28541854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971414,0.00010721015,0.0009761093,0.000547457,0.0011008601,0.00012695209],"domain_scores_gemma":[0.9864292,0.008970886,0.00083733624,0.0031109927,0.0006201701,0.00003137916],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008608942,0.00011956462,0.00040057654,0.0005082992,0.00024916933,0.00028561184,0.0032721544,0.00008320868,0.0015284469],"category_scores_gemma":[0.02134599,0.00006669708,0.00021384872,0.0016329174,0.000055403118,0.00031232662,0.00031632138,0.00006421438,0.00008024676],"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":[0.000051348452,0.0001023125,0.000029731831,0.00007073611,0.0028535123,1.7263865e-7,0.0022247199,0.0016229317,0.0000093448725,0.03972033,0.3804006,0.57291424],"study_design_scores_gemma":[0.00008814556,0.00001875107,0.0014834979,0.000016646756,0.003211514,9.598261e-9,0.008177697,0.90301824,0.000009830244,0.01057594,0.07328978,0.00010993921],"about_ca_topic_score_codex":0.00035250597,"about_ca_topic_score_gemma":0.012413348,"teacher_disagreement_score":0.9013953,"about_ca_system_score_codex":0.000010329471,"about_ca_system_score_gemma":0.000092170885,"threshold_uncertainty_score":0.9993843},"labels":[],"label_agreement":null},{"id":"W2950622432","doi":"","title":"Guided Data Repair","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Rank (graph theory); Process (computing); Quality (philosophy); Set (abstract data type); Data quality; Data mining; Data set; Machine learning; Information retrieval; Artificial intelligence; Engineering","score_opus":0.7109900226280569,"score_gpt":0.33696403490400567,"score_spread":0.3740259877240512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950622432","genre_codex":"other","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":[0.16630024,0.00023985219,0.38391194,0.0008395549,0.005834663,0.001644935,0.002731471,0.0015055988,0.43699175],"genre_scores_gemma":[0.94282705,0.00024147585,0.0016396521,0.0005624679,0.00014628631,6.259426e-7,0.00051763334,0.000023052766,0.054041784],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995446,0.00054282474,0.0006092171,0.002607727,0.00042190723,0.00037229643],"domain_scores_gemma":[0.98830736,0.00039058892,0.0005734244,0.010218272,0.00028589083,0.00022444253],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0051111965,0.00031606347,0.0005073203,0.00045072773,0.00017768289,0.00023413668,0.009684685,0.00027786047,0.0018562444],"category_scores_gemma":[0.0015947551,0.0003052939,0.00028825458,0.0007625874,0.00024196591,0.0008596128,0.022682372,0.00047952414,0.0033473454],"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":[0.00006555197,0.00019727094,0.0026272137,0.000051791834,0.00023846666,0.0005296469,0.00021920465,0.00521205,0.0000016734729,0.35019016,0.63848484,0.0021821626],"study_design_scores_gemma":[0.00040871187,0.0000321672,0.002472156,0.00005476881,0.00022972011,0.000002621542,0.0007132172,0.051349215,0.000011353075,0.52365065,0.42044863,0.00062681496],"about_ca_topic_score_codex":0.0010283003,"about_ca_topic_score_gemma":0.0004560393,"teacher_disagreement_score":0.7765268,"about_ca_system_score_codex":0.000091734175,"about_ca_system_score_gemma":0.00018844388,"threshold_uncertainty_score":0.9999399},"labels":[],"label_agreement":null},{"id":"W2950704571","doi":"10.1109/icde.2019.00149","title":"Distributed Discovery of Functional Dependencies","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"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; Focus (optics); Distributed computing; Distributed database; Distributed algorithm; Computation; Distributed Computing Environment; Big data; Distributed data store; Data mining; Algorithm","score_opus":0.14862455253260098,"score_gpt":0.36350999751358415,"score_spread":0.21488544498098316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950704571","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":[0.46617806,0.00002331321,0.43203872,0.0011055693,0.00082416245,0.00017344758,0.0003577033,0.00003046954,0.09926857],"genre_scores_gemma":[0.95670027,0.0000017753043,0.0001837371,0.00019496196,0.00001258353,0.0000013634161,0.000050881492,0.0000013035392,0.04285312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99844384,0.00004882942,0.0002916183,0.00019219865,0.0009379156,0.00008561037],"domain_scores_gemma":[0.9989252,0.0004458526,0.000087908375,0.0004316349,0.00008827663,0.000021129343],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012692875,0.000044231525,0.00011632277,0.00006779844,0.000022012588,0.00011025759,0.00034899524,0.000018221175,0.004003143],"category_scores_gemma":[0.00047125955,0.000027758333,0.00005911584,0.00026241885,0.000038456954,0.0006871918,0.00023633154,0.000028710212,0.0015432131],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061708175,0.00012882618,0.034648053,0.000014891026,0.000034705565,0.000001255593,0.00007266072,0.00057559443,0.0018978044,0.7692994,0.18718389,0.006081222],"study_design_scores_gemma":[0.00074050855,0.00012609958,0.5563281,0.000015535019,0.000015546675,0.0000024849737,0.0070176935,0.0013055009,0.0047464822,0.13778065,0.29167154,0.00024984198],"about_ca_topic_score_codex":0.00005269159,"about_ca_topic_score_gemma":0.000055240245,"teacher_disagreement_score":0.6315187,"about_ca_system_score_codex":0.000009510958,"about_ca_system_score_gemma":0.000022829257,"threshold_uncertainty_score":0.9992342},"labels":[],"label_agreement":null},{"id":"W2951405260","doi":"10.1007/978-3-030-23381-5_5","title":"Big Data Quality: A Data Quality Profiling Model","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Data quality; Profiling (computer programming); Computer science; Data governance; Big data; Data mining; Data science; Engineering","score_opus":0.5635995789952036,"score_gpt":0.47028224481804565,"score_spread":0.09331733417715798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951405260","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":[0.00006264286,0.0003095366,0.9803907,0.0026832016,0.0033064727,0.0008376845,0.0025870346,0.000102552374,0.009720135],"genre_scores_gemma":[0.052551236,0.0002448047,0.8968768,0.019680785,0.0031959452,0.00001546358,0.004959987,0.00017141434,0.022303531],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98454285,0.00038193402,0.0023482433,0.0057082395,0.0061176587,0.0009011055],"domain_scores_gemma":[0.9727358,0.0040671355,0.0012083309,0.021253863,0.00048478672,0.0002500763],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.039560933,0.00068451517,0.0012904822,0.0010778289,0.00035237035,0.0021355061,0.031405266,0.0003983438,0.00007898422],"category_scores_gemma":[0.0066046556,0.0005411217,0.00012739259,0.0010216347,0.0012195876,0.0024681552,0.034709774,0.0011211113,0.0005962455],"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":[0.000027044181,0.00005735486,0.00008901255,0.00009290673,0.00002513983,0.00001559363,0.00030669617,0.023997057,0.000037372156,0.04619346,0.0014053066,0.92775303],"study_design_scores_gemma":[0.00026512262,0.000036302965,0.000057499736,0.0001614134,0.000019653293,0.0000045818238,0.000003941423,0.64696336,0.00003948657,0.31625083,0.035467703,0.00073011126],"about_ca_topic_score_codex":0.0002381147,"about_ca_topic_score_gemma":0.001486263,"teacher_disagreement_score":0.92702293,"about_ca_system_score_codex":0.00018813269,"about_ca_system_score_gemma":0.0017870524,"threshold_uncertainty_score":0.999704},"labels":[],"label_agreement":null},{"id":"W2952029797","doi":"10.1145/3294052.3322190","title":"Database Repairs and Consistent Query Answering","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Database; Query language; Information retrieval; Database theory; View; Query optimization; Tracing; Query by Example; Database design; Web search query; Programming language; Search engine","score_opus":0.14865963805331375,"score_gpt":0.39704578246770367,"score_spread":0.24838614441438991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952029797","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":[0.6995891,0.00015825519,0.010419299,0.0035991292,0.00077161315,0.0003872236,0.00006601745,0.00013171532,0.2848777],"genre_scores_gemma":[0.94795066,0.000039020637,0.004794701,0.0026285956,0.000020743037,0.0000035404746,0.000015117245,0.000004438416,0.044543166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99867374,0.00007166674,0.00027130832,0.00036109803,0.00050262694,0.00011956934],"domain_scores_gemma":[0.9986653,0.00040688823,0.000053878415,0.00076640846,0.000038769012,0.00006876311],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0026759184,0.000058184873,0.0001225615,0.000084199804,0.00004342454,0.00019357077,0.00025646854,0.00001569,0.0017579844],"category_scores_gemma":[0.00050472585,0.000039990584,0.000028974151,0.00014518516,0.000045025645,0.00045097413,0.00048551528,0.000039208033,0.0014080631],"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":[0.000055180542,0.00011617518,0.04093411,0.00006301634,0.000052856336,0.000041245734,0.00060198194,0.000033898326,0.001477972,0.48100638,0.37447146,0.10114572],"study_design_scores_gemma":[0.00032674294,0.000043468914,0.011463338,0.00001630761,0.0000074970467,0.0000066633493,0.005285253,0.0016432768,0.00027676506,0.005068757,0.97570163,0.00016027172],"about_ca_topic_score_codex":0.000139322,"about_ca_topic_score_gemma":0.00012749301,"teacher_disagreement_score":0.6012302,"about_ca_system_score_codex":0.000006929755,"about_ca_system_score_gemma":0.000011562743,"threshold_uncertainty_score":0.99936944},"labels":[],"label_agreement":null},{"id":"W2952039710","doi":"10.1109/icde.2019.00024","title":"CurrentClean: Spatio-Temporal Cleaning of Stale Data","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":23,"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; Timestamp; Data mining; Probabilistic logic; Inference; Set (abstract data type); Data set; Data modeling; Database; Artificial intelligence; Real-time computing","score_opus":0.3638930345167121,"score_gpt":0.4612833997347684,"score_spread":0.09739036521805627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952039710","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":[0.6968037,0.00007497104,0.05787608,0.002356787,0.0018458421,0.00063440204,0.00074003916,0.00010438937,0.23956378],"genre_scores_gemma":[0.9853703,0.0000049904297,0.0028947627,0.0002713877,0.000025527495,5.6682404e-7,0.0002687569,0.000004094733,0.011159635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978701,0.000097070304,0.0004904584,0.00041121463,0.0009999432,0.00013122451],"domain_scores_gemma":[0.99737066,0.0002831826,0.00019438297,0.0020252524,0.00008112524,0.000045369365],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0034026522,0.00006465388,0.00017862169,0.000107706335,0.000028730545,0.00011503883,0.0018484249,0.00002004725,0.0077443053],"category_scores_gemma":[0.00053038524,0.000046586156,0.000032779448,0.00031694808,0.00004343368,0.00093671656,0.0015837081,0.000051041876,0.002773799],"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":[0.00004367479,0.00018169374,0.06568171,0.00003457582,0.000026960473,0.0000019179445,0.0004862608,0.00007547303,0.00005126966,0.089694954,0.63319314,0.2105284],"study_design_scores_gemma":[0.0003116695,0.00005622882,0.0058452208,0.000012763957,0.0000059832187,3.4605497e-7,0.0034012415,0.0068533737,0.00014104623,0.0057523847,0.9775105,0.000109227694],"about_ca_topic_score_codex":0.0001865084,"about_ca_topic_score_gemma":0.00030314768,"teacher_disagreement_score":0.3443174,"about_ca_system_score_codex":0.0000061100463,"about_ca_system_score_gemma":0.000025416606,"threshold_uncertainty_score":0.99800265},"labels":[],"label_agreement":null},{"id":"W2952193585","doi":"10.3917/proj.020.0155","title":"Data governance maturity assessment tool: A design science approach","year":2019,"lang":"fr","type":"article","venue":"Projectics / Proyéctica / Projectique","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Ministère de l’Immigration, de la Francisation et de l’Intégration; Université du Québec à Montréal","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.25794174737655695,"score_gpt":0.45577485403319234,"score_spread":0.1978331066566354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952193585","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":[0.0039915857,0.003076293,0.7079885,0.026263462,0.013897133,0.021835571,0.0029518434,0.00068367255,0.21931195],"genre_scores_gemma":[0.20424116,0.0023526081,0.70054704,0.0023907013,0.00092493807,0.0008739497,0.00021240661,0.00021203782,0.08824515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9797801,0.0029399607,0.0024434223,0.005603815,0.006644007,0.0025886956],"domain_scores_gemma":[0.9840456,0.0024323475,0.0015711248,0.009730705,0.001723319,0.00049688277],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.05050621,0.0011084805,0.0013874033,0.000777225,0.0011672872,0.004974378,0.011681193,0.0006230546,0.0009889631],"category_scores_gemma":[0.01177923,0.0009955243,0.00025082438,0.0069765453,0.002357,0.012291353,0.01048452,0.0024299498,0.0020455564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053044735,0.005601287,0.0027256506,0.002656532,0.00042550894,0.00009801016,0.0034696364,0.00055385206,0.00056396803,0.7363009,0.055124592,0.19194962],"study_design_scores_gemma":[0.0017542788,0.0012067992,0.0033106562,0.00042919867,0.00030132235,0.00030920198,0.003699559,0.25192925,0.0009303345,0.03835271,0.69573534,0.0020413666],"about_ca_topic_score_codex":0.0011308214,"about_ca_topic_score_gemma":0.00011592898,"teacher_disagreement_score":0.6979482,"about_ca_system_score_codex":0.0016367353,"about_ca_system_score_gemma":0.010750688,"threshold_uncertainty_score":0.99992424},"labels":[],"label_agreement":null},{"id":"W2953388369","doi":"10.48550/arxiv.cs/0211042","title":"Database Repairs and Analytic Tableaux","year":2002,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Data Quality and Management","field":"Decision Sciences","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":"Carleton University","funders":"","keywords":"Database; Computer science; Information retrieval","score_opus":0.4269583216933262,"score_gpt":0.4318917152394451,"score_spread":0.0049333935461188805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953388369","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":[0.9422476,0.0019536112,0.0065160748,0.006031104,0.002104678,0.00083494285,0.0010716527,0.00028362754,0.038956653],"genre_scores_gemma":[0.94525003,0.0012409778,0.0017419253,0.0021882711,0.00029691227,0.00004262664,0.00031248177,0.00003230125,0.048894476],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99547243,0.00033162985,0.0009490058,0.0015698755,0.0012856127,0.00039146992],"domain_scores_gemma":[0.9951002,0.0006371167,0.00046914336,0.0033978287,0.00016340095,0.00023233402],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0048734383,0.00032101007,0.0005941849,0.00039385766,0.00018726519,0.0005186434,0.0016328368,0.00017776768,0.0023702316],"category_scores_gemma":[0.0033859243,0.00026161116,0.00016201603,0.00050494913,0.00021507146,0.00047967842,0.005296622,0.00054070656,0.002546535],"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":[0.000040182273,0.00031510953,0.2675293,0.00032053184,0.00028379454,0.0002866321,0.000865608,0.00028672416,0.000045206143,0.0053559956,0.697729,0.026941912],"study_design_scores_gemma":[0.00045470038,0.000052857922,0.12850255,0.00017403436,0.00018009328,0.000009090999,0.0012144091,0.0053128833,0.000064291635,0.01478823,0.84848934,0.0007575323],"about_ca_topic_score_codex":0.0004942719,"about_ca_topic_score_gemma":0.00022953891,"teacher_disagreement_score":0.15076032,"about_ca_system_score_codex":0.000051253202,"about_ca_system_score_gemma":0.00005791797,"threshold_uncertainty_score":0.9999836},"labels":[],"label_agreement":null},{"id":"W2955281392","doi":"10.1145/3331184.3331311","title":"On Tradeoffs Between Document Signature Methods for a Legal Due Diligence Corpus","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cisco Systems (Canada)","funders":"","keywords":"Due diligence; Computer science; Hash function; Context (archaeology); Diligence; Signature (topology); Limit (mathematics); Information retrieval; Computer security; Political science; Mathematics; Law; Geography","score_opus":0.152014877530545,"score_gpt":0.4960927056453076,"score_spread":0.3440778281147626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955281392","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":[0.028623141,0.00007689004,0.9230621,0.0067446376,0.0014273224,0.0015992706,0.00010765255,0.00010067269,0.0382583],"genre_scores_gemma":[0.78490305,0.000007434994,0.10896334,0.004618889,0.00015825315,0.00007396675,0.000053325977,0.000018124168,0.101203606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99714017,0.00037213418,0.00055328704,0.0006947402,0.0009200088,0.0003196758],"domain_scores_gemma":[0.9940513,0.0046239877,0.00016257036,0.00095051364,0.00008857127,0.00012309515],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007029541,0.0001639642,0.00036623274,0.00016624911,0.00009973646,0.00041102088,0.001187918,0.00009462094,0.0015312574],"category_scores_gemma":[0.0011670694,0.00010655309,0.00016994974,0.00039621687,0.00004248833,0.00050213694,0.00023342238,0.00015052041,0.0010415915],"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":[0.0000676249,0.000055640823,0.00018833569,0.000015190001,0.000038879043,0.0000021077606,0.00017400188,0.00007752963,0.000251945,0.53288114,0.06147116,0.40477642],"study_design_scores_gemma":[0.00044126227,0.0003619668,0.0023534892,0.000010551299,0.00002117568,7.63939e-7,0.00038049786,0.00044387157,0.0037705232,0.21488157,0.777128,0.00020635493],"about_ca_topic_score_codex":0.00006442242,"about_ca_topic_score_gemma":0.000031260257,"teacher_disagreement_score":0.8140988,"about_ca_system_score_codex":0.000038361544,"about_ca_system_score_gemma":0.000038075224,"threshold_uncertainty_score":0.9997362},"labels":[],"label_agreement":null},{"id":"W2962752375","doi":"10.4230/lipics.icdt.2019.6","title":"A Formal Framework for Probabilistic Unclean Databases.","year":2019,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":22,"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":"Probabilistic logic; Computer science; Tuple; Cardinality (data modeling); Database; Probabilistic database; Realization (probability); Data mining; Theoretical computer science; Database theory; Database design; Artificial intelligence; Mathematics","score_opus":0.13311431167096552,"score_gpt":0.405443553735199,"score_spread":0.2723292420642335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962752375","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":[0.113455415,0.000026789945,0.85543907,0.001457039,0.0032015787,0.006668034,0.009539324,0.00024954733,0.009963198],"genre_scores_gemma":[0.8148492,0.000028188286,0.16087522,0.010657941,0.00057737814,0.0009677893,0.0055806804,0.00013410694,0.0063295253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938823,0.00008126233,0.002459985,0.00062306074,0.0017104453,0.001242948],"domain_scores_gemma":[0.99347526,0.002230088,0.0009820468,0.002380971,0.0006168958,0.0003147145],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005921926,0.00048209395,0.00082062045,0.00044410568,0.00047378667,0.0010130348,0.0023514493,0.00021611726,0.0005734117],"category_scores_gemma":[0.0040482124,0.0003762308,0.0004944293,0.0006364348,0.00018366013,0.004297352,0.0012379814,0.0004202593,0.0022701533],"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":[0.0008097622,0.00066478545,0.0058162846,0.0015056729,0.0002473922,0.000002523675,0.0063571525,0.00030404388,0.0000070465812,0.8122048,0.08001695,0.09206363],"study_design_scores_gemma":[0.003096557,0.00047160877,0.00088852714,0.00021003364,0.0000737871,0.000011408166,0.005856572,0.027732087,0.00007626743,0.069838546,0.891052,0.00069258665],"about_ca_topic_score_codex":0.000018627738,"about_ca_topic_score_gemma":0.00005217171,"teacher_disagreement_score":0.8110351,"about_ca_system_score_codex":0.00013488728,"about_ca_system_score_gemma":0.00012330951,"threshold_uncertainty_score":0.999869},"labels":[],"label_agreement":null},{"id":"W2964507227","doi":"","title":"Entity Retrieval Docker Image for OSIRRC at SIGIR 2019.","year":2019,"lang":"en","type":"article","venue":"International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Information retrieval; Natural language processing; Artificial intelligence","score_opus":0.23495533717681732,"score_gpt":0.4577698368885389,"score_spread":0.22281449971172157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964507227","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":[0.91348004,0.000021626756,0.0062665665,0.009548864,0.001988938,0.002215516,0.00050287734,0.00006812875,0.06590741],"genre_scores_gemma":[0.9692096,0.00016924097,0.006775473,0.0010257869,0.00009143858,0.00006436439,0.0010941239,0.000013319275,0.021556638],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99367183,0.00017246793,0.0011870158,0.00050165213,0.0039454964,0.000521538],"domain_scores_gemma":[0.994002,0.002736847,0.0002947728,0.0006245256,0.002144059,0.00019781046],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008696611,0.00020109786,0.000279245,0.0012945753,0.0002603116,0.0014334396,0.0017382817,0.00013113984,0.0028920732],"category_scores_gemma":[0.010950635,0.00016657049,0.000057234567,0.00063272903,0.0001791337,0.0026286743,0.0014675255,0.00035974957,0.005294649],"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":[0.018583575,0.00094221666,0.052727774,0.0003159462,0.00029057954,0.000024392035,0.007007212,0.0000990791,0.0033804786,0.45644853,0.35434803,0.10583218],"study_design_scores_gemma":[0.0033728597,0.00043944392,0.055382263,0.00011911736,0.0000020656705,0.0000050079843,0.0014894118,0.002605948,0.007639399,0.0531845,0.8753053,0.00045469552],"about_ca_topic_score_codex":0.000035333218,"about_ca_topic_score_gemma":0.000043670632,"teacher_disagreement_score":0.52095723,"about_ca_system_score_codex":0.00043726488,"about_ca_system_score_gemma":0.00042660753,"threshold_uncertainty_score":0.99960315},"labels":[],"label_agreement":null},{"id":"W2965162069","doi":"10.1002/pds.4861","title":"Validation of drug prescription records for senior patients in Alberta's Tomorrow Project: Assessing agreement between two population‐level administrative pharmaceutical databases in Alberta, Canada","year":2019,"lang":"en","type":"article","venue":"Pharmacoepidemiology and Drug Safety","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services; Alberta Health; University of Alberta","funders":"Alberta Cancer Foundation","keywords":"Medicine; Medical prescription; Database; Medical record; Socioeconomic status; Cohort; Pharmacoepidemiology; Population; Family medicine; Demography; Environmental health; Internal medicine; Pharmacology; Computer science","score_opus":0.2259439955820089,"score_gpt":0.4808991853069036,"score_spread":0.2549551897248947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965162069","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":[0.9900799,0.000029066035,0.0020813253,0.003773843,0.00070485973,0.0017088106,0.0009386029,0.0000060798448,0.0006775241],"genre_scores_gemma":[0.9947448,0.000042304746,0.0015756851,0.00073175447,0.000064499654,0.000077279015,0.0017916054,0.000009550981,0.00096252793],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99391836,0.0026088846,0.0017871626,0.00077771,0.0004873701,0.00042051545],"domain_scores_gemma":[0.9854747,0.013247307,0.00067942456,0.0003371963,0.00015125056,0.000110103225],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009439223,0.00024043761,0.00071973464,0.000275645,0.000109439534,0.0000315213,0.00035693435,0.00004594449,0.00014517465],"category_scores_gemma":[0.004774238,0.00020559393,0.00006625127,0.00039545773,0.000078103025,0.0009906121,0.00023742013,0.00024251918,0.000007611942],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038073925,0.00015867098,0.97575283,0.000081774735,0.000037506503,9.201027e-7,0.00061695854,0.00035109377,0.000022826147,0.0015920025,0.0064764665,0.014528232],"study_design_scores_gemma":[0.0041842805,0.000044454227,0.959512,0.00010143056,0.0000893854,8.1720856e-7,0.00094441796,0.009282888,0.0009536458,0.0020074765,0.022539623,0.00033957927],"about_ca_topic_score_codex":0.8255597,"about_ca_topic_score_gemma":0.837115,"teacher_disagreement_score":0.01624081,"about_ca_system_score_codex":0.00019388404,"about_ca_system_score_gemma":0.00026891983,"threshold_uncertainty_score":0.8383877},"labels":[],"label_agreement":null},{"id":"W2965517117","doi":"","title":"Limits and Potentials of Grasping User Interaction in Controlled and Open World Environments - Contrasting PIAAC Large-Scale-Assessment Usage Data with Web Analytics.","year":2017,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Analytics; Scale (ratio); Computer science; Data science; World Wide Web; Geography; Cartography","score_opus":0.11396934142905063,"score_gpt":0.3862381193686624,"score_spread":0.2722687779396118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965517117","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":[0.85793525,0.000049972707,0.1300306,0.00039674883,0.00021718781,0.001535849,0.00021892994,0.000015103912,0.009600333],"genre_scores_gemma":[0.9966716,0.000067380744,0.002827015,0.00012982273,0.000012278777,0.00002751232,0.0001154938,0.000005307378,0.00014357995],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99755746,0.0001951351,0.0011334991,0.00029045856,0.000604824,0.00021864625],"domain_scores_gemma":[0.9970454,0.0003826354,0.0014873315,0.00093293603,0.000080187296,0.000071499686],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0063601653,0.00015147816,0.00052215793,0.0003970568,0.00039762788,0.0023787143,0.001068322,0.000043039097,0.00003210867],"category_scores_gemma":[0.0013909301,0.00011535773,0.000022128046,0.00016795217,0.00019018263,0.012536986,0.0013968649,0.00011091919,0.0000057792927],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002288816,0.00044578477,0.56028813,0.0005357208,0.0005977161,0.000022279675,0.009870524,0.0018080133,0.0010792827,0.010181806,0.001464797,0.41141713],"study_design_scores_gemma":[0.010360947,0.00017124019,0.7554922,0.00075513776,0.00013146634,0.000010576815,0.01647317,0.20536993,0.00014549348,0.002445169,0.008288751,0.00035589436],"about_ca_topic_score_codex":0.0002659484,"about_ca_topic_score_gemma":0.0021673206,"teacher_disagreement_score":0.41106126,"about_ca_system_score_codex":0.000074015334,"about_ca_system_score_gemma":0.00004585174,"threshold_uncertainty_score":0.9986569},"labels":[],"label_agreement":null},{"id":"W2966210203","doi":"10.29173/cais436","title":"Theories for the New Millennium: The Deployment of Theory in LIS Research","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Sociology; Library science; Epistemology; Psychology; Social science; Philosophy; Computer science","score_opus":0.146704670753629,"score_gpt":0.38757768989470687,"score_spread":0.24087301914107787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966210203","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":[0.91978616,0.001252359,0.0008025248,0.05948691,0.00036854576,0.0030693747,0.0002743361,0.000026228068,0.0149335805],"genre_scores_gemma":[0.994858,0.00035896842,0.0002645983,0.00043002912,0.00008321278,0.0001701531,0.0000014474482,0.000015211092,0.003818326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99612606,0.00024488012,0.0009996293,0.0004118635,0.0017063038,0.0005112445],"domain_scores_gemma":[0.88571817,0.01725801,0.0021667737,0.001835614,0.092765525,0.0002558889],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.015365404,0.00021134074,0.00047923,0.0002728073,0.00027818192,0.0029620049,0.006298685,0.000105651205,0.00015413822],"category_scores_gemma":[0.09446051,0.00009684292,0.00022002033,0.0010818534,0.0014943933,0.005245466,0.0019171046,0.00034787258,0.000012536958],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038012536,0.00017133645,0.011087047,0.00013961553,0.00011803059,1.7098083e-7,0.06604216,0.00001101427,0.0023010036,0.7123284,0.14666733,0.060753796],"study_design_scores_gemma":[0.00056451623,0.00030040133,0.043333985,0.0001743644,0.00004957413,0.0000023203493,0.06746199,0.00026101238,0.0146074835,0.6227643,0.25031006,0.00017000058],"about_ca_topic_score_codex":0.0015098049,"about_ca_topic_score_gemma":0.00017511449,"teacher_disagreement_score":0.11040789,"about_ca_system_score_codex":0.000038351995,"about_ca_system_score_gemma":0.00029850478,"threshold_uncertainty_score":0.99907774},"labels":[],"label_agreement":null},{"id":"W2966214405","doi":"10.1017/ice.2019.184","title":"Using data linkage methodologies to augment healthcare-associated infection surveillance data","year":2019,"lang":"en","type":"article","venue":"Infection Control and Hospital Epidemiology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Health Services; Alberta Health; University of Calgary","funders":"","keywords":"Medicine; Medical record; Health care; Population; Infection control; Record linkage; Linkage (software); Medical emergency; Database; Emergency medicine; Environmental health; Intensive care medicine; Internal medicine","score_opus":0.5950403739063242,"score_gpt":0.5430483500076243,"score_spread":0.051992023898699946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966214405","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":[0.39354804,0.00057645584,0.566176,0.031866003,0.004866492,0.00124427,0.0012121592,0.00019328877,0.00031726746],"genre_scores_gemma":[0.98663974,0.0004916749,0.0054843104,0.006415935,0.00022175767,0.000018485363,0.0005329478,0.000013572676,0.00018157382],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9914861,0.0049570827,0.0012238224,0.0014659599,0.00035865113,0.0005084246],"domain_scores_gemma":[0.9855531,0.010654267,0.00072372187,0.0026329868,0.00024628686,0.00018964482],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03970615,0.00023063646,0.0009853021,0.00027327528,0.00023847942,0.00012897493,0.0009999282,0.00022671258,0.00008408512],"category_scores_gemma":[0.055685993,0.0001822939,0.000067802706,0.0004987521,0.00011835599,0.0010134102,0.002094637,0.0002851444,0.00025431457],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009052871,0.00008580109,0.848672,0.000028103617,0.00016300869,0.0000022175054,0.0000872217,0.0022132527,0.00006469063,0.0051360624,0.017722726,0.12573442],"study_design_scores_gemma":[0.0008893499,0.00053864124,0.8210376,0.000021354781,0.000032504053,0.000004913074,0.000060959843,0.04142411,0.0000015992428,0.02015876,0.11554983,0.0002803744],"about_ca_topic_score_codex":0.016571984,"about_ca_topic_score_gemma":0.005262218,"teacher_disagreement_score":0.59309167,"about_ca_system_score_codex":0.000097839256,"about_ca_system_score_gemma":0.00006230498,"threshold_uncertainty_score":0.98997676},"labels":[],"label_agreement":null},{"id":"W2966581343","doi":"10.14778/3339490.3339501","title":"Ontology-based entity matching in attributed graphs","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":42,"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":"Subgraph isomorphism problem; Computer science; Matching (statistics); Theoretical computer science; Graph; Node (physics); Ontology; Ontology alignment; Factor-critical graph; Induced subgraph isomorphism problem; Semantic Web; Line graph; Mathematics; Artificial intelligence; Voltage graph; Process ontology","score_opus":0.07418500935219877,"score_gpt":0.34623299728772483,"score_spread":0.2720479879355261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966581343","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":[0.98475546,0.000033870314,0.00015314102,0.0034702083,0.00046629945,0.00067367504,0.000025715577,0.00002720511,0.010394404],"genre_scores_gemma":[0.9976239,0.0000056124086,0.0008196006,0.00068469,0.000007864894,0.000024880035,0.0000025636862,0.0000056471868,0.0008252035],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974928,0.00004000347,0.0006309997,0.0004183921,0.0011375081,0.00028028898],"domain_scores_gemma":[0.99881697,0.00021766378,0.00040446437,0.00034165813,0.00017174552,0.00004748088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004184755,0.00013012227,0.00031638573,0.00028027146,0.000066725406,0.00012778424,0.0015108541,0.000051136096,0.000250012],"category_scores_gemma":[0.0005835287,0.00008234577,0.00015047236,0.00085262844,0.000077742014,0.00036156047,0.0005871282,0.00015359814,0.0001539824],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023374766,0.00085560465,0.51670027,0.00024159494,0.00008698645,0.0000016849737,0.0017937744,0.00047849593,0.027812595,0.41533756,0.026402518,0.010055174],"study_design_scores_gemma":[0.0035719716,0.00021557864,0.30878088,0.00027340982,0.000053733373,0.0000033144022,0.00486704,0.0010644203,0.04916881,0.56806576,0.06345311,0.0004819681],"about_ca_topic_score_codex":0.00039071255,"about_ca_topic_score_gemma":0.00016100743,"teacher_disagreement_score":0.2079194,"about_ca_system_score_codex":0.00007171022,"about_ca_system_score_gemma":0.000026213926,"threshold_uncertainty_score":0.3357963},"labels":[],"label_agreement":null},{"id":"W2967736654","doi":"10.1007/978-3-030-27615-7_29","title":"Ontario: Federated Query Processing Against a Semantic Data Lake","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Exploit; Schema (genetic algorithms); Semantic heterogeneity; Query optimization; SPARQL; Information retrieval; RDF; Query language; Data integration; Database; Overhead (engineering); Data mining; Semantic Web; Ontology-based data integration","score_opus":0.13596844554397938,"score_gpt":0.3560912968233141,"score_spread":0.2201228512793347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967736654","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":[0.00027030415,0.0001960383,0.968456,0.0010880255,0.0020159136,0.0005671293,0.00010207746,0.000072795505,0.027231775],"genre_scores_gemma":[0.56292903,0.00015394468,0.25258046,0.044714976,0.0022585774,0.000023293329,0.002090343,0.00025174688,0.13499759],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922545,0.00008801117,0.0010768969,0.0027877681,0.0031385655,0.0006542784],"domain_scores_gemma":[0.99432164,0.0009660012,0.0006148497,0.0035310274,0.00040816647,0.00015828863],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0065577934,0.00051273213,0.0007756901,0.00095114805,0.00042576695,0.0033203745,0.0075078914,0.00027777356,0.00036434276],"category_scores_gemma":[0.000861646,0.0003981697,0.00009220961,0.0008043811,0.00070577295,0.0016571403,0.0055722347,0.00089480565,0.0007522059],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013583152,0.000037821945,0.00026047305,0.000055959485,0.000013897369,0.00010090143,0.00072298065,0.005303232,0.000012254752,0.0010027029,0.0016501459,0.9908261],"study_design_scores_gemma":[0.00054606586,0.00013149051,0.0009442326,0.001304718,0.00003548343,0.000033566277,0.0000051041866,0.41564843,0.000045415272,0.10473627,0.47515872,0.0014105112],"about_ca_topic_score_codex":0.0008228503,"about_ca_topic_score_gemma":0.21041156,"teacher_disagreement_score":0.9894155,"about_ca_system_score_codex":0.00025910226,"about_ca_system_score_gemma":0.002177135,"threshold_uncertainty_score":0.999847},"labels":[],"label_agreement":null},{"id":"W2969231583","doi":"","title":"Welcome to Sigmod 2019 - The 2019 ACM SIGMOD International Conference on the Management of Data!","year":2019,"lang":"en","type":"article","venue":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Oak Ridge National Laboratory; University of Illinois at Urbana-Champaign; Universität Rostock; Universität Stuttgart; Universidade Federal de Minas Gerais; Tsinghua University; Technische Universität München; Indian Institute of Technology Delhi; Universität Salzburg; University of California, San Diego; Universitetet i Oslo; Johannes Gutenberg-Universität Mainz; National and Kapodistrian University of Athens; Centre National de la Recherche Scientifique; University of Pennsylvania; George Washington University; Georgia Institute of Technology; Rice University; Technische Universität Dresden; Hochschule Darmstadt; Pohang University of Science and Technology; Brandeis University; Nanyang Technological University; Seoul National University; Google; York University; University of Glasgow; University of Oxford; University of Warwick; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; Universiteit van Amsterdam; Université du Luxembourg; Huazhong University of Science and Technology; Athens University of Economics and Business; Carnegie Mellon University; University at Buffalo; Renmin University of China; National University of Singapore; Ohio State University; Technische Universität Kaiserslautern; Imperial College London; National Technical University of Athens; Washington State University; Harvard University; University of Texas at Arlington; University of Waterloo; University of Science and Technology of China; Microsoft Research; Technische Universität Darmstadt; Aalborg Universitet; Universiteit Antwerpen; State University of New York; Beijing Institute of Technology; Loughborough University; University of Wisconsin-Madison; Arizona State University; Brown University; Massachusetts Institute of Technology","keywords":"Library science; Computer science","score_opus":0.4059641957481789,"score_gpt":0.485559362712492,"score_spread":0.07959516696431312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969231583","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":[0.15891008,0.00009935775,0.37964982,0.34104192,0.0053106816,0.014483099,0.0020604376,0.000066295266,0.09837832],"genre_scores_gemma":[0.97167706,0.0002221026,0.022153381,0.004082583,0.00026785312,0.00017944763,0.000096279975,0.000014493221,0.0013068037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9910589,0.0002238327,0.000932773,0.00046563556,0.0067562046,0.0005626794],"domain_scores_gemma":[0.9913523,0.005012103,0.0003234511,0.0022960415,0.0009207423,0.00009531796],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.04681807,0.00019554487,0.00025160334,0.00041117676,0.0008281136,0.0017508675,0.01484505,0.000046684214,0.00008992568],"category_scores_gemma":[0.0019332628,0.0000805082,0.00007406424,0.0015175401,0.001179802,0.0014062721,0.004637511,0.00039944984,0.00022925567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051739455,0.00014098102,0.000014595621,0.00004532013,0.000049441598,5.3020614e-7,0.0045980187,0.0035580622,0.0000066076873,0.9259101,0.041956034,0.02366854],"study_design_scores_gemma":[0.00045791324,0.00016105024,0.0007103355,0.00016010038,0.00000875612,0.0000069803077,0.0039023424,0.5633927,0.00001699023,0.34896475,0.08208681,0.0001312789],"about_ca_topic_score_codex":0.000030018922,"about_ca_topic_score_gemma":0.00003062065,"teacher_disagreement_score":0.81276697,"about_ca_system_score_codex":0.00011959997,"about_ca_system_score_gemma":0.00028374224,"threshold_uncertainty_score":0.9992854},"labels":[],"label_agreement":null},{"id":"W2970727798","doi":"10.14778/3342263.3342638","title":"Distributed implementations of dependency discovery algorithms","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":27,"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; Implementation; Pruning; Dependency (UML); Focus (optics); Space (punctuation); Computation; Distributed computing; Big data; Theoretical computer science; Distributed algorithm; Algorithm; Parallel computing; Data mining; Artificial intelligence; Programming language","score_opus":0.07908823019991898,"score_gpt":0.3774095362212648,"score_spread":0.29832130602134577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970727798","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":[0.9667907,0.0000726735,0.0033724345,0.003610219,0.00085716223,0.0015522186,0.0012258309,0.00003067185,0.022488091],"genre_scores_gemma":[0.9968333,0.000018676517,0.0009405906,0.00010579873,0.000020206731,0.000026400936,0.00001295579,0.0000058572555,0.0020361624],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996812,0.000018787943,0.00077431847,0.00031919454,0.0018687225,0.0002069648],"domain_scores_gemma":[0.9983375,0.00019277105,0.0006506442,0.00034793498,0.00042828542,0.0000428547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002252459,0.00011455639,0.00025915678,0.0001185201,0.00007360909,0.00013234159,0.0013754949,0.000026259968,0.00032719996],"category_scores_gemma":[0.0006641033,0.00006889862,0.00016789186,0.0006234606,0.000080383536,0.0007502263,0.0008783225,0.00007308929,0.00005789742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014170432,0.0010027615,0.16609113,0.0003129117,0.0003544421,5.417889e-7,0.0027569423,0.00015256002,0.054206166,0.64535916,0.094592266,0.035029385],"study_design_scores_gemma":[0.003519723,0.0005813181,0.17173222,0.00024021845,0.0002450055,0.000008155084,0.036157276,0.0007551209,0.34045133,0.34142417,0.10423032,0.0006551354],"about_ca_topic_score_codex":0.00015827289,"about_ca_topic_score_gemma":0.000017339196,"teacher_disagreement_score":0.30393502,"about_ca_system_score_codex":0.00006158742,"about_ca_system_score_gemma":0.000037736067,"threshold_uncertainty_score":0.35826102},"labels":[],"label_agreement":null},{"id":"W2970992672","doi":"10.14778/3352063.3352116","title":"Data lake management","year":2019,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":236,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TD Bank Group; University of Toronto","funders":"","keywords":"Metadata; Data management; Metadata management; Data science; Data management plan; Computer science; Data integration; Software versioning; Data mapping; Data extraction; Data element; Research data; Data virtualization; Data curation; Database; World Wide Web; Software","score_opus":0.19096554616353498,"score_gpt":0.3896089267691528,"score_spread":0.19864338060561784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970992672","genre_codex":"other","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":[0.21318969,0.00013218504,0.00026199353,0.012052642,0.0021087513,0.0025781002,0.0005677844,0.000097855685,0.769011],"genre_scores_gemma":[0.94992584,0.00007182606,0.0026983237,0.0012261103,0.00006681453,0.000030666233,0.00002150233,0.00001461448,0.045944292],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99663407,0.000016608958,0.00058983057,0.000625041,0.0018801609,0.00025427833],"domain_scores_gemma":[0.9979554,0.00010453135,0.00039833755,0.0013374187,0.00014767765,0.000056676807],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0039867936,0.00013409548,0.00023356757,0.00013503643,0.0000818218,0.000221756,0.0055228253,0.000027945136,0.0008325573],"category_scores_gemma":[0.00029328867,0.00007762691,0.00008796646,0.00058597256,0.000071151895,0.0006484029,0.0057442994,0.00009131345,0.000896293],"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":[0.00006041762,0.0002915908,0.014538794,0.00019110406,0.00017358296,8.7280773e-7,0.00038638516,0.000021883334,0.0011219103,0.37607518,0.5550478,0.052090466],"study_design_scores_gemma":[0.00046774835,0.000037125898,0.01089679,0.00005279854,0.00004019351,0.0000016245751,0.001976713,0.00022190128,0.0016090437,0.032707166,0.9518612,0.00012771656],"about_ca_topic_score_codex":0.000013332878,"about_ca_topic_score_gemma":0.000025716168,"teacher_disagreement_score":0.7367362,"about_ca_system_score_codex":0.000024845214,"about_ca_system_score_gemma":0.00000963265,"threshold_uncertainty_score":0.9998816},"labels":[],"label_agreement":null},{"id":"W2971298513","doi":"","title":"OPERA: Operations-oriented Probabilistic Extraction, Reasoning, and Analysis.","year":2018,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Probabilistic logic; Opera; Computer science; Artificial intelligence; Art; Art history","score_opus":0.036190137567943564,"score_gpt":0.37420932681193797,"score_spread":0.33801918924399443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971298513","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":[0.15139961,0.00036612886,0.8375531,0.0005645038,0.000049054746,0.0004952371,0.00008365485,0.000044336437,0.009444389],"genre_scores_gemma":[0.9947443,0.000057041147,0.0020873817,0.00010438304,0.00005799379,0.00011695266,0.000047421723,0.0000036136933,0.0027809136],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986946,0.00022057274,0.00039551334,0.00033436966,0.0002591656,0.00009578154],"domain_scores_gemma":[0.99830246,0.00053980737,0.0001103397,0.00057583366,0.0004109776,0.000060557995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032975269,0.00008490451,0.0002015175,0.00021524866,0.0004099345,0.00015978393,0.00024041679,0.000033346547,0.00024511167],"category_scores_gemma":[0.00092622836,0.000064201864,0.000031261774,0.0010761344,0.0008683697,0.00037024904,0.00013783385,0.000046695735,0.00002931341],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003169998,0.000045244975,0.0006315716,0.0000061217347,0.00006479039,6.7119636e-8,0.0007558263,0.000031237,0.000083706356,0.98233604,0.0003249745,0.015688736],"study_design_scores_gemma":[0.00020083495,0.00008447813,0.015335602,0.0000048179445,0.00035591383,0.0000038847197,0.0064821746,0.000960927,0.0010268358,0.82621366,0.1491611,0.00016980672],"about_ca_topic_score_codex":0.000049980295,"about_ca_topic_score_gemma":0.00012772482,"teacher_disagreement_score":0.8433447,"about_ca_system_score_codex":0.000006091732,"about_ca_system_score_gemma":0.000025813155,"threshold_uncertainty_score":0.31995443},"labels":[],"label_agreement":null},{"id":"W2972941956","doi":"10.1109/tkde.2019.2940019","title":"Bayesian Networks for Data Integration in the Absence of Foreign Keys","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Relational database; Probabilistic logic; Inference; Data integration; Bayesian network; Data mining; Cardinality (data modeling); Relation (database); Population; Theoretical computer science; Data science; Information retrieval; Machine learning; Artificial intelligence","score_opus":0.12352446206391332,"score_gpt":0.36871568932336674,"score_spread":0.24519122725945341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972941956","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":[0.001230318,0.000119786695,0.99680245,0.00007699007,0.0003507523,0.00035184555,0.0005194247,0.000013306358,0.0005351476],"genre_scores_gemma":[0.99663115,0.00007915783,0.0028660698,0.000037104386,0.00003175615,0.000016732634,0.00019650391,0.000006575117,0.00013495772],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998862,0.00004984558,0.00034554675,0.00040145044,0.00020827357,0.00013287285],"domain_scores_gemma":[0.99689454,0.0011261518,0.00005092088,0.0018625873,0.00003853228,0.000027294212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026728623,0.0000928476,0.00015534711,0.00016705027,0.000048184946,0.00009553989,0.0015743341,0.000041364416,0.00002824515],"category_scores_gemma":[0.00009193257,0.00006370349,0.00002292748,0.00038869915,0.000021345866,0.0008133609,0.000027598968,0.00012449347,0.000016056367],"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":[0.00010970451,0.00040993062,0.00016829272,0.00017808285,0.00006214937,0.0000019133624,0.0016485108,0.14296232,0.00041434178,0.016221173,0.014996892,0.8228267],"study_design_scores_gemma":[0.00024341376,0.000046821693,0.00020721633,0.00005513913,0.000011755861,0.0000011279345,0.000621536,0.9838045,0.00013181682,0.00039934384,0.01439507,0.00008225713],"about_ca_topic_score_codex":0.000027762935,"about_ca_topic_score_gemma":0.0002893638,"teacher_disagreement_score":0.99540085,"about_ca_system_score_codex":0.000007877881,"about_ca_system_score_gemma":0.000013856022,"threshold_uncertainty_score":0.29255307},"labels":[],"label_agreement":null},{"id":"W2974677520","doi":"10.1109/icmcis.2019.8842749","title":"CRISIS: Integrating AIS and Ocean Data Streams Using Semantic Web Standards for Event Detection","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Computer science; Data stream mining; Semantic Web; Interoperability; Data science; Agile software development; Event (particle physics); Process (computing); World Wide Web; Data mining; Software engineering","score_opus":0.17588645195985086,"score_gpt":0.45533094904342614,"score_spread":0.27944449708357527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974677520","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":[0.43571776,0.000049166774,0.56139493,0.0005290091,0.00042163467,0.00045430026,0.0005715991,0.00003933418,0.00082225335],"genre_scores_gemma":[0.9938437,0.000012533827,0.0052325376,0.00024935632,0.000041117382,0.0000016094016,0.000035886773,0.0000072892035,0.0005759889],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978508,0.00010227542,0.00044657444,0.0005694252,0.0008517622,0.00017918322],"domain_scores_gemma":[0.99821854,0.0003773006,0.0001506335,0.0010060362,0.000189758,0.000057711022],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063353432,0.000103665894,0.00019598768,0.00014128123,0.000149456,0.0005129913,0.0005948795,0.000035708123,0.00022429362],"category_scores_gemma":[0.0012745383,0.000071079485,0.000037553295,0.00023762452,0.000023906625,0.00094209105,0.00066828437,0.000059849343,0.000023215482],"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":[0.00015372617,0.00014989337,0.0030825348,0.00018318136,0.00012190098,0.0000025650786,0.0010218574,0.0002780139,0.002541806,0.007878244,0.10614713,0.8784391],"study_design_scores_gemma":[0.0009071034,0.00027243988,0.00026900417,0.00007866888,0.00007509277,0.0000057464795,0.038949512,0.7739152,0.0014136581,0.011673228,0.17214122,0.00029913528],"about_ca_topic_score_codex":0.0003538297,"about_ca_topic_score_gemma":0.0012914762,"teacher_disagreement_score":0.87814003,"about_ca_system_score_codex":0.000044706205,"about_ca_system_score_gemma":0.000063545944,"threshold_uncertainty_score":0.49467865},"labels":[],"label_agreement":null},{"id":"W2974699184","doi":"10.1002/pra2.2018.14505501026","title":"Understanding the information needs of social scientists in Germany","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Information needs; Data collection; Quarter (Canadian coin); Data science; Social needs; Information seeking; Computer science; Knowledge management; Sociology; World Wide Web; Information retrieval; Social science; Political science; Geography","score_opus":0.08734379789931224,"score_gpt":0.34830575575210093,"score_spread":0.2609619578527887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974699184","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":[0.87067723,0.0000048099014,0.005138609,0.035303805,0.0007552132,0.0012653718,0.00007328524,0.00005748676,0.08672416],"genre_scores_gemma":[0.9995134,0.000002285297,0.00009084961,0.00026112044,0.000010573642,0.000014443367,8.829388e-7,8.464111e-7,0.000105593186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977625,0.000006960966,0.00068041845,0.00006304347,0.0012980665,0.00018900285],"domain_scores_gemma":[0.99590987,0.00015036581,0.0013515097,0.00010987165,0.0024644241,0.000013948956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011720365,0.000054931865,0.00012693007,0.0015202302,0.0006034262,0.00032135827,0.0011086931,0.00007880282,0.0000034445288],"category_scores_gemma":[0.008899038,0.0000332739,0.000030266525,0.0064971736,0.0010018555,0.005853,0.00042889253,0.00007460033,0.000009295567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008934466,0.000006795365,0.008455824,0.000014674524,0.000003934818,4.849987e-10,0.011385926,9.922916e-7,0.00044172944,0.9708672,0.0036535414,0.005160415],"study_design_scores_gemma":[0.0013955928,0.00018869304,0.098441124,0.000045609453,0.000029182269,0.0000024409646,0.17463773,0.0043156077,0.014947755,0.4619802,0.24378866,0.00022740339],"about_ca_topic_score_codex":0.0000061562414,"about_ca_topic_score_gemma":0.0000075157786,"teacher_disagreement_score":0.50888705,"about_ca_system_score_codex":0.00022445552,"about_ca_system_score_gemma":0.00008950632,"threshold_uncertainty_score":0.99944943},"labels":[],"label_agreement":null},{"id":"W2974767122","doi":"10.22230/cjc.2019v44n3a3647","title":"Special Section: Data Power","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Communication","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Universität Bremen","keywords":"Section (typography); Special section; Power (physics); Computer science; Engineering; Physics; Engineering physics","score_opus":0.24225037217171924,"score_gpt":0.4055047114123008,"score_spread":0.16325433924058158,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974767122","genre_codex":"other","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":[0.1406951,0.0012673079,0.003578821,0.039942022,0.015662381,0.00036277133,0.00021281403,0.000010747528,0.798268],"genre_scores_gemma":[0.9932528,0.000044493452,0.0009892463,0.0008274718,0.0011337491,2.52387e-7,0.000038603626,0.000004801941,0.003708593],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985637,0.00029055873,0.00048420537,0.00010523342,0.00044883753,0.00010743306],"domain_scores_gemma":[0.99647534,0.0002698673,0.0003642854,0.0023764793,0.0003113305,0.00020271401],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048898673,0.00004600499,0.00012791631,0.0002874677,0.00012348,0.0003171645,0.0035982218,0.000033818545,0.0048101973],"category_scores_gemma":[0.0009942245,0.00003839929,0.000038207945,0.00030816603,0.000058150046,0.0011071053,0.00019353931,0.00018616112,0.00065943995],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008477539,0.0000090020985,0.002807371,8.344592e-7,0.000015292177,0.0000035735004,0.0005470129,0.000044080603,0.00000529516,0.015018834,0.9572561,0.024284165],"study_design_scores_gemma":[0.00014527682,0.000029960493,0.015944468,0.000012954605,0.0000053863305,0.000017832908,0.0012322924,0.000047019854,0.0000030066792,0.005293844,0.9772233,0.000044701534],"about_ca_topic_score_codex":0.0012620109,"about_ca_topic_score_gemma":0.04365654,"teacher_disagreement_score":0.8525577,"about_ca_system_score_codex":0.00007200429,"about_ca_system_score_gemma":0.00047453717,"threshold_uncertainty_score":0.99609953},"labels":[],"label_agreement":null},{"id":"W2976986740","doi":"","title":"Analyse de la performance de la méthode d'imputation de données manquantes missForest et application à des données environnementales","year":2019,"lang":"fr","type":"article","venue":"Espace École de technologie supérieure (École de technologie supérieure)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Imputation (statistics); Humanities; Political science; Forestry; Mathematics; Philosophy; Geography; Missing data; Statistics","score_opus":0.05752648360426363,"score_gpt":0.3485177996458281,"score_spread":0.2909913160415645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2976986740","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":[0.67013586,0.0041473075,0.30777994,0.011069771,0.00021055609,0.0019026368,0.00031228559,0.0028716752,0.0015699678],"genre_scores_gemma":[0.9008253,0.009024223,0.083443746,0.0016530015,0.00010972329,0.00095363485,0.0001698374,0.00018803874,0.00363248],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98846924,0.0022362904,0.0017834821,0.0026001523,0.001564432,0.0033463729],"domain_scores_gemma":[0.9892324,0.004787527,0.0012316185,0.0038981573,0.00032900536,0.000521264],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.015524479,0.0014870706,0.0014473451,0.0020725532,0.0011043242,0.001627595,0.006172801,0.0035558871,0.0002833817],"category_scores_gemma":[0.009757655,0.0015115979,0.0005973884,0.004237638,0.005760717,0.0018995197,0.0028080652,0.0032103842,0.0007687946],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000562333,0.0022202004,0.5540091,0.0014821073,0.0005115451,0.0006960451,0.0042212317,0.14567703,0.038676202,0.10146806,0.012314602,0.13816155],"study_design_scores_gemma":[0.0039426307,0.0020464764,0.15202723,0.0014732154,0.00083766435,0.0012224672,0.0954911,0.26445973,0.091183096,0.1900815,0.19359967,0.0036352],"about_ca_topic_score_codex":0.0013367023,"about_ca_topic_score_gemma":0.002766204,"teacher_disagreement_score":0.40198186,"about_ca_system_score_codex":0.0021295515,"about_ca_system_score_gemma":0.0013675939,"threshold_uncertainty_score":0.99978787},"labels":[],"label_agreement":null},{"id":"W2980058748","doi":"10.29173/iasl7390","title":"School Librarians as Data Coaches","year":2019,"lang":"en","type":"article","venue":"IASL Annual Conference Proceedings","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Museum and Library Services","keywords":"Information literacy; Medical education; Focus group; Service (business); Psychology; Pedagogy; Medicine; Sociology; Business","score_opus":0.24690350325259464,"score_gpt":0.40067053009046766,"score_spread":0.15376702683787302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980058748","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":[0.7554417,0.000078076846,0.0013324042,0.009795284,0.0007066934,0.00078830787,0.00080526446,0.00029941127,0.23075281],"genre_scores_gemma":[0.96687853,0.00001886971,0.0009496051,0.003456464,0.0001411938,0.000013227583,0.0000799311,0.000015367028,0.02844678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99594176,0.000044025146,0.0006584089,0.0012375294,0.0016657715,0.00045248336],"domain_scores_gemma":[0.9971555,0.0002900307,0.0003116587,0.001251296,0.00066934596,0.00032216206],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003465814,0.0002367199,0.00037846612,0.00024084917,0.00014273102,0.0023417275,0.005315363,0.00012045071,0.0048733843],"category_scores_gemma":[0.0044616763,0.00018338239,0.00005998772,0.00069480244,0.00014855579,0.005582713,0.0031042118,0.0002910696,0.021925295],"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":[0.00016635224,0.00021127007,0.08130269,0.0000797922,0.0000799813,0.000010512538,0.03226906,0.000001664283,0.00021608527,0.19257034,0.6551153,0.037976936],"study_design_scores_gemma":[0.00044164484,0.00019044557,0.0057333373,0.000053831118,0.000021438389,0.0000127942585,0.18305564,0.0012590387,0.00019821238,0.07018802,0.7384426,0.0004029644],"about_ca_topic_score_codex":0.0001403609,"about_ca_topic_score_gemma":0.00001232907,"teacher_disagreement_score":0.21143682,"about_ca_system_score_codex":0.000019833209,"about_ca_system_score_gemma":0.0002545379,"threshold_uncertainty_score":0.99869394},"labels":[],"label_agreement":null},{"id":"W2981358885","doi":"10.1007/s40273-019-00850-0","title":"Improving Transparency in Decision Models: Current Issues and Potential Solutions","year":2019,"lang":"en","type":"editorial","venue":"PharmacoEconomics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Quality of Life Research; Transparency (behavior); Health economics; Health administration; Public health; Current (fluid); Management science; Business; Risk analysis (engineering); Computer science; Economics; Medicine; Engineering; Nursing","score_opus":0.1391068268644732,"score_gpt":0.440017613013958,"score_spread":0.30091078614948474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981358885","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":[0.0011068447,0.0075843027,0.03723712,0.0003691049,0.94986737,0.0006592025,0.002227494,0.00004265881,0.0009058846],"genre_scores_gemma":[0.022212263,0.06734134,0.0029937092,0.00024598048,0.90100586,0.0001747214,0.001689624,0.00016687045,0.0041695964],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954954,0.0002234741,0.0015232624,0.0012693726,0.00097331475,0.0005152046],"domain_scores_gemma":[0.9966657,0.0016774284,0.00054317614,0.0007887671,0.00016055896,0.00016434744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0051813587,0.00037772482,0.0007444421,0.0006314017,0.00015447402,0.0007878915,0.0014922667,0.00029711387,0.0002903921],"category_scores_gemma":[0.0007782674,0.00036347896,0.0001773489,0.00018337894,0.000090576345,0.0014688887,0.00082655513,0.00081478513,0.0004242166],"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":[0.00007251997,0.00007660401,0.0000046783944,0.000059862377,0.00001849862,0.000004423322,0.00017257432,0.0042264434,0.000006126107,0.00058515003,0.78831595,0.20645717],"study_design_scores_gemma":[0.0010475194,0.000023207154,0.0000069224443,0.000054420372,0.00005993215,7.05006e-7,0.0001087167,0.115807444,0.0000051163256,0.030292762,0.8522236,0.00036967825],"about_ca_topic_score_codex":0.0005160652,"about_ca_topic_score_gemma":0.00024884343,"teacher_disagreement_score":0.20608748,"about_ca_system_score_codex":0.00021315724,"about_ca_system_score_gemma":0.00029808548,"threshold_uncertainty_score":0.99988174},"labels":[],"label_agreement":null},{"id":"W2981442932","doi":"10.4095/219696","title":"Data Quality Requirements for Future SAR","year":2000,"lang":"en","type":"report","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Natural Resources Canada","funders":"","keywords":"Quality (philosophy); Computer science; Data quality; Remote sensing; Geology; Engineering; Operations management; Physics","score_opus":0.8194886233788209,"score_gpt":0.622003661711994,"score_spread":0.19748496166682694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981442932","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004400022,0.000842545,0.01925025,0.005641795,0.0077209384,0.0016798154,0.036308497,0.00015387857,0.92835826],"genre_scores_gemma":[0.0002881756,0.0037161317,0.014002655,0.0035150547,0.005292015,0.00004967169,0.0309672,0.000060826584,0.9421083],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9879343,0.0003960823,0.002343422,0.00210719,0.006744853,0.00047417445],"domain_scores_gemma":[0.9882384,0.0010106694,0.0010071746,0.0088129565,0.0007555112,0.00017529805],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.03815879,0.00037008934,0.0009422435,0.00029219346,0.0002300115,0.00079192966,0.007271393,0.0003717589,0.0107291695],"category_scores_gemma":[0.0059913686,0.00025514056,0.00026750372,0.00044128162,0.00008889939,0.0009984957,0.0023490964,0.00024575414,0.0014719212],"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":[0.000025357653,0.00006601901,0.00002167369,0.000072089664,0.00007557547,0.0000027759304,0.000021629938,4.562788e-7,2.3910846e-7,0.0018909986,0.7459283,0.25189492],"study_design_scores_gemma":[0.0002538904,0.00003258168,0.0006276122,0.000028048016,0.00007232248,0.0000020651125,0.00074220524,0.000027324706,0.0000015981444,0.012497357,0.985355,0.00036000097],"about_ca_topic_score_codex":0.0006384745,"about_ca_topic_score_gemma":0.001473725,"teacher_disagreement_score":0.25153494,"about_ca_system_score_codex":0.00013495548,"about_ca_system_score_gemma":0.0007959985,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null},{"id":"W2985772508","doi":"10.5703/1288284317068","title":"What Are We Doing? Capturing the Uncaptured: Workload Data to Demonstrate Service","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Purdue Pharma (Canada)","funders":"","keywords":"Computer science; Service (business); Workload; Task (project management); Categorization; Data as a service; World Wide Web; Database; Services computing; Database transaction; Web service; Data science; Engineering; Business; Artificial intelligence","score_opus":0.33004837715176083,"score_gpt":0.4184693254346535,"score_spread":0.08842094828289265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2985772508","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":[0.16263632,0.0025524497,0.026297634,0.6869944,0.008806797,0.0026781245,0.00033782073,0.00037818757,0.10931828],"genre_scores_gemma":[0.85713816,0.00047122754,0.0057796,0.08149397,0.0002895324,0.00002092628,0.00005684377,0.000026883843,0.054722875],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968192,0.0002182395,0.00047702237,0.0008397809,0.00130545,0.00034033405],"domain_scores_gemma":[0.9947165,0.00078442215,0.0001697628,0.0040571154,0.00013430539,0.00013785175],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0047732117,0.0001625536,0.00022853154,0.0001106807,0.00016018834,0.0024522655,0.0049913498,0.000052350297,0.0015750785],"category_scores_gemma":[0.00024503111,0.0000870359,0.00004362607,0.0009882415,0.00003158124,0.0024563484,0.0033290605,0.00016664881,0.0110180015],"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":[0.0000710602,0.00009837891,0.0024906537,0.000047291865,0.00009238347,0.000021431266,0.004295975,0.0025241498,0.00018133271,0.009887209,0.61554337,0.36474675],"study_design_scores_gemma":[0.00016273998,0.000011205173,0.002043587,0.0001334198,0.000014093878,0.0000028143443,0.060174767,0.0015152879,0.00008566401,0.003444256,0.9322209,0.00019130345],"about_ca_topic_score_codex":0.00032781833,"about_ca_topic_score_gemma":0.006703272,"teacher_disagreement_score":0.6945018,"about_ca_system_score_codex":0.000017950599,"about_ca_system_score_gemma":0.000036282523,"threshold_uncertainty_score":0.9993376},"labels":[],"label_agreement":null},{"id":"W2989076415","doi":"10.5703/1288284317002","title":"Data Expeditions: Mining Data for Effective Decision-Making","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Purdue Pharma (Canada)","funders":"","keywords":"Computer science; Sorting; Variety (cybernetics); Session (web analytics); Data science; Publishing; World Wide Web; Scratch; Political science; Artificial intelligence","score_opus":0.37462084330536694,"score_gpt":0.5247623304457705,"score_spread":0.15014148714040354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989076415","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":[0.008397581,0.00009344968,0.9573905,0.0009258265,0.0018417375,0.0014379268,0.006459243,0.000080007245,0.023373716],"genre_scores_gemma":[0.5693735,0.000022649876,0.4120731,0.004569567,0.0006603962,0.00013204994,0.0053263623,0.00003573515,0.007806626],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679136,0.00013695519,0.000544118,0.0012418521,0.0010421587,0.00024355609],"domain_scores_gemma":[0.9740521,0.018010471,0.00018670828,0.00755059,0.00013953872,0.000060639777],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009338515,0.000117348645,0.00024675828,0.000192961,0.00016892322,0.0005692975,0.006313297,0.000044632405,0.0021383944],"category_scores_gemma":[0.018369861,0.00008356161,0.000038657534,0.00039973904,0.000041160663,0.002993899,0.006335625,0.000058112146,0.0018709817],"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":[0.000031877273,0.000034315148,0.00015610135,0.0000058142896,0.000017849328,0.0000011051569,0.00006905849,0.000015846676,0.0000047544017,0.0075179613,0.6112918,0.3808535],"study_design_scores_gemma":[0.0004159004,0.000057484496,0.0009917013,0.00006752976,0.000019444416,0.0000016087465,0.0047914246,0.039357796,0.000005970415,0.04300574,0.9111219,0.00016347817],"about_ca_topic_score_codex":0.000013413113,"about_ca_topic_score_gemma":0.00018620306,"teacher_disagreement_score":0.5609759,"about_ca_system_score_codex":0.000017554685,"about_ca_system_score_gemma":0.00003791534,"threshold_uncertainty_score":0.999063},"labels":[],"label_agreement":null},{"id":"W2990073915","doi":"10.29249/selcuksbmyd.580424","title":"Veri Ambarı Projelerinde ETL Performansını Etkileyen Faktörlerin Belirlenmesi","year":2019,"lang":"tr","type":"article","venue":"Selçuk Üniversitesi Sosyal Bilimler Meslek Yüksekokulu dergisi","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Yukon University","funders":"","keywords":"Mathematics; Physics","score_opus":0.041888416829430355,"score_gpt":0.30598130087538017,"score_spread":0.2640928840459498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990073915","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":[0.82810503,0.0016907662,0.00062758505,0.0051165046,0.006734606,0.0042835944,0.0014597283,0.000677914,0.15130427],"genre_scores_gemma":[0.8763085,0.0021564465,0.0031244778,0.0027155387,0.00068871066,0.00006282301,0.0005360967,0.00021725224,0.114190154],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9812786,0.0012763242,0.0029648668,0.004778981,0.0061750803,0.003526154],"domain_scores_gemma":[0.9890975,0.0015035954,0.0015946517,0.0048589366,0.0013591708,0.00158618],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0062230895,0.0021877822,0.0026790728,0.0021129095,0.0015993785,0.0023373293,0.0068473425,0.0013167387,0.026267616],"category_scores_gemma":[0.0007428898,0.0021027983,0.0015567391,0.0040884432,0.0010274695,0.004061309,0.0050096004,0.0022282684,0.04407383],"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":[0.004700166,0.0044828206,0.1765979,0.002210838,0.00482108,0.0013990997,0.024589328,0.00369338,0.0056927595,0.064817846,0.49095637,0.21603844],"study_design_scores_gemma":[0.0066232933,0.0017315083,0.082260616,0.0005349423,0.0008844529,0.00006875923,0.03679929,0.0062069935,0.0013806471,0.0019105033,0.8578626,0.003736369],"about_ca_topic_score_codex":0.0012087482,"about_ca_topic_score_gemma":0.00064823224,"teacher_disagreement_score":0.36690626,"about_ca_system_score_codex":0.0009854886,"about_ca_system_score_gemma":0.0010746573,"threshold_uncertainty_score":0.99997973},"labels":[],"label_agreement":null},{"id":"W2990325812","doi":"10.23889/ijpds.v4i3.1209","title":"Linked Administrative Data at Statistics Canada – new data resources for horizontal research","year":2019,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Record linkage; Linkage (software); Immigration; Analytics; Data science; Business; Public relations; Geography; Database; Political science; Sociology; Computer science; Law","score_opus":0.6937162468840304,"score_gpt":0.6065499564550645,"score_spread":0.08716629042896595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990325812","genre_codex":"dataset","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":[0.08807018,0.00017229922,0.38939643,0.028132485,0.024065033,0.0030987419,0.46543375,0.000045530047,0.0015855592],"genre_scores_gemma":[0.69938976,0.00008885317,0.15998206,0.0012670959,0.0032224953,0.00001605814,0.11141714,0.00004224172,0.024574336],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.990311,0.0001801672,0.0010441005,0.001439019,0.006553828,0.00047188424],"domain_scores_gemma":[0.9891706,0.0033471875,0.0006894989,0.004446929,0.0019908103,0.00035497095],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.022138195,0.0001437089,0.0002199523,0.00044249295,0.00093780115,0.0025062284,0.027101718,0.000041828276,0.00037011824],"category_scores_gemma":[0.026722569,0.00011654571,0.000021278174,0.000679787,0.00023851646,0.007172492,0.010801751,0.00024299808,0.00006374328],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002495709,0.000038872942,0.003403589,0.0000050284775,0.000041472766,0.00000787681,0.00009972018,0.000095551804,0.000089917776,0.017168676,0.93159866,0.04720106],"study_design_scores_gemma":[0.0006304268,0.00011025801,0.016493328,0.000026646954,0.000012572468,0.00002736153,0.0008409765,0.08805827,0.000011948782,0.013071982,0.88055587,0.00016035834],"about_ca_topic_score_codex":0.073937654,"about_ca_topic_score_gemma":0.48490328,"teacher_disagreement_score":0.61131954,"about_ca_system_score_codex":0.00047698582,"about_ca_system_score_gemma":0.0027558606,"threshold_uncertainty_score":0.99852926},"labels":[],"label_agreement":null},{"id":"W2991578290","doi":"10.5703/1288284317144","title":"The Time Has Come... To Build, Reflect, and Analyze Connections Between Qualitative and Quantitative Data","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Purdue Pharma (Canada)","funders":"","keywords":"Computer science; Extant taxon; Transparency (behavior); Accountability; Process (computing); Process management; Qualitative property; Data science; Management science; Knowledge management; Engineering; Political science","score_opus":0.6070544362019351,"score_gpt":0.5467733598393073,"score_spread":0.060281076362627806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991578290","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":[0.07547284,0.00053618976,0.27230743,0.623787,0.0001513476,0.0011342454,0.0029628607,0.00015237859,0.023495754],"genre_scores_gemma":[0.9414671,0.00012851434,0.03303207,0.015354903,0.00015897033,0.000027341086,0.00027250155,0.000024150495,0.009534417],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99724245,0.00082277885,0.00047615962,0.00067964336,0.0005904335,0.00018855125],"domain_scores_gemma":[0.98922884,0.0094362255,0.00012450581,0.00081663375,0.00014615827,0.00024765023],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0058005066,0.0001181268,0.00027433084,0.000090965485,0.0006307367,0.0010016568,0.0010473387,0.00002682159,0.00015834621],"category_scores_gemma":[0.009031463,0.00007012862,0.000022342552,0.0008429869,0.0003575888,0.00060167647,0.0016930344,0.000103650804,0.0006185007],"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":[0.000091365466,0.000024076688,0.00066577026,0.0000073110527,0.00020631589,0.0000028451134,0.028722253,0.000007539253,0.00012020546,0.243366,0.70586383,0.020922484],"study_design_scores_gemma":[0.00027532957,0.0003082284,0.0032724794,0.0000056094736,0.000047219066,6.3276457e-7,0.06162993,0.0023565018,0.00003291128,0.031946816,0.8999455,0.0001788228],"about_ca_topic_score_codex":0.00034759782,"about_ca_topic_score_gemma":0.0009302837,"teacher_disagreement_score":0.8659943,"about_ca_system_score_codex":0.000008637133,"about_ca_system_score_gemma":0.000030091025,"threshold_uncertainty_score":0.99931586},"labels":[],"label_agreement":null},{"id":"W2992507139","doi":"10.1177/1833358319887743","title":"Data quality in healthcare: A report of practical experience with the Canadian Primary Care Sentinel Surveillance Network data","year":2019,"lang":"en","type":"article","venue":"Health Information Management Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Consistency (knowledge bases); Data quality; Computer science; Context (archaeology); Completeness (order theory); Quality (philosophy); Data consistency; Construct (python library); Health care; Data mining; Risk analysis (engineering); Medicine; Operations management; Database; Engineering; Artificial intelligence; Mathematics","score_opus":0.28133070735268717,"score_gpt":0.48354025563839564,"score_spread":0.20220954828570847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992507139","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":[0.035541337,0.0011678473,0.10643254,0.75253385,0.0041052173,0.007943451,0.0026345695,0.00010422746,0.08953694],"genre_scores_gemma":[0.9284338,0.00066652946,0.01952754,0.04495555,0.00021928753,0.000029408344,0.005531436,0.000017333483,0.00061913754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99291676,0.0009847765,0.0024101816,0.00042060704,0.0026711065,0.0005965381],"domain_scores_gemma":[0.99272496,0.00036961844,0.002282076,0.0039182687,0.0004076732,0.00029741443],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03477419,0.00014704243,0.00038542322,0.0003321031,0.00048405744,0.00064777257,0.0029197712,0.000044620363,0.00007761188],"category_scores_gemma":[0.00062519085,0.000094787174,0.000026091664,0.0011321525,0.000094233554,0.004726014,0.00151621,0.00044025,0.000089257795],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003273512,0.00009890455,0.33281913,0.0014602233,0.00009225894,0.00014652804,0.006199261,0.0022796255,3.478672e-8,0.045582812,0.5183663,0.09262758],"study_design_scores_gemma":[0.000498081,0.00004308408,0.32107064,0.00007986914,0.0000036817412,0.00009789377,0.01071601,0.0014698103,2.3004883e-8,0.00044228544,0.66546416,0.00011443949],"about_ca_topic_score_codex":0.025523232,"about_ca_topic_score_gemma":0.23400487,"teacher_disagreement_score":0.8928924,"about_ca_system_score_codex":0.0003816988,"about_ca_system_score_gemma":0.0015086898,"threshold_uncertainty_score":0.9939031},"labels":[],"label_agreement":null},{"id":"W2996302565","doi":"10.17269/s41997-019-00265-6","title":"A new record linkage for assessing infant mortality rates in Ontario, Canada","year":2019,"lang":"en","type":"article","venue":"Canadian Journal of Public Health","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto; St. Michael's Hospital; Ontario Stroke Network; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"Ontario Ministry of Health and Long-Term Care; CHEO Research Institute","keywords":"Infant mortality; Medicine; Demography; Live birth; Mortality rate; Birth records; Pediatrics; Birth weight; Population; Pregnancy; Environmental health","score_opus":0.2975005878732344,"score_gpt":0.4327427143190817,"score_spread":0.13524212644584727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996302565","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":[0.9402587,0.0001888007,0.012609964,0.04103597,0.0027499741,0.00044295602,0.00007408806,0.000002877271,0.0026367018],"genre_scores_gemma":[0.98065054,0.0000078157955,0.004971168,0.0095513975,0.00014638374,0.0000025097022,0.000019170846,0.000010912628,0.004640114],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965186,0.00039496482,0.0013675338,0.00025175555,0.0007355993,0.0007315462],"domain_scores_gemma":[0.9955345,0.0006276218,0.00079281646,0.00043465008,0.00034284548,0.00226757],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.017321588,0.00011260105,0.00047339583,0.00061631494,0.00013046923,0.00077058753,0.00086695177,0.000050638533,0.0015328013],"category_scores_gemma":[0.0034419436,0.0000936807,0.000080623424,0.0005573538,0.000023910614,0.0010929985,0.000030808038,0.00035378273,0.000010813135],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028097709,0.000008967086,0.6504083,0.000018586035,0.000019950296,0.000035444118,0.00096697273,0.000027920107,4.802514e-7,0.0031744952,0.24363475,0.10170133],"study_design_scores_gemma":[0.0003092844,0.00005116798,0.41199145,0.00003355872,0.0000016003685,0.000005375736,0.0017814918,0.00005277144,3.9741016e-7,0.002396054,0.5833094,0.00006740557],"about_ca_topic_score_codex":0.9995535,"about_ca_topic_score_gemma":0.9999949,"teacher_disagreement_score":0.33967468,"about_ca_system_score_codex":0.0028051175,"about_ca_system_score_gemma":0.12776601,"threshold_uncertainty_score":0.99937993},"labels":[],"label_agreement":null},{"id":"W2997328546","doi":"10.1007/978-3-030-25674-6_12","title":"Information Ecology to Map the Arctic Information Ecosystem","year":2020,"lang":"en","type":"book-chapter","venue":"Informed decisionmaking for sustainability","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Arctic; Ecology; Environmental resource management; Resilience (materials science); The arctic; Ecosystem; Computer science; Geography; Environmental science; Oceanography; Biology","score_opus":0.07595091540846031,"score_gpt":0.37672227488969084,"score_spread":0.3007713594812305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997328546","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":[0.00072340306,0.0000729051,0.45529857,0.093744524,0.008668815,0.029646173,0.004737987,0.0006546177,0.406453],"genre_scores_gemma":[0.74238473,0.00005532136,0.011335886,0.07288962,0.0015429464,0.0036468175,0.004268132,0.0002008418,0.16367568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911512,0.0001524713,0.0042916997,0.0005787055,0.00308707,0.0007388376],"domain_scores_gemma":[0.9801292,0.009626082,0.0022275234,0.0027931486,0.0048380275,0.000386054],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011112277,0.00063658884,0.0010538243,0.0011329344,0.0008235185,0.0020443606,0.0033402797,0.00056923454,0.00048376957],"category_scores_gemma":[0.070622854,0.000428886,0.00067521696,0.00047207758,0.00019024518,0.0047145155,0.0020629317,0.0006145697,0.0051642773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004034752,0.000010770202,0.00002794409,0.0005334777,0.000061035265,0.0000017402879,0.0025363567,0.00057823316,1.3659894e-8,0.62536246,0.10594395,0.26454055],"study_design_scores_gemma":[0.00031777335,0.00019660582,0.00017025872,0.000054899378,0.000039888,0.000004021522,0.0033572253,0.00059700507,6.137064e-7,0.40739697,0.5875719,0.00029283002],"about_ca_topic_score_codex":0.000024457202,"about_ca_topic_score_gemma":0.00045995336,"teacher_disagreement_score":0.74166137,"about_ca_system_score_codex":0.002155032,"about_ca_system_score_gemma":0.0014033284,"threshold_uncertainty_score":0.9998163},"labels":[],"label_agreement":null},{"id":"W2999189714","doi":"10.2196/15917","title":"Comparing Methods for Record Linkage for Public Health Action: Matching Algorithm Validation Study","year":2020,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Record linkage; Precision and recall; Context (archaeology); Computer science; Public health; Matching (statistics); Algorithm; Linkage (software); Data mining; Psychological intervention; Medicine; Population; Machine learning; Statistics; Mathematics; Environmental health; Geography","score_opus":0.5653348348544291,"score_gpt":0.5458407834458321,"score_spread":0.019494051408597057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999189714","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":[0.009588611,0.00021629319,0.84457445,0.14157462,0.00065633823,0.003023881,0.00011317558,0.00013608835,0.00011656174],"genre_scores_gemma":[0.47018102,0.00039447093,0.47585633,0.048274666,0.0014164171,0.0021145374,0.0009208716,0.00007605656,0.00076560857],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933244,0.0026427133,0.001474345,0.0010119955,0.0006849662,0.0008615874],"domain_scores_gemma":[0.9945869,0.0026182744,0.0007793552,0.0005312453,0.00036168782,0.0011225468],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.03589801,0.00021183437,0.00079769164,0.00023255976,0.0009155175,0.0012640611,0.00061617646,0.00006275247,0.000027209711],"category_scores_gemma":[0.004025183,0.00018443844,0.0001034045,0.0009025058,0.000041036812,0.00095054915,0.00025471507,0.00020179787,0.000011723956],"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":[0.000031913023,0.0001565292,0.009226123,0.00022002736,0.000024395225,1.8616815e-7,0.0039398395,0.0000035373487,7.274317e-7,0.0013653595,0.021700785,0.96333057],"study_design_scores_gemma":[0.0013036163,0.00088591414,0.012402771,0.0000051184447,5.976005e-7,0.0000012319657,0.011382174,0.023823204,3.7835238e-7,0.002187913,0.9478015,0.00020558963],"about_ca_topic_score_codex":0.00017792251,"about_ca_topic_score_gemma":0.0003295292,"teacher_disagreement_score":0.963125,"about_ca_system_score_codex":0.00012888305,"about_ca_system_score_gemma":0.00062688574,"threshold_uncertainty_score":0.9997727},"labels":[],"label_agreement":null},{"id":"W2999486412","doi":"","title":"Identification des informations sensibles dans des sources de données hétérogènes","year":2019,"lang":"fr","type":"article","venue":"Archipelago (Université du Québec à Montréal)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.029944044051013256,"score_gpt":0.2398146214254995,"score_spread":0.20987057737448625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999486412","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":[0.949199,0.004874891,0.033071935,0.0058989148,0.0004096824,0.0004501809,0.00017326733,0.00013620911,0.005785881],"genre_scores_gemma":[0.9746218,0.0017831178,0.0024117297,0.00029944585,0.00008672393,0.0000061698775,0.000055498076,0.000025574744,0.02070998],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.996473,0.0005808702,0.0007459203,0.00059365516,0.0008846997,0.00072183326],"domain_scores_gemma":[0.9966141,0.001111759,0.00046975465,0.0011233394,0.00032982108,0.00035120136],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021833961,0.0003464864,0.00040367167,0.00063349283,0.0018505328,0.0006896986,0.0014890743,0.0001508469,0.0009400469],"category_scores_gemma":[0.00055694825,0.00035510742,0.00029402197,0.0011069671,0.0015156126,0.0035928139,0.0009113672,0.00025675676,0.003847493],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008561582,0.00031178666,0.04071537,0.0003294993,0.00024150853,0.000058079637,0.55212176,0.0034109675,0.0027638855,0.108818986,0.0056667044,0.28547585],"study_design_scores_gemma":[0.0009726112,0.00019004958,0.1764987,0.0002792465,0.00027309102,0.00009008586,0.6047454,0.010657675,0.0007155053,0.0691293,0.13579923,0.00064914214],"about_ca_topic_score_codex":0.39051858,"about_ca_topic_score_gemma":0.7354709,"teacher_disagreement_score":0.34495232,"about_ca_system_score_codex":0.00055216317,"about_ca_system_score_gemma":0.0004518416,"threshold_uncertainty_score":0.99997324},"labels":[],"label_agreement":null},{"id":"W2999637374","doi":"10.1145/3379106.3379118","title":"Winners of 2018 SIGAda Awards","year":2020,"lang":"en","type":"article","venue":"ACM SIGAda Ada Letters","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"General Dynamics (Canada)","funders":"","keywords":"Management; Library science; Engineering; State (computer science); Art history; Art; Computer science; Programming language","score_opus":0.2553201262360162,"score_gpt":0.38521288592447095,"score_spread":0.12989275968845476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999637374","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":[0.5307932,0.000114926646,0.028693944,0.43410483,0.001190848,0.00044986667,0.00017174153,0.00014396258,0.0043366896],"genre_scores_gemma":[0.8976725,0.000013251283,0.0058642006,0.09580554,0.000256758,0.00000961095,0.00002625747,0.000021471944,0.00033046253],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960068,0.00023071031,0.00082369405,0.0006324497,0.0019611863,0.0003451476],"domain_scores_gemma":[0.99674296,0.0011425323,0.00033589487,0.0014629497,0.000091474,0.00022416397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001569595,0.00019646742,0.00040626602,0.00013412058,0.00009197363,0.00015712275,0.0027845493,0.00005390397,0.0007582472],"category_scores_gemma":[0.0051126764,0.00016037143,0.00017530035,0.00088657805,0.00023508839,0.0005636432,0.0010216937,0.0001706834,0.0006942341],"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":[0.000048284313,0.000030200821,0.0010692405,0.000025429323,0.000057055244,0.000039945713,0.0009522394,0.0003250498,0.013894307,0.0012973925,0.97155684,0.010704034],"study_design_scores_gemma":[0.0006608203,0.00014048802,0.0027320755,0.00002581991,0.000041772186,0.0000018509353,0.002555579,0.00026385684,0.0071934755,0.0038108085,0.9821947,0.00037873388],"about_ca_topic_score_codex":0.00028383965,"about_ca_topic_score_gemma":0.000038785503,"teacher_disagreement_score":0.36687925,"about_ca_system_score_codex":0.000030395257,"about_ca_system_score_gemma":0.000053467644,"threshold_uncertainty_score":0.89232063},"labels":[],"label_agreement":null},{"id":"W3006704404","doi":"10.2196/16757","title":"Privacy-Preserving Record Linkage of Deidentified Records Within a Public Health Surveillance System: Evaluation Study","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NSW Ministry of Health; Department of Health, State Government of Victoria; Department of Health, Government of Western Australia; Monash University; NSW Health Pathology; McGill University; University of New South Wales; Burnet Institute; University of Pennsylvania","keywords":"Record linkage; Medical record; Internet privacy; Public health; Computer science; Medicine; Environmental health; Nursing","score_opus":0.649057499612472,"score_gpt":0.5757913744496808,"score_spread":0.0732661251627913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006704404","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":[0.8901748,0.00045331716,0.019623965,0.08618411,0.0014997588,0.0009041074,0.000010322485,0.000016798233,0.0011327903],"genre_scores_gemma":[0.99826086,0.00008127501,0.00042523845,0.0003701545,0.00040377537,0.0000107699725,0.0000038546664,0.000010896098,0.00043320103],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94489855,0.019135917,0.004695386,0.0006981899,0.02991378,0.0006581942],"domain_scores_gemma":[0.9878372,0.004145261,0.0018638403,0.00095574744,0.004070905,0.0011270217],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27898037,0.00012486031,0.00074814056,0.00072619464,0.00009805775,0.0006309553,0.005763255,0.00011192665,0.0021530795],"category_scores_gemma":[0.15725058,0.00008486854,0.00015544039,0.0017686519,0.00018483501,0.0006326708,0.00260377,0.0013644194,0.00011224391],"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":[0.00064861955,0.0013335474,0.051895358,0.00064354105,0.00044221646,0.0003009196,0.028019156,0.000029496347,0.000043432497,0.0015148083,0.5902057,0.3249232],"study_design_scores_gemma":[0.011535233,0.01590808,0.111882575,0.0033615413,0.00007617466,0.00015385986,0.27618125,0.38348594,0.00018077064,0.0068850964,0.18968976,0.0006597283],"about_ca_topic_score_codex":0.0014292491,"about_ca_topic_score_gemma":0.0016703643,"teacher_disagreement_score":0.40051597,"about_ca_system_score_codex":0.00029694042,"about_ca_system_score_gemma":0.0016369257,"threshold_uncertainty_score":0.999616},"labels":[],"label_agreement":null},{"id":"W3011721738","doi":"10.1101/2020.03.16.20036962","title":"Assessing the quality of clinical and administrative data extracted from hospitals: The General Medicine Inpatient Initiative (GEMINI) experience","year":2020,"lang":"en","type":"preprint","venue":"medRxiv","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":true,"ca_institutions":"Sunnybrook Health Science Centre; Trillium Health Centre; Institute for Clinical Evaluative Sciences; University Health Network; University of Toronto; Health Sciences Centre; Mount Sinai Hospital; Queen's University; St. Michael's Hospital","funders":"","keywords":"Data quality; Gold standard (test); Computer science; Medicine; Quality (philosophy); Quality management; Medical record; Data mining; Database; Missing data; Data collection; Medical physics; Statistics; Machine learning; Operations management; Surgery; Internal medicine; Mathematics","score_opus":0.8098649904626021,"score_gpt":0.6374224943190503,"score_spread":0.17244249614355178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011721738","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":[0.96319336,0.0005196058,0.007943956,0.021843212,0.0016361892,0.0007784778,0.0016228566,0.000029084551,0.0024332793],"genre_scores_gemma":[0.9944278,0.00030992398,0.0016863055,0.0023703561,0.0005634742,0.000055216595,0.0005202672,0.0000130295675,0.000053625798],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9854502,0.005924055,0.0037487485,0.0018111493,0.0028097378,0.00025611147],"domain_scores_gemma":[0.97055876,0.020210296,0.0035816638,0.0049399324,0.00049168477,0.00021765988],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.02315095,0.00036583058,0.0012364878,0.000066549954,0.00026638684,0.00056727877,0.0058794226,0.00021201975,0.0003124478],"category_scores_gemma":[0.05719379,0.00017329193,0.0001419467,0.00045151552,0.0029649872,0.00072998094,0.009411947,0.0011115283,0.00001494758],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039270736,0.0006728112,0.63215333,0.00014785881,0.0010293317,0.00007825629,0.12581018,0.000021729975,0.0002786852,0.014036595,0.048928503,0.17645003],"study_design_scores_gemma":[0.00037832692,0.00011813155,0.91471744,0.00014007797,0.00009422711,4.461348e-7,0.042896893,0.0016616288,0.00009568638,0.027137231,0.012524194,0.00023571406],"about_ca_topic_score_codex":0.0008691905,"about_ca_topic_score_gemma":0.00020529915,"teacher_disagreement_score":0.28256413,"about_ca_system_score_codex":0.000014667713,"about_ca_system_score_gemma":0.00033851416,"threshold_uncertainty_score":0.99974835},"labels":[],"label_agreement":null},{"id":"W3012331815","doi":"10.1108/rmj-03-2019-0010","title":"The adoption of electronic records management system (ERMS) in the Yemeni oil and gas sector","year":2020,"lang":"en","type":"article","venue":"Records Management Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Business; Context (archaeology); Ranking (information retrieval); Knowledge management; Originality; Identification (biology); Marketing; Computer science; Qualitative research; Geography","score_opus":0.07092484439600934,"score_gpt":0.3248076612507608,"score_spread":0.2538828168547515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012331815","genre_codex":"other","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":[0.25367463,0.004437326,0.07104061,0.11492383,0.006271329,0.0030637484,0.00008165382,0.00024928155,0.5462576],"genre_scores_gemma":[0.9616645,0.023100074,0.00217952,0.0025155358,0.00065676746,0.00012479982,0.000015036997,0.000043312906,0.009700439],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99447554,0.0010543208,0.0013614104,0.00051435677,0.0020043997,0.00058997585],"domain_scores_gemma":[0.9978067,0.0004605396,0.0007531806,0.00074475235,0.00010614189,0.00012865395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0126882065,0.00024190388,0.00035664314,0.00033259584,0.00048250525,0.0009205289,0.0020347687,0.000046762685,0.00012018325],"category_scores_gemma":[0.00016927689,0.0001370408,0.00016602446,0.0012046302,0.00010571864,0.0004596748,0.0006560206,0.0004406541,0.00011752007],"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":[0.00023246545,0.00009184355,0.00074898184,0.00026985368,0.0002522561,0.00010945963,0.00081908924,0.0001321454,0.0000044137505,0.13763115,0.043751232,0.8159571],"study_design_scores_gemma":[0.0014385316,0.0003948613,0.0067691393,0.00019120832,0.00017853941,0.000049677197,0.040014975,0.0036343152,0.0000050181898,0.022131676,0.9249094,0.00028261676],"about_ca_topic_score_codex":0.000028413953,"about_ca_topic_score_gemma":0.00018012518,"teacher_disagreement_score":0.88115823,"about_ca_system_score_codex":0.0001788249,"about_ca_system_score_gemma":0.000027055676,"threshold_uncertainty_score":0.88766813},"labels":[],"label_agreement":null},{"id":"W3013218212","doi":"10.23889/ijpds.v4i2.1133","title":"Population Data BC: Supporting population data science in British Columbia.","year":2019,"lang":"en","type":"article","venue":"PubMed","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia; The Quebec Population Health Research Network","funders":"","keywords":"Data access; Computer science; Variety (cybernetics); Data science; Data governance; Data quality; Identifier; Population; Linkage (software); Linked data; Record linkage; Data management; Process (computing); Database; World Wide Web; Business; Service (business)","score_opus":0.28120928523712746,"score_gpt":0.41126158589052864,"score_spread":0.13005230065340118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013218212","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":[0.9941729,0.000015774436,0.00030015732,0.0004656349,0.0009856627,0.0010191007,0.00043012408,0.00004510407,0.0025655862],"genre_scores_gemma":[0.99412733,0.0000066859016,0.0005881706,0.00024646352,0.000058985464,0.000040475683,0.0023117943,0.000007030857,0.00261304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99531996,0.00016541181,0.0008642237,0.0013058464,0.0018373283,0.0005072337],"domain_scores_gemma":[0.9954697,0.0002469458,0.00037714228,0.003710012,0.00008035678,0.00011585831],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.022030506,0.00006731795,0.00022291813,0.00020448427,0.00017729502,0.0029382112,0.0049122144,0.00004153856,0.000331026],"category_scores_gemma":[0.008346939,0.000093459515,0.000016014097,0.0015291823,0.00007277556,0.007736121,0.004169266,0.00010420542,0.0001666357],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015610406,0.000023966746,0.5826125,0.0000048731013,0.0000011321541,0.0000025601253,0.000011969668,0.000017183287,7.8457435e-7,0.000118356525,0.007094022,0.41011107],"study_design_scores_gemma":[0.0002160199,0.0000032939977,0.9708968,0.000009030001,0.000004715321,0.0000017683191,0.00025614048,0.008206179,3.5537846e-7,0.0033946042,0.01688833,0.00012280751],"about_ca_topic_score_codex":0.15804575,"about_ca_topic_score_gemma":0.3494828,"teacher_disagreement_score":0.40998825,"about_ca_system_score_codex":0.000086453445,"about_ca_system_score_gemma":0.00003882686,"threshold_uncertainty_score":0.9992669},"labels":[],"label_agreement":null},{"id":"W3015809928","doi":"10.1016/j.knosys.2020.105881","title":"A situation refinement model for complex event processing","year":2020,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Event (particle physics); Process mining; Complex event processing; Process (computing); Context (archaeology); Data mining; Set (abstract data type); Task (project management); Domain (mathematical analysis); Domain knowledge; Artificial intelligence; Work in process; Programming language; Business process management","score_opus":0.4712097033115339,"score_gpt":0.45519512028276765,"score_spread":0.01601458302876624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015809928","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":[0.0009663688,0.00033865642,0.98880225,0.0043325094,0.00031360885,0.001209625,0.00013992793,0.000113483424,0.0037835622],"genre_scores_gemma":[0.9919574,8.9693697e-7,0.0041168574,0.0009726715,0.00025603693,0.00031200884,0.00014620871,0.000018073075,0.0022198316],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686337,0.00025482307,0.0010038004,0.0006448077,0.0009478721,0.00028530508],"domain_scores_gemma":[0.9979711,0.00037664405,0.0003818176,0.0004950169,0.0005844844,0.00019092465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036219116,0.00018155064,0.00037854005,0.00015244474,0.00026396237,0.00047679004,0.0007226858,0.00005698707,0.00005524617],"category_scores_gemma":[0.0010845918,0.00014430391,0.000142906,0.0005623882,0.000041250387,0.00024371629,0.00013232503,0.00006738294,0.0003657092],"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":[0.0003135832,0.0006009515,0.00013461396,0.0016576231,0.000055868,0.0000027963279,0.008396366,0.3069255,0.0027888499,0.018304566,0.5304862,0.13033308],"study_design_scores_gemma":[0.00076492986,0.0000858491,0.000035474102,0.00006111643,0.000020520043,1.6534933e-7,0.0008775129,0.8115871,0.00007456634,0.0005753787,0.18576545,0.00015194318],"about_ca_topic_score_codex":0.000016706132,"about_ca_topic_score_gemma":0.000081187776,"teacher_disagreement_score":0.99099106,"about_ca_system_score_codex":0.00010150673,"about_ca_system_score_gemma":0.00022797943,"threshold_uncertainty_score":0.58845425},"labels":[],"label_agreement":null},{"id":"W3016677020","doi":"10.1109/access.2020.2988120","title":"Sampling for Big Data Profiling: A Survey","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":32,"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":"National Natural Science Foundation of China","keywords":"Big data; Profiling (computer programming); Computer science; Data mining; Metadata; Data science; World Wide Web","score_opus":0.9190001080756124,"score_gpt":0.5835216452442223,"score_spread":0.33547846283139005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016677020","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":[0.02941288,0.00005265144,0.9578327,0.0052239015,0.0024973196,0.00069664005,0.0032370042,0.00008345741,0.0009634763],"genre_scores_gemma":[0.9820813,0.000018092753,0.0057961303,0.00892619,0.0014874703,0.00004579995,0.0011368676,0.000022483418,0.00048564465],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99765104,0.00018138123,0.0004838168,0.0007543503,0.0007075651,0.00022185026],"domain_scores_gemma":[0.99619275,0.0019326183,0.00017632112,0.0013842206,0.00018651295,0.00012755363],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0061719646,0.00009752527,0.00021824925,0.000070661285,0.00012907104,0.0011412497,0.005399233,0.00003534901,0.000045391],"category_scores_gemma":[0.010144954,0.000075241114,0.00003934333,0.00069184776,0.000038784194,0.0011105647,0.0014476256,0.00007209623,0.00019756737],"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":[0.00021461058,0.000088799505,0.015351726,0.00007531729,0.000054928863,0.000004175305,0.00028140142,0.00031322372,0.00029697543,0.0015154196,0.70992416,0.27187926],"study_design_scores_gemma":[0.0006323175,0.00006245152,0.012177867,0.0000103538905,0.000022987308,3.8497143e-7,0.00031091415,0.010895087,0.0019233391,0.012527914,0.9611356,0.00030077124],"about_ca_topic_score_codex":0.00020230394,"about_ca_topic_score_gemma":0.00043169004,"teacher_disagreement_score":0.9526684,"about_ca_system_score_codex":0.0000069996518,"about_ca_system_score_gemma":0.00006302812,"threshold_uncertainty_score":0.99998206},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"medium"}],"label_agreement":"split"},{"id":"W3023802345","doi":"10.1093/jamia/ocaa031","title":"Assessment of the Nursing Quality Indicators for Reporting and Evaluation (NQuIRE) database using a data quality index","year":2020,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Registered Nurses' Association of Ontario","funders":"Government of Ontario","keywords":"Data quality; Database; Quality (philosophy); Metric (unit); Index (typography); Computer science; Quality management; Data mining; Operations management; Engineering; World Wide Web","score_opus":0.46353160777092506,"score_gpt":0.5916964321350855,"score_spread":0.12816482436416043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023802345","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":[0.80817705,0.000013637785,0.17924695,0.011609128,0.00035393983,0.00033163856,0.00012779798,0.0000034457032,0.0001364268],"genre_scores_gemma":[0.9887143,0.000013674745,0.008449571,0.0026658175,0.00012973424,0.0000014430957,0.00001703251,0.000004058621,0.000004391711],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9869705,0.0016207378,0.0046148314,0.00013548954,0.0064908187,0.00016764343],"domain_scores_gemma":[0.9537769,0.0033057164,0.04087559,0.0009580335,0.00087834493,0.00020539433],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.089751706,0.000091164846,0.00052840105,0.00010119332,0.00021869657,0.00015488632,0.0015589418,0.000050162944,0.000017221404],"category_scores_gemma":[0.15903747,0.00004992834,0.00014322996,0.0009450057,0.00025613635,0.00093032565,0.0007735702,0.0003521262,2.669859e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012224793,0.00030274328,0.54464704,0.00022409436,0.00045614544,5.879256e-7,0.010784496,0.0015669904,0.0003056111,0.0026908093,0.023301473,0.41559774],"study_design_scores_gemma":[0.0007990782,0.00007017395,0.49085835,0.00020008908,0.00022852933,0.000004331113,0.016522747,0.48700228,0.000046532212,0.002577824,0.0015831125,0.00010697277],"about_ca_topic_score_codex":0.00008659442,"about_ca_topic_score_gemma":0.000021143482,"teacher_disagreement_score":0.48543528,"about_ca_system_score_codex":0.0003491955,"about_ca_system_score_gemma":0.00094466,"threshold_uncertainty_score":0.93729216},"labels":[],"label_agreement":null},{"id":"W3023807074","doi":"10.1002/cpe.5746","title":"Data linking over RDF knowledge graphs: A survey","year":2020,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","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":"Université du Québec à Chicoutimi; Université du Québec à Montréal","funders":"","keywords":"Computer science; Matching (statistics); Relation (database); Context (archaeology); Process (computing); Task (project management); RDF; Data science; Asset (computer security); Information retrieval; Object (grammar); Data mining; Semantic Web; Artificial intelligence; Mathematics; Programming language","score_opus":0.48924196060170927,"score_gpt":0.5236692874574922,"score_spread":0.034427326855782925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023807074","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":[0.54419494,0.015092778,0.4179058,0.011459027,0.0017209745,0.00068648317,0.0005104198,0.0001796581,0.008249918],"genre_scores_gemma":[0.99481225,0.0007012231,0.0009686161,0.0032759698,0.000050298295,0.000006697563,0.00013715147,0.000004119412,0.000043700584],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99763507,0.0005720825,0.00045154185,0.00072433625,0.00046495564,0.00015202476],"domain_scores_gemma":[0.9959857,0.0030152346,0.00025599072,0.0003675308,0.00021129669,0.0001642744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026599877,0.00012024601,0.00018546713,0.00006487325,0.00027209258,0.0006907744,0.00061538996,0.000038606944,0.00006426466],"category_scores_gemma":[0.0070973956,0.00010183647,0.000015925794,0.00061495224,0.00017536373,0.0031298525,0.00088126166,0.000139744,0.00007519533],"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":[0.00018365636,0.000202034,0.0134543395,0.00006857319,0.00004636435,0.000021380516,0.074735574,0.000033964316,0.000045469675,0.044468615,0.048823185,0.81791687],"study_design_scores_gemma":[0.0008323353,0.00020239098,0.034524303,0.000045430348,0.000039928986,0.000013588803,0.026141822,0.115000986,0.000013583182,0.008601109,0.81415105,0.00043349786],"about_ca_topic_score_codex":0.00007491941,"about_ca_topic_score_gemma":0.000034249762,"teacher_disagreement_score":0.81748337,"about_ca_system_score_codex":0.0000036391364,"about_ca_system_score_gemma":0.00004937831,"threshold_uncertainty_score":0.8496758},"labels":[],"label_agreement":null},{"id":"W3027407410","doi":"10.1108/rmj-09-2019-0055","title":"Natural language processing and machine learning as practical toolsets for archival processing","year":2020,"lang":"en","type":"article","venue":"Records Management Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":39,"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 Saskatchewan","funders":"","keywords":"Workflow; Artificial intelligence; Computer science; Machine learning; Implementation; Interoperability; USable; Natural language processing; Originality; Software engineering; Database; World Wide Web","score_opus":0.1476724865815801,"score_gpt":0.43580338208965674,"score_spread":0.28813089550807663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3027407410","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":[0.061283544,0.0042524342,0.7740122,0.08171159,0.0012045073,0.0020157476,0.00004105868,0.00034862632,0.07513027],"genre_scores_gemma":[0.93303454,0.00024347586,0.055843703,0.0045098285,0.0006453341,0.000021148699,0.000026838326,0.00003427298,0.0056408285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99686843,0.0002756636,0.00070416,0.0005451378,0.0011853828,0.0004212474],"domain_scores_gemma":[0.99854267,0.00035883128,0.0005202235,0.00017033333,0.00012851904,0.00027945364],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0036444247,0.00020625105,0.00031215907,0.00023176325,0.0006672253,0.0022254623,0.0005468421,0.00003150825,0.00013659219],"category_scores_gemma":[0.0026444132,0.00015628918,0.000109658184,0.00041270524,0.00007160268,0.0013068655,0.00054006826,0.0005811941,0.000064994245],"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":[0.0002661269,0.00004857598,0.00036508378,0.00017572012,0.00005030523,0.0001667946,0.0014464036,0.000035511915,0.000041297502,0.0025529936,0.008066369,0.9867848],"study_design_scores_gemma":[0.0029576356,0.0007704983,0.0031164794,0.00027874674,0.00026562123,0.0003363569,0.020943975,0.22363535,0.00006814349,0.0432634,0.70358586,0.00077793206],"about_ca_topic_score_codex":0.000005315168,"about_ca_topic_score_gemma":0.0000056925005,"teacher_disagreement_score":0.98600686,"about_ca_system_score_codex":0.00003692517,"about_ca_system_score_gemma":0.000057102257,"threshold_uncertainty_score":0.99881035},"labels":[],"label_agreement":null},{"id":"W3033222122","doi":"","title":"Improving and assessing data quality of knowledge graphs","year":2020,"lang":"en","type":"dissertation","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Vlaamse regering; Universiteit Gent; European Commission; Fonds Wetenschappelijk Onderzoek; Agentschap Innoveren en Ondernemen","keywords":"Knowledge graph; Data science; Computer science; Quality (philosophy); Data quality; Information retrieval; Data mining; Natural language processing; Engineering; Epistemology; Operations management; Philosophy","score_opus":0.24364253656691043,"score_gpt":0.4041145478195157,"score_spread":0.1604720112526053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033222122","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":[0.70410496,0.019032482,0.04005524,0.0031632977,0.006288181,0.0044376752,0.011181981,0.0012015724,0.2105346],"genre_scores_gemma":[0.8147139,0.14135952,0.0033707025,0.0004132176,0.00031278262,8.1955505e-7,0.011138228,0.0001440943,0.028546719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9925716,0.0013684919,0.0011073328,0.002294987,0.002054667,0.00060294586],"domain_scores_gemma":[0.99319273,0.001312529,0.002265897,0.002015423,0.00065854064,0.00055485964],"candidate_categories":["metaepi_narrow","bibliometrics","open_science"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0038250033,0.00061723264,0.0012317466,0.03776136,0.0006858157,0.00028965584,0.0066965036,0.0008823823,0.00014837155],"category_scores_gemma":[0.00052706996,0.0007052202,0.00058877334,0.041974064,0.00056764745,0.0039672763,0.0035681338,0.0015598458,0.000033336797],"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":[0.0025670433,0.0010419165,0.071412325,0.0034563015,0.0026469775,0.0003436039,0.0070049395,0.00001560196,0.0039002113,0.49460837,0.33583987,0.07716283],"study_design_scores_gemma":[0.0026289464,0.00015085514,0.083587565,0.0005122473,0.0014503534,0.0000022532568,0.0791741,0.00052805815,0.0001605772,0.007950171,0.82228273,0.0015721216],"about_ca_topic_score_codex":0.0010125363,"about_ca_topic_score_gemma":0.00045910952,"teacher_disagreement_score":0.48665822,"about_ca_system_score_codex":0.000088471475,"about_ca_system_score_gemma":0.00031691752,"threshold_uncertainty_score":0.9995399},"labels":[],"label_agreement":null},{"id":"W3035096436","doi":"","title":"A comparison of machine learning classifiers for use on historical record linkage","year":2020,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linkage (software); Artificial intelligence; Record linkage; Machine learning; Computer science; Biology; Sociology; Genetics; Demography","score_opus":0.19990060368948404,"score_gpt":0.3669767055172541,"score_spread":0.16707610182777005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035096436","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":[0.7853149,0.0013894059,0.13255,0.027443333,0.00836871,0.0047259,0.0016831049,0.00034954728,0.038175102],"genre_scores_gemma":[0.9266254,0.00011716233,0.0024411306,0.000080020254,0.00006067954,5.6931043e-7,0.0007512813,0.000017073293,0.069906704],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977079,0.00034412203,0.00044624184,0.0004224589,0.0009217185,0.00015753519],"domain_scores_gemma":[0.9960592,0.001867681,0.0011713365,0.00055889384,0.00026362788,0.000079260666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013986274,0.0001654694,0.00066948606,0.0002859717,0.00028952447,0.000041506413,0.001461509,0.00017020326,0.00017467942],"category_scores_gemma":[0.0014804004,0.00014331233,0.0003849295,0.00050038955,0.00007812631,0.00020703663,0.00018313387,0.00042788876,0.000063351836],"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":[0.011247257,0.0007803099,0.0038795997,0.00092294125,0.00069680216,0.000025173646,0.041604627,0.00072924653,0.0066768047,0.01949417,0.6955244,0.21841869],"study_design_scores_gemma":[0.0006867667,0.00073350675,0.013263877,0.000068467954,0.00030543795,1.3783784e-7,0.03359781,0.010130687,0.000071851435,0.0011595356,0.93975365,0.00022828038],"about_ca_topic_score_codex":0.0013900046,"about_ca_topic_score_gemma":0.0014333267,"teacher_disagreement_score":0.24422926,"about_ca_system_score_codex":0.00014189357,"about_ca_system_score_gemma":0.00006624003,"threshold_uncertainty_score":0.5844107},"labels":[],"label_agreement":null},{"id":"W3036298035","doi":"10.18438/eblip29746","title":"Researchers at Arab Universities Hold Positive Views on Research Data Management and Data Sharing","year":2020,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data sharing; Data management; Metadata; Data management plan; Confidentiality; Publishing; Research data; Scholarly communication; Psychology; Medical education; World Wide Web; Computer science; Political science; Medicine; Data curation; Alternative medicine","score_opus":0.6510536390123486,"score_gpt":0.5121208040241152,"score_spread":0.1389328349882334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036298035","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005705541,0.0015311417,0.008887842,0.850152,0.00015800295,0.001472649,0.0013734011,0.00014126091,0.13057812],"genre_scores_gemma":[0.23774646,0.039431937,0.03856745,0.6553395,0.0004459559,0.000054675373,0.009543214,0.0000552096,0.018815618],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955555,0.0011564423,0.000501124,0.0007459192,0.0017818017,0.00025917045],"domain_scores_gemma":[0.98903984,0.007898561,0.0002830976,0.0024037533,0.000096179516,0.0002785537],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.012870563,0.00011951344,0.00015008566,0.00037838548,0.00056889554,0.0024792112,0.003475848,0.000045365203,0.00040358427],"category_scores_gemma":[0.006832527,0.00010028576,0.00001303757,0.000991042,0.00022042793,0.29629874,0.013309618,0.00037009097,0.0005144771],"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":[0.0023076497,0.000048002625,0.00020818276,0.0002458728,0.00005910757,0.000057754172,0.0019170172,0.000109954286,0.0000059828603,0.4284349,0.50519615,0.061409432],"study_design_scores_gemma":[0.0002962622,0.00016763336,0.0027386833,0.00016338033,0.000019998504,0.0000024032922,0.023350738,0.029519003,0.00005031688,0.00042391184,0.94314736,0.0001203362],"about_ca_topic_score_codex":0.000021141921,"about_ca_topic_score_gemma":4.3202908e-7,"teacher_disagreement_score":0.43795118,"about_ca_system_score_codex":0.000027381186,"about_ca_system_score_gemma":0.00010362636,"threshold_uncertainty_score":0.9985563},"labels":[],"label_agreement":null},{"id":"W3040360098","doi":"10.1017/ssh.2020.15","title":"Selection Bias Encountered in the Systematic Linking of Historical Census Records","year":2020,"lang":"en","type":"article","venue":"Social Science History","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Francis Xavier University; University of Guelph","funders":"","keywords":"Census; Selection bias; Matching (statistics); Sample (material); Population; Selection (genetic algorithm); Sampling bias; Econometrics; Statistics; Information bias; Genealogy; Geography; Sample size determination; Computer science; Sociology; Economics; History; Demography; Mathematics; Artificial intelligence","score_opus":0.44764715922640047,"score_gpt":0.3994208451867887,"score_spread":0.04822631403961175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040360098","genre_codex":"other","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":[0.4078337,0.0039241896,0.025697233,0.057292283,0.026669942,0.005961255,0.000083117215,0.0004752378,0.47206303],"genre_scores_gemma":[0.9980163,0.0000038193934,0.00013032854,0.0012367137,0.00015141531,0.000012644755,8.7839163e-7,0.0000028828329,0.00044500176],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959419,0.0006226016,0.00066886586,0.00036583815,0.002192034,0.00020875986],"domain_scores_gemma":[0.9986672,0.0004683777,0.00041640722,0.0002178299,0.00017509655,0.00005509532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012340084,0.00007609107,0.0002761341,0.00021204355,0.00027059982,0.00007026278,0.0015411489,0.000043062544,0.00005143511],"category_scores_gemma":[0.0047429865,0.00005155679,0.00008524855,0.0020122796,0.00038255018,0.0004050183,0.0001355333,0.00015582668,0.00003879177],"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":[0.00012042562,0.00045272044,0.004054192,0.0024884036,0.000019989757,0.0000261571,0.33736902,0.0000343899,0.0036205829,0.13283126,0.4889678,0.030015025],"study_design_scores_gemma":[0.0006617587,0.00039049226,0.015297723,0.0004163282,0.0000649799,0.0000047604435,0.047673408,0.0036988186,0.00006300448,0.012521487,0.9186612,0.0005460357],"about_ca_topic_score_codex":0.00034820475,"about_ca_topic_score_gemma":0.0001860302,"teacher_disagreement_score":0.5901826,"about_ca_system_score_codex":0.0019034657,"about_ca_system_score_gemma":0.00024224316,"threshold_uncertainty_score":0.56781405},"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":"W3043650557","doi":"10.5220/0009820201930199","title":"Toward a New Quality Measurement Model for Big Data","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Quality (philosophy); Big data; Data modeling; Data science; Data mining; Database","score_opus":0.964848145575868,"score_gpt":0.5473252033427349,"score_spread":0.417522942233133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043650557","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":[0.000058695954,0.000042013053,0.91830343,0.072986454,0.00027337356,0.0003674618,0.00034139596,0.00006602551,0.007561162],"genre_scores_gemma":[0.7609846,0.000035177043,0.13229387,0.082435414,0.001563054,0.00004639029,0.00034122335,0.00003068843,0.022269571],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960223,0.00012155497,0.0006907356,0.00080286135,0.0021458159,0.0002167712],"domain_scores_gemma":[0.9973475,0.00027928018,0.00014194209,0.0017228897,0.00021590629,0.00029250985],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009010759,0.0001087489,0.0002509924,0.000043507145,0.000072350966,0.0003391762,0.0027622345,0.000031829004,0.00020247002],"category_scores_gemma":[0.008439453,0.000076277705,0.00007652624,0.00029661824,0.000026639153,0.00049184513,0.001478431,0.000051552026,0.00043747475],"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":[0.000050183833,0.00003133888,0.000011331047,0.000014217679,0.00001873488,2.9055485e-7,0.0005829118,0.00027354067,0.000054156146,0.026196975,0.8092211,0.16354522],"study_design_scores_gemma":[0.0005159665,0.000034445606,0.00006798527,0.0000025527295,0.000015860984,7.14519e-8,0.0009324428,0.23572916,0.000072645475,0.067653894,0.69483703,0.00013792883],"about_ca_topic_score_codex":0.0002608069,"about_ca_topic_score_gemma":0.00057998067,"teacher_disagreement_score":0.78600955,"about_ca_system_score_codex":0.000022617267,"about_ca_system_score_gemma":0.00021340208,"threshold_uncertainty_score":0.99991286},"labels":[],"label_agreement":null},{"id":"W3046273131","doi":"10.29173/jchla29436","title":"Implementing a Three-Tiered Service Model for Knowledge Syntheses at an Academic Teaching Hospital","year":2020,"lang":"en","type":"article","venue":"Journal of the Canadian Health Libraries Association / Journal de l Association de bilbiothèques de la santé du Canada","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto","funders":"","keywords":"Publishing; Service model; Service (business); Computer science; Knowledge management; Control (management); Engineering management; World Wide Web; Data science; Business; Engineering; Political science","score_opus":0.06125921148517065,"score_gpt":0.3562460078358835,"score_spread":0.29498679635071284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046273131","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":[0.42307654,0.016598811,0.0360956,0.51381737,0.0032948174,0.0015591752,0.0034403855,0.0000870968,0.002030212],"genre_scores_gemma":[0.9436542,0.00091609295,0.0048972955,0.04778535,0.0020533858,0.000010505947,0.000018655632,0.000047817437,0.0006167178],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9907545,0.0034903293,0.0021120575,0.00029326952,0.0019057464,0.0014441127],"domain_scores_gemma":[0.9825479,0.007839248,0.006275835,0.00027659856,0.0012417644,0.0018186659],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031138297,0.00026315489,0.0006512544,0.00028242674,0.0027709133,0.0023143862,0.0019197601,0.0003503784,0.0001143217],"category_scores_gemma":[0.048866533,0.00021634094,0.0003113402,0.00057198375,0.000028682474,0.0024095424,0.00025400252,0.0015368644,0.0000024760843],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000067583744,0.000039836355,0.15941162,0.000052153926,0.0002962701,0.00001604195,0.01589531,0.0029096107,0.000017965356,0.0032100189,0.8125997,0.005483865],"study_design_scores_gemma":[0.001079533,0.00019638253,0.0390158,0.00015973387,0.00014584164,0.000088523484,0.0058215205,0.10627969,0.00004198867,0.023431225,0.82330626,0.0004334809],"about_ca_topic_score_codex":0.10817929,"about_ca_topic_score_gemma":0.8126264,"teacher_disagreement_score":0.70444715,"about_ca_system_score_codex":0.022595368,"about_ca_system_score_gemma":0.026882568,"threshold_uncertainty_score":0.9987213},"labels":[],"label_agreement":null},{"id":"W3046721769","doi":"10.3233/sji-200658","title":"A vision on future advanced data collection","year":2020,"lang":"en","type":"article","venue":"Statistical Journal of the IAOS","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":"Statistics Canada","funders":"","keywords":"Data collection; Metadata; Confidentiality; Big data; Computer science; Data science; Data governance; Data quality; Process (computing); Business; Knowledge management; Marketing; World Wide Web; Data mining; Computer security; Sociology","score_opus":0.2210306705076511,"score_gpt":0.470280161569638,"score_spread":0.24924949106198688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046721769","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":[0.00441365,0.0001396341,0.76628524,0.22084089,0.0035452468,0.0003414306,0.0008817638,0.000016644814,0.0035355245],"genre_scores_gemma":[0.9045196,0.00018109252,0.06920966,0.022803225,0.0019150431,0.0000018640948,0.000035731053,0.000023519999,0.0013102713],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973008,0.00037509084,0.0005391627,0.00020525663,0.001472121,0.000107572705],"domain_scores_gemma":[0.99782604,0.0009883032,0.0003441622,0.0005590375,0.00014413673,0.00013831357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001854718,0.0000698675,0.00018474925,0.000046269986,0.00013237144,0.00016341945,0.0017337145,0.000024888554,0.00039653576],"category_scores_gemma":[0.007497913,0.000035132805,0.000050561586,0.0004197298,0.00006217755,0.00033430348,0.0004931351,0.00025112653,0.00013993034],"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":[0.0004450563,0.0000636149,0.000021303907,0.000005339147,0.000019454787,0.000026750691,0.00017975754,0.00014294317,0.00011446393,0.024782315,0.7227824,0.25141665],"study_design_scores_gemma":[0.0008663097,0.0008457606,0.0056689503,0.000040379902,0.000045862696,0.000021093054,0.0010989797,0.007253422,0.000104481725,0.07423116,0.9097201,0.00010344969],"about_ca_topic_score_codex":0.0000022025556,"about_ca_topic_score_gemma":0.000009139095,"teacher_disagreement_score":0.90010595,"about_ca_system_score_codex":0.000020661484,"about_ca_system_score_gemma":0.00007509548,"threshold_uncertainty_score":0.8976244},"labels":[],"label_agreement":null},{"id":"W304693962","doi":"10.1007/978-3-319-13186-3_34","title":"Models for Distributed, Large Scale Data Cleaning","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data quality; Big data; Data mining; Dynamic data; Scale (ratio); Data stream mining; Variety (cybernetics); Distributed computing; Real-time computing; Database; Artificial intelligence","score_opus":0.17030871493081626,"score_gpt":0.3783480416925222,"score_spread":0.20803932676170592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W304693962","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":[0.0000068961504,0.000113402355,0.9917003,0.0012359926,0.0014657956,0.00052461843,0.0016688588,0.00006185108,0.0032223156],"genre_scores_gemma":[0.11544693,0.00007315075,0.8618183,0.0117376605,0.0023795227,0.00003391053,0.0024203502,0.00011426066,0.005975905],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937856,0.00006483463,0.0008874905,0.0023707757,0.002196784,0.0006945101],"domain_scores_gemma":[0.99253106,0.0022948973,0.00044392364,0.0042173583,0.0003420022,0.00017074417],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0112347435,0.00037889957,0.0006325504,0.0005654545,0.00041748886,0.0012241151,0.009130902,0.0002241517,0.0000734412],"category_scores_gemma":[0.0013189075,0.00030094179,0.00012152691,0.00047571553,0.00053736457,0.0009873674,0.0060809897,0.00041138465,0.00012148518],"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":[0.000018316954,0.00002938428,0.00001119032,0.000034145603,0.000010982955,0.000007752034,0.00034296268,0.0637655,0.0000026751834,0.09352476,0.0077119996,0.8345403],"study_design_scores_gemma":[0.00016336146,0.000036609963,0.0000055225573,0.00007115337,0.000008033521,0.000002526616,0.0000010843619,0.49455,0.000009837675,0.36852512,0.13640387,0.00022290797],"about_ca_topic_score_codex":0.000015650716,"about_ca_topic_score_gemma":0.0004927431,"teacher_disagreement_score":0.83431745,"about_ca_system_score_codex":0.00010703167,"about_ca_system_score_gemma":0.00019617124,"threshold_uncertainty_score":0.99994427},"labels":[],"label_agreement":null},{"id":"W3047731084","doi":"10.23889/ijpds.v5i2.1383","title":"Prospective data linkage to facilitate COVID-19 trials – A call to action","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 British Columbia; Institute for Work & Health; Process Simulations Limited (Canada); British Columbia Environmental and Occupational Health Research Network; University of Toronto","funders":"Medical Research Council","keywords":"Coronavirus disease 2019 (COVID-19); Linkage (software); Call to action; Record linkage; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); 2019-20 coronavirus outbreak; Clinical trial; Data science; Computer science; Business; Medicine; Outbreak; Biology; Virology; Marketing; Environmental health; Internal medicine; Disease; Infectious disease (medical specialty)","score_opus":0.8802420608172462,"score_gpt":0.6327254420537285,"score_spread":0.24751661876351772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047731084","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":[0.0075198244,0.00000958035,0.86405563,0.11138661,0.0034739235,0.0010337427,0.012256146,0.00004530521,0.00021922536],"genre_scores_gemma":[0.8836847,0.00003122626,0.06844719,0.040288433,0.002151767,0.00004777874,0.0034792665,0.000019493844,0.0018501598],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99262196,0.00031873884,0.0014299708,0.0013610531,0.003968605,0.00029964867],"domain_scores_gemma":[0.99399996,0.0014138996,0.00069541304,0.0016853554,0.0011253739,0.001079986],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031338584,0.00014820954,0.0003258152,0.00065902295,0.00058853265,0.0026617672,0.012075407,0.000034761382,0.00026853342],"category_scores_gemma":[0.18396075,0.0001154389,0.000069857575,0.0013766747,0.00009299644,0.007204645,0.0043573673,0.00016606803,0.00042940828],"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":[0.00090804923,0.00009584885,0.0040021306,0.00001039618,0.00007645728,0.000019091049,0.0022104238,0.009780368,0.001421906,0.008722223,0.8373232,0.13542993],"study_design_scores_gemma":[0.00070816267,0.00014407972,0.011700107,0.000015026118,0.000019655628,0.000017687893,0.00085943897,0.033319835,0.000052961426,0.008883944,0.9440779,0.00020118589],"about_ca_topic_score_codex":0.0004403982,"about_ca_topic_score_gemma":0.00046272684,"teacher_disagreement_score":0.87616485,"about_ca_system_score_codex":0.00033315623,"about_ca_system_score_gemma":0.00045637146,"threshold_uncertainty_score":0.99837357},"labels":[],"label_agreement":null},{"id":"W3080942770","doi":"10.2196/18920","title":"Secure Record Linkage of Large Health Data Sets: Evaluation of a Hybrid Cloud Model","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Australian Government","keywords":"Cloud computing; Custodians; Computer science; Identifier; Container (type theory); Overhead (engineering); Linkage (software); Record linkage; Database; Computer security; Software; Data mining; Distributed computing; Computer network; Operating system; Engineering","score_opus":0.3796766782781779,"score_gpt":0.5127085377994934,"score_spread":0.13303185952131552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080942770","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":[0.15477763,0.00022375816,0.7952019,0.032504044,0.0006592585,0.0020630518,0.0061242324,0.000091323156,0.008354819],"genre_scores_gemma":[0.9451664,0.00024569908,0.023655366,0.02870857,0.00016811838,0.00002770835,0.0019465988,0.000013928823,0.00006758179],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908849,0.00034241483,0.0023045007,0.00019391994,0.006034896,0.0002393458],"domain_scores_gemma":[0.99663967,0.0003671968,0.0010528137,0.0012312278,0.00035723415,0.00035187116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020043045,0.00010797697,0.0004479309,0.000101231824,0.000051706647,0.000044009972,0.0021148734,0.000065428685,0.0007054913],"category_scores_gemma":[0.0072111245,0.00007982163,0.00006150921,0.0004863146,0.00010187834,0.00083202514,0.0014634025,0.00025307716,0.000113035676],"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":[0.000032386695,0.00018775341,0.00004281156,0.0005465153,0.000037732363,0.0000010680939,0.015164593,0.00044090312,6.220446e-7,0.0050051515,0.7357562,0.24278423],"study_design_scores_gemma":[0.00075392023,0.000100913145,0.00002175915,0.00008066211,0.000019922016,9.196919e-7,0.0059011104,0.9041124,0.000010555596,0.005009208,0.083917834,0.000070786446],"about_ca_topic_score_codex":0.000013161873,"about_ca_topic_score_gemma":0.000027894479,"teacher_disagreement_score":0.9036715,"about_ca_system_score_codex":0.000027398391,"about_ca_system_score_gemma":0.00074486097,"threshold_uncertainty_score":0.8632911},"labels":[],"label_agreement":null},{"id":"W3081234131","doi":"10.48550/arxiv.2008.10549","title":"On sampling from data with duplicate records","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Waterloo","funders":"","keywords":"Computer science; Data deduplication; Sampling (signal processing); Data mining; Set (abstract data type); Task (project management); Complement (music); Mathematical proof; Data set; Process (computing); Sample (material); Algorithm; Database; Mathematics; Artificial intelligence","score_opus":0.6244679694520039,"score_gpt":0.32815989725208594,"score_spread":0.29630807219991795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081234131","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":[0.19770166,0.000027244801,0.773966,0.0023258778,0.0008703587,0.00058846694,0.0039599002,0.00025676208,0.020303698],"genre_scores_gemma":[0.99188995,0.00010980287,0.0020146342,0.0009804431,0.00015043106,7.465139e-7,0.0013637181,0.000024889647,0.0034653996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957086,0.00028648108,0.00038946164,0.0028583389,0.00046737943,0.00028978387],"domain_scores_gemma":[0.9921615,0.0012374962,0.0005057939,0.0057131876,0.00013500817,0.00024699894],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013386733,0.0003304889,0.00051157916,0.00024578202,0.0001743886,0.0004457552,0.0067960806,0.00017761167,0.0006677337],"category_scores_gemma":[0.0008432708,0.00028750644,0.00011040659,0.00078537996,0.00014923504,0.00049286016,0.009293856,0.0006649972,0.0019891334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023211685,0.0006121873,0.006199637,0.0001151558,0.0011611967,0.0015404017,0.00073003565,0.23543352,0.000028638231,0.5212761,0.20497231,0.025609601],"study_design_scores_gemma":[0.00076132396,0.00013459327,0.0036721579,0.00016056263,0.0002512955,5.8819205e-7,0.00085987087,0.102856755,0.00001678534,0.7549387,0.13558742,0.0007599114],"about_ca_topic_score_codex":0.0012807227,"about_ca_topic_score_gemma":0.0007045329,"teacher_disagreement_score":0.79418826,"about_ca_system_score_codex":0.000090776666,"about_ca_system_score_gemma":0.00014061067,"threshold_uncertainty_score":0.9999577},"labels":[],"label_agreement":null},{"id":"W3081840895","doi":"10.1029/2020gl088048","title":"Thank You to Our 2019 Peer Reviewers","year":2020,"lang":"en","type":"article","venue":"Geophysical Research Letters","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":17,"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 Calgary","funders":"","keywords":"Presentation (obstetrics); Reading (process); Library science; Rigour; Quality (philosophy); Peer review; Computer science; Political science; History; Engineering ethics; Data science; Public relations; Law; Medicine; Epistemology; Engineering","score_opus":0.39791782158928635,"score_gpt":0.5136762855153798,"score_spread":0.11575846392609346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081840895","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.046941876,0.000040479903,0.0041927206,0.9434158,0.0003466611,0.0006542766,0.000084431056,0.000054875018,0.0042688767],"genre_scores_gemma":[0.73754555,0.00005477625,0.0019506172,0.227039,0.0025216236,0.00011896264,0.00006323376,0.00004354433,0.030662678],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98973894,0.0009944494,0.0004487732,0.0009059977,0.0071210195,0.0007908471],"domain_scores_gemma":[0.9966982,0.00089850836,0.00005763173,0.0010539854,0.00055192196,0.0007397379],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008137881,0.00014935633,0.00034453528,0.00021077578,0.00020640319,0.0006115083,0.0023310473,0.000028382936,0.0002564785],"category_scores_gemma":[0.019844431,0.000109749664,0.00018008855,0.0021322775,0.0001092897,0.00042504925,0.001585779,0.00053517043,0.05297312],"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":[0.00006222361,0.000037728096,0.000039863182,0.000013705874,0.000013215756,0.000034753702,0.0005236295,0.000019827283,0.0029398634,0.0038189162,0.95608926,0.036407005],"study_design_scores_gemma":[0.00016407837,0.000132308,0.0027289304,0.000016780275,0.000004284317,2.1113726e-7,0.001142539,0.000096186624,0.00023728276,0.002475136,0.99285007,0.00015220193],"about_ca_topic_score_codex":0.0002789015,"about_ca_topic_score_gemma":0.000008583411,"teacher_disagreement_score":0.7163768,"about_ca_system_score_codex":0.000051054085,"about_ca_system_score_gemma":0.00005086308,"threshold_uncertainty_score":0.98841184},"labels":[],"label_agreement":null},{"id":"W3087826863","doi":"10.48550/arxiv.2009.12415","title":"A Big Data Lake for Multilevel Streaming Analytics","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Queen's University","funders":"Ontario Centres of Excellence","keywords":"Computer science; Big data; Analytics; Data warehouse; Data science; Data management; Scalability; Raw data; Volume (thermodynamics); Data analysis; Database; Unstructured data; Variety (cybernetics); Architecture; Business intelligence; Data mining","score_opus":0.7545566830413366,"score_gpt":0.3475097281097882,"score_spread":0.4070469549315484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087826863","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":[0.012161119,0.000020352853,0.9735736,0.0007990405,0.0012088249,0.0006785762,0.008738223,0.00011705331,0.002703191],"genre_scores_gemma":[0.9866648,0.00008754679,0.002695878,0.00047959888,0.0003260155,0.0000012584674,0.0017909849,0.00002387952,0.007930079],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963257,0.0002023548,0.0005249435,0.0022232963,0.00036779238,0.000355939],"domain_scores_gemma":[0.9936922,0.0011802912,0.0005492679,0.0040580607,0.00027743366,0.00024274271],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0021311175,0.0003126845,0.0005548364,0.0003764998,0.00019730796,0.00041639752,0.0062419088,0.00021663628,0.00012711772],"category_scores_gemma":[0.0027746456,0.00031557077,0.00024295287,0.000696949,0.00014416534,0.0004297606,0.011273142,0.0003858498,0.0002872203],"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":[0.0006156524,0.00077404577,0.0066569964,0.0007241739,0.0015161583,0.0008645057,0.0011633189,0.1695743,0.000024178404,0.30077448,0.32422465,0.1930875],"study_design_scores_gemma":[0.00060067733,0.000034765977,0.0012490596,0.00004736143,0.0002755703,3.8931847e-7,0.0010386955,0.60982764,0.0000063788784,0.116337895,0.27017185,0.0004097157],"about_ca_topic_score_codex":0.00014663198,"about_ca_topic_score_gemma":0.0020827332,"teacher_disagreement_score":0.97450364,"about_ca_system_score_codex":0.0000685432,"about_ca_system_score_gemma":0.00021609374,"threshold_uncertainty_score":0.99992967},"labels":[],"label_agreement":null},{"id":"W3088102886","doi":"10.31485/admindatahandbook.1.0","title":"Handbook on Using Administrative Data for Research and Evidence-based Policy","year":2020,"lang":"en","type":"book","venue":"Abdul Latif Jameel Poverty Action Lab eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Research data; Public administration; Business; Data science; Computer science; Data curation","score_opus":0.882626387677327,"score_gpt":0.5973062587538313,"score_spread":0.2853201289234958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088102886","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013977541,0.001763794,0.076543815,0.029576924,0.0023243055,0.010882266,0.01800173,0.00045219163,0.8603152],"genre_scores_gemma":[0.002178372,0.0002199299,0.0048084366,0.010877356,0.0019392427,0.0001303747,0.0011643162,0.00012507148,0.9785569],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9921223,0.000771016,0.0011323369,0.0021526166,0.0032127376,0.00060897286],"domain_scores_gemma":[0.9854297,0.00951629,0.00082212855,0.0030383216,0.0008070834,0.00038647736],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0067031356,0.0005093564,0.00080066395,0.0009644663,0.00083718466,0.001392023,0.0023901854,0.00046493285,0.00017506228],"category_scores_gemma":[0.009603073,0.00042371557,0.00016077251,0.00030285236,0.0006220916,0.0010172536,0.0014695284,0.0009444349,0.00025014498],"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":[0.0014063595,0.00007515549,0.000005081222,0.00032407086,0.00016287848,0.000021776723,0.00027524584,0.000028797449,0.00016913626,0.07647626,0.8419326,0.07912264],"study_design_scores_gemma":[0.00067676237,0.0007997597,0.000016323083,0.0011102086,0.000074790456,0.000003516419,0.00027553082,0.0060305456,0.00039417297,0.087855354,0.9023405,0.00042253736],"about_ca_topic_score_codex":0.0003561676,"about_ca_topic_score_gemma":0.00045294536,"teacher_disagreement_score":0.118241705,"about_ca_system_score_codex":0.00060500856,"about_ca_system_score_gemma":0.0032158028,"threshold_uncertainty_score":0.9998215},"labels":[],"label_agreement":null},{"id":"W3094404806","doi":"10.1145/3340531.3412173","title":"IoT Data Quality","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"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; Data science; Quality (philosophy); Data consistency; Consistency (knowledge bases); Data management; Benchmark (surveying); Data mining; Artificial intelligence; Database; Engineering","score_opus":0.9391081827859995,"score_gpt":0.6295491855445623,"score_spread":0.3095589972414372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094404806","genre_codex":"other","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":[0.010577662,0.000052899493,0.33324343,0.24114673,0.00043217858,0.00025228443,0.0006423914,0.00023921691,0.4134132],"genre_scores_gemma":[0.86902034,0.000009620867,0.017330486,0.092262596,0.00030603618,0.0000026607486,0.00020793172,0.000007795428,0.020852508],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99775845,0.00021483384,0.0004159579,0.0005143561,0.0009859076,0.00011050009],"domain_scores_gemma":[0.99745816,0.0005151807,0.00007610049,0.0017768382,0.000045043358,0.00012868435],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004825729,0.000050679668,0.00013145765,0.000023225855,0.00005145213,0.00025304337,0.0028186194,0.000016759832,0.005376844],"category_scores_gemma":[0.0061969683,0.000033428998,0.000024696603,0.0003723161,0.000038054022,0.00033883157,0.002248925,0.00004902218,0.0074615576],"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":[0.0000074960094,0.000016701943,0.00029303058,0.000002509153,0.0000052180976,0.0000017429379,0.00013713585,0.000003716507,0.00003070416,0.083615854,0.84018046,0.07570544],"study_design_scores_gemma":[0.00009724939,0.000011914419,0.0030625984,4.298209e-7,0.0000023613302,9.1005596e-8,0.0011113076,0.0018695799,0.000058916157,0.010911673,0.98281133,0.000062527506],"about_ca_topic_score_codex":0.00011932281,"about_ca_topic_score_gemma":0.00010641522,"teacher_disagreement_score":0.8584427,"about_ca_system_score_codex":0.0000030945034,"about_ca_system_score_gemma":0.000017540657,"threshold_uncertainty_score":0.9955324},"labels":[],"label_agreement":null},{"id":"W3094735162","doi":"10.2196/21811","title":"Developing a Standardized and Reusable Method to Link Distributed Health Plan Databases to the National Death Index: Methods Development Study Protocol","year":2020,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Perelman School of Medicine, University of Pennsylvania; University of Illinois at Urbana-Champaign; Hamilton Health Sciences Foundation; University of Washington; University of Pennsylvania; U.S. Department of Health and Human Services","keywords":"Medicine; Protocol (science); Database; National Death Index; Medical emergency; Computer science; Confidence interval; Alternative medicine","score_opus":0.8752735118553996,"score_gpt":0.7522096772877518,"score_spread":0.1230638345676478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094735162","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000011093324,3.4768405e-7,0.4418146,0.02778409,0.0000030783913,0.5300157,0.00020784127,0.00003930973,0.00012395765],"genre_scores_gemma":[0.000030997253,4.4885642e-8,0.3266701,0.0028310884,0.000079597776,0.670204,0.000024427321,0.000013642823,0.0001460787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98025167,0.009645324,0.0014753744,0.0014464636,0.006247186,0.0009339885],"domain_scores_gemma":[0.9935613,0.0032514727,0.00024116292,0.0008272054,0.00132962,0.00078918453],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08296224,0.00026168692,0.0005619547,0.00044366543,0.0012492465,0.0014184564,0.0022320752,0.000046133944,0.00016374903],"category_scores_gemma":[0.015525237,0.0001630787,0.000042634823,0.0032225077,0.0000680324,0.000458329,0.004802222,0.00056941726,0.00018205239],"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":[0.0052706636,0.0008619828,0.0055641644,0.00062299555,0.00016046982,0.000025458687,0.017361732,0.00028528186,0.000115235336,0.015063189,0.3870076,0.5676612],"study_design_scores_gemma":[0.0017473232,0.0010264576,0.009495918,0.00027317417,7.629183e-7,0.0000014122036,0.0028630055,0.00024604966,0.00050484674,0.0016510438,0.9819736,0.00021642717],"about_ca_topic_score_codex":0.000113707574,"about_ca_topic_score_gemma":0.0002567562,"teacher_disagreement_score":0.594966,"about_ca_system_score_codex":0.0004583468,"about_ca_system_score_gemma":0.0023735291,"threshold_uncertainty_score":0.9996182},"labels":[],"label_agreement":null},{"id":"W3095626157","doi":"","title":"Author Name Disambiguation Using Co-training","year":2020,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Windsor","keywords":"Training (meteorology); Computer science; Artificial intelligence; Natural language processing; Linguistics; Philosophy; Geography","score_opus":0.43159331807673795,"score_gpt":0.4039498218923242,"score_spread":0.02764349618441375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095626157","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":[0.97028583,0.000042374144,0.015656946,0.008524045,0.00021143092,0.00026011237,0.00018035519,0.000091537026,0.004747359],"genre_scores_gemma":[0.99162245,0.0000036821755,0.0047840825,0.0007559675,0.00009011724,1.657016e-7,0.000060793656,0.000015855034,0.002666875],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959335,0.00058735587,0.00045816562,0.0007726012,0.0018555468,0.0003928662],"domain_scores_gemma":[0.9977614,0.0004026598,0.00051453075,0.0006855845,0.00024665412,0.00038912456],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00395188,0.00020626059,0.0004557061,0.00030756427,0.0006978037,0.0001911063,0.0016442363,0.00016774166,0.0026678962],"category_scores_gemma":[0.0020743012,0.00023307864,0.0002502502,0.0010744958,0.00029411432,0.002090724,0.00075233146,0.00034999996,0.0012210379],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033263362,0.0008986955,0.35689193,0.00043347976,0.0010020758,0.0006149143,0.2113338,0.0057061077,0.091785915,0.04132919,0.063740395,0.22293715],"study_design_scores_gemma":[0.0047826525,0.0005711536,0.4239564,0.0001843747,0.00039244443,0.000022497026,0.116642885,0.015954377,0.0029414808,0.018160338,0.4147173,0.0016741311],"about_ca_topic_score_codex":0.00008017978,"about_ca_topic_score_gemma":0.00008881117,"teacher_disagreement_score":0.35097688,"about_ca_system_score_codex":0.00011070711,"about_ca_system_score_gemma":0.00011872702,"threshold_uncertainty_score":0.9995566},"labels":[],"label_agreement":null},{"id":"W3106195149","doi":"10.1093/jamia/ocaa225","title":"Assessing the quality of clinical and administrative data extracted from hospitals: the General Medicine Inpatient Initiative (GEMINI) experience","year":2020,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Sunnybrook Health Science Centre; Trillium Health Centre; Institute for Clinical Evaluative Sciences; Health Sciences Centre; Mount Sinai Hospital; University of Toronto; University Health Network; Queen's University; St. Michael's Hospital","funders":"University of Toronto","keywords":"Data quality; Data extraction; Computer science; Gold standard (test); Quality (philosophy); Quality management; Data collection; Data mining; Database; Medicine; MEDLINE; Statistics; Operations management; Mathematics","score_opus":0.540661436719735,"score_gpt":0.5948575964308802,"score_spread":0.05419615971114522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106195149","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":[0.9196126,0.000046432295,0.009087991,0.06996868,0.0004803486,0.00016437205,0.00010314358,0.0000039312863,0.0005325031],"genre_scores_gemma":[0.98162794,0.00021902336,0.0014483677,0.01626003,0.00041414076,0.0000018082504,0.000014506725,0.0000033903377,0.0000108124505],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98846877,0.002604991,0.0039223665,0.00014229027,0.0047058454,0.00015572237],"domain_scores_gemma":[0.9619874,0.02015221,0.015868029,0.00088267546,0.0008382773,0.00027142512],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.026948579,0.00011962598,0.0007019647,0.000036335165,0.00020214249,0.000225763,0.002738889,0.00006304524,0.00007633808],"category_scores_gemma":[0.14915156,0.000047289665,0.00012036622,0.00066925626,0.0013355326,0.0012582688,0.0010172998,0.00071504543,0.000003145027],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025694582,0.00028466078,0.34939635,0.000026166676,0.00085094,0.00000566268,0.15059644,0.00004194603,0.000042719526,0.0016291363,0.14034349,0.35652554],"study_design_scores_gemma":[0.00071544637,0.00036373388,0.80926126,0.00008574195,0.000103478946,0.0000020129287,0.1616699,0.015562645,0.000032071865,0.0022082913,0.009897513,0.0000979286],"about_ca_topic_score_codex":0.00014938737,"about_ca_topic_score_gemma":0.000025115865,"teacher_disagreement_score":0.45986488,"about_ca_system_score_codex":0.00004691573,"about_ca_system_score_gemma":0.00036450604,"threshold_uncertainty_score":0.9339893},"labels":[],"label_agreement":null},{"id":"W3107627972","doi":"10.1145/3397536.3422227","title":"NUMA-Aware Spatio-Textual Similarity Join","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 New Brunswick","funders":"","keywords":"Joins; Join (topology); Similarity (geometry); Computer science; Information retrieval; Resource (disambiguation); Artificial intelligence; Programming language; Mathematics; Image (mathematics)","score_opus":0.35557215213223436,"score_gpt":0.4236913501634345,"score_spread":0.06811919803120015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107627972","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":[0.025268825,0.000031962383,0.53928596,0.14506838,0.000467895,0.0005085755,0.00031060993,0.00038253015,0.28867525],"genre_scores_gemma":[0.9680378,0.0000044097765,0.0015877504,0.024668224,0.00012179892,0.0000040947434,0.00004079998,0.000005055506,0.0055300747],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99765927,0.00016343631,0.00043378587,0.00044489044,0.0011212707,0.00017735643],"domain_scores_gemma":[0.9987727,0.00035424053,0.000087374734,0.0005026424,0.00010232735,0.0001807466],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015116838,0.000092710456,0.00018410773,0.00005189519,0.00010690068,0.00032601156,0.0008542916,0.00003941698,0.014086373],"category_scores_gemma":[0.0019632608,0.00006619304,0.000077301396,0.00047533683,0.000052441363,0.00042854183,0.0005401359,0.00009651194,0.0070369593],"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":[0.000013731143,0.000039117163,0.0011291853,0.0000049042997,0.000009025284,0.000009510369,0.0004941489,0.000041129268,0.000011761416,0.07936914,0.8801362,0.038742132],"study_design_scores_gemma":[0.00026450906,0.00006763776,0.007412017,0.0000019959589,0.000007081201,4.87147e-7,0.0044893012,0.006290413,0.00020460632,0.014604708,0.9664995,0.00015776213],"about_ca_topic_score_codex":0.00013384098,"about_ca_topic_score_gemma":0.00039113653,"teacher_disagreement_score":0.942769,"about_ca_system_score_codex":0.000010912814,"about_ca_system_score_gemma":0.000027725815,"threshold_uncertainty_score":0.99373615},"labels":[],"label_agreement":null},{"id":"W3110853613","doi":"10.23889/ijpds.v5i5.1556","title":"Using the Canadian Institute for Health Information’s Information Quality Framework to Support Integration and Utilization of Complex, Multi-Jurisdictional Data","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Institute for Health Information","funders":"","keywords":"Data quality; Information quality; Computer science; Documentation; Operationalization; Data science; Health informatics; Quality (philosophy); Information system; Data governance; Health care; Knowledge management; Business; Engineering","score_opus":0.7470190652398002,"score_gpt":0.5982658809769009,"score_spread":0.1487531842628993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110853613","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":[0.0023746141,0.000004835911,0.94617546,0.035328534,0.0014747399,0.0007024721,0.013902892,0.000010853793,0.000025598374],"genre_scores_gemma":[0.7562675,0.000015962038,0.21678853,0.01183522,0.000228413,0.000010085922,0.014842822,0.000004274627,0.000007203408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959131,0.00009819821,0.0014868075,0.0003222698,0.0019652543,0.00021436777],"domain_scores_gemma":[0.99555415,0.00031189213,0.0011158556,0.00074069697,0.0019522525,0.00032512977],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.010899685,0.00010847796,0.00017987181,0.0005869973,0.0011158132,0.001818835,0.0038506873,0.000043103963,0.000036888432],"category_scores_gemma":[0.016317794,0.00008216475,0.00003383815,0.00077708444,0.00018844237,0.019475495,0.00088411133,0.00012967679,0.000007710297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035966022,0.00006406775,0.008643672,0.000053382253,0.00007589806,2.7286657e-7,0.0076567093,0.01982592,0.00006454362,0.34678388,0.07204919,0.5444228],"study_design_scores_gemma":[0.000447135,0.0000800032,0.053987626,0.000030528303,0.000010887352,0.000009057008,0.0011615081,0.58153456,0.000009537071,0.0068732314,0.35573602,0.00011993319],"about_ca_topic_score_codex":0.013518417,"about_ca_topic_score_gemma":0.04181983,"teacher_disagreement_score":0.7538929,"about_ca_system_score_codex":0.0002597967,"about_ca_system_score_gemma":0.0011104281,"threshold_uncertainty_score":0.9992174},"labels":[],"label_agreement":null},{"id":"W3111257782","doi":"10.23889/ijpds.v5i5.1542","title":"Evaluating PPRL Vs Clear Text Linkage with Real-World Data","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Linkage (software); Identifier; Genetic linkage; Computer science; Record linkage; Population; Hash function; Genetics; Biology; Gene; Medicine","score_opus":0.6781494335367946,"score_gpt":0.5956232882520471,"score_spread":0.08252614528474744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111257782","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":[0.22053093,0.000058493475,0.61741745,0.13417552,0.009065728,0.0015861957,0.010689627,0.00022736598,0.0062486785],"genre_scores_gemma":[0.89047265,0.000048910177,0.10118659,0.0036471733,0.001349901,0.000004667953,0.0024079892,0.000019081654,0.0008630148],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99222904,0.00015795705,0.000979,0.0011282427,0.0052021947,0.00030356034],"domain_scores_gemma":[0.9950277,0.0006903172,0.0009484146,0.0018951378,0.0011401039,0.0002982885],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.015254593,0.0001426015,0.00021705539,0.0004723427,0.00064017985,0.0030113002,0.014319866,0.000019732892,0.0002687066],"category_scores_gemma":[0.013013974,0.00010310984,0.000038492784,0.0014287152,0.00028332983,0.00974243,0.003914248,0.00022820961,0.00017284672],"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":[0.0021040763,0.00019235814,0.03925466,0.000017221846,0.00014639141,0.000053212654,0.000814227,0.00986361,0.0005750745,0.05210825,0.14764215,0.74722874],"study_design_scores_gemma":[0.0011130085,0.00044430664,0.06025486,0.00006856714,0.000042901516,0.000035497604,0.00070104335,0.51164925,0.000056756893,0.0068425187,0.4184654,0.00032590728],"about_ca_topic_score_codex":0.00036500295,"about_ca_topic_score_gemma":0.00092852104,"teacher_disagreement_score":0.7469028,"about_ca_system_score_codex":0.00009872331,"about_ca_system_score_gemma":0.00028034518,"threshold_uncertainty_score":0.9980237},"labels":[],"label_agreement":null},{"id":"W3112495257","doi":"10.23889/ijpds.v5i5.1630","title":"Using A Privacy Preserving Record Linkage to Facilitate an Ongoing Crosswalk Between Research and Health Administrative Databases","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Indoc Research; Ontario Brain Institute","funders":"","keywords":"Schema crosswalk; Record linkage; Computer science; Database; Data science; Medicine; Engineering; Transport engineering","score_opus":0.9620375251486527,"score_gpt":0.6997589936175305,"score_spread":0.26227853153112224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112495257","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":[0.55038255,0.000029195131,0.41243318,0.03141327,0.0007527528,0.00064069737,0.0042253565,0.000026434327,0.00009657463],"genre_scores_gemma":[0.8905129,0.000019975894,0.10703528,0.0011638659,0.00057413947,0.000004887301,0.00054840563,0.000008624085,0.00013192165],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99387455,0.00030454126,0.0009861472,0.0009948392,0.0034317377,0.00040820095],"domain_scores_gemma":[0.9958295,0.0008576331,0.00044397207,0.00084303867,0.0013327054,0.00069310213],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.021981489,0.00011791595,0.00021560787,0.0006036862,0.0013384413,0.0034561467,0.0053279195,0.00001976947,0.000057955593],"category_scores_gemma":[0.015780296,0.00010077675,0.000026879168,0.0010934761,0.00023583314,0.009811196,0.0037419193,0.00026150877,0.000018037264],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062090537,0.00029512882,0.29133326,0.0000806471,0.000113946706,0.000045312154,0.017799294,0.002245883,0.0020172326,0.032212608,0.044714972,0.6085208],"study_design_scores_gemma":[0.0012413814,0.0014323189,0.35350972,0.0003467447,0.000015435553,0.000047048117,0.008528743,0.17979741,0.00022448356,0.03845972,0.41580352,0.0005934722],"about_ca_topic_score_codex":0.0015172221,"about_ca_topic_score_gemma":0.00062790053,"teacher_disagreement_score":0.6079273,"about_ca_system_score_codex":0.00017502453,"about_ca_system_score_gemma":0.0004596198,"threshold_uncertainty_score":0.9999617},"labels":[],"label_agreement":null},{"id":"W3112904752","doi":"10.23889/ijpds.v5i5.1420","title":"Creation of First Nations Health Profiles Through Data Linkage in Manitoba","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"First Nations Health and Social Secretariat of Manitoba","funders":"","keywords":"Mandate; Information governance; Data sharing; Political science; Business; Public administration; Medicine; Information system; Law","score_opus":0.5272190626369835,"score_gpt":0.5404742119118103,"score_spread":0.01325514927482685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112904752","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":[0.04306562,0.00023873041,0.7709506,0.15970328,0.0053757876,0.0016289792,0.01665997,0.00006051831,0.0023164863],"genre_scores_gemma":[0.9631613,0.00020582236,0.03152837,0.0011492004,0.0003728579,0.000006114897,0.0035119331,0.000006833351,0.000057602516],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995095,0.000111367284,0.0012701707,0.00067747594,0.0026452993,0.00020069329],"domain_scores_gemma":[0.996353,0.0007138664,0.0009687246,0.0010949759,0.00074680225,0.00012264041],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.007773942,0.00009482189,0.00019709184,0.00053735415,0.00045927532,0.00071865926,0.008311358,0.000026817766,0.00009049769],"category_scores_gemma":[0.019612953,0.000079887606,0.000034151653,0.0013302072,0.00016295459,0.009043418,0.0019667782,0.00012931888,0.00002294783],"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":[0.000366525,0.00079916924,0.22837152,0.00014361067,0.00010986884,0.000018534543,0.005268225,0.011937089,0.0002528887,0.36368147,0.16863164,0.22041947],"study_design_scores_gemma":[0.0013488926,0.00016188336,0.16047913,0.00022215798,0.000014896205,0.000021566411,0.0038597237,0.32172504,0.000091517184,0.032076642,0.4797164,0.0002821517],"about_ca_topic_score_codex":0.0010700045,"about_ca_topic_score_gemma":0.0077034817,"teacher_disagreement_score":0.9200956,"about_ca_system_score_codex":0.00013308156,"about_ca_system_score_gemma":0.00027627253,"threshold_uncertainty_score":0.99705416},"labels":[],"label_agreement":null},{"id":"W3115634801","doi":"10.23889/ijpds.v5i5.1541","title":"How Are Linkage Results Using Privacy-Preserving Record Linkage Different?","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Linkage (software); Record linkage; Computer science; Internet privacy; Genetics; Biology; Medicine; Environmental health; Gene","score_opus":0.5276143466944776,"score_gpt":0.49682370186658736,"score_spread":0.030790644827890234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115634801","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":[0.34191114,0.00004977829,0.5510169,0.09457855,0.007851099,0.00052246393,0.0036549428,0.0000788617,0.0003362393],"genre_scores_gemma":[0.9701872,0.000040026698,0.0255436,0.001640388,0.0014291807,0.000002656388,0.0005006329,0.000013384182,0.0006429182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936215,0.00016141144,0.0010833092,0.0009865627,0.0037982867,0.0003488734],"domain_scores_gemma":[0.9952088,0.0006061457,0.0013844689,0.0012905066,0.0011562658,0.0003538399],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0059504155,0.00017595035,0.00025643205,0.00048411405,0.00071295275,0.0057339724,0.0113269435,0.00005355501,0.00007523073],"category_scores_gemma":[0.039546516,0.00013586857,0.000106272164,0.00082092365,0.00014513527,0.009278892,0.004301073,0.00027781763,0.000027096852],"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":[0.0019162024,0.00059480267,0.12710801,0.000093694354,0.00034464244,0.00024648313,0.0036563047,0.009085793,0.012784941,0.024503421,0.31158197,0.50808376],"study_design_scores_gemma":[0.0014549829,0.00009411268,0.062416945,0.0001485304,0.000030423025,0.00003401712,0.0013507252,0.560946,0.00025675297,0.020440485,0.35243136,0.00039570758],"about_ca_topic_score_codex":0.00007995835,"about_ca_topic_score_gemma":0.0000865472,"teacher_disagreement_score":0.62827605,"about_ca_system_score_codex":0.0001481602,"about_ca_system_score_gemma":0.00010074869,"threshold_uncertainty_score":0.99529815},"labels":[],"label_agreement":null},{"id":"W3116133199","doi":"","title":"Attribute-Based Semantic Reconciliation of Multiple Data Sources.","year":2003,"lang":"en","type":"article","venue":"Journal on Data Semantics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Schema (genetic algorithms); Information retrieval; Semantics (computer science); Information integration; Data mining","score_opus":0.4778145243269458,"score_gpt":0.43881745860081595,"score_spread":0.038997065726129876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116133199","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":[0.22208652,0.0004970594,0.74765414,0.012218231,0.004218532,0.0007765793,0.010893921,0.00007878341,0.0015762264],"genre_scores_gemma":[0.98283964,0.00021807509,0.012539113,0.0016967913,0.00020041772,9.366446e-7,0.0018626289,0.000024045696,0.00061833026],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99433327,0.0007593312,0.0014822242,0.00070663285,0.0023806985,0.00033784859],"domain_scores_gemma":[0.9899854,0.0023043023,0.0012579326,0.00586428,0.0004000243,0.00018808302],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.018022817,0.00019443835,0.00047266946,0.00038851262,0.0002483662,0.0005468326,0.00546246,0.00009005062,0.00041132473],"category_scores_gemma":[0.027556932,0.00014618505,0.00008004712,0.0007283701,0.0001051231,0.0015976711,0.0010392346,0.00036575322,0.0003505636],"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":[0.00017848125,0.0013598115,0.06308924,0.0001273176,0.00024892946,0.00013453582,0.00023467667,0.0031214529,0.00034718442,0.007115704,0.8913848,0.032657877],"study_design_scores_gemma":[0.001744577,0.0001922496,0.007233129,0.00014052635,0.00013546705,0.00003854282,0.00093677116,0.0653846,0.0010569852,0.004009116,0.91879725,0.00033079568],"about_ca_topic_score_codex":0.000020447354,"about_ca_topic_score_gemma":0.00015690268,"teacher_disagreement_score":0.76075315,"about_ca_system_score_codex":0.000044257285,"about_ca_system_score_gemma":0.00023945761,"threshold_uncertainty_score":0.99991846},"labels":[],"label_agreement":null},{"id":"W3121734764","doi":"10.2139/ssrn.1975336","title":"Dependence Modeling in Multivariate Claims Run-Off Triangles","year":2011,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua","funders":"","keywords":"Multivariate statistics; Multivariate analysis; Econometrics; Statistics; Mathematics","score_opus":0.22825680730450323,"score_gpt":0.3817565436088361,"score_spread":0.15349973630433286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121734764","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":[0.50151193,0.0020996646,0.48602322,0.0009403743,0.00068898464,0.00029935344,0.000007781337,0.00004908215,0.008379595],"genre_scores_gemma":[0.99574316,0.0014034145,0.00095689343,0.00017264542,0.00009799487,0.0000054818765,0.0000016338146,0.000012106965,0.001606701],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953071,0.00046275673,0.0008951773,0.00042074727,0.001046544,0.0018677115],"domain_scores_gemma":[0.99882096,0.00019691729,0.00027367802,0.0004692283,0.00012772367,0.00011151498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018797467,0.00016076824,0.00027972617,0.0004432229,0.00019814244,0.00020535906,0.0014654212,0.00008167406,0.0002521913],"category_scores_gemma":[0.00092706666,0.00012076695,0.0001322669,0.00054952345,0.000041710817,0.0009779602,0.00022131966,0.0013737258,0.000340368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032645513,0.00028061657,0.001658653,0.0000028454094,0.000088596615,0.000048281312,0.0025510923,0.00149961,0.000112456844,0.52947736,0.00021482781,0.4637392],"study_design_scores_gemma":[0.000962157,0.00013639219,0.0007488807,0.000018197496,0.000013486575,0.000072662275,0.008448265,0.026962914,0.000033709763,0.9611062,0.0013130027,0.00018416022],"about_ca_topic_score_codex":0.0007346803,"about_ca_topic_score_gemma":0.00844814,"teacher_disagreement_score":0.49423116,"about_ca_system_score_codex":0.00038627742,"about_ca_system_score_gemma":0.00081451767,"threshold_uncertainty_score":0.6514864},"labels":[],"label_agreement":null},{"id":"W3122531144","doi":"10.6084/m9.figshare.14687696","title":"Fast Bayesian Record Linkage With Record-Specific Disagreement Parameters","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Record linkage; Linkage (software); Bayesian probability; Computer science; Statistics; Econometrics; Artificial intelligence; Mathematics; Biology; Sociology; Genetics; Demography","score_opus":0.20242576117650027,"score_gpt":0.36523436655654057,"score_spread":0.1628086053800403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122531144","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012794303,0.00021257554,0.0001652226,0.00047722456,0.0007232606,0.00068881264,0.9963301,0.000052869113,0.001348695],"genre_scores_gemma":[0.0000012414753,0.0001543404,0.0017489024,0.0014541529,0.0003216149,0.0003843913,0.9914995,0.0000338281,0.004402066],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928164,0.0005547635,0.0012353774,0.0019174567,0.0028090344,0.0006669803],"domain_scores_gemma":[0.9928204,0.0013476489,0.00096278806,0.004160976,0.00035778,0.00035040427],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00092263817,0.0006377094,0.00091924414,0.0004341929,0.00025974488,0.001982113,0.0033981504,0.00034495475,0.61394125],"category_scores_gemma":[0.0031133997,0.00047554265,0.00031144483,0.0011786853,0.000040314157,0.00049544085,0.0017436768,0.00075115793,0.043775495],"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":[0.000028584756,0.000112615395,0.0000029058308,0.0001740291,0.00007780771,0.00036820563,0.000027025211,0.000008356661,7.1759715e-8,0.00000250678,0.91721094,0.08198694],"study_design_scores_gemma":[0.0002923078,0.00016862161,0.000065790344,0.0023464328,0.00003855867,0.0000070480414,0.00053206366,0.000011476473,0.0000039363103,0.000112654874,0.9957361,0.00068500533],"about_ca_topic_score_codex":0.00012056233,"about_ca_topic_score_gemma":0.0025736466,"teacher_disagreement_score":0.57016575,"about_ca_system_score_codex":0.00014804876,"about_ca_system_score_gemma":0.0001525296,"threshold_uncertainty_score":0.9997696},"labels":[],"label_agreement":null},{"id":"W3124015549","doi":"10.2966/scrip.120215.154","title":"Reflections on the Concept of Open Data","year":2015,"lang":"en","type":"article","venue":"SCRIPTed A Journal of Law Technology & Society","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Open data; Linked data; Interoperability; Computer science; Transparency (behavior); Data science; Accountability; Meaning (existential); Knowledge management; Open education; World Wide Web; Political science; Semantic Web; Epistemology; Computer security; Law","score_opus":0.6257464399519292,"score_gpt":0.5407464510057203,"score_spread":0.08499998894620897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124015549","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":[0.0663156,0.0037774886,0.043361835,0.6282549,0.0062989276,0.001861832,0.0011068025,0.00022546534,0.24879718],"genre_scores_gemma":[0.9816927,0.00006709605,0.010362251,0.0069565745,0.00007665156,0.0000036738486,0.000008548567,0.000008506673,0.0008240306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975782,0.00024635292,0.00081660686,0.00025561082,0.0009337029,0.00016949668],"domain_scores_gemma":[0.9962185,0.00037853964,0.0008619365,0.0017684464,0.0007040554,0.00006849106],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.009408119,0.00009397326,0.00033265701,0.000098559394,0.0002128684,0.00018988218,0.008039039,0.00012950829,0.00012456092],"category_scores_gemma":[0.0029129589,0.000052139672,0.00012213674,0.0010613224,0.0009827996,0.0007981142,0.0027903474,0.00050337747,0.000036564663],"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":[0.000018084354,0.00008357518,0.000018349989,5.481742e-7,0.00008759362,0.00000285977,0.00080852956,0.00000777482,0.00019296214,0.47011322,0.52579266,0.0028738442],"study_design_scores_gemma":[0.00045968225,0.00024704935,0.000023272729,0.00002320757,0.00003323807,0.000024241082,0.027390635,0.00004286924,0.0012261935,0.2199228,0.7505532,0.000053655884],"about_ca_topic_score_codex":0.00009804165,"about_ca_topic_score_gemma":0.00009781892,"teacher_disagreement_score":0.9153771,"about_ca_system_score_codex":0.0000502362,"about_ca_system_score_gemma":0.00017837873,"threshold_uncertainty_score":0.9973279},"labels":[],"label_agreement":null},{"id":"W3124163813","doi":"","title":"Open or Closed? Open Licensing of Real-Time Public Sector Transit Data","year":2016,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Open data; Business; Public transport; Public sector; Transit (satellite); Open government; Transport engineering; Computer science; Economics; Engineering; World Wide Web; Economy","score_opus":0.3281475856506092,"score_gpt":0.44504167216564205,"score_spread":0.11689408651503286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124163813","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":[0.28430635,0.0015997626,0.30975327,0.20498632,0.0025831126,0.0062286663,0.0022235962,0.00022046667,0.18809846],"genre_scores_gemma":[0.91518265,0.004552358,0.0027685578,0.0007760619,0.00038939618,0.0000072058133,0.00005697409,0.00005354401,0.076213256],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994361,0.0007850674,0.0010877319,0.0007156058,0.001278527,0.0017720809],"domain_scores_gemma":[0.9958662,0.0008467457,0.00068128627,0.0021212632,0.00029211078,0.00019242933],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03229819,0.00018321315,0.00052598625,0.00026203983,0.00030463812,0.0017798741,0.014798529,0.00007040108,0.0030361973],"category_scores_gemma":[0.0022696024,0.00009719283,0.000083095096,0.0007195465,0.00011964381,0.0053780642,0.004211173,0.00048385203,0.0004886317],"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":[0.00067626836,0.00026803228,0.00020463295,0.0000054202765,0.00037380453,0.000016435484,0.0002578027,0.0000014232837,0.0042822775,0.19324152,0.05680801,0.74386436],"study_design_scores_gemma":[0.0041981065,0.0009019678,0.0010093543,0.00013419743,0.00010009649,0.000320219,0.0037354643,0.00016091442,0.0004272126,0.47284383,0.5156709,0.00049771747],"about_ca_topic_score_codex":0.0006027849,"about_ca_topic_score_gemma":0.008448392,"teacher_disagreement_score":0.74336666,"about_ca_system_score_codex":0.0003388114,"about_ca_system_score_gemma":0.003940632,"threshold_uncertainty_score":0.9992564},"labels":[],"label_agreement":null},{"id":"W3125002781","doi":"10.5539/gjhs.v13n3p23","title":"Data Cleaning Needs and Issues: A Case Study of the National Reproductive Health Assessment (RHA) Data from Solomon Islands","year":2021,"lang":"en","type":"article","venue":"Global Journal of Health Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data collection; Reproductive health; Standardization; Data entry; Reliability (semiconductor); Process (computing); Research data; Medicine; Computer science; Environmental health; Database; Data science; Statistics; Mathematics","score_opus":0.4862324880655968,"score_gpt":0.5819926248280866,"score_spread":0.09576013676248973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125002781","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":[0.9359757,0.0027049794,0.0059317555,0.049058255,0.0020149765,0.0005636304,0.003012459,0.000008967091,0.0007292969],"genre_scores_gemma":[0.99112296,0.00016078916,0.006628746,0.0019099171,0.00013318779,4.6308762e-7,0.000018931676,0.0000022291365,0.000022767337],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9919685,0.0009033443,0.0015829531,0.00083983643,0.0043886974,0.0003166351],"domain_scores_gemma":[0.99416125,0.00031668518,0.0019501431,0.0023107561,0.0010452875,0.00021588408],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.041361235,0.00010974723,0.00044393467,0.00015627994,0.00077622646,0.00041337055,0.004222566,0.000018170114,0.000023225655],"category_scores_gemma":[0.0040065055,0.00006940771,0.000025886768,0.0023991924,0.0003628612,0.002018164,0.0052348515,0.00023025015,0.0000019427462],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017767418,0.004257038,0.28868744,0.00011401088,0.0002776987,0.00088547816,0.02775365,0.0008345645,0.000084074476,0.005276958,0.3620891,0.30956233],"study_design_scores_gemma":[0.0022924703,0.0014341044,0.35509914,0.00029965094,0.000056549758,0.0055352943,0.5798387,0.009016417,0.000014547912,0.016512407,0.029611502,0.0002892101],"about_ca_topic_score_codex":0.0030988543,"about_ca_topic_score_gemma":0.0024851265,"teacher_disagreement_score":0.55208504,"about_ca_system_score_codex":0.00024539072,"about_ca_system_score_gemma":0.0040586917,"threshold_uncertainty_score":0.98712033},"labels":[],"label_agreement":null},{"id":"W3125074818","doi":"","title":"Is Practitioners' Views on Core Concepts of Information Integrity","year":2005,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"COBIT; Process management; Information quality; Knowledge management; Information system; Data integrity; Guideline; Computer science; Business; Control (management); Engineering; Computer security; Political science","score_opus":0.1427847610628718,"score_gpt":0.44481753360301507,"score_spread":0.30203277254014327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125074818","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":[0.41071206,0.0015637679,0.3815096,0.0737148,0.0016703033,0.0010912765,0.00020508163,0.000094646035,0.12943844],"genre_scores_gemma":[0.9925144,0.0011048642,0.0005148179,0.0031059992,0.00015201305,0.0000028365619,0.000014356367,0.0000034988102,0.0025872237],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997178,0.00016801308,0.00075853354,0.00012893435,0.0011096604,0.0006568341],"domain_scores_gemma":[0.99840623,0.00023999882,0.0007007981,0.00031972915,0.0002730265,0.00006023053],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009873235,0.00009330666,0.0001850583,0.00024048131,0.00013783589,0.00014229107,0.0005813147,0.000053912703,0.0005779843],"category_scores_gemma":[0.0012201464,0.00006596288,0.00011597873,0.0003236073,0.00006164506,0.0019273955,0.000064069376,0.0011193361,0.0009945852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007465201,0.00008382956,0.00014946108,0.0000027178282,0.000039853807,2.2675115e-7,0.0011751279,0.000065171174,0.000021474676,0.59685946,0.042676505,0.35885155],"study_design_scores_gemma":[0.00049664575,0.00030511126,0.0005162561,0.000017097536,0.000013396866,0.00003330411,0.0093641905,0.0002629684,0.00023316414,0.32983863,0.65882635,0.00009290326],"about_ca_topic_score_codex":0.000035752808,"about_ca_topic_score_gemma":0.00044605386,"teacher_disagreement_score":0.61614984,"about_ca_system_score_codex":0.00037491688,"about_ca_system_score_gemma":0.00064758386,"threshold_uncertainty_score":0.9997833},"labels":[],"label_agreement":null},{"id":"W3125101722","doi":"10.2139/ssrn.3180340","title":"Publishing Privacy Logs to Facilitate Transparency and Accountability","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Computer science; Accountability; Privacy policy; Audit; Transparency (behavior); Information privacy; SPARQL; Implementation; Computer security; World Wide Web; Internet privacy; Semantic Web; Accounting; Business; RDF; Software engineering","score_opus":0.19793799768639578,"score_gpt":0.3898169333303212,"score_spread":0.1918789356439254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125101722","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":[0.7517141,0.0005022434,0.22080493,0.019532172,0.0005370876,0.00028430042,0.000039763498,0.000044580414,0.0065408065],"genre_scores_gemma":[0.9955245,0.00027029746,0.00043678228,0.00095829385,0.0002366343,0.0000042874553,0.0000029130817,0.0000074479617,0.0025588006],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955087,0.00032084747,0.00069601566,0.0005354946,0.0011864435,0.0017525528],"domain_scores_gemma":[0.9983035,0.00031806418,0.00017144269,0.0006154607,0.00036254787,0.00022903511],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.023731884,0.00015062341,0.00024014724,0.00026287342,0.00042954186,0.0018577221,0.0014906039,0.000060069044,0.00029652656],"category_scores_gemma":[0.003465325,0.00011147797,0.00007980099,0.00062738254,0.00015835206,0.0029937306,0.00029538217,0.00093230815,0.0003292518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019281253,0.00012084461,0.008104032,0.000008248497,0.00009514273,0.0000027570388,0.0087639475,0.0000075671715,0.0001750587,0.1890115,0.01603822,0.7774799],"study_design_scores_gemma":[0.000376215,0.00039195034,0.009960795,0.000008428085,0.000013166753,0.000047155885,0.0068645473,0.000034990604,0.000026009158,0.75177103,0.23034547,0.00016021365],"about_ca_topic_score_codex":0.0003527181,"about_ca_topic_score_gemma":0.006173926,"teacher_disagreement_score":0.77731967,"about_ca_system_score_codex":0.00034264394,"about_ca_system_score_gemma":0.00065469893,"threshold_uncertainty_score":0.99917847},"labels":[],"label_agreement":null},{"id":"W3126588461","doi":"10.29012/jpc.765","title":"Reflections on the Successes and Challenges of Research Data Centers in Canada and the U.S.","year":2021,"lang":"en","type":"article","venue":"Journal of Privacy and Confidentiality","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Regional science; Library science; Data science; Engineering ethics; Geography; Engineering; Computer science","score_opus":0.513031489092612,"score_gpt":0.5069444633669749,"score_spread":0.00608702572563713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126588461","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":[0.85827506,0.0060236054,0.00013032656,0.13358508,0.00029531782,0.00012406381,0.00005253232,8.3985236e-7,0.0015131551],"genre_scores_gemma":[0.98927575,0.010305425,0.000020927147,0.00031033866,0.00003305337,7.325576e-7,8.2386805e-7,0.0000013080529,0.000051639166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9966484,0.0015759768,0.0005282039,0.00018966402,0.0009533332,0.00010442829],"domain_scores_gemma":[0.9952601,0.003497747,0.00025103547,0.00064368325,0.00029834223,0.000049088558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015500897,0.00004867007,0.00020023095,0.000082311824,0.00016955564,0.0002407879,0.00079294614,0.000016121017,0.00004901009],"category_scores_gemma":[0.00476271,0.000024155408,0.00001835987,0.00024700307,0.0003518943,0.00031105118,0.00095658016,0.00024402185,2.6285736e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014131021,0.0003901474,0.017648106,0.00036993675,0.00042772797,0.0001717144,0.015205275,0.000014511449,0.00034346743,0.79537725,0.03290143,0.13573731],"study_design_scores_gemma":[0.0027301414,0.000119367694,0.4115006,0.00027028032,0.000082036095,0.00012061546,0.15429658,0.00015256704,0.00080159155,0.21461172,0.21515884,0.00015567461],"about_ca_topic_score_codex":0.38447738,"about_ca_topic_score_gemma":0.8562723,"teacher_disagreement_score":0.58076555,"about_ca_system_score_codex":0.000020657844,"about_ca_system_score_gemma":0.00035980696,"threshold_uncertainty_score":0.61962146},"labels":[],"label_agreement":null},{"id":"W3126683361","doi":"10.5281/zenodo.3988104","title":"Engaging Citizens in Data Governance in Net Zero Precincts","year":2020,"lang":"en","type":"article","venue":"Monash University Research Portal (Monash University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Simon Fraser University","funders":"","keywords":"Corporate governance; Zero (linguistics); Business; Political science; Public administration; Finance; Linguistics; Philosophy","score_opus":0.44643837642139783,"score_gpt":0.41171423010937125,"score_spread":0.03472414631202658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126683361","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":[0.52934283,0.00016147309,0.0027580762,0.019059349,0.00028404387,0.0016243837,0.0020636963,0.0002127936,0.44449338],"genre_scores_gemma":[0.9748019,0.00042296897,0.00034990517,0.00028637025,0.00004601352,2.1322745e-7,0.00020031889,0.000016973889,0.023875354],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9922244,0.0017564747,0.00047088377,0.0017550528,0.0027809408,0.001012231],"domain_scores_gemma":[0.99576724,0.0014077999,0.0002089929,0.0017291699,0.00030930384,0.0005775204],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055035236,0.00026350384,0.0005089298,0.0013859117,0.00044076378,0.00022002187,0.006596016,0.00016405073,0.000933511],"category_scores_gemma":[0.0024845696,0.00031347232,0.000105913314,0.007050104,0.00051206024,0.0029478297,0.007999847,0.0012438855,0.00045552818],"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":[0.001928994,0.0009934006,0.14587982,0.00013758757,0.00014189325,0.040051486,0.005976963,0.0019936543,0.00032110987,0.28789285,0.47800633,0.036675937],"study_design_scores_gemma":[0.0022800276,0.0001141318,0.052993603,0.00007625339,0.0000140463335,0.000003582808,0.024668686,0.0052180905,0.000032553206,0.0023265134,0.91182375,0.00044874128],"about_ca_topic_score_codex":0.0025680885,"about_ca_topic_score_gemma":0.011930885,"teacher_disagreement_score":0.44545907,"about_ca_system_score_codex":0.00037906767,"about_ca_system_score_gemma":0.0004488452,"threshold_uncertainty_score":0.9999798},"labels":[],"label_agreement":null},{"id":"W3126704983","doi":"10.5539/ibr.v14n3p15","title":"Investigating IT Governance Practice and Its Application, Benefits, and Administrative Implications in the Banking Sector, Saudi Arabia","year":2021,"lang":"en","type":"article","venue":"International Business Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Corporate governance; Reputation; Likert scale; Business; Accounting; Value (mathematics); Control (management); Customer satisfaction; Competitive advantage; Marketing; Scale (ratio); Finance; Economics; Management","score_opus":0.39759292426441756,"score_gpt":0.5201846290822916,"score_spread":0.12259170481787401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126704983","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":[0.26274323,0.0023208421,0.003492822,0.6750015,0.00021106687,0.0008463361,0.0003271141,0.000021588457,0.05503551],"genre_scores_gemma":[0.9952441,0.0010149721,0.00080918876,0.0020472943,0.0001031038,0.00014922004,0.00005200078,0.0000056806703,0.00057446636],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9965737,0.000550536,0.00041617034,0.00052839424,0.0017414275,0.00018980296],"domain_scores_gemma":[0.9911438,0.0055308323,0.00018031905,0.00040939034,0.0026812572,0.00005439257],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006347547,0.00008324562,0.00010913115,0.00013665661,0.00029964914,0.00087892846,0.00083877385,0.000039842133,0.00012324074],"category_scores_gemma":[0.026269604,0.00006432226,0.000013994496,0.0016719364,0.0001677262,0.0009615464,0.00060354406,0.00027508617,0.00004323316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001835543,0.00015693977,0.015900027,0.000024367999,0.00002638292,0.000014970211,0.002011574,0.00011958639,0.00078785676,0.9225485,0.007083519,0.05130794],"study_design_scores_gemma":[0.00021915135,0.000010260985,0.6899374,0.00007051669,0.00000378712,0.000051393217,0.0033016559,0.0007745407,0.00016294305,0.04655708,0.25881648,0.00009476171],"about_ca_topic_score_codex":0.00024565743,"about_ca_topic_score_gemma":0.0011030622,"teacher_disagreement_score":0.8759914,"about_ca_system_score_codex":0.000048524456,"about_ca_system_score_gemma":0.00019680816,"threshold_uncertainty_score":0.9819325},"labels":[],"label_agreement":null},{"id":"W3126869922","doi":"10.1080/0960085x.2020.1869507","title":"Skipping class: improving human-driven data exploration and querying through instances","year":2021,"lang":"en","type":"article","venue":"European Journal of Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of British Columbia","funders":"","keywords":"Computer science; Data science; Class (philosophy); Analytics; Schema (genetic algorithms); USable; External Data Representation; Information retrieval; Data mining; World Wide Web; Artificial intelligence","score_opus":0.32684809512526897,"score_gpt":0.3967332117913389,"score_spread":0.06988511666606995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126869922","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":[0.023034956,0.0008340497,0.9158972,0.0012220213,0.0018422356,0.00018882894,0.00006424049,0.00003148118,0.056885023],"genre_scores_gemma":[0.9950514,0.00019292392,0.0037220786,0.00046311587,0.00029191567,6.576291e-7,0.00007505783,0.000006968907,0.00019588789],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958984,0.00092971156,0.0018461295,0.00014593307,0.0010574573,0.00012234661],"domain_scores_gemma":[0.9966108,0.00019469352,0.0018533153,0.0005944879,0.0006824447,0.00006421618],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.009795648,0.00009454947,0.00023677829,0.0001999392,0.00025477965,0.0020013975,0.0008238562,0.000016371716,0.00001414555],"category_scores_gemma":[0.0018299104,0.000072448274,0.000038320875,0.00034255645,0.000038719812,0.018110787,0.0005443095,0.00014768462,0.000101809186],"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":[0.00009809277,0.00011301441,0.0012724919,0.000770993,0.00031991617,0.00035517907,0.07329263,0.017339416,0.0025690214,0.12544274,0.13126329,0.6471632],"study_design_scores_gemma":[0.00076873455,0.000082951046,0.00077360834,0.00039078065,0.000022761498,0.00015807425,0.08753535,0.0082355775,0.00008568451,0.00046793575,0.90130264,0.00017592277],"about_ca_topic_score_codex":0.000010388212,"about_ca_topic_score_gemma":0.000009572197,"teacher_disagreement_score":0.97201645,"about_ca_system_score_codex":0.000032386433,"about_ca_system_score_gemma":0.00006394454,"threshold_uncertainty_score":0.99903464},"labels":[],"label_agreement":null},{"id":"W3128109697","doi":"10.21810/jicw.v3i3.2529","title":"Leading in a Data Centric Society","year":2021,"lang":"en","type":"article","venue":"The Journal of Intelligence Conflict and Warfare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Data quality; Key (lock); Data science; Quality (philosophy); Political science; Computer science; Computer security; Public relations; Engineering; Geography; Operations management; Epistemology","score_opus":0.3582713015373094,"score_gpt":0.45455658729887205,"score_spread":0.09628528576156264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128109697","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":[0.508007,0.05996437,0.35033563,0.070330195,0.0024714014,0.0005172645,0.00022161045,0.00002827044,0.008124246],"genre_scores_gemma":[0.98063,0.014007992,0.0009362419,0.002072204,0.00013121954,3.4717397e-7,0.000007293758,0.0000059761037,0.0022087733],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979867,0.00027783733,0.00070664135,0.00017070504,0.00069278205,0.00016536657],"domain_scores_gemma":[0.99744284,0.0011998513,0.00030960742,0.0006819265,0.00029690698,0.000068878195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0078038275,0.00007910157,0.00022971144,0.00008711509,0.00010464572,0.0002113971,0.0015515222,0.000033275468,0.00025453107],"category_scores_gemma":[0.0021709271,0.00004465156,0.00006289772,0.00066636235,0.000107496075,0.0005185011,0.00077926007,0.00025126952,0.000037100257],"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":[0.00014102203,0.00020667596,0.006501795,0.000050207254,0.00015677114,0.00022689106,0.03057936,0.0008021078,0.00065773836,0.01109733,0.14368291,0.8058972],"study_design_scores_gemma":[0.00024445908,0.00006744924,0.0032651592,0.0001566236,0.00005833106,0.00023295512,0.0748506,0.005757999,0.002497119,0.010443277,0.90224415,0.00018186706],"about_ca_topic_score_codex":0.00002451325,"about_ca_topic_score_gemma":0.00008363904,"teacher_disagreement_score":0.8057153,"about_ca_system_score_codex":0.000018340537,"about_ca_system_score_gemma":0.00008441471,"threshold_uncertainty_score":0.28831398},"labels":[],"label_agreement":null},{"id":"W3129744650","doi":"10.14778/3436905.3436907","title":"Astrid","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"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 Toronto","funders":"","keywords":"Substring; Computer science; Suffix; String (physics); Embedding; String searching algorithm; Suffix tree; Prefix; Theoretical computer science; Artificial intelligence; Algorithm; Pattern matching; Data structure; Mathematics","score_opus":0.23727257312021974,"score_gpt":0.3685803821593431,"score_spread":0.13130780903912334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129744650","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":[0.43085164,0.00024410128,0.0015449723,0.23463301,0.0012367474,0.0018680387,0.00013247674,0.0001911545,0.32929784],"genre_scores_gemma":[0.99463326,0.000011536804,0.00085147464,0.003094351,0.00008625298,0.000012896247,5.447293e-7,0.000005221107,0.0013044851],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978124,0.000011695125,0.000443128,0.00029951116,0.0012725078,0.0001607695],"domain_scores_gemma":[0.99917275,0.00009041185,0.00029648736,0.00017408904,0.0001738307,0.00009240432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013217991,0.000088944296,0.0001762848,0.000044756034,0.000079841324,0.00014072865,0.0016350687,0.00002013584,0.00025656924],"category_scores_gemma":[0.0017892872,0.000049946695,0.000118964046,0.0005834355,0.000075054166,0.00026496765,0.0009852855,0.000083488616,0.00022311318],"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":[0.000085641164,0.00013679477,0.0049301153,0.00006872585,0.000061068466,5.706894e-7,0.0026777708,0.000030874984,0.019813828,0.19976592,0.72573215,0.046696533],"study_design_scores_gemma":[0.00055762246,0.00014776093,0.0040365746,0.000026576838,0.000032281147,0.0000015618142,0.0038704344,0.0003229242,0.09918325,0.042425442,0.84923977,0.00015579663],"about_ca_topic_score_codex":0.000013649885,"about_ca_topic_score_gemma":9.058845e-7,"teacher_disagreement_score":0.56378156,"about_ca_system_score_codex":0.000017586028,"about_ca_system_score_gemma":0.000013401373,"threshold_uncertainty_score":0.30383915},"labels":[],"label_agreement":null},{"id":"W3129961804","doi":"10.23889/ijpds.v6i1.1407","title":"Use of administrative record linkage to measure medical and social risk factors for early developmental vulnerability in Ontario, Canada","year":2021,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Hospital for Sick Children; McMaster University; University of Toronto","funders":"","keywords":"Medical record; Population; Concordance; Vulnerability (computing); Record linkage; Residence; Medicine; Demography; Psychology; Gerontology; Environmental health; Computer security","score_opus":0.48513685475496204,"score_gpt":0.4814978207620087,"score_spread":0.0036390339929533444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129961804","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":[0.97331697,0.0000018967792,0.021128356,0.0020342388,0.0012200744,0.0002019148,0.0020707203,0.0000021217072,0.000023717894],"genre_scores_gemma":[0.9851521,0.0000021082674,0.014071227,0.0002462538,0.00005049428,0.0000050850313,0.00029113173,0.0000027042033,0.00017889723],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957493,0.0001317442,0.0008077153,0.0004679415,0.002675541,0.00016776637],"domain_scores_gemma":[0.99701047,0.0012039985,0.00036648617,0.00021555988,0.0010469761,0.00015651381],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062231338,0.00008309659,0.00017615962,0.00020127055,0.00031438848,0.0005349795,0.0014642831,0.0000363927,0.00016176683],"category_scores_gemma":[0.024767831,0.00006870209,0.000033542103,0.00031067154,0.000105895626,0.0020538303,0.0005824234,0.00016780898,4.950027e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019472852,0.00009999465,0.9307928,0.00000422215,0.000038705803,0.0000140612,0.0017013403,0.00007327213,0.0000674438,0.0027289053,0.0058241766,0.058460355],"study_design_scores_gemma":[0.00033998396,0.00003695442,0.9611774,0.00002353011,0.0000058737164,0.000009383715,0.0011920709,0.0011799282,0.00010906082,0.003089428,0.0327403,0.00009605643],"about_ca_topic_score_codex":0.6119447,"about_ca_topic_score_gemma":0.98665935,"teacher_disagreement_score":0.37471467,"about_ca_system_score_codex":0.00049201126,"about_ca_system_score_gemma":0.002942187,"threshold_uncertainty_score":0.98344696},"labels":[],"label_agreement":null},{"id":"W3133429097","doi":"10.1007/s11192-020-03840-8","title":"Mapping the intellectual structure of GIS-T field (2008–2019): a dynamic co-word analysis","year":2021,"lang":"en","type":"article","venue":"Scientometrics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Kungliga Tekniska Högskolan","keywords":"Field (mathematics); Computer science; Geographic information system; Data science; Geography; Cartography; Mathematics","score_opus":0.15018153582932317,"score_gpt":0.4231165180604795,"score_spread":0.2729349822311563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133429097","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":[0.6214622,0.001964664,0.3621791,0.004536949,0.0016803071,0.00029985298,0.00055788463,0.000045558994,0.0072734714],"genre_scores_gemma":[0.9916468,0.00010185523,0.0017032721,0.00095345965,0.00002378392,0.0000011414206,0.00005577948,0.000004385886,0.005509496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950147,0.0003239149,0.0006925504,0.0005858497,0.003053088,0.00032989276],"domain_scores_gemma":[0.9925238,0.004927371,0.00031184353,0.0014142679,0.0007130405,0.00010968652],"candidate_categories":["metaresearch","bibliometrics","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052230796,0.00012467551,0.00035881624,0.0055365353,0.00023456383,0.0005534725,0.001790265,0.00007235801,0.0032527316],"category_scores_gemma":[0.033832423,0.00007893023,0.00025649712,0.08218203,0.00019749178,0.00024303299,0.0006889948,0.00020203383,0.00012592415],"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":[0.000038076498,0.00028328618,0.015477556,0.000047000347,0.000998196,0.00003617815,0.013152299,0.0027995051,0.0022349171,0.0054099695,0.34077552,0.6187475],"study_design_scores_gemma":[0.0007232401,0.00016640674,0.10466667,0.00002957616,0.00046791325,0.000014582295,0.030906355,0.032055072,0.010086856,0.01798619,0.802209,0.000688144],"about_ca_topic_score_codex":0.00006924326,"about_ca_topic_score_gemma":0.0003440056,"teacher_disagreement_score":0.61805934,"about_ca_system_score_codex":0.000052046158,"about_ca_system_score_gemma":0.00012594461,"threshold_uncertainty_score":0.99765843},"labels":[],"label_agreement":null},{"id":"W3136500690","doi":"","title":"Les réutilisateurs et les réutilisatrices des données publiques ouvertes : Le cas de Montréal","year":2021,"lang":"fr","type":"article","venue":"EspaceINRS (National Institute for Scientific Research (Canada))","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Art; Humanities","score_opus":0.2428502168306204,"score_gpt":0.4158214539767816,"score_spread":0.1729712371461612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136500690","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05350761,0.039386734,0.019754209,0.83400226,0.010296325,0.0015878353,0.0088341,0.000102593855,0.032528315],"genre_scores_gemma":[0.6621867,0.0028054472,0.016511096,0.001633175,0.0006685168,0.00033552301,0.0020701152,0.00007401318,0.3137154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98458785,0.0022639974,0.0011212655,0.0018461997,0.008407366,0.0017733484],"domain_scores_gemma":[0.98340225,0.00508149,0.0003266041,0.0011287675,0.00923518,0.0008257002],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["sts"],"category_scores_codex":[0.02720924,0.00044379153,0.00053490326,0.00096232415,0.0058331448,0.006261734,0.0025599417,0.00025290094,0.00062221754],"category_scores_gemma":[0.03071558,0.0004306277,0.0002636587,0.003942006,0.0040194998,0.003746777,0.0013665165,0.0008257525,0.00003606814],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005536954,0.0002545923,0.0004415183,0.00019861522,0.00010730467,0.00013350394,0.00076088286,0.0040677236,0.00012324064,0.52311975,0.42286137,0.047876164],"study_design_scores_gemma":[0.00053793716,0.000061179664,0.004181366,0.00017101901,0.000024701787,0.00002841456,0.013973755,0.0074945195,0.0023965081,0.05774466,0.9129664,0.0004195444],"about_ca_topic_score_codex":0.96976405,"about_ca_topic_score_gemma":0.99981016,"teacher_disagreement_score":0.8323691,"about_ca_system_score_codex":0.003081909,"about_ca_system_score_gemma":0.046586562,"threshold_uncertainty_score":0.99981457},"labels":[],"label_agreement":null},{"id":"W3137444831","doi":"10.7202/1075712ar","title":"Le projet 1142 : mise en place de nouveaux espaces numériques de travail à l’Université de Montréal1","year":2021,"lang":"fr","type":"article","venue":"Archives","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.027234275998372172,"score_gpt":0.2967873321323399,"score_spread":0.2695530561339677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3137444831","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.510978,0.01770398,0.045127958,0.14718205,0.00063880533,0.00059300766,0.00069595437,0.00018657015,0.27689373],"genre_scores_gemma":[0.3090414,0.019127175,0.053064413,0.0029769228,0.00036662357,0.000033432974,0.00009691009,0.00005238315,0.6152407],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956849,0.0020328672,0.00036624854,0.00065462745,0.0004948202,0.00076652085],"domain_scores_gemma":[0.99660724,0.0021196487,0.00015460132,0.00071294006,0.000046096502,0.00035947183],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001815451,0.00023591807,0.00032733008,0.00016182651,0.0004627511,0.00040190943,0.0010427277,0.00010215741,0.000701223],"category_scores_gemma":[0.000879934,0.0002459608,0.00019700026,0.00033064687,0.00043652297,0.0005874719,0.0010375314,0.00025343566,0.00025126152],"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":[0.00045977553,0.0010202395,0.010921354,0.00028663757,0.00030969366,0.0017338055,0.2838728,0.0010809904,0.0069215423,0.14686939,0.2818558,0.26466796],"study_design_scores_gemma":[0.0006228481,0.000094519455,0.009767586,0.0001346667,0.000049485872,0.000079446465,0.11343616,0.0027150644,0.006368951,0.04698702,0.81944555,0.00029867794],"about_ca_topic_score_codex":0.0028491584,"about_ca_topic_score_gemma":0.017289197,"teacher_disagreement_score":0.5375898,"about_ca_system_score_codex":0.00014133302,"about_ca_system_score_gemma":0.0012246774,"threshold_uncertainty_score":0.9999993},"labels":[],"label_agreement":null},{"id":"W3146147323","doi":"","title":"Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics.","year":2021,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":123,"is_retracted":false,"has_abstract":false,"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; Analytics; Data warehouse; Data science; Database","score_opus":0.946872203848267,"score_gpt":0.6271471361658597,"score_spread":0.31972506768240727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146147323","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":[0.249746,0.0027703966,0.5759263,0.023073073,0.0034406069,0.009840389,0.06722741,0.00019456184,0.06778129],"genre_scores_gemma":[0.9801367,0.00037585036,0.002712554,0.00013178543,0.00013672862,0.000019000538,0.010260554,0.000020799074,0.006206062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9932848,0.0007882873,0.0010139283,0.0016013354,0.002890029,0.0004215709],"domain_scores_gemma":[0.9875896,0.0012918293,0.0004681597,0.007103241,0.003382313,0.00016486396],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.019207867,0.00018466251,0.00056346966,0.00059909845,0.0003330643,0.003047313,0.007935701,0.000091730806,0.00023713899],"category_scores_gemma":[0.008996663,0.00014009132,0.000011425733,0.004048625,0.00034387552,0.0041077984,0.017280541,0.00043297556,0.00007979927],"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":[0.0001245676,0.00017454982,0.001017623,0.00013185429,0.0001444601,0.000058347774,0.00076859584,0.00007274096,0.0034837474,0.46158478,0.3228096,0.20962912],"study_design_scores_gemma":[0.0036883366,0.0005489678,0.0037389675,0.0014846445,0.00003481059,0.00003717185,0.06252182,0.17396653,0.006345469,0.0286581,0.7179775,0.0009976816],"about_ca_topic_score_codex":0.0013094897,"about_ca_topic_score_gemma":0.0018380821,"teacher_disagreement_score":0.73039067,"about_ca_system_score_codex":0.0000617585,"about_ca_system_score_gemma":0.0014795832,"threshold_uncertainty_score":0.99935097},"labels":[],"label_agreement":null},{"id":"W31491858","doi":"10.3390/vetsci6030073","title":"Entwicklung von Konzepten zur flexiblen Integration der Datenqualitätssicherung in analytischen Anwendungen.","year":2005,"lang":"en","type":"article","venue":"Veterinary Sciences","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.4367512115559696,"score_gpt":0.4963433225596985,"score_spread":0.05959211100372891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W31491858","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":[0.94793224,0.0008396033,0.0073391655,0.007211106,0.00085605675,0.0004691634,0.00003885343,0.00011684436,0.035196986],"genre_scores_gemma":[0.9828956,0.00006959734,0.011712049,0.0012543747,0.00014790132,0.000027278875,0.000023330454,0.0000081267635,0.0038617337],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951747,0.00064173876,0.00093989185,0.0010055635,0.0017122105,0.0005258712],"domain_scores_gemma":[0.99828345,0.0004727762,0.00027772656,0.0007339303,0.00009335787,0.00013878588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010094436,0.00022656463,0.00032346047,0.00082913105,0.00030868934,0.00080786686,0.0020218715,0.00008215076,0.0008664085],"category_scores_gemma":[0.00067650474,0.00016605247,0.00009806731,0.0023204568,0.00041172843,0.0037295632,0.00062514486,0.00017595492,0.00074986485],"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":[0.0001492911,0.00049718324,0.017030424,0.000025692736,0.00005590016,0.00013585472,0.007083059,0.0024135825,0.010756607,0.028934633,0.03563758,0.8972802],"study_design_scores_gemma":[0.0008751186,0.0011691459,0.08833712,0.00012678189,0.000038047507,0.000054458273,0.01228775,0.054715674,0.0013366356,0.013697629,0.8263849,0.000976729],"about_ca_topic_score_codex":0.00032638412,"about_ca_topic_score_gemma":0.00066409085,"teacher_disagreement_score":0.8963035,"about_ca_system_score_codex":0.000089183544,"about_ca_system_score_gemma":0.00009302786,"threshold_uncertainty_score":0.96382457},"labels":[],"label_agreement":null},{"id":"W3150711643","doi":"10.5441/002/edbt.2021.35","title":"HorsePower: Accelerating Database Queries for Advanced Data Analytics","year":2021,"lang":"en","type":"article","venue":"Movebank","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Horsepower; Computer science; Analytics; Database; Data analysis; Data modeling; Data mining; Engineering","score_opus":0.5144424565501053,"score_gpt":0.4858367395349261,"score_spread":0.02860571701517922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3150711643","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":[0.05512867,0.0013883437,0.88659847,0.010087703,0.002778443,0.00089292676,0.012188201,0.0002013071,0.030735912],"genre_scores_gemma":[0.38286674,0.000523448,0.4727196,0.01691169,0.0011595155,0.00014159176,0.01958925,0.00010469455,0.105983436],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972721,0.00012495514,0.00062701234,0.0008573518,0.00083427597,0.0002843515],"domain_scores_gemma":[0.99503297,0.0011092525,0.00019827658,0.0032377439,0.0003307214,0.00009105129],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032479116,0.00013117892,0.0002612258,0.000085563894,0.00023733849,0.0008199291,0.0016889031,0.000038391554,0.0007364862],"category_scores_gemma":[0.011516177,0.00011109881,0.000068113324,0.0005506921,0.000068649475,0.0017219036,0.002046225,0.000090143054,0.00013398891],"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":[0.000102836704,0.00025595416,0.0018368743,0.00008021259,0.00011970287,0.00010204726,0.00042806263,0.0006545861,0.0027561495,0.13181184,0.56774426,0.29410747],"study_design_scores_gemma":[0.00045580562,0.000023986588,0.0006257263,0.000015955899,0.000025048452,0.0000023078728,0.0016560232,0.0086794775,0.0024561686,0.010510961,0.9753561,0.0001924139],"about_ca_topic_score_codex":0.000022895982,"about_ca_topic_score_gemma":0.0005024541,"teacher_disagreement_score":0.41387886,"about_ca_system_score_codex":0.000019680574,"about_ca_system_score_gemma":0.00010637224,"threshold_uncertainty_score":0.99681026},"labels":[],"label_agreement":null},{"id":"W3151061208","doi":"","title":"An Information Governance Methodology to Tackle Digital Recordkeeping Challenges: The Convergence of Artificial Intelligence, Business Analysis and Information Architecture","year":2020,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l'ACSI","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Ottawa","funders":"","keywords":"Humanities; Corporate governance; Knowledge management; Process management; Computer science; Artificial intelligence; Engineering; Management; Philosophy","score_opus":0.12994318594565615,"score_gpt":0.33762642501605117,"score_spread":0.20768323907039501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3151061208","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":[0.8436602,0.00006642431,0.13258718,0.019959968,0.00017491901,0.0006057889,0.00073329115,0.000028892278,0.0021833759],"genre_scores_gemma":[0.9965411,0.00018407228,0.002397448,0.00079929305,0.000035380894,0.000013484928,0.0000132464575,0.0000041116364,0.000011872731],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99739623,0.000088661734,0.0011442206,0.0002607722,0.0008852207,0.00022489001],"domain_scores_gemma":[0.979317,0.00065350154,0.0016080732,0.00031900124,0.017973347,0.00012903952],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002675222,0.00018139523,0.00052279484,0.00026980852,0.00011066337,0.001866488,0.0021052368,0.00009209068,0.000027626766],"category_scores_gemma":[0.053951174,0.000118307515,0.00012195019,0.0020547626,0.00037900073,0.020784609,0.0007550123,0.00017549226,0.0000073349597],"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":[0.00056188373,0.000063145395,0.010939184,0.00037658477,0.00023040264,1.9030098e-7,0.1474488,0.0010242508,0.0009790126,0.14308773,0.0006195767,0.69466925],"study_design_scores_gemma":[0.00052749715,0.0014280127,0.49691415,0.00035345726,0.0006805135,0.000015149307,0.16474219,0.031045202,0.02378986,0.084061876,0.19537379,0.0010683336],"about_ca_topic_score_codex":0.00017810274,"about_ca_topic_score_gemma":0.00005924292,"teacher_disagreement_score":0.6936009,"about_ca_system_score_codex":0.000016917154,"about_ca_system_score_gemma":0.00010355026,"threshold_uncertainty_score":0.99916965},"labels":[],"label_agreement":null},{"id":"W3154149429","doi":"","title":"Collaborating for Greater Impact: Building an Integrated Data Ecosystem","year":2018,"lang":"en","type":"article","venue":"TSpace","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Toronto; Australian Government","keywords":"Ecosystem; Environmental resource management; Environmental science; Business; Computer science; Ecology","score_opus":0.4099295516535472,"score_gpt":0.558409725810772,"score_spread":0.14848017415722475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154149429","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":[0.6251596,0.000029890954,0.3663876,0.001587866,0.00088327733,0.0007425941,0.001520723,0.00015309555,0.0035353345],"genre_scores_gemma":[0.96861744,9.5062455e-7,0.026286054,0.0003201222,0.00035225708,0.000014387935,0.00021381787,0.000015534106,0.0041794134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99797064,0.00021234933,0.00038117944,0.00062732445,0.00052042224,0.00028806145],"domain_scores_gemma":[0.9968797,0.00036743918,0.00020101418,0.0019530784,0.00047378193,0.0001250117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005850243,0.00012932936,0.00022607014,0.00014110704,0.0002456326,0.00082701916,0.001790423,0.000047797046,0.0005784054],"category_scores_gemma":[0.0025452394,0.00008548505,0.000033313994,0.0007205476,0.000051580697,0.0010126018,0.0005921278,0.00005278877,0.00029745293],"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":[0.00027465582,0.00010916668,0.0018418755,0.00003897461,0.00011301135,0.000009296718,0.010246298,0.00009175633,0.0031515257,0.0101580955,0.891721,0.08224433],"study_design_scores_gemma":[0.0005197521,0.0003918014,0.000668041,0.000042061816,0.00002682769,0.0000038411454,0.02052135,0.0659311,0.0018115782,0.0014409883,0.9083839,0.00025876536],"about_ca_topic_score_codex":0.0003187042,"about_ca_topic_score_gemma":0.0016844687,"teacher_disagreement_score":0.34345785,"about_ca_system_score_codex":0.000051116356,"about_ca_system_score_gemma":0.000084992294,"threshold_uncertainty_score":0.7974965},"labels":[],"label_agreement":null},{"id":"W3155972762","doi":"10.1136/bmjopen-2020-043497","title":"Can synthetic data be a proxy for real clinical trial data? A validation study","year":2021,"lang":"en","type":"article","venue":"BMJ Open","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University Health Centre; Children's Hospital of Eastern Ontario; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Univariate; Medicine; Bivariate analysis; Multivariate statistics; Metric (unit); Synthetic data; Statistic; Multivariate analysis; Data mining; Proxy (statistics); Statistics; Internal medicine; Computer science; Mathematics","score_opus":0.8969700184148548,"score_gpt":0.6912436001651321,"score_spread":0.2057264182497227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155972762","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":[0.31409842,0.000040399635,0.034062877,0.1971376,0.01688208,0.2959386,0.05875337,0.00030042347,0.0827862],"genre_scores_gemma":[0.75175434,0.000080317426,0.06257853,0.011392223,0.0051325285,0.012536872,0.06252386,0.00014618346,0.09385513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993495,0.001932288,0.0014690467,0.001570087,0.0013203284,0.00021323729],"domain_scores_gemma":[0.98673844,0.002839098,0.00046498413,0.009598044,0.00024395363,0.00011549777],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.057896085,0.000110443754,0.00046607773,0.000055481487,0.00018751455,0.0021186117,0.008854667,0.000049742455,0.00042565004],"category_scores_gemma":[0.03995207,0.00008422801,0.00005108284,0.00038140392,0.00005435321,0.0014852094,0.016955482,0.00009007742,0.00012532412],"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":[0.0093494775,0.002684507,0.001290391,0.000021791748,0.00016851701,0.00005535458,0.00059153483,0.0000027979786,0.0000027053177,0.004588807,0.8325784,0.1486657],"study_design_scores_gemma":[0.03917745,0.0012382343,0.0029157547,0.0000483101,0.00028078555,0.0000050873446,0.012657198,0.0068674013,0.000018997245,0.0121184625,0.9242839,0.00038837304],"about_ca_topic_score_codex":0.00081919675,"about_ca_topic_score_gemma":0.005955818,"teacher_disagreement_score":0.43765593,"about_ca_system_score_codex":0.000016328908,"about_ca_system_score_gemma":0.00066857267,"threshold_uncertainty_score":0.9989173},"labels":[],"label_agreement":null},{"id":"W3159065547","doi":"","title":"Overview of TAC-KBP 2019 Fine-grained Entity Extraction.","year":2019,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Extraction (chemistry); Chemistry; Chromatography","score_opus":0.06709713054902026,"score_gpt":0.39385835955841175,"score_spread":0.3267612290093915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159065547","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":[0.57437426,0.007097547,0.32099935,0.0024064467,0.00047871147,0.0025546062,0.00086126645,0.00011558408,0.09111226],"genre_scores_gemma":[0.9879637,0.00028992398,0.0003483643,0.00006747119,0.000025134015,0.000038962142,0.000037325986,0.0000040309524,0.011225099],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987112,0.00016850753,0.00045190332,0.0002295134,0.00035107322,0.000087746586],"domain_scores_gemma":[0.9976933,0.0010301215,0.0003108121,0.00075244554,0.00017866633,0.000034624976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003250993,0.00007780931,0.00023161329,0.000117636955,0.00007368796,0.000045220433,0.00044478878,0.000035845664,0.00090083835],"category_scores_gemma":[0.000260826,0.000060350387,0.000059315007,0.00041688283,0.0002389787,0.00035660472,0.00016285857,0.000051422656,0.00019660208],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037470552,0.00006945065,0.00035927686,0.000055200595,0.00001617558,3.9772466e-8,0.00017775396,0.00000792927,0.00080973184,0.9594868,0.0024055326,0.03657466],"study_design_scores_gemma":[0.00015242644,0.00003470973,0.003826041,0.000007232062,0.000021832375,7.785409e-7,0.001342101,0.000007874904,0.0031929647,0.80160004,0.1897442,0.00006980781],"about_ca_topic_score_codex":0.00004480304,"about_ca_topic_score_gemma":0.000014174324,"teacher_disagreement_score":0.41358945,"about_ca_system_score_codex":0.0000044235076,"about_ca_system_score_gemma":0.000026646576,"threshold_uncertainty_score":0.9863548},"labels":[],"label_agreement":null},{"id":"W3159720274","doi":"10.18438/eblip29879","title":"A Pilot to Initiate Research Data Management Services Within Academic Libraries Helps Librarians to Learn About, Engage With, and Enhance Skills Within Their Research Communities","year":2021,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"RDM; Phone; Medical education; Library science; Miller; Psychology; Sociology; Public relations; Medicine; Computer science; Political science; Pedagogy","score_opus":0.3451696637035892,"score_gpt":0.47323814499927713,"score_spread":0.12806848129568793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159720274","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":[0.21244131,0.0067527713,0.048304565,0.65294456,0.0009607593,0.0067244377,0.0016794025,0.0007733312,0.06941887],"genre_scores_gemma":[0.68211263,0.010199278,0.077993385,0.22099286,0.00022155466,0.00041511926,0.0010378733,0.00006363062,0.0069636777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9877324,0.006886347,0.0012578074,0.0007517752,0.0027572263,0.00061445014],"domain_scores_gemma":[0.97428215,0.021583099,0.00044185846,0.0026597409,0.00054020336,0.000492941],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.02781965,0.00028178416,0.0003502473,0.0012484469,0.0015865914,0.008643467,0.0033567157,0.000099051365,0.00030991327],"category_scores_gemma":[0.008726196,0.00021930912,0.000020508558,0.0041541527,0.00045903318,0.2825255,0.008404426,0.0017297398,0.00040517867],"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":[0.004430356,0.0003427637,0.0012035653,0.001404028,0.00016682423,0.000101258796,0.07518092,0.0012088531,0.00009263823,0.80610305,0.06261062,0.04715511],"study_design_scores_gemma":[0.00048251,0.0008631514,0.0034290832,0.0026588882,0.000026684387,0.000034772092,0.20395519,0.0020319745,0.00343321,0.009319291,0.77335036,0.00041489123],"about_ca_topic_score_codex":0.0001563602,"about_ca_topic_score_gemma":0.000036523925,"teacher_disagreement_score":0.7967838,"about_ca_system_score_codex":0.000017732285,"about_ca_system_score_gemma":0.0005413325,"threshold_uncertainty_score":0.9997132},"labels":[],"label_agreement":null},{"id":"W3160270149","doi":"10.48550/arxiv.2105.04021","title":"MS MARCO: Benchmarking Ranking Models in the Large-Data Regime","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Waterloo; Microsoft (Canada)","funders":"","keywords":"Benchmarking; Clef; Computer science; Ranking (information retrieval); Field (mathematics); Data science; Best practice; Track (disk drive); Artificial intelligence; Information retrieval; Political science; Task (project management); Engineering","score_opus":0.4743132750901781,"score_gpt":0.3087619711037293,"score_spread":0.1655513039864488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160270149","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":[0.18517517,0.00045020948,0.7552918,0.0017369312,0.001551464,0.0009682503,0.0005169199,0.00010269823,0.054206572],"genre_scores_gemma":[0.9952391,0.00045348733,0.00056759344,0.0008274651,0.00012712023,0.0000012834271,0.0005288464,0.000014634274,0.0022405195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99451435,0.0015048395,0.00058776373,0.0021485072,0.00072693976,0.00051761843],"domain_scores_gemma":[0.99210864,0.0012377162,0.00046917712,0.00591639,0.00017625988,0.000091810216],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.011718329,0.00031534312,0.000517085,0.00050102203,0.00027958804,0.0009747268,0.009074244,0.00024779057,0.0005682747],"category_scores_gemma":[0.0006700647,0.0002654622,0.00022158783,0.0015935398,0.00013240144,0.0013876577,0.013692008,0.0008982055,0.00009865966],"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":[0.00012670647,0.0005544931,0.003730084,0.0001424571,0.0002387295,0.003140658,0.0047919275,0.44463977,0.0000031791765,0.4793936,0.05401755,0.009220836],"study_design_scores_gemma":[0.0006372753,0.000014818848,0.0017696832,0.00020803181,0.000110817076,0.0000041274902,0.008904108,0.65653497,0.0000016055684,0.29044738,0.040882654,0.0004845564],"about_ca_topic_score_codex":0.0009805718,"about_ca_topic_score_gemma":0.0033597276,"teacher_disagreement_score":0.8100639,"about_ca_system_score_codex":0.00012364339,"about_ca_system_score_gemma":0.0001971987,"threshold_uncertainty_score":0.99997973},"labels":[],"label_agreement":null},{"id":"W3160528426","doi":"10.2172/1782589","title":"Next Generation Hydrogen Station Composite Data Products: Retail Stations; Summer 2020 (Q2 FY2020)","year":2021,"lang":"en","type":"report","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Renewable Energy Laboratory","keywords":"Software deployment; Reliability (semiconductor); Composite number; Quarter (Canadian coin); Hydrogen production; Environmental science; Data quality; Component (thermodynamics); Hydrogen; Environmental economics; Computer science; Business; Service (business); Marketing; Chemistry; Geography","score_opus":0.670532853712078,"score_gpt":0.48186204244176456,"score_spread":0.1886708112703135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160528426","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013520182,0.025148438,0.26313025,0.07626233,0.026445268,0.010168281,0.055673823,0.0010904146,0.52856106],"genre_scores_gemma":[0.0082033165,0.014623968,0.042322896,0.0035127343,0.0045405775,0.00016224492,0.45450294,0.00014413586,0.4719872],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9872941,0.0010175643,0.0023242228,0.0026184965,0.0063321376,0.00041347294],"domain_scores_gemma":[0.9890642,0.00062020647,0.0012852699,0.0056630773,0.0031838578,0.00018335726],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013106297,0.00043923708,0.00078523136,0.0004037006,0.00036749034,0.002577473,0.0026326834,0.00024526415,0.0056605297],"category_scores_gemma":[0.009668946,0.00036865953,0.00012835105,0.0017318795,0.000109380715,0.002934718,0.002171003,0.00039259682,0.0017390593],"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":[0.000008278816,0.0001123147,0.00011792237,0.000085921085,0.0001684172,0.000049713704,0.00014272862,0.00015792274,0.00058849365,0.00047461336,0.9132497,0.08484403],"study_design_scores_gemma":[0.00018837584,0.000029102419,0.00027733372,0.000038532413,0.00020468516,0.000016733511,0.00087895035,0.0062103397,0.0004399306,0.0005948185,0.990658,0.0004632128],"about_ca_topic_score_codex":0.0017209114,"about_ca_topic_score_gemma":0.0054727155,"teacher_disagreement_score":0.39882913,"about_ca_system_score_codex":0.00025129213,"about_ca_system_score_gemma":0.0021790466,"threshold_uncertainty_score":0.99987656},"labels":[],"label_agreement":null},{"id":"W3162028309","doi":"10.1145/3411764.3445227","title":"KTabulator: Interactive Ad hoc Table Creation using Knowledge Graphs","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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; Table (database); Information retrieval; Knowledge graph; Testbed; Construct (python library); World Wide Web; Graph; Post hoc; Data mining; Theoretical computer science; Programming language","score_opus":0.21552636783225454,"score_gpt":0.46971911151106305,"score_spread":0.2541927436788085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162028309","genre_codex":"other","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":[0.34056252,0.0023826184,0.1317574,0.001504301,0.002259209,0.0003449672,0.00008120434,0.00014953848,0.52095824],"genre_scores_gemma":[0.91196257,0.00013258508,0.010520984,0.0010559171,0.00005628914,0.000008091495,0.0000552315,0.000011625168,0.07619673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983811,0.00022857622,0.00036945258,0.00042223863,0.00043144778,0.00016721692],"domain_scores_gemma":[0.9984032,0.0004594664,0.00010969466,0.00056665286,0.0003898005,0.000071218434],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013536955,0.00008915405,0.00017150264,0.00016919652,0.00014676224,0.00045122358,0.00031980837,0.000036224938,0.004629727],"category_scores_gemma":[0.001006905,0.00006992331,0.00007212772,0.0009705857,0.000042382864,0.0009381362,0.00038940003,0.00007014168,0.00095923216],"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":[0.00007228061,0.0006758429,0.0010702884,0.000021482505,0.00013357907,0.000038230035,0.0042308294,0.0002749123,0.0043217093,0.44831643,0.2466038,0.29424062],"study_design_scores_gemma":[0.00033988018,0.000029442734,0.0017256957,0.000023370672,0.000027793412,0.0000065278427,0.009134953,0.009051524,0.006686203,0.08374149,0.88903403,0.00019905966],"about_ca_topic_score_codex":0.000055201348,"about_ca_topic_score_gemma":0.000540374,"teacher_disagreement_score":0.64243025,"about_ca_system_score_codex":0.00005003953,"about_ca_system_score_gemma":0.000086465174,"threshold_uncertainty_score":0.9998186},"labels":[],"label_agreement":null},{"id":"W3164503825","doi":"","title":"Reflections on the Successes and Challenges of Research Data Centers in Canada and the U.S.","year":2021,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Library science; Public relations; Computer science","score_opus":0.8564487430690108,"score_gpt":0.6947039409183844,"score_spread":0.16174480215062637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164503825","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":[0.7952091,0.08367089,0.00005272029,0.08704719,0.0007579688,0.00088851096,0.00048608312,0.000006956568,0.03188057],"genre_scores_gemma":[0.90625983,0.09294877,0.000022416938,0.0005329089,0.000030000434,0.000013258402,0.0000057144553,0.000006898885,0.00018021445],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99434155,0.0023241404,0.0007431268,0.00051037775,0.0018378941,0.00024288418],"domain_scores_gemma":[0.98948926,0.008169588,0.00037822715,0.0014697062,0.00039649208,0.00009672315],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01806738,0.00011611711,0.0004232065,0.00043538798,0.00036310684,0.0014419267,0.005146515,0.00002738888,0.0013455175],"category_scores_gemma":[0.007295917,0.00006295055,0.000029895979,0.00149596,0.00049145496,0.0013969835,0.005144924,0.00037584806,0.000001803197],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011599404,0.0006500057,0.21154337,0.0003918447,0.00050902076,0.00019988907,0.0035296965,0.00018548577,0.0018433594,0.107734844,0.46909374,0.20315881],"study_design_scores_gemma":[0.0008429462,0.000010194618,0.72428775,0.0004191312,0.0000324685,0.00001144173,0.021221057,0.00012321475,0.0017397567,0.07822309,0.17289451,0.00019446368],"about_ca_topic_score_codex":0.60080737,"about_ca_topic_score_gemma":0.9033949,"teacher_disagreement_score":0.51274437,"about_ca_system_score_codex":0.000063097454,"about_ca_system_score_gemma":0.0005370139,"threshold_uncertainty_score":0.9995947},"labels":[],"label_agreement":null},{"id":"W3165068300","doi":"10.1177/10497323211015960","title":"What Are Data?","year":2021,"lang":"en","type":"article","venue":"Qualitative Health Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Psychology; Medicine","score_opus":0.9756802608194425,"score_gpt":0.7995023206113255,"score_spread":0.17617794020811695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165068300","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0137918815,0.016624305,0.024632595,0.91931826,0.0028865242,0.0014378483,0.0018870276,0.00012362676,0.019297939],"genre_scores_gemma":[0.3345096,0.028827213,0.046622057,0.107287094,0.002104753,0.00048121018,0.0054295245,0.00018234999,0.47455618],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9624318,0.027569829,0.0011260639,0.0014339227,0.00644641,0.0009920128],"domain_scores_gemma":[0.9683756,0.023221862,0.00034407055,0.00452604,0.0029228663,0.00060955255],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.1422172,0.000119315526,0.00042446304,0.00042742118,0.0007614611,0.0017250797,0.0025191996,0.00005690195,0.0017151223],"category_scores_gemma":[0.047889803,0.00009544252,0.000053009517,0.0029793011,0.00042705424,0.0024888758,0.0030866025,0.0006196986,0.005357231],"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":[0.000025509391,0.0001640515,0.00004169485,0.00008240458,0.00001771658,0.000045600333,0.034184564,0.0000013932237,0.0000049127466,0.097855985,0.7417921,0.12578408],"study_design_scores_gemma":[0.00014685112,0.00005576532,0.0007324096,0.00006273072,5.662454e-7,0.0000012021319,0.38097942,0.000085561,0.000019193836,0.09282988,0.5250244,0.00006200698],"about_ca_topic_score_codex":0.00038215905,"about_ca_topic_score_gemma":0.002166034,"teacher_disagreement_score":0.81203115,"about_ca_system_score_codex":0.00016288493,"about_ca_system_score_gemma":0.0011361273,"threshold_uncertainty_score":0.9993112},"labels":[],"label_agreement":null},{"id":"W3165615601","doi":"10.3233/shti210153","title":"Using Interactive Visual Analytics to Optimize in Real-Time Blood Products Inventory at a Blood Bank","year":2021,"lang":"en","type":"book-chapter","venue":"Studies in health technology and informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority; Dalhousie University","funders":"Canadian Blood Services","keywords":"Dashboard; Analytics; Computer science; Product (mathematics); Visualization; Inventory management; Visual analytics; Blood product; Blood transfusion; Operations management; Database; Medicine; Engineering; Data mining; Surgery","score_opus":0.24235612779801405,"score_gpt":0.46475810056794437,"score_spread":0.22240197276993032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165615601","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3694337,0.05248312,0.0016621591,0.05099393,0.007924314,0.018249033,0.0012713779,0.0012086254,0.49677375],"genre_scores_gemma":[0.032491684,0.19468817,0.21636185,0.019939125,0.00064198545,0.00051554374,0.00051359937,0.00032762723,0.5345204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953223,0.00011499959,0.002765954,0.00055495277,0.00069078454,0.0005509965],"domain_scores_gemma":[0.99681383,0.0005845654,0.0011987948,0.0008857079,0.0004146043,0.00010248492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0040475135,0.00040771323,0.0014316895,0.0029559878,0.00025858896,0.00006247547,0.0006289987,0.00041968777,0.00006579234],"category_scores_gemma":[0.003948072,0.00036440342,0.00006239751,0.001036771,0.0006389438,0.00037913324,0.0035870315,0.00078476407,0.00007773271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086743594,0.0018345092,0.0053937244,0.014414782,0.005283662,0.0012202498,0.12116088,0.0033951115,0.00003213386,0.6617336,0.07211537,0.11254849],"study_design_scores_gemma":[0.0072893105,0.004368752,0.00036499967,0.015528463,0.00087906135,0.00047328614,0.13357365,0.015527444,0.00028176175,0.15103708,0.6667643,0.0039118626],"about_ca_topic_score_codex":0.000042175252,"about_ca_topic_score_gemma":0.000374193,"teacher_disagreement_score":0.59464896,"about_ca_system_score_codex":0.00041678245,"about_ca_system_score_gemma":0.00030116734,"threshold_uncertainty_score":0.9998808},"labels":[],"label_agreement":null},{"id":"W3168854329","doi":"10.14778/3467861.3467872","title":"Data acquisition for improving machine learning models","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":37,"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 Toronto; York University","funders":"","keywords":"Data acquisition; Process (computing); Data modeling; Online machine learning; Knowledge acquisition; Training set; Annotation; Data integration; Supervised learning","score_opus":0.28485107715764413,"score_gpt":0.3865902747486838,"score_spread":0.10173919759103967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168854329","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":[0.34090647,0.0057663396,0.42422983,0.08517427,0.0057165683,0.008959401,0.006814382,0.00065220817,0.12178054],"genre_scores_gemma":[0.9832612,0.000044959266,0.01113982,0.0006037925,0.00009906612,0.000044733228,0.00009258271,0.000013597734,0.0047002416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997707,0.000024167575,0.0005174584,0.0005506269,0.0009839372,0.00021679357],"domain_scores_gemma":[0.99829924,0.00023395833,0.00042211078,0.00053675455,0.0004596683,0.00004828629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003924377,0.00011057221,0.00020817966,0.00007268613,0.00023440333,0.0002969926,0.0018212791,0.000032396198,0.00006977861],"category_scores_gemma":[0.0020432211,0.000072175,0.000098573946,0.00036925025,0.000045768316,0.0009666055,0.0027392702,0.00010470805,0.000010632699],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027277885,0.0006811334,0.0018762513,0.0006955244,0.0002340544,0.0000021070473,0.0024178128,0.002590723,0.12323816,0.51967067,0.08047108,0.26784968],"study_design_scores_gemma":[0.001653374,0.00015896161,0.00046786,0.0001174401,0.00018600131,0.000012674619,0.006433871,0.34921727,0.09174051,0.3349099,0.21471637,0.00038579613],"about_ca_topic_score_codex":0.00004646267,"about_ca_topic_score_gemma":0.000017219705,"teacher_disagreement_score":0.6423547,"about_ca_system_score_codex":0.000037372865,"about_ca_system_score_gemma":0.000034403554,"threshold_uncertainty_score":0.34143046},"labels":[],"label_agreement":null},{"id":"W3168932797","doi":"10.1186/s12911-021-01550-6","title":"Record linkage under suboptimal conditions for data-intensive evaluation of primary care in Rio de Janeiro, Brazil","year":2021,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","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":"McGill University; McGill University Health Centre","funders":"Medical Research Council; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Record linkage; Identifier; Linkage (software); Probabilistic logic; Quality (philosophy); Gold standard (test); Health informatics; Computer science; Database; Health care; Data quality; Data mining; Medicine; Public health; Artificial intelligence; Population; Environmental health; Nursing; Business; Service (business)","score_opus":0.32106487536970196,"score_gpt":0.5008400079838637,"score_spread":0.17977513261416178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168932797","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":[0.21791913,0.0003097574,0.7778837,0.00010284738,0.00025572363,0.0003221228,0.00025273964,0.000008469042,0.0029455286],"genre_scores_gemma":[0.44428712,0.00026017372,0.54763925,0.006214738,0.000087240565,0.000041716215,0.0014000151,0.000012942075,0.00005679648],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99517244,0.00023507306,0.001472003,0.0002665982,0.0026346217,0.00021927198],"domain_scores_gemma":[0.9896215,0.0076126917,0.00040426027,0.0008271479,0.0013978475,0.00013653346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012044767,0.00011190759,0.0003722236,0.0002604074,0.00011883579,0.00021893591,0.00065038394,0.00013716237,0.00038305155],"category_scores_gemma":[0.019394401,0.00008898576,0.000068384725,0.00041237846,0.00011745393,0.00064467284,0.0009651841,0.00015785798,0.00001790767],"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":[0.000102467144,0.000053821812,0.0009991925,0.00021836562,0.000016670354,0.000006018803,0.001543506,0.002465099,0.0000035968917,0.004382215,0.014389132,0.9758199],"study_design_scores_gemma":[0.0018202164,0.000052584583,0.0071801427,0.0005871549,0.000056828925,0.000016667314,0.027839925,0.8885913,0.000008713746,0.066852525,0.00685756,0.0001363804],"about_ca_topic_score_codex":0.00001349535,"about_ca_topic_score_gemma":0.001161952,"teacher_disagreement_score":0.9756835,"about_ca_system_score_codex":0.00009291431,"about_ca_system_score_gemma":0.0010542814,"threshold_uncertainty_score":0.9888657},"labels":[],"label_agreement":null},{"id":"W3174181760","doi":"10.1145/3448016.3450586","title":"Temporal Dependencies for Graphs","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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; Graph product; Product (mathematics); Knowledge graph; Relational database; Theoretical computer science; Information retrieval; Data mining; Graph; Chordal graph; Mathematics","score_opus":0.34115366956646953,"score_gpt":0.46325589940902506,"score_spread":0.12210222984255553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174181760","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":[0.037378777,0.00020971545,0.6485092,0.023740508,0.0014933551,0.00043136164,0.00017142374,0.00014558961,0.28792006],"genre_scores_gemma":[0.81287616,0.000011318989,0.031362478,0.004156462,0.000043226573,0.000024972764,0.00004865402,0.0000047925014,0.15147191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987373,0.000058294583,0.00025216342,0.0002683654,0.0005601758,0.00012375053],"domain_scores_gemma":[0.99876374,0.00050940475,0.000043525743,0.0004479989,0.00019028127,0.000045022774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018279116,0.000046026016,0.00010271572,0.00006356949,0.000087557186,0.00027239014,0.00036610354,0.000020076044,0.002028945],"category_scores_gemma":[0.001513155,0.000031699234,0.00008860977,0.00032013372,0.000028152943,0.00025730045,0.00019356137,0.00002211583,0.00034432506],"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":[0.000005145253,0.000033718017,0.0012014065,0.0000034359869,0.000009032805,0.0000062843487,0.00007785985,0.0000027544172,0.00007577421,0.5702244,0.39532486,0.033035297],"study_design_scores_gemma":[0.00011564811,0.000012239522,0.0011555598,9.337177e-7,0.0000030757724,0.0000012469295,0.0024399718,0.00009258859,0.0012349634,0.39550784,0.5993881,0.00004784744],"about_ca_topic_score_codex":0.000034509318,"about_ca_topic_score_gemma":0.00077783404,"teacher_disagreement_score":0.77549744,"about_ca_system_score_codex":0.000004552607,"about_ca_system_score_gemma":0.000037532485,"threshold_uncertainty_score":0.9988833},"labels":[],"label_agreement":null},{"id":"W3175120204","doi":"10.1109/wiiat50758.2020.00087","title":"Analytics of Similar-Sounding Names from the Web with Phonetic Based Clustering","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"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 Manitoba","funders":"University of Manitoba","keywords":"Computer science; Cluster analysis; Big data; Task (project management); Web intelligence; Web mining; World Wide Web; Semantic Web; Analytics; Data science; Focus (optics); Depth sounding; Data Web; Information retrieval; The Internet; Web page; Data mining; Artificial intelligence; Web modeling; Geography; Engineering","score_opus":0.25441121919444054,"score_gpt":0.3696189409535637,"score_spread":0.11520772175912314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175120204","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":[0.118410915,0.000059748465,0.826493,0.04053304,0.00016087538,0.00026908497,0.00013726359,0.00006550304,0.013870556],"genre_scores_gemma":[0.9858864,0.0000053788413,0.00663373,0.007133336,0.0000396525,0.0000016868566,0.0000075963185,0.000005087438,0.00028715885],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998239,0.0001295487,0.00035103055,0.00026958663,0.0008910853,0.0001197444],"domain_scores_gemma":[0.99778616,0.0014413334,0.00014023996,0.0005040979,0.00006336698,0.0000647819],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010993835,0.00008189312,0.0001837418,0.00003861399,0.00007266378,0.0002039253,0.0008052815,0.000018152943,0.0012692588],"category_scores_gemma":[0.00084263406,0.000040786876,0.00005057412,0.00055927754,0.00009131505,0.00014138738,0.00026699927,0.00006427043,0.0000705541],"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":[0.0010788345,0.00042499203,0.11200172,0.00016496627,0.0007661948,0.000090261194,0.019372454,0.19274105,0.0051853242,0.018285368,0.5613928,0.08849604],"study_design_scores_gemma":[0.0008888294,0.00017254063,0.007276777,0.000042184245,0.00008099421,2.4968537e-7,0.015304909,0.83207333,0.0010398603,0.0024079478,0.1405013,0.00021108413],"about_ca_topic_score_codex":0.00011140286,"about_ca_topic_score_gemma":0.0005683009,"teacher_disagreement_score":0.86747545,"about_ca_system_score_codex":0.000007864112,"about_ca_system_score_gemma":0.0000367126,"threshold_uncertainty_score":0.99964374},"labels":[],"label_agreement":null},{"id":"W3176788992","doi":"10.1109/icde51399.2021.00116","title":"Automating Entity Matching Model Development","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"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":"Pipeline (software); Bottleneck; Benchmark (surveying); Computer science; Process (computing); Artificial intelligence; Machine learning; Matching (statistics); Task (project management); Engineering; Systems engineering; Programming language","score_opus":0.3130788376251375,"score_gpt":0.44985236232381043,"score_spread":0.13677352469867293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176788992","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":[0.14457227,0.000013527455,0.7647389,0.00090295397,0.0001441192,0.000041137286,0.0000030526398,0.000079257465,0.08950475],"genre_scores_gemma":[0.6419401,0.0000024599308,0.30384725,0.0020233856,0.000017918466,0.000005628254,0.000014514706,0.000004475329,0.05214423],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99804485,0.00008702126,0.0004410785,0.00032031542,0.0009492886,0.00015742786],"domain_scores_gemma":[0.9991258,0.00018871376,0.000074437536,0.00043738776,0.00011538877,0.000058278372],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028583293,0.000063096624,0.00011788491,0.000061430124,0.00018880233,0.00048046152,0.0004065214,0.000020303709,0.001557146],"category_scores_gemma":[0.00066499825,0.000048623413,0.000039730632,0.00028128503,0.000012598782,0.00042767907,0.00070507015,0.000051864852,0.001219331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028035204,0.00017576758,0.0009249089,0.000026142785,0.00003916336,0.000034965222,0.0041437186,0.008184702,0.0008426566,0.2987134,0.049571246,0.63734055],"study_design_scores_gemma":[0.0005570051,0.000008469001,0.01612961,0.000052599422,0.00001604782,0.000010198844,0.011235195,0.22302514,0.019913578,0.52648896,0.20191398,0.0006492163],"about_ca_topic_score_codex":0.000018379105,"about_ca_topic_score_gemma":0.00026400198,"teacher_disagreement_score":0.63669133,"about_ca_system_score_codex":0.000027524984,"about_ca_system_score_gemma":0.000118293894,"threshold_uncertainty_score":0.9995583},"labels":[],"label_agreement":null},{"id":"W3181069700","doi":"10.1109/seh52539.2021.00012","title":"Provenance-based Trust Model for Assessing Data Quality during Clinical Decision Making","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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 Victoria","funders":"","keywords":"Provenance; Computer science; Quality (philosophy); Data modeling; Data quality; Decision-making models; Data mining; Artificial intelligence; Database; Engineering; Geology; Operations management","score_opus":0.7061120359354508,"score_gpt":0.6196761781888325,"score_spread":0.08643585774661833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181069700","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":[0.080336474,0.000055843775,0.91355735,0.0015650399,0.00047795582,0.00029173848,0.0002681899,0.00006841773,0.0033789978],"genre_scores_gemma":[0.7264649,0.000015067034,0.26783293,0.0021618856,0.00012558329,0.000016612878,0.00013557562,0.000013664183,0.003233749],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99450606,0.0004784641,0.0018149362,0.001414112,0.0014352627,0.00035118082],"domain_scores_gemma":[0.98973703,0.005678702,0.00046580163,0.0035963655,0.00040988813,0.00011221205],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.019546783,0.00015438444,0.00046021093,0.00007816652,0.00035146298,0.0013083961,0.0019620068,0.00010030459,0.0001982537],"category_scores_gemma":[0.025529802,0.00011756731,0.00015725658,0.00046940587,0.00008269725,0.0016132114,0.0018215653,0.00015435435,0.000062315514],"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":[0.00043295947,0.00085130526,0.010996213,0.00014492136,0.000052665913,0.000033201908,0.000103671984,0.0060310117,0.0003287306,0.057898346,0.090057604,0.8330694],"study_design_scores_gemma":[0.0013320639,0.000015919037,0.021522602,0.00010676042,0.000025279101,0.0000011875335,0.0007134997,0.8711827,0.00015344175,0.0752374,0.029441534,0.00026761924],"about_ca_topic_score_codex":0.000008119681,"about_ca_topic_score_gemma":0.00016740954,"teacher_disagreement_score":0.8651517,"about_ca_system_score_codex":0.00004017014,"about_ca_system_score_gemma":0.00037368305,"threshold_uncertainty_score":0.9997283},"labels":[],"label_agreement":null},{"id":"W3184230022","doi":"10.2139/ssrn.3882450","title":"A Scoping Review on Data Governance","year":2021,"lang":"en","type":"review","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Corporate governance; Political science; Data science; Business; Computer science; Finance","score_opus":0.4140001928615419,"score_gpt":0.539057422538472,"score_spread":0.12505722967693012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184230022","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.140898e-9,0.9920056,0.0024502918,0.0010778231,0.00069353095,0.0008137614,0.00016613363,0.00001733008,0.0027755296],"genre_scores_gemma":[6.5743436e-8,0.9907851,0.000076429606,0.0011080081,0.0005030102,0.00002181566,0.00023816983,0.0000361347,0.007231249],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98964554,0.0018344489,0.0022671893,0.0012619104,0.0027290334,0.0022618691],"domain_scores_gemma":[0.99196965,0.0013517356,0.0023415503,0.0040152147,0.00017643553,0.00014543714],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.039119586,0.00046206755,0.0027471608,0.0001677896,0.00027201706,0.0006827916,0.0075430516,0.00014319981,0.0006342667],"category_scores_gemma":[0.009019099,0.0003038726,0.0006808986,0.001266189,0.000052901574,0.0006998164,0.0018179159,0.003746367,0.0016789967],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010087417,0.000033728287,3.639859e-8,0.009128161,0.00015275925,0.000022421975,0.000001881931,1.550865e-7,6.776901e-10,0.08476648,0.035659183,0.8702342],"study_design_scores_gemma":[0.00005885214,0.000045292687,3.2017788e-8,0.32303485,0.00032723456,0.0003195643,0.000032952965,7.3546846e-7,4.331618e-9,0.008230208,0.6677366,0.0002136933],"about_ca_topic_score_codex":0.000012881732,"about_ca_topic_score_gemma":0.00059769565,"teacher_disagreement_score":0.8700205,"about_ca_system_score_codex":0.0009856059,"about_ca_system_score_gemma":0.012296957,"threshold_uncertainty_score":0.99994135},"labels":[],"label_agreement":null},{"id":"W3186833835","doi":"10.2196/29286","title":"Leveraging National Claims and Hospital Big Data: Cohort Study on a Statin-Drug Interaction Use Case","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche","keywords":"Medicine; Cohort; Blueprint; Big data; Linkage (software); Record linkage; Data sharing; Medical record; Data warehouse; Medical emergency; Computer science; Database; Data mining; Engineering; Surgery; Population","score_opus":0.2809144353763157,"score_gpt":0.46315693702203675,"score_spread":0.18224250164572103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186833835","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":[0.98899347,0.000004322055,0.006209509,0.0016451806,0.0009427365,0.00045954884,0.00016786816,0.00003392684,0.0015434336],"genre_scores_gemma":[0.9948266,0.000016103915,0.00094385067,0.003170372,0.000142579,0.000031764102,0.00031869826,0.000005575851,0.0005444552],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9949401,0.00020287403,0.00097429246,0.00027038722,0.0034379396,0.00017441237],"domain_scores_gemma":[0.99692166,0.0015743694,0.00025898882,0.00072971423,0.00029768518,0.00021758216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049801446,0.00012260374,0.00022300651,0.00016902416,0.00017862227,0.00084691244,0.00049586094,0.000047366506,0.00023106838],"category_scores_gemma":[0.0053551393,0.00009218945,0.000026885033,0.0003782807,0.00008925652,0.0020145793,0.0011806991,0.00032389184,0.0001696721],"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":[0.000052398915,0.0021842693,0.036758594,0.000083383464,0.00026299412,0.002528204,0.07588399,0.00004535097,4.628526e-7,0.002961247,0.53162575,0.34761336],"study_design_scores_gemma":[0.0025710708,0.0003194592,0.067789555,0.0001447875,0.00006272474,0.0007493742,0.47368553,0.074080184,0.0000105670015,0.0029424792,0.37708488,0.0005593774],"about_ca_topic_score_codex":0.00006788341,"about_ca_topic_score_gemma":0.00018386712,"teacher_disagreement_score":0.39780155,"about_ca_system_score_codex":0.000054884516,"about_ca_system_score_gemma":0.00019046181,"threshold_uncertainty_score":0.8166796},"labels":[],"label_agreement":null},{"id":"W3188912472","doi":"10.2196/27842","title":"Quality of Hospital Electronic Health Record (EHR) Data Based on the International Consortium for Health Outcomes Measurement (ICHOM) in Heart Failure: Pilot Data Quality Assessment Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Innovative Medicines Initiative; European Commission; European Federation of Pharmaceutical Industries and Associations","keywords":"Documentation; Electronic health record; Medicine; Quality (philosophy); Data collection; Data quality; Health care; Health records; Quality management; Medical emergency; Data science; Computer science; Operations management","score_opus":0.4831762659776266,"score_gpt":0.5421808990779007,"score_spread":0.059004633100274095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188912472","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":[0.113324724,0.00006138483,0.15463726,0.7169289,0.002129421,0.0069807386,0.005264732,0.00009025414,0.00058255455],"genre_scores_gemma":[0.9496576,0.00003305602,0.009344023,0.03872341,0.00007458601,0.0002143449,0.0018819979,0.00001372466,0.00005724755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98072255,0.0027194887,0.0052232808,0.00072657823,0.009918917,0.0006892184],"domain_scores_gemma":[0.9887051,0.004039426,0.0016478696,0.0047906223,0.0005190169,0.0002979654],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.10280245,0.00024193675,0.00096948654,0.00018245676,0.00020466407,0.0002966157,0.0052633067,0.00006449036,0.00038012926],"category_scores_gemma":[0.020423282,0.00015722477,0.00009886773,0.0006032217,0.00016948984,0.0008110741,0.0025347203,0.00059387024,0.000022367418],"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":[0.00030362402,0.01156407,0.13234699,0.00051853113,0.00035567573,0.0000021155497,0.0034171306,0.000042285334,0.0000013457999,0.024929373,0.7769453,0.04957354],"study_design_scores_gemma":[0.008525931,0.003897115,0.4205371,0.00030862278,0.00002350705,0.0000010279642,0.068513095,0.04839622,0.0000067213055,0.0047511337,0.44443002,0.0006094892],"about_ca_topic_score_codex":0.00064420415,"about_ca_topic_score_gemma":0.012434559,"teacher_disagreement_score":0.83633286,"about_ca_system_score_codex":0.00054493,"about_ca_system_score_gemma":0.0044850884,"threshold_uncertainty_score":0.98782814},"labels":[],"label_agreement":null},{"id":"W3193868442","doi":"10.21747/21836671/pag15a1","title":"Ontologias bibliográficas e Web Semântica: limitações e propostas de investigação","year":2021,"lang":"en","type":"article","venue":"Páginas a&b Arquivos & Bibliotecas","topic":"Data Quality and Management","field":"Decision Sciences","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":"Cascades (Canada)","funders":"","keywords":"Computer science; Ontology; Semantic Web; Semantic interoperability; Interoperability; Information retrieval; Semantic integration; Semantic Web Stack; World Wide Web; Knowledge management; Epistemology","score_opus":0.27646829760356306,"score_gpt":0.44263997899364266,"score_spread":0.1661716813900796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193868442","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":[0.7430444,0.008972834,0.022583919,0.102572985,0.002985091,0.0016856961,0.00053576607,0.001403377,0.116215944],"genre_scores_gemma":[0.96184266,0.0030913425,0.015493407,0.009769528,0.0004068526,0.00009755924,0.0000892556,0.00007533574,0.009134074],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911294,0.0013098519,0.0014504986,0.0017708763,0.002941534,0.0013978699],"domain_scores_gemma":[0.99295694,0.0019248611,0.00050284684,0.0028806052,0.0009520431,0.0007826993],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","scholarly_communication","insufficient_payload"],"consensus_categories":["bibliometrics","insufficient_payload"],"category_scores_codex":[0.007447159,0.00056565355,0.0008730132,0.014085691,0.0005810291,0.002984896,0.0025004363,0.000376429,0.0030141233],"category_scores_gemma":[0.010656796,0.00046753976,0.00041573404,0.04837598,0.00062736013,0.0017842212,0.001873323,0.00071139866,0.0036817787],"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":[0.000112073605,0.00085814315,0.01304728,0.000095286545,0.00025622928,0.0018787833,0.0010059322,0.00011514255,0.008928216,0.053776156,0.8581521,0.061774652],"study_design_scores_gemma":[0.0009158418,0.00027348928,0.018463513,0.00008505606,0.00015812293,0.00027854642,0.0029423812,0.0016959994,0.017560553,0.06360476,0.893175,0.00084673363],"about_ca_topic_score_codex":0.00019857577,"about_ca_topic_score_gemma":0.0013435192,"teacher_disagreement_score":0.21879826,"about_ca_system_score_codex":0.000116448304,"about_ca_system_score_gemma":0.000849856,"threshold_uncertainty_score":0.9997776},"labels":[],"label_agreement":null},{"id":"W3196867679","doi":"10.14778/3476311.3476364","title":"RONIN","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":33,"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 Toronto","funders":"","keywords":"Computer science; Information retrieval; Set (abstract data type); Data mining; Focus (optics); Nearest neighbor search; Data set; Artificial intelligence","score_opus":0.1406382432299656,"score_gpt":0.3809184801512673,"score_spread":0.24028023692130168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196867679","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":[0.4804395,0.00058951386,0.00048333433,0.04221652,0.0016395466,0.00068538205,0.00006042078,0.00007851747,0.47380725],"genre_scores_gemma":[0.9762882,0.000035285226,0.0014249325,0.0010451176,0.000056120527,0.00001783146,0.0000011813275,0.0000058426594,0.021125503],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99779195,0.000018119796,0.0004320659,0.0003129895,0.0012682908,0.00017660054],"domain_scores_gemma":[0.99891376,0.00011885011,0.00024745948,0.0003046986,0.0003657482,0.00004950802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019107901,0.00008340477,0.00017131149,0.00005737561,0.000101211415,0.00018480327,0.0011014874,0.000024018727,0.00047268005],"category_scores_gemma":[0.0016489527,0.000048975202,0.0001284088,0.00059782196,0.00007221659,0.00024800588,0.0011062807,0.000075980824,0.00013896008],"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":[0.000024271416,0.00030152552,0.0062036165,0.000052082636,0.00007166926,0.0000021839644,0.0012425383,0.000020623087,0.02952056,0.55710566,0.35787448,0.047580805],"study_design_scores_gemma":[0.00037321,0.000032629538,0.0074127265,0.000041000363,0.00002726179,0.000007480076,0.0040583415,0.000064022934,0.26923838,0.13959633,0.5790274,0.00012121171],"about_ca_topic_score_codex":0.000020487536,"about_ca_topic_score_gemma":0.000009381887,"teacher_disagreement_score":0.4958487,"about_ca_system_score_codex":0.00003358756,"about_ca_system_score_gemma":0.000031696378,"threshold_uncertainty_score":0.5175515},"labels":[],"label_agreement":null},{"id":"W3196877232","doi":"10.14778/3476311.3476317","title":"A demonstration of KGLac","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; SPARQL; Metadata; Data science; Knowledge graph; Knowledge extraction; Data discovery; Information retrieval; Pipeline (software); Annotation; RDF; Graph; World Wide Web; Data mining; Semantic Web; Artificial intelligence; Theoretical computer science","score_opus":0.12604269999402856,"score_gpt":0.37172051449046417,"score_spread":0.2456778144964356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196877232","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":[0.752775,0.00025877618,0.0010402,0.013215906,0.0006407837,0.0005654376,0.000053638738,0.00002856534,0.23142166],"genre_scores_gemma":[0.9949608,0.000025744577,0.0015046119,0.00021119443,0.00002210992,0.000009580924,0.0000011715498,0.0000029822577,0.0032617946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9980476,0.000018376948,0.0005238903,0.0002214717,0.0010781497,0.00011051998],"domain_scores_gemma":[0.9987438,0.00011703688,0.00039328376,0.0002242978,0.00049047504,0.00003111715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017312103,0.0000661122,0.0001712227,0.00006345713,0.000043499804,0.00007060956,0.00065499276,0.000023855804,0.00012968972],"category_scores_gemma":[0.0010943022,0.000040826413,0.000111771624,0.0005520632,0.00008383944,0.0002395424,0.0004812306,0.00005070557,0.000018175544],"study_design_candidate":"bench_or_experimental","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":[0.000045631707,0.00042810192,0.013169458,0.00012618996,0.00008606206,8.153006e-7,0.0015818576,0.000027108743,0.16656572,0.6959935,0.075051084,0.04692447],"study_design_scores_gemma":[0.0004344225,0.000060633625,0.01036923,0.00007540858,0.000045366036,0.000005692648,0.0055575883,0.00013184437,0.8172494,0.1126685,0.05329797,0.00010390501],"about_ca_topic_score_codex":0.00002185203,"about_ca_topic_score_gemma":0.000011768813,"teacher_disagreement_score":0.6506837,"about_ca_system_score_codex":0.0000187178,"about_ca_system_score_gemma":0.000035934336,"threshold_uncertainty_score":0.16648528},"labels":[],"label_agreement":null},{"id":"W3199853562","doi":"10.1111/ropr.12448","title":"Holding out the promise of Lasswell's dream: Big data analytics in public policy research and teaching","year":2021,"lang":"en","type":"article","venue":"Review of Policy Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"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; Carleton University","funders":"","keywords":"Big data; Scope (computer science); Policy analysis; Public policy; Curriculum; Corporate governance; Analytics; Policy Sciences; Political science; Policy studies; Public relations; Education policy; Sociology; Data science; Public administration; Higher education; Pedagogy; Computer science; Economics; Management; Data mining","score_opus":0.9023683653060873,"score_gpt":0.6734491997677207,"score_spread":0.22891916553836666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199853562","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":[0.039423928,0.11411881,0.00042313285,0.6344323,0.00021095878,0.0042201,0.0011545188,0.000032976335,0.20598324],"genre_scores_gemma":[0.72446066,0.26355863,0.00065293955,0.0012918428,0.0009626132,0.00006116888,0.000117770054,0.00003545875,0.008858932],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9827555,0.008547263,0.0015192156,0.00090774486,0.005319671,0.00095059734],"domain_scores_gemma":[0.9800824,0.011215886,0.00036417792,0.006019618,0.002001802,0.00031615287],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1341627,0.00013863067,0.00068025733,0.0021148536,0.00033619846,0.00050186086,0.0045545795,0.00007016767,0.00007949021],"category_scores_gemma":[0.16055667,0.000088374705,0.0000838949,0.0059438045,0.0010248787,0.0005457721,0.008881981,0.0010991779,0.00006839303],"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":[0.000013358722,0.0003309198,0.001326191,0.0038513618,0.00004952158,0.000019743185,0.0007575602,7.8563204e-7,0.00033378374,0.3178317,0.09573524,0.5797498],"study_design_scores_gemma":[0.0003561065,0.00010633461,0.0023238007,0.0037790902,0.000012059949,0.000008753594,0.0031516238,0.0003371377,0.00024648724,0.03875331,0.9507879,0.00013739182],"about_ca_topic_score_codex":0.0043141763,"about_ca_topic_score_gemma":0.001543091,"teacher_disagreement_score":0.85505265,"about_ca_system_score_codex":0.0001515028,"about_ca_system_score_gemma":0.0023660087,"threshold_uncertainty_score":0.999134},"labels":[],"label_agreement":null},{"id":"W3199898089","doi":"10.1016/j.acalib.2021.102449","title":"Love Data Week in the time of COVID-19: A content analysis of Love Data Week 2021 events","year":2021,"lang":"en","type":"article","venue":"The Journal of Academic Librarianship","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cape Breton University; McGill University","funders":"","keywords":"Outreach; Context (archaeology); Tracking (education); Qualitative property; Content analysis; Pandemic; Coronavirus disease 2019 (COVID-19); World Wide Web; Psychology; Public relations; Medical education; Computer science; Sociology; Medicine; Political science; Social science; History; Pedagogy","score_opus":0.5707753550266078,"score_gpt":0.45022210471394514,"score_spread":0.12055325031266267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199898089","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":[0.25967696,0.015829416,0.07428411,0.6181332,0.0015654939,0.001532966,0.017268918,0.000015674024,0.011693287],"genre_scores_gemma":[0.9591189,0.0045264717,0.0019052383,0.022558346,0.000602074,0.0000010747461,0.0011481649,0.00003748664,0.010102265],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98910856,0.004451714,0.0027611468,0.00048876513,0.0028737397,0.00031607365],"domain_scores_gemma":[0.9825438,0.010030517,0.0025876854,0.004389184,0.00022921753,0.00021954115],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038964503,0.00019103634,0.00092921994,0.0006304071,0.00005116238,0.00013634558,0.015224085,0.00015597709,0.0032927638],"category_scores_gemma":[0.020001786,0.000102346436,0.00021954264,0.0037126772,0.00028457728,0.0030120711,0.0038483082,0.0010264132,0.00017640866],"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":[0.0017335785,0.0016441128,0.019028338,0.00012568504,0.004934935,0.0002421376,0.032434035,0.0031118651,0.0015784819,0.008799617,0.9163235,0.010043725],"study_design_scores_gemma":[0.0064332727,0.0008543325,0.10909293,0.00065591146,0.010126855,0.00028783086,0.23960443,0.031150399,0.0010598185,0.15259364,0.44722196,0.00091859716],"about_ca_topic_score_codex":0.00014548739,"about_ca_topic_score_gemma":0.00008872429,"teacher_disagreement_score":0.6994419,"about_ca_system_score_codex":0.000039620892,"about_ca_system_score_gemma":0.0009185158,"threshold_uncertainty_score":0.9976184},"labels":[],"label_agreement":null},{"id":"W3209614841","doi":"10.1007/s00799-021-00311-0","title":"Improving data quality in large-scale repositories through conflict resolution","year":2021,"lang":"en","type":"article","venue":"International Journal on Digital Libraries","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"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; Technische Universität Wien; Vienna Science and Technology Fund; Technische Universität Wien Bibliothek; Ontario Research Foundation","keywords":"Metadata; Computer science; Data quality; Correctness; Scalability; Profiling (computer programming); Data mining; Data science; Conflict resolution; Quality (philosophy); Data collection; Database; Information retrieval; World Wide Web","score_opus":0.20670035911686424,"score_gpt":0.4259471446766152,"score_spread":0.21924678555975097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209614841","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":[0.3167973,0.002794235,0.2636025,0.09106276,0.024944007,0.0005076742,0.010571875,0.0003076143,0.28941205],"genre_scores_gemma":[0.97846735,0.00013691162,0.005389538,0.003684867,0.0014347007,0.000004193125,0.0011048324,0.000020295865,0.009757346],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956418,0.00025145497,0.0011356091,0.0005413893,0.0021868146,0.00024288404],"domain_scores_gemma":[0.99711037,0.0009951978,0.0004939765,0.00088156766,0.00043212256,0.00008679413],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002161196,0.00013780968,0.0002443509,0.00017425405,0.00016612359,0.007993273,0.0022376562,0.00006186411,0.00021414022],"category_scores_gemma":[0.007950504,0.00011199784,0.000095561256,0.0003529169,0.00011349396,0.012050305,0.001936166,0.0003088012,0.00012096303],"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":[0.0008726743,0.001160201,0.039447196,0.000015176912,0.00023234542,0.0014686771,0.0034640017,0.00031167213,0.00015225566,0.7396085,0.12973338,0.08353385],"study_design_scores_gemma":[0.0006784792,0.000044298067,0.0155559275,0.00006167451,0.0000044629883,0.000102347745,0.00438292,0.00068989897,0.00063957094,0.07895861,0.8986949,0.00018693627],"about_ca_topic_score_codex":0.00003336521,"about_ca_topic_score_gemma":0.00009093128,"teacher_disagreement_score":0.7689615,"about_ca_system_score_codex":0.000076940545,"about_ca_system_score_gemma":0.00023080365,"threshold_uncertainty_score":0.9930365},"labels":[],"label_agreement":null},{"id":"W3210057673","doi":"10.18438/eblip29674","title":"Making Job Postings More Equitable: Evidence Based Recommendations from an Analysis of Data Professionals Job Postings Between 2013-2018","year":2020,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Illinois at Urbana-Champaign; Florida Institute of Technology; Oregon State University; Georgia State University; University of Massachusetts Amherst; East Carolina University; Drexel University; DePaul University; Johns Hopkins University; Princeton University; University of Washington; Virginia Polytechnic Institute and State University; University of Minnesota; San José State University; University of Texas at Arlington; Harvard University; Georgia Southern University; George Washington University; Western Michigan University; Dartmouth College; York University; University of Miami; Northwestern University; Florida State University; Indiana University Bloomington; San Diego State University; Rice University; Ohio State University; Washington University in St. Louis; City University of New York; North Carolina State University; Reed College; Purdue University; Yale University","keywords":"Professional development; Job analysis; Coding (social sciences); Psychology; Equity (law); Public relations; Medical education; Computer science; Sociology; Medicine; Political science; Job satisfaction; Social psychology","score_opus":0.35045121973566534,"score_gpt":0.47785300365053895,"score_spread":0.1274017839148736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210057673","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022519117,0.0006162562,0.14675698,0.8242144,0.0002018135,0.0007836546,0.003978083,0.00018986106,0.0007398274],"genre_scores_gemma":[0.5530015,0.00055072905,0.112967804,0.3263845,0.00022499614,0.000033084863,0.0066880854,0.000021740278,0.00012748406],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99363816,0.0015718513,0.0019762677,0.0007209427,0.0017682728,0.00032452313],"domain_scores_gemma":[0.96771014,0.027454985,0.0024103425,0.0017019961,0.0004109351,0.00031159577],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.008481917,0.0002531191,0.0005385857,0.0007013866,0.0004994238,0.0016529203,0.0026427745,0.00012135871,0.002319442],"category_scores_gemma":[0.04584303,0.00021536861,0.00009150206,0.0037040499,0.00014061408,0.4120665,0.0019507548,0.0003528303,0.00011796534],"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":[0.0032745372,0.0004358918,0.15305091,0.0008476867,0.0013121797,0.000020073398,0.0094097005,0.005636709,0.00045563056,0.03336392,0.52244383,0.26974893],"study_design_scores_gemma":[0.00053947297,0.00036710716,0.16494852,0.0019066227,0.0016138988,0.0000011142185,0.013371138,0.33887014,0.00036703126,0.00034947196,0.47706935,0.00059610873],"about_ca_topic_score_codex":0.00023079342,"about_ca_topic_score_gemma":0.0000021094106,"teacher_disagreement_score":0.5304824,"about_ca_system_score_codex":0.000016782129,"about_ca_system_score_gemma":0.00042681463,"threshold_uncertainty_score":0.99938345},"labels":[],"label_agreement":null},{"id":"W3210155192","doi":"10.1145/3459637.3482087","title":"Discovery of Temporal Graph Functional Dependencies","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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":"Functional dependency; Computer science; Dependency graph; Dependency (UML); USable; Satisfiability; P; Graph; Dependency theory (database theory); Theoretical computer science; Bounded function; Boolean satisfiability problem; Data mining; Time complexity; Algorithm; Artificial intelligence; Mathematics; Relational database","score_opus":0.20662333450558584,"score_gpt":0.38059529019922994,"score_spread":0.1739719556936441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210155192","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":[0.22878498,0.0002289327,0.55242515,0.0039200895,0.0013756912,0.00010962129,0.0001503692,0.000045729666,0.21295944],"genre_scores_gemma":[0.9334292,0.000008974909,0.00173547,0.0005449745,0.000026202553,0.0000018898446,0.000030417728,0.0000017087667,0.06422116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819857,0.00009306547,0.000339163,0.00023307359,0.0010496053,0.000086540276],"domain_scores_gemma":[0.99895346,0.00034791423,0.00007993816,0.00042565542,0.0001683775,0.000024634075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013090188,0.00004781497,0.00012156894,0.00009069404,0.00004590881,0.00016537245,0.00025687384,0.00001940846,0.0023116756],"category_scores_gemma":[0.0007684799,0.00003246712,0.00009356157,0.0004659712,0.00006731698,0.00067370175,0.00028428173,0.000033889035,0.00018502309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002640162,0.00019120213,0.022686211,0.000012708353,0.00004449004,0.000021913986,0.00012439526,0.00006417265,0.0016550127,0.7203724,0.24479018,0.01001095],"study_design_scores_gemma":[0.0005165643,0.00005848625,0.19281033,0.000016063552,0.000022489772,0.000012312149,0.015260386,0.000116965995,0.02419663,0.56084436,0.20590092,0.00024446787],"about_ca_topic_score_codex":0.000092213115,"about_ca_topic_score_gemma":0.0005942994,"teacher_disagreement_score":0.7046442,"about_ca_system_score_codex":0.0000055686933,"about_ca_system_score_gemma":0.0000660508,"threshold_uncertainty_score":0.99860036},"labels":[],"label_agreement":null},{"id":"W3210954531","doi":"10.5281/zenodo.3420179","title":"Time to Professionalise Data Stewardship","year":2019,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Impact","funders":"","keywords":"Stewardship (theology); Business; Computer science; Environmental resource management; Political science; Environmental science","score_opus":0.45715321693023697,"score_gpt":0.47055978914024654,"score_spread":0.01340657221000957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210954531","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012543388,0.000032896653,0.000005552215,0.004485498,0.0002122573,0.00077302824,0.90304565,0.00007460917,0.090116166],"genre_scores_gemma":[0.019780979,2.28563e-7,0.00052900956,0.009316341,0.00021920043,0.00009420657,0.46898046,0.000019969748,0.5010596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976067,0.00014321292,0.00028050222,0.0005845974,0.0011903114,0.00019468369],"domain_scores_gemma":[0.99643046,0.0006581291,0.00009189901,0.0025589806,0.00012828498,0.00013226536],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011573747,0.000087041604,0.00015235165,0.00010208165,0.00005572654,0.00024383653,0.0032113453,0.000039914594,0.8953863],"category_scores_gemma":[0.008539597,0.00006220054,0.000031239113,0.00041785018,0.0000033251479,0.0006989637,0.0036366275,0.000076393706,0.79977286],"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":[0.000007477423,0.000020106621,0.000012488868,0.000014484997,0.0000036930858,0.0000029435905,0.00006289019,0.000010342963,0.000007691952,0.00005246918,0.9883908,0.011414617],"study_design_scores_gemma":[0.000092779395,0.000019507857,0.0019245134,0.00023176198,0.0000014539868,3.4161326e-7,0.00014032028,0.0004730941,0.000019214287,0.00036357084,0.9966285,0.00010491077],"about_ca_topic_score_codex":0.0000023159675,"about_ca_topic_score_gemma":0.0000053928916,"teacher_disagreement_score":0.4340652,"about_ca_system_score_codex":0.000013352347,"about_ca_system_score_gemma":0.0000481884,"threshold_uncertainty_score":0.9998119},"labels":[],"label_agreement":null},{"id":"W3211227609","doi":"10.5281/zenodo.4041661","title":"Can I Share My Data?","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Portage College; Western University; University of Guelph; University of British Columbia; York University; University of Waterloo; Carleton University; University of Windsor; Council of Prairie and Pacific University Libraries; University of Ottawa","funders":"","keywords":"Computer science","score_opus":0.38430687311341544,"score_gpt":0.3793507665785343,"score_spread":0.004956106534881155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211227609","genre_codex":"other","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":[0.006436465,0.00018775032,0.053813342,0.14833511,0.00047951157,0.0015320996,0.017485877,0.002883418,0.7688464],"genre_scores_gemma":[0.96438694,0.000077689,0.0010050253,0.009119118,0.00055074954,3.17739e-8,0.019214448,0.0012995927,0.0043463996],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969193,0.00051885034,0.00037724586,0.0007650819,0.0011311607,0.00028839012],"domain_scores_gemma":[0.9976303,0.00007275199,0.0001280504,0.0014305634,0.00043580946,0.00030249782],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0024772214,0.000107315784,0.00015309948,0.00014061203,0.0013960575,0.0023318625,0.0056447354,0.00003386081,0.05076655],"category_scores_gemma":[0.0075538643,0.00009720122,0.000035486955,0.0010272358,0.00012188738,0.00065382797,0.008121217,0.00019003355,0.048447877],"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":[0.000020063344,0.000032639848,0.0000019462116,0.000012636642,0.00001375898,0.000011673301,0.0009880918,0.000018224866,0.00014006335,0.007880572,0.8271683,0.16371205],"study_design_scores_gemma":[0.00023446819,0.00009097018,0.00025356203,0.0000060242373,0.000007038357,0.000008157839,0.0014414956,0.0014131687,0.000043503995,0.0010213823,0.99536085,0.0001193567],"about_ca_topic_score_codex":0.000021190048,"about_ca_topic_score_gemma":0.0000015168051,"teacher_disagreement_score":0.9579505,"about_ca_system_score_codex":0.00003881294,"about_ca_system_score_gemma":0.0000040885284,"threshold_uncertainty_score":0.999904},"labels":[],"label_agreement":null},{"id":"W3212670429","doi":"10.18280/ijsse.110504","title":"Coupling of Inference and Access Controls to Ensure Privacy Protection","year":2021,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Access control; Inference; Computer science; Computer security; Data access; Obligation; Data mining; Risk analysis (engineering); Database; Artificial intelligence","score_opus":0.07465132137388023,"score_gpt":0.38491490023599684,"score_spread":0.31026357886211664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212670429","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":[0.6829627,0.00030129813,0.31251448,0.0034160237,0.0005757094,0.00010032822,0.000034494646,0.0000055109767,0.00008944821],"genre_scores_gemma":[0.99879026,0.00026311143,0.00076093053,0.000076514174,0.00008876367,0.0000011138932,0.0000014252998,0.0000024598273,0.000015403024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864596,0.000017925686,0.0005299459,0.0001152273,0.0006245957,0.00006636591],"domain_scores_gemma":[0.99859196,0.00035982355,0.00021067889,0.00008854149,0.0006789308,0.00007007226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013796616,0.000059853493,0.0001859958,0.00018135813,0.000025152882,0.00020524465,0.00034195086,0.000028345212,0.000029314437],"category_scores_gemma":[0.0028973722,0.000051091443,0.000038881582,0.00014848536,0.000016206805,0.0005594133,0.0002904928,0.00012822417,7.91302e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019158237,0.0005601321,0.013339533,0.00034099797,0.001199855,0.00044388202,0.015519093,0.41067654,0.060290776,0.16670251,0.00046691476,0.32854396],"study_design_scores_gemma":[0.0063870233,0.00059185224,0.28214765,0.0021170983,0.00012951014,0.00074998185,0.0040180236,0.36005086,0.03064698,0.045421712,0.26684117,0.00089815084],"about_ca_topic_score_codex":0.000011603001,"about_ca_topic_score_gemma":0.000009216351,"teacher_disagreement_score":0.3276458,"about_ca_system_score_codex":0.000020723981,"about_ca_system_score_gemma":0.00003002564,"threshold_uncertainty_score":0.34686345},"labels":[],"label_agreement":null},{"id":"W3215282674","doi":"10.5281/zenodo.831805","title":"Replication Package For How The R Community Creates And Curates Knowledge: An Extended Study Of Stack Overflow And Mailing Lists","year":2017,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Victoria","funders":"","keywords":"Replication (statistics); Stack (abstract data type); Computer science; R package; World Wide Web; Operating system; Biology; Programming language; Virology","score_opus":0.28101975437067334,"score_gpt":0.43084575850810003,"score_spread":0.1498260041374267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215282674","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031305697,0.00021096056,0.0005758648,0.0007352486,0.00011832045,0.0023025165,0.9635799,0.00012345932,0.0010480438],"genre_scores_gemma":[0.12857033,0.0004182344,0.000084103565,0.000056263518,0.0001091754,6.624517e-7,0.86937714,0.00036162045,0.0010224833],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99562854,0.0023642802,0.00045204628,0.00069413654,0.0006260945,0.00023492805],"domain_scores_gemma":[0.9934824,0.00063327857,0.00063140277,0.004075441,0.0010444238,0.00013306212],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009978983,0.00020430762,0.00034174533,0.00025392853,0.0048543597,0.004304276,0.0035970556,0.00008915064,0.00046101783],"category_scores_gemma":[0.013826189,0.00015159066,0.00003895403,0.00026955517,0.00045468612,0.00070883916,0.004278881,0.00039959347,0.0001887875],"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":[0.00008539161,0.0005022353,0.0000037759562,0.00014781204,0.00005293401,0.0000011699119,0.002264248,8.599034e-7,0.00005746381,0.00024011196,0.9454431,0.05120091],"study_design_scores_gemma":[0.00056606473,0.00086376973,0.0020062742,0.00004104652,0.00006560373,0.000008075101,0.00926787,0.00012922654,0.000035521603,0.001026539,0.98582685,0.00016315859],"about_ca_topic_score_codex":0.0001898249,"about_ca_topic_score_gemma":0.00008687512,"teacher_disagreement_score":0.09726463,"about_ca_system_score_codex":0.00003784696,"about_ca_system_score_gemma":0.0000062863573,"threshold_uncertainty_score":0.9967294},"labels":[],"label_agreement":null},{"id":"W3215670116","doi":"10.1109/icde53745.2022.00169","title":"Efficiently Transforming Tables for Joinability","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"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 Alberta","funders":"","keywords":"Disk formatting; Computer science; Row; Transformation (genetics); Set (abstract data type); Representation (politics); State (computer science); Table (database); Theoretical computer science; Join (topology); Data mining; Data transformation; Algorithm; Programming language; Information retrieval; Data warehouse; Mathematics","score_opus":0.33510305283268205,"score_gpt":0.4249302990745663,"score_spread":0.08982724624188426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215670116","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":[0.048726816,0.000085632644,0.86719906,0.012679205,0.012825138,0.0018310793,0.04731748,0.00030399603,0.009031607],"genre_scores_gemma":[0.9853244,0.000027525255,0.0032416054,0.00067838264,0.0002570064,0.00027179054,0.004902103,0.000031817413,0.005265385],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960146,0.00009522816,0.00069154263,0.00091114093,0.0019507549,0.00033672902],"domain_scores_gemma":[0.9974089,0.0006706145,0.00016931127,0.0014489983,0.00019994212,0.00010220835],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004949576,0.00020251602,0.0002644795,0.00038751704,0.00027187212,0.00041208876,0.0043511284,0.000033308672,0.0052183247],"category_scores_gemma":[0.0015829761,0.0001942792,0.00010038129,0.00041380216,0.00004128055,0.0006957519,0.00097496004,0.00029972076,0.000082003025],"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":[0.00040921796,0.0007227311,0.00016800105,0.000091403934,0.00023429938,0.00002601015,0.0009549084,0.1599289,0.004079582,0.53527474,0.237385,0.06072518],"study_design_scores_gemma":[0.0004083788,0.00010954973,0.000115555755,0.000012827764,0.0000118102525,0.0000039352326,0.00075856777,0.3950798,0.0002801055,0.0030593544,0.5999498,0.0002103329],"about_ca_topic_score_codex":0.00008035039,"about_ca_topic_score_gemma":0.00005499364,"teacher_disagreement_score":0.9365976,"about_ca_system_score_codex":0.00019154507,"about_ca_system_score_gemma":0.00010616105,"threshold_uncertainty_score":0.99569106},"labels":[],"label_agreement":null},{"id":"W3216023068","doi":"10.1108/dta-05-2021-0108","title":"Data repair of density-based data cleaning approach using conditional functional dependencies","year":2021,"lang":"en","type":"article","venue":"Data Technologies and Applications","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":"McMaster University","funders":"","keywords":"Computer science; Data mining; Data quality; Functional dependency; Scalability; Set (abstract data type); Data set; Quality (philosophy); Data validation; Database; Artificial intelligence; Engineering; Relational database","score_opus":0.5594296950545075,"score_gpt":0.4357612867051186,"score_spread":0.12366840834938886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216023068","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":[0.0016450664,0.00044268914,0.95085686,0.0009917056,0.000032666394,0.00023325061,0.04517161,0.00027206322,0.00035406149],"genre_scores_gemma":[0.36687303,0.00022607151,0.42957407,0.00040095075,0.00008180238,0.00004815603,0.20266129,0.00001534078,0.00011930501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99728847,0.00007655817,0.00050260604,0.0012681194,0.0007044554,0.0001597859],"domain_scores_gemma":[0.98928535,0.00067184435,0.00024968977,0.009562922,0.0001996844,0.000030508489],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0027067417,0.000112598565,0.00021781147,0.00015192675,0.0003681256,0.00019269796,0.004621487,0.000090847454,0.00005380671],"category_scores_gemma":[0.002575277,0.000098515775,0.000021412312,0.00081858167,0.0004606417,0.0010881053,0.0142472135,0.00015492464,0.000015096361],"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":[0.00002515845,0.00077983807,0.0065473,0.00017598401,0.00022672603,0.000012004415,0.000019571338,0.00074581656,0.0015994328,0.532269,0.29640216,0.161197],"study_design_scores_gemma":[0.00027209122,0.000010413772,0.0028682735,0.00002016402,0.00011949731,0.000031787353,0.012153679,0.2696049,0.00039057495,0.042428378,0.67185646,0.00024378723],"about_ca_topic_score_codex":0.000051943487,"about_ca_topic_score_gemma":0.00013357852,"teacher_disagreement_score":0.52128285,"about_ca_system_score_codex":0.000012702345,"about_ca_system_score_gemma":0.00016416982,"threshold_uncertainty_score":0.99372536},"labels":[],"label_agreement":null},{"id":"W3217093369","doi":"","title":"Environmental Decision Support Systems: Exactly What Are They?","year":2000,"lang":"en","type":"book-chapter","venue":"IFIP advances in information and communication technology","topic":"Data Quality and Management","field":"Decision Sciences","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 Guelph","funders":"","keywords":"Decision support system; Management science; Computer science; Engineering; Artificial intelligence","score_opus":0.032767156516840985,"score_gpt":0.3210601548778049,"score_spread":0.28829299836096395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217093369","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081052305,0.06808295,0.007530541,0.003868616,0.0009890215,0.0020159164,0.00045050654,0.00042082136,0.9158311],"genre_scores_gemma":[0.17476563,0.78712034,0.0023503802,0.0017536929,0.000030928273,0.00022464352,0.0010014217,0.000037871938,0.032715093],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969424,0.00008189607,0.0016386559,0.00032475576,0.0008091318,0.00020314404],"domain_scores_gemma":[0.9959447,0.00050850544,0.0012227851,0.0021975958,0.00007053886,0.00005592231],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016163602,0.00027856132,0.00048680074,0.0014384072,0.00021041029,0.0005885684,0.001890179,0.00048517258,0.00074951025],"category_scores_gemma":[0.00019985897,0.00024639958,0.00006212107,0.00014940763,0.00041101637,0.0065342826,0.0008570522,0.00052740984,0.0015534818],"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":[0.000023454191,0.00001340977,0.000039098988,0.00001222001,0.000005891825,0.000001013541,0.00023917791,0.00009354214,1.1403714e-7,0.27239645,0.00063397334,0.72654164],"study_design_scores_gemma":[0.00024355488,0.000035089924,0.00005578539,0.00019864812,0.0000061816486,0.000013201746,0.005147452,0.00013532623,0.0000019555546,0.29791,0.69607365,0.0001791557],"about_ca_topic_score_codex":0.000007059762,"about_ca_topic_score_gemma":0.00012625425,"teacher_disagreement_score":0.883116,"about_ca_system_score_codex":0.00013268497,"about_ca_system_score_gemma":0.000027277873,"threshold_uncertainty_score":0.9999988},"labels":[],"label_agreement":null},{"id":"W414933534","doi":"","title":"A FOUNDATION FOR OPEN INFORMATION ENVIRONMENTS","year":2014,"lang":"en","type":"article","venue":"Journal of the Association for Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"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 British Columbia; Memorial University of Newfoundland","funders":"","keywords":"Flexibility (engineering); Computer science; Knowledge management; Diversity (politics); Information system; Set (abstract data type); Information quality; Data science; Information management; Information access; World Wide Web; Engineering","score_opus":0.08888593698032196,"score_gpt":0.37140951018263885,"score_spread":0.2825235732023169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W414933534","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":[0.0015457176,0.000006509865,0.9704374,0.0043345625,0.0054065976,0.0025643131,0.0001881,0.000010071716,0.015506742],"genre_scores_gemma":[0.9876679,0.0000074551426,0.001905139,0.0023927977,0.00039980718,0.00016006664,0.00017088947,0.000007261864,0.0072886352],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961223,0.0002530523,0.0019027304,0.00005582892,0.0015249439,0.00014115483],"domain_scores_gemma":[0.9912969,0.0011350774,0.006285175,0.00030716648,0.00092820596,0.000047484293],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.022304775,0.00008181726,0.0002523987,0.00024432506,0.00032613895,0.0022452231,0.0013563551,0.000076330434,0.0000069243415],"category_scores_gemma":[0.011644058,0.000051894356,0.00018780037,0.0002580807,0.000010475592,0.011654397,0.00017399712,0.00006996593,0.00018548631],"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":[0.0003001223,0.00006687312,0.003749368,0.00011012371,0.0002345853,8.290196e-9,0.0045260875,0.016278572,0.000025405403,0.32715976,0.5420479,0.10550119],"study_design_scores_gemma":[0.001414589,0.0000861147,0.0036914684,0.000022084554,0.000030271083,0.0000014523935,0.0014358533,0.008390115,0.000039456318,0.0064293374,0.9783928,0.000066480265],"about_ca_topic_score_codex":0.000013607069,"about_ca_topic_score_gemma":0.0000038122178,"teacher_disagreement_score":0.98612225,"about_ca_system_score_codex":0.00042696277,"about_ca_system_score_gemma":0.00006113728,"threshold_uncertainty_score":0.99879056},"labels":[],"label_agreement":null},{"id":"W41971205","doi":"10.18584/iipj.2014.5.4.1","title":"The Strategic Power of Data: A Key Aspect of Sovereignty","year":2014,"lang":"en","type":"article","venue":"International Indigenous Policy Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sovereignty; Indigenous; Action (physics); Key (lock); Power (physics); Political science; Space (punctuation); Task (project management); Public relations; Law; Computer science; Politics; Computer security; Economics; Management; Ecology","score_opus":0.2381241877854981,"score_gpt":0.46309834965325014,"score_spread":0.22497416186775204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W41971205","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":[0.500503,0.00027359038,0.013555781,0.0071826535,0.0020001212,0.00028836864,0.0011268673,0.000019380002,0.47505024],"genre_scores_gemma":[0.99764454,0.00010091264,0.0004180452,0.0003207279,0.0004486844,8.0729507e-7,0.00001394761,0.000006178597,0.0010461368],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963267,0.0002965071,0.0010081129,0.00020837493,0.001927559,0.00023278617],"domain_scores_gemma":[0.9961216,0.001302661,0.0010242144,0.00087008136,0.00059201877,0.00008941905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007593226,0.00009808386,0.00020400673,0.0003516115,0.00025925823,0.0004196261,0.004285466,0.000038712682,0.00048688264],"category_scores_gemma":[0.0021010626,0.00005836948,0.00011082757,0.0002913175,0.00019561198,0.0006129922,0.00056584994,0.00020486393,0.00008159969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007004517,0.00015098858,0.00075399724,0.0000025973695,0.00016332876,0.0000055589876,0.0020463679,0.000121079844,0.00009902635,0.97116446,0.006018142,0.019404413],"study_design_scores_gemma":[0.00044124763,0.00018849382,0.007647842,0.000020737805,0.000013245697,0.00011698369,0.003600361,0.000379488,0.00024130759,0.868442,0.118804656,0.00010362693],"about_ca_topic_score_codex":0.00047078793,"about_ca_topic_score_gemma":0.00020030148,"teacher_disagreement_score":0.49714157,"about_ca_system_score_codex":0.000065238455,"about_ca_system_score_gemma":0.000388832,"threshold_uncertainty_score":0.79635334},"labels":[],"label_agreement":null},{"id":"W4200253121","doi":"10.1007/978-3-030-74753-4_16","title":"Mapping CKC Model Through NLP Modelling for APT Groups Reports","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Natural language processing; Artificial intelligence; Computer science; Information retrieval","score_opus":0.45666395393604914,"score_gpt":0.4044982961121337,"score_spread":0.05216565782391541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200253121","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000024288088,0.00023745987,0.5342301,0.00057364,0.00047829366,0.0003969759,0.00008549563,0.00006012941,0.46393546],"genre_scores_gemma":[0.00042932504,0.00025106277,0.12025911,0.00222886,0.00024900178,0.000041160878,0.00034788792,0.000054552256,0.87613904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9939372,0.000032629712,0.0019105556,0.0017017933,0.0020044344,0.00041338438],"domain_scores_gemma":[0.99555284,0.0006509745,0.00086942007,0.0022880551,0.00052247086,0.000116264906],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040832167,0.00044154635,0.00087757595,0.00026861724,0.0002692783,0.000683636,0.00090016215,0.00035243668,0.0014558061],"category_scores_gemma":[0.0003669488,0.00036348356,0.00059027167,0.000107136046,0.000088200264,0.000710519,0.00095162686,0.00028208792,0.00020860584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070982737,0.00001764874,1.5440182e-7,0.000050011753,0.00007654768,0.000073666095,0.00036759683,0.04358569,0.0000017129507,0.8414463,0.10805933,0.0063142884],"study_design_scores_gemma":[0.000057060784,0.00000784134,2.6868383e-8,0.000059113812,0.000021798776,0.0000071474187,0.00029312386,0.1423688,0.000004364979,0.44445446,0.41249275,0.00023353618],"about_ca_topic_score_codex":0.00005129823,"about_ca_topic_score_gemma":0.00007378257,"teacher_disagreement_score":0.413971,"about_ca_system_score_codex":0.000076124285,"about_ca_system_score_gemma":0.0001463277,"threshold_uncertainty_score":0.9998817},"labels":[],"label_agreement":null},{"id":"W4200373115","doi":"10.23974/ijol.2021.vol6.2.204","title":"Virtualization of Research Data Services during the COVID-19 Pandemic as an Opportunity to Enhance Research Data Support","year":2021,"lang":"en","type":"article","venue":"International Journal of Librarianship","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Service (business); Service delivery framework; Data as a service; World Wide Web; Computer science; Coronavirus disease 2019 (COVID-19); Business; Marketing; Medicine","score_opus":0.8286677096185385,"score_gpt":0.6533455342779906,"score_spread":0.17532217534054795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200373115","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":[0.78192174,0.00046755167,0.02380514,0.17070341,0.002917508,0.00069077755,0.0047108047,0.000049352206,0.014733738],"genre_scores_gemma":[0.98953813,0.00030652242,0.000984077,0.0042454368,0.0007434634,0.0000032781977,0.000923289,0.0000147223445,0.0032410752],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98594576,0.0042101317,0.001404089,0.0006961151,0.007428732,0.00031514833],"domain_scores_gemma":[0.98378396,0.006550799,0.0007541051,0.0042304825,0.0038370362,0.00084362994],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.057285927,0.00010617899,0.0002474731,0.0008981143,0.00031962665,0.0016018881,0.017789103,0.00007597772,0.003258499],"category_scores_gemma":[0.046505738,0.0000761448,0.000047007663,0.0015316355,0.00025849024,0.006195166,0.008682891,0.00066740165,0.00011587795],"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":[0.004271119,0.002238045,0.16116774,0.0003230715,0.0010667384,0.0034699296,0.020321116,0.00096703897,0.010069631,0.20917363,0.4762714,0.11066055],"study_design_scores_gemma":[0.000572363,0.00024072207,0.012903942,0.00017145227,0.000019095452,0.00042018667,0.026074719,0.00074366725,0.0028437865,0.1186316,0.8372026,0.0001758395],"about_ca_topic_score_codex":0.0004038329,"about_ca_topic_score_gemma":0.0009581565,"teacher_disagreement_score":0.36093125,"about_ca_system_score_codex":0.00011255487,"about_ca_system_score_gemma":0.0029224236,"threshold_uncertainty_score":0.99943453},"labels":[],"label_agreement":null},{"id":"W4200546404","doi":"10.29173/iq1025","title":"IASSIST gone glocal","year":2021,"lang":"en","type":"article","venue":"IASSIST Quarterly","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Glocalization; Acronym; Framing (construction); Documentation; Political science; Media studies; History; Law; Sociology; Linguistics; Globalization","score_opus":0.15653857254677414,"score_gpt":0.41942364759280903,"score_spread":0.26288507504603487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200546404","genre_codex":"other","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":[0.27541232,0.001412666,0.21077766,0.07025928,0.008599614,0.00068873743,0.0007241899,0.0007301054,0.43139544],"genre_scores_gemma":[0.96565217,0.0000055360942,0.0016452936,0.0027055712,0.00024900798,0.000020192461,0.0000691452,0.000015185993,0.029637922],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960198,0.00044819384,0.0007872719,0.0007894814,0.0015607768,0.00039452274],"domain_scores_gemma":[0.99725515,0.00053572113,0.00018614375,0.0015179717,0.00028946224,0.00021552647],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002194768,0.0001830937,0.0003572752,0.0001352239,0.0002389049,0.0010178357,0.00093058357,0.000084017694,0.0027314129],"category_scores_gemma":[0.0006571875,0.00015089223,0.00021786182,0.00089871726,0.00015474291,0.0005279186,0.00015069912,0.00015838815,0.00626774],"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":[0.000025425285,0.0003099881,0.0005523408,0.000011175276,0.000049025406,0.00027984008,0.00094537967,0.0000032756027,0.00045735727,0.03593353,0.24251476,0.7189179],"study_design_scores_gemma":[0.0005397204,0.00019326022,0.040312782,0.00001967388,0.000030893105,0.000032758722,0.008048995,0.00021830045,0.0004130226,0.029134465,0.92073476,0.00032136272],"about_ca_topic_score_codex":0.00008941768,"about_ca_topic_score_gemma":0.0008979169,"teacher_disagreement_score":0.7185965,"about_ca_system_score_codex":0.000055159253,"about_ca_system_score_gemma":0.00011441322,"threshold_uncertainty_score":0.9981802},"labels":[],"label_agreement":null},{"id":"W4200604891","doi":"10.1061/(asce)cp.1943-5487.0001001","title":"Automating Common Data Integration for Improved Data-Driven Decision-Support System in Industrial Construction","year":2021,"lang":"en","type":"article","venue":"Journal of Computing in Civil Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"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 Alberta","funders":"","keywords":"Data integration; Computer science; Data quality; Identification (biology); Data mining; Semantic integration; Data mapping; Key (lock); Decision support system; Information integration; Data science; Database; Information retrieval; Semantic Web; Engineering; Semantic computing","score_opus":0.18723894972623292,"score_gpt":0.39126347606754397,"score_spread":0.20402452634131105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200604891","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":[0.12535053,0.000046751768,0.87163055,0.00018021812,0.0023830088,0.00019043776,0.00008904029,0.00002745226,0.00010199171],"genre_scores_gemma":[0.8696754,0.000005628449,0.12981819,0.000025883606,0.0003368531,8.692066e-7,0.00012216507,0.000011116851,0.000003915412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657613,0.00015806188,0.0020205101,0.00037704155,0.0006451829,0.00022305654],"domain_scores_gemma":[0.99502677,0.0027974327,0.0008448091,0.0010139901,0.0002488053,0.000068218964],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0116634015,0.00013114288,0.0005105751,0.0005314507,0.00005696675,0.00037628968,0.0016272826,0.00009227621,0.000010820155],"category_scores_gemma":[0.008691252,0.000116968,0.00005541565,0.0007719491,0.000015856127,0.0011661521,0.0010871812,0.0004162955,0.0000020725809],"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":[0.00006971373,0.000096075506,0.0031979207,0.00009981644,0.000056990804,0.00009752428,0.000465736,0.3235343,0.00066603895,0.0021396952,0.0041414923,0.6654347],"study_design_scores_gemma":[0.0012055838,0.000040677798,0.002387734,0.00085534336,0.000016682083,0.0001221178,0.0014776273,0.98990864,0.000063942505,0.00018279304,0.0036243952,0.000114495575],"about_ca_topic_score_codex":0.000020571759,"about_ca_topic_score_gemma":0.0004791104,"teacher_disagreement_score":0.74432486,"about_ca_system_score_codex":0.0001742961,"about_ca_system_score_gemma":0.00020027712,"threshold_uncertainty_score":0.99965894},"labels":[],"label_agreement":null},{"id":"W4210809982","doi":"10.2196/preprints.12465","title":"Improving Digital Hospital Transformation: Development of an Outcomes-Based Infrastructure Maturity Assessment Framework (Preprint)","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Cisco Systems (Canada)","funders":"","keywords":"Capability Maturity Model; Preprint; Maturity (psychological); Health care; Analytics; Information technology; Digital transformation; Business; Process management; Quality (philosophy); Information system; Digital health; Knowledge management; Health information technology; Computer science; Data science; Engineering; World Wide Web","score_opus":0.05618803089164384,"score_gpt":0.3910087864215082,"score_spread":0.33482075552986434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210809982","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":[0.30277136,0.0000041583157,0.68781304,0.00066357915,0.0012748291,0.0009875555,0.0003707335,0.00012753013,0.005987184],"genre_scores_gemma":[0.71317333,8.042092e-7,0.28585488,0.00028300926,0.00006816816,0.000056983732,0.00042817058,0.00001780104,0.00011683133],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924946,0.00021220917,0.002403958,0.0012899357,0.0031789101,0.00042037872],"domain_scores_gemma":[0.9946922,0.0005249818,0.001224279,0.0026736378,0.0006335463,0.00025132403],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004662571,0.0005384211,0.000914143,0.0004292583,0.00022593985,0.0017814644,0.003039084,0.0005365269,0.0017954953],"category_scores_gemma":[0.0011350072,0.0003969604,0.00035334204,0.0003525137,0.0002193605,0.0013481403,0.0023937337,0.00088102376,0.00013153449],"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":[0.00010785733,0.0014207882,0.017926939,0.00083677063,0.00040507005,0.000010238922,0.0097701615,0.0035507749,0.000013577377,0.022396024,0.0032898537,0.9402719],"study_design_scores_gemma":[0.0015037272,0.00050054473,0.52500767,0.00048161804,0.0001123616,0.0000019538297,0.008681206,0.02975063,0.0023784288,0.3937786,0.035456497,0.0023467746],"about_ca_topic_score_codex":0.000044465978,"about_ca_topic_score_gemma":0.000050194092,"teacher_disagreement_score":0.93792516,"about_ca_system_score_codex":0.00024759973,"about_ca_system_score_gemma":0.00095546356,"threshold_uncertainty_score":0.99984825},"labels":[],"label_agreement":null},{"id":"W4210862833","doi":"10.1186/s40537-021-00468-0","title":"Big data quality framework: a holistic approach to continuous quality management","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Big data; Computer science; Data quality; Profiling (computer programming); Data science; Data mining; Quality (philosophy); Data management; Exploratory data analysis; Engineering; Operations management","score_opus":0.7948772270531455,"score_gpt":0.5341265486844159,"score_spread":0.26075067836872956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210862833","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":[0.0051803603,0.00066493574,0.9570451,0.008075943,0.0047591478,0.0003519765,0.006621786,0.00002873136,0.017272016],"genre_scores_gemma":[0.6252039,0.0011314885,0.3299585,0.018971471,0.0061247917,0.0000145405065,0.0051567936,0.00008357462,0.013354921],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98893905,0.0019356688,0.0030110741,0.0014158335,0.004177032,0.0005213502],"domain_scores_gemma":[0.9817297,0.0021597894,0.0017153798,0.013071508,0.00079468807,0.00052894617],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.040043317,0.00027553967,0.0010198185,0.0004144787,0.00020622801,0.0014006472,0.012576649,0.0001231949,0.00015494459],"category_scores_gemma":[0.026830984,0.00021256179,0.00015011702,0.0016588402,0.0001337335,0.0013288544,0.015088393,0.0005726027,0.00029152958],"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":[0.0001520835,0.0009380399,0.00045112928,0.000107609914,0.00029874028,0.00022944418,0.00031074195,0.00003254838,0.000023777813,0.026836554,0.3750104,0.5956089],"study_design_scores_gemma":[0.00076544966,0.00005569167,0.01954164,0.0001260307,0.00017023509,0.000062544255,0.007386626,0.00016722253,0.000015897142,0.029006477,0.94234633,0.0003558746],"about_ca_topic_score_codex":0.00015622175,"about_ca_topic_score_gemma":0.00021521508,"teacher_disagreement_score":0.62708664,"about_ca_system_score_codex":0.00007502545,"about_ca_system_score_gemma":0.0002600313,"threshold_uncertainty_score":0.999636},"labels":[],"label_agreement":null},{"id":"W4210979382","doi":"10.2200/s00878ed1v01y201810dtm052","title":"Data Profiling","year":2018,"lang":"en","type":"article","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Metadata; Computer science; Data science; Research data; Information retrieval; World Wide Web; Data curation; Operating system","score_opus":0.484101918142008,"score_gpt":0.4815667505532124,"score_spread":0.0025351675887955727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210979382","genre_codex":"other","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":[0.0032401956,0.00039116232,0.25060531,0.025620483,0.0046062586,0.0033732643,0.018244648,0.0008294906,0.6930892],"genre_scores_gemma":[0.8634092,0.00038187855,0.092258304,0.018885942,0.0023947915,0.00017390533,0.0063476367,0.00013522289,0.01601309],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9933612,0.0004981734,0.0007871318,0.0023856666,0.0024249507,0.0005428895],"domain_scores_gemma":[0.9801961,0.001398888,0.00028232604,0.017882837,0.000099683755,0.00014012499],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.010508154,0.00029909902,0.000361493,0.00050028163,0.00042359892,0.0010864604,0.017137906,0.00006541733,0.002094951],"category_scores_gemma":[0.006264756,0.00021549272,0.00005026725,0.00085596513,0.00025137138,0.0013841346,0.013922841,0.0001553815,0.0062313154],"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":[0.00006593727,0.00012538215,0.000040022485,0.000021713013,0.0001414978,0.000022304472,0.00002563823,0.000012186265,0.0000143453235,0.025711084,0.59031796,0.38350192],"study_design_scores_gemma":[0.00015513223,0.00005704506,0.00095920614,0.000043441767,0.00010255206,0.0000013770582,0.00044311,0.0034521024,0.0008636045,0.011566673,0.98205805,0.0002977346],"about_ca_topic_score_codex":0.000042027255,"about_ca_topic_score_gemma":0.00030099292,"teacher_disagreement_score":0.86016905,"about_ca_system_score_codex":0.000042517266,"about_ca_system_score_gemma":0.0000267424,"threshold_uncertainty_score":0.9999505},"labels":[],"label_agreement":null},{"id":"W4211029301","doi":"10.2200/s00439ed1v01y201207dtm030","title":"Foundations of Data Quality Management","year":2012,"lang":"en","type":"article","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":131,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; Engineering and Physical Sciences Research Council; Universiteit Antwerpen; University of Waterloo; National Natural Science Foundation of China","keywords":"Data quality; Data management; Computer science; Quality (philosophy); Data governance; Data science; Data administration; Database; Database design; Operations management; Engineering; Database model","score_opus":0.6066300196494542,"score_gpt":0.5319929733621165,"score_spread":0.0746370462873377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211029301","genre_codex":"other","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":[0.0034892573,0.0008780266,0.3307499,0.012690927,0.0030134546,0.0037809014,0.013879341,0.00040241654,0.63111573],"genre_scores_gemma":[0.937087,0.00056905806,0.04946674,0.002483559,0.00031211076,0.00013663329,0.0035934127,0.000054203538,0.0062972615],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920037,0.0009916719,0.0015056756,0.0016230503,0.003175681,0.0007002618],"domain_scores_gemma":[0.9797807,0.0023259572,0.00066759397,0.016926048,0.000086540975,0.00021315922],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.018718543,0.00035818465,0.000573521,0.0007232066,0.0002991184,0.00042870198,0.012816688,0.00007258045,0.0020192352],"category_scores_gemma":[0.002529032,0.00027895774,0.0001080621,0.001098389,0.00020181456,0.0028334642,0.012655957,0.00015835784,0.001552274],"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":[0.000072860945,0.0007017435,0.00034129192,0.00014641843,0.0005127017,0.000005366129,0.00008089448,0.000045435256,0.000006242631,0.2117513,0.2972604,0.48907533],"study_design_scores_gemma":[0.00029210895,0.00002380189,0.028003672,0.00006337895,0.0003219129,8.8324566e-7,0.0013823523,0.0002606537,0.00014768075,0.010048802,0.9590755,0.0003792356],"about_ca_topic_score_codex":0.00011940646,"about_ca_topic_score_gemma":0.00013868428,"teacher_disagreement_score":0.93359774,"about_ca_system_score_codex":0.00007324387,"about_ca_system_score_gemma":0.000016556985,"threshold_uncertainty_score":0.99996626},"labels":[],"label_agreement":null},{"id":"W4214900227","doi":"10.23889/ijpds.v7i1.1689","title":"Describing the linkage between administrative social assistance and health care databases in Ontario, Canada","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","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":true,"ca_institutions":"Ministry of Children, Community and Social Services; Hospital for Sick Children; Public Health Ontario; Trillium Health Centre; SickKids Foundation; University of Toronto; Institute for Clinical Evaluative Sciences; Centre for Addiction and Mental Health","funders":"","keywords":"Record linkage; Database; Linkage (software); Representativeness heuristic; Population; Service (business); Medicine; Christian ministry; Business; Computer science; Environmental health; Psychology; Political science","score_opus":0.658627486546011,"score_gpt":0.5247302681115205,"score_spread":0.13389721843449054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214900227","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":[0.8447929,0.00033616202,0.031094844,0.09269216,0.0075874454,0.0011377933,0.021552417,0.00002092005,0.0007853394],"genre_scores_gemma":[0.99583536,0.000003464738,0.0014218373,0.001397553,0.00012730592,0.000008851744,0.0010553836,0.0000028925233,0.00014734776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9958652,0.00018323533,0.00062713993,0.0004379714,0.002676481,0.00020994511],"domain_scores_gemma":[0.99836254,0.0004102063,0.0005003981,0.00037086176,0.00025846632,0.000097518976],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.008498362,0.00007593482,0.00012977161,0.00020596058,0.0019301508,0.00073768094,0.003242055,0.0000056522676,0.00012437247],"category_scores_gemma":[0.0013674576,0.000057768426,0.000020201998,0.00040371675,0.00012139684,0.0019720653,0.0015376693,0.00027629588,4.5029188e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010101724,0.00006185213,0.6898725,0.000005317736,0.000040462903,0.00003270306,0.007442559,0.0008270035,0.000008927401,0.053502362,0.10063249,0.14747283],"study_design_scores_gemma":[0.0002691165,0.000026787453,0.7507484,0.00001249254,0.0000039711917,0.0000142125255,0.010889794,0.0006294482,0.000002185257,0.0015077624,0.23580638,0.00008947956],"about_ca_topic_score_codex":0.7720856,"about_ca_topic_score_gemma":0.9880192,"teacher_disagreement_score":0.21593359,"about_ca_system_score_codex":0.0013878202,"about_ca_system_score_gemma":0.0028588434,"threshold_uncertainty_score":0.9993692},"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":"W4225009152","doi":"10.1080/10903127.2022.2044417","title":"Joint Statement on Lights &amp; Siren Vehicle Operations on Emergency Medical Services Responses","year":2022,"lang":"en","type":"article","venue":"Prehospital Emergency Care","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Niagara College","funders":"","keywords":"Siren (mythology); Medicine; Emergency medical services; Medical emergency; Statement (logic); Joint (building); Aeronautics; Engineering; Law","score_opus":0.11843764649449767,"score_gpt":0.4120196332112333,"score_spread":0.29358198671673563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225009152","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":[0.97012687,0.0006643963,0.00022574274,0.0086795185,0.005047743,0.00083768915,0.0011525991,0.00015228616,0.013113162],"genre_scores_gemma":[0.98517257,0.00032345817,0.00010946773,0.0008902074,0.00017897115,0.00040434365,0.00045653505,0.000029745068,0.012434693],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99099785,0.0009621843,0.001510975,0.0010639345,0.004974426,0.000490655],"domain_scores_gemma":[0.99748904,0.000148336,0.00023441415,0.0014731248,0.00032362182,0.00033147907],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027210256,0.00031658876,0.00034375006,0.00037665394,0.0012590204,0.00012413794,0.0018529235,0.000068102345,0.05967998],"category_scores_gemma":[0.00080182374,0.00025922497,0.00026319173,0.00089418056,0.000044778903,0.0004412413,0.0014446956,0.00038590422,0.002866502],"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":[0.00077332184,0.0031933717,0.010627128,0.00024404113,0.00034778903,0.00014931368,0.06599903,0.014251271,0.00053541735,0.05589739,0.7869554,0.061026514],"study_design_scores_gemma":[0.00061841344,0.001544416,0.022030633,0.000038020382,0.000039775674,0.0000016184707,0.025748506,0.0009645751,0.00037631928,0.0072806147,0.94066274,0.00069436495],"about_ca_topic_score_codex":0.00050023856,"about_ca_topic_score_gemma":0.0018363576,"teacher_disagreement_score":0.15370733,"about_ca_system_score_codex":0.00021109814,"about_ca_system_score_gemma":0.00014785348,"threshold_uncertainty_score":0.999986},"labels":[],"label_agreement":null},{"id":"W4225143092","doi":"10.1145/3533021","title":"A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":13,"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 Ottawa","funders":"","keywords":"Categorical variable; Computer science; Field (mathematics); Machine learning; Data mining; Artificial intelligence; Set (abstract data type); Data field; Software; Mathematics","score_opus":0.3306833255399733,"score_gpt":0.4220707860804389,"score_spread":0.09138746054046559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225143092","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":[0.003516193,0.00016807271,0.99535877,0.00022941822,0.00021108949,0.00017547769,0.00019406037,0.00013723939,0.000009670572],"genre_scores_gemma":[0.29686266,0.000055593173,0.7024347,0.00009472036,0.0000108851955,0.00009923197,0.00018292986,0.000012479184,0.00024675843],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983908,0.00036783918,0.000404708,0.0003978476,0.0002475862,0.0001912311],"domain_scores_gemma":[0.99391234,0.0053124633,0.000078216566,0.00063031766,0.000024620285,0.000042032807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005326908,0.00009919571,0.00030119144,0.00035483149,0.00014039484,0.00001883535,0.00071715965,0.00006303361,0.000053219243],"category_scores_gemma":[0.004852156,0.00008775925,0.000048684553,0.0004366402,0.00002259414,0.00012277426,0.00012441057,0.00035242477,5.0618513e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009696207,0.000111046225,0.00012560481,0.000057461028,0.000044952674,0.0000024974968,0.00065658905,0.9154909,0.000033208238,0.0008473601,0.00021756567,0.08231585],"study_design_scores_gemma":[0.00077335804,0.00022526475,0.00029985566,0.0000051987563,0.000039900013,0.000023901353,0.00090095244,0.96240747,0.00011190363,0.002630606,0.032416694,0.00016490715],"about_ca_topic_score_codex":0.000098790944,"about_ca_topic_score_gemma":0.000016622393,"teacher_disagreement_score":0.29334646,"about_ca_system_score_codex":0.000022831644,"about_ca_system_score_gemma":0.000020058358,"threshold_uncertainty_score":0.5808835},"labels":[],"label_agreement":null},{"id":"W4225160911","doi":"10.1016/j.compeleceng.2022.107985","title":"An efficient framework for semantically-correlated term detection and sanitization in clinical documents","year":2022,"lang":"en","type":"article","venue":"Computers & Electrical Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Term (time); Computer science; Information retrieval; Data mining; Physics","score_opus":0.044887310654674134,"score_gpt":0.37684828744487653,"score_spread":0.3319609767902024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225160911","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":[0.2324127,0.000033481552,0.7665279,0.00009639789,0.00058764196,0.0002705091,0.0000030897681,0.00006125379,0.000007055775],"genre_scores_gemma":[0.9880182,0.000005319081,0.011597628,0.00024200749,0.00006437431,0.000040189752,0.000012930653,0.000011084613,0.00000827474],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979817,0.00018306618,0.00062259374,0.00046687233,0.00047842663,0.00026728868],"domain_scores_gemma":[0.9979597,0.0015416158,0.000087269065,0.0002651185,0.00003728933,0.00010904244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024567437,0.00010624592,0.00022534408,0.00032713855,0.00014007291,0.00017934784,0.00037419642,0.0000602633,0.000014516273],"category_scores_gemma":[0.0011297272,0.00010496393,0.000057071018,0.00093332963,0.000017007298,0.00013340269,0.00021655804,0.00033038092,0.0000041308354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001222683,0.0004148229,0.0010613734,0.000016027476,0.000027538299,0.000015383399,0.00028330652,0.50741076,0.00025851582,0.027819887,0.00025210707,0.462318],"study_design_scores_gemma":[0.00043724861,0.00032565813,0.015002519,0.000009446644,0.000008785568,0.0000039748056,0.000023778925,0.9778281,0.00002867543,0.0042509534,0.0019507668,0.00013012563],"about_ca_topic_score_codex":0.000005342571,"about_ca_topic_score_gemma":0.0000010968188,"teacher_disagreement_score":0.7556055,"about_ca_system_score_codex":0.00009263118,"about_ca_system_score_gemma":0.00001512986,"threshold_uncertainty_score":0.4280305},"labels":[],"label_agreement":null},{"id":"W4226372432","doi":"10.2196/36711","title":"Linking Biomedical Data Warehouse Records With the National Mortality Database in France: Large-scale Matching Algorithm","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Conseil Régional des Pays de la Loire; Agence Nationale de la Recherche","keywords":"Algorithm; Database; Matching (statistics); Computer science; Data mining; Identifier; Scale (ratio); Medicine; Statistics; Mathematics; Cartography; Geography","score_opus":0.12455254929085986,"score_gpt":0.4246629664904805,"score_spread":0.30011041719962067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226372432","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":[0.1389079,0.00008071556,0.8230654,0.021164957,0.0014729929,0.0014264705,0.009549318,0.00021495202,0.004117312],"genre_scores_gemma":[0.49612832,0.00035043777,0.24834745,0.20697196,0.0032116638,0.0020110859,0.03816611,0.00017913859,0.0046338574],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9876535,0.00043075066,0.0013583006,0.0003490544,0.009769137,0.00043929036],"domain_scores_gemma":[0.99665266,0.0011767725,0.00040540437,0.0014115896,0.0001061247,0.00024742467],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.025387168,0.00016532802,0.00030511004,0.00026288783,0.0005432549,0.00026763033,0.004369222,0.00007761544,0.0019648296],"category_scores_gemma":[0.0010322965,0.0000986364,0.0000436065,0.0014688971,0.00029404205,0.0014195595,0.005353059,0.0010957395,0.000114717936],"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":[0.000053791682,0.0016355943,0.0055703428,0.00019359557,0.00011962269,0.00016149461,0.03640609,0.00056105753,9.3746553e-7,0.003979421,0.6942838,0.25703427],"study_design_scores_gemma":[0.0008177545,0.000049124003,0.0021167404,0.000047273566,0.000008542575,0.000022412454,0.024678882,0.245315,4.2333886e-7,0.0018736491,0.7249083,0.00016190372],"about_ca_topic_score_codex":0.00010663916,"about_ca_topic_score_gemma":0.00037822057,"teacher_disagreement_score":0.57471794,"about_ca_system_score_codex":0.00008559029,"about_ca_system_score_gemma":0.00043326936,"threshold_uncertainty_score":0.9989475},"labels":[],"label_agreement":null},{"id":"W4229784727","doi":"10.4018/978-1-59904-951-9.ch077","title":"The Use of Smart Tokens in Cleaning Integrated Warehouse Data","year":2008,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Data warehouse; Computer science; Security token; Database; Alphanumeric; Matching (statistics); Data mining","score_opus":0.3727475774821563,"score_gpt":0.38089613504841335,"score_spread":0.008148557566257042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229784727","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032826053,0.00033858584,0.0010854333,0.00031302185,0.00086955924,0.00062428846,0.004097533,0.000083607054,0.9922597],"genre_scores_gemma":[0.08896004,0.0009009904,0.0045123864,0.0046828543,0.0003493687,0.000025037029,0.0004315276,0.00015789099,0.8999799],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99579406,0.00016706415,0.0013190032,0.00082416314,0.0015587275,0.0003369911],"domain_scores_gemma":[0.9944052,0.0010139346,0.0006079798,0.0036426405,0.00022766202,0.00010255356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020983054,0.0003229992,0.00057127577,0.00015296493,0.0001642541,0.00039491424,0.0036184785,0.00021952752,0.000053018826],"category_scores_gemma":[0.0017007497,0.00021014862,0.00013727398,0.000094924355,0.00039921227,0.00030873236,0.0025461023,0.00036704596,0.00031550042],"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":[0.00009562838,0.000013369002,0.000042825635,0.0000056316903,0.000055199856,0.00008835274,0.00012226695,0.000024886815,4.4792537e-7,0.58983636,0.3205917,0.08912337],"study_design_scores_gemma":[0.00019814385,0.000045195793,0.00009177911,0.00012299133,0.000023411958,0.000009580382,0.00012483298,0.00022363392,0.000002921209,0.06203735,0.93690753,0.0002126337],"about_ca_topic_score_codex":0.001337499,"about_ca_topic_score_gemma":0.0122505855,"teacher_disagreement_score":0.61631584,"about_ca_system_score_codex":0.00012161798,"about_ca_system_score_gemma":0.00022057339,"threshold_uncertainty_score":0.8569612},"labels":[],"label_agreement":null},{"id":"W4230003669","doi":"10.1007/978-0-387-39940-9_2388","title":"Data Reconciliation","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Geology; Computer science","score_opus":0.24306039818885264,"score_gpt":0.3890158151243503,"score_spread":0.14595541693549766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230003669","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000046578457,0.002307941,0.0034681188,0.00024286102,0.0027774654,0.00076814165,0.04422382,0.000058157555,0.9461488],"genre_scores_gemma":[0.00008698339,0.0037294098,0.0009864547,0.00014306269,0.00096277567,0.000008669482,0.02056519,0.000036804777,0.97348064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99269444,0.00022086408,0.002342631,0.001430558,0.0030329742,0.0002785451],"domain_scores_gemma":[0.98881775,0.0010153942,0.0018802668,0.007736814,0.00037917274,0.00017058144],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009055703,0.00040248933,0.0009938875,0.0005271473,0.00008701084,0.0001945924,0.004365214,0.00025389032,0.0012041087],"category_scores_gemma":[0.0026185827,0.0003348012,0.00013198216,0.00015003048,0.00011160397,0.001355196,0.0016847164,0.00032897593,0.0027150689],"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":[0.00001528026,0.000028235194,0.000007961167,0.00011233131,0.000057811136,0.000024769428,0.000049734703,0.000008427633,0.0000018268302,0.12968054,0.7756371,0.094375975],"study_design_scores_gemma":[0.00019558868,0.000049121514,0.000023240862,0.0003465952,0.00009162906,0.0000052810833,0.00012520474,0.00024970213,8.8322037e-7,0.006970971,0.9915964,0.00034535988],"about_ca_topic_score_codex":0.00022131992,"about_ca_topic_score_gemma":0.00032776542,"teacher_disagreement_score":0.21595931,"about_ca_system_score_codex":0.00006399676,"about_ca_system_score_gemma":0.00023438499,"threshold_uncertainty_score":0.9999104},"labels":[],"label_agreement":null},{"id":"W4230325026","doi":"10.32920/ryerson.14639367.v1","title":"ORCID IDs in the open knowledge era","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Toronto Metropolitan University","funders":"","keywords":"Metadata; Identifier; World Wide Web; Computer science; Interoperability; Unique identifier; Outreach; Library science; Political science; Programming language","score_opus":0.530129337104347,"score_gpt":0.55318074981532,"score_spread":0.023051412710972996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230325026","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004848192,0.0003298872,0.0092619555,0.014218275,0.0013862328,0.0009444757,0.00004040783,0.000022366456,0.9689482],"genre_scores_gemma":[0.79402053,0.0002866699,0.01022878,0.015255699,0.0003318997,0.00043182488,0.0003567788,0.000023481844,0.17906435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956581,0.0013626743,0.0007755393,0.0009196111,0.001064857,0.00021919007],"domain_scores_gemma":[0.9955326,0.0012196242,0.00016647282,0.0028692498,0.00016340733,0.000048676273],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.017331118,0.00017460281,0.00041495424,0.00019134785,0.00009169287,0.005029863,0.010044125,0.0001293212,0.006035502],"category_scores_gemma":[0.0018028909,0.0000943072,0.00012736634,0.0007108102,0.00006589555,0.0003823977,0.021096049,0.00055845303,0.0013100031],"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":[0.00000912354,0.00032305336,0.00026737803,0.000028793538,0.000026196209,0.000045239867,0.006031595,0.00007959077,0.0000023289797,0.22127293,0.6413461,0.13056764],"study_design_scores_gemma":[0.00020283589,0.000013377865,0.00811844,0.00005886256,0.000011064475,0.0000014960001,0.016254753,0.00039022326,0.000025247833,0.13753797,0.83716965,0.00021605426],"about_ca_topic_score_codex":0.0015483582,"about_ca_topic_score_gemma":0.013977572,"teacher_disagreement_score":0.78988385,"about_ca_system_score_codex":0.00003917883,"about_ca_system_score_gemma":0.00036486666,"threshold_uncertainty_score":0.9994676},"labels":[],"label_agreement":null},{"id":"W4230742320","doi":"10.1007/978-0-387-39940-9_2353","title":"Data Flow Diagrams","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.19180635649045114,"score_gpt":0.3763419300888647,"score_spread":0.18453557359841355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230742320","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002713301,0.0038532023,0.0070743565,0.0002423757,0.0034881681,0.0009606307,0.06833275,0.00008464238,0.91596115],"genre_scores_gemma":[0.00007830044,0.005498845,0.002368413,0.00018224497,0.001481332,0.000015205405,0.02747947,0.00006463955,0.96283156],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99085563,0.0002659877,0.0026097246,0.001875537,0.0039487816,0.00044431968],"domain_scores_gemma":[0.98557776,0.0013117435,0.0016364917,0.010849183,0.00032934992,0.00029547687],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008432045,0.0005989794,0.0014136843,0.00058355153,0.00011901899,0.0003076576,0.0069314735,0.00031506372,0.0013550526],"category_scores_gemma":[0.0023098984,0.00047589865,0.0002127831,0.00020367498,0.0002119048,0.0013106972,0.0032575293,0.00047957498,0.0036577485],"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":[0.000016417038,0.000055062974,0.000008733626,0.00014326708,0.00009057799,0.00008586545,0.000054107615,0.000021322603,9.232555e-7,0.095736615,0.7692569,0.13453023],"study_design_scores_gemma":[0.00025020936,0.00006418779,0.000017530772,0.00046244575,0.00013460855,0.000009739719,0.00012890837,0.0007149459,6.205406e-7,0.00664885,0.99105793,0.000510022],"about_ca_topic_score_codex":0.00022784101,"about_ca_topic_score_gemma":0.00041949586,"teacher_disagreement_score":0.22180106,"about_ca_system_score_codex":0.000051524246,"about_ca_system_score_gemma":0.00022332424,"threshold_uncertainty_score":0.9997693},"labels":[],"label_agreement":null},{"id":"W4232185901","doi":"10.1109/icse.2001.919157","title":"2nd international workshop on living with inconsistency","year":2001,"lang":"en","type":"article","venue":"Proceedings of the 23rd International Conference on Software Engineering. ICSE 2001","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.10551223806098867,"score_gpt":0.3396156170632339,"score_spread":0.23410337900224523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232185901","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":[0.65177125,0.000044845678,0.04255517,0.0217274,0.0066891047,0.0010701539,0.00024362859,0.0005727166,0.27532575],"genre_scores_gemma":[0.98293644,0.00009069479,0.0052609476,0.0007245599,0.00022483409,0.00003519289,0.00000825941,0.000025771364,0.010693297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99647737,0.000013052627,0.00058828795,0.0005254493,0.0021075653,0.00028829754],"domain_scores_gemma":[0.9974119,0.0005736988,0.0004156279,0.00033788857,0.0011516379,0.000109224224],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012606363,0.00025756616,0.0002595727,0.0004454105,0.00009043776,0.00043077432,0.002616144,0.00008124923,0.001341784],"category_scores_gemma":[0.0075677107,0.0001726673,0.00012898973,0.0005535899,0.00009998113,0.00061298185,0.0005383144,0.00034083676,0.00010777183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006361799,0.001120624,0.09217725,0.0000613946,0.00061564305,0.000018796803,0.0014941357,0.0074027316,0.0008105089,0.76206505,0.085702874,0.047894802],"study_design_scores_gemma":[0.0034651158,0.001119497,0.21356706,0.0068028057,0.00015065618,0.00020217686,0.0076828203,0.09708103,0.0024020802,0.032655727,0.6321053,0.0027657044],"about_ca_topic_score_codex":0.000019761761,"about_ca_topic_score_gemma":0.000015229923,"teacher_disagreement_score":0.72940934,"about_ca_system_score_codex":0.00012829021,"about_ca_system_score_gemma":0.000050425228,"threshold_uncertainty_score":0.99957114},"labels":[],"label_agreement":null},{"id":"W4232692662","doi":"10.21203/rs.2.22164/v2","title":"Innovative use of data sources: A Cross-sectional study of Data Linkage and Artificial Intelligence Practices across European Countries","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Data Quality and Management","field":"Decision Sciences","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":"National Research Council Canada; Institute of Health Economics","funders":"Norwegian Institute of Public Health; Public Health Agency; Helsedirektoratet; Institut National de la Santé et de la Recherche Médicale; Folkhälsomyndigheten; European Commission","keywords":"Linkage (software); Artificial intelligence; Cross-sectional study; Cross-sectional data; Data science; Computer science; Psychology; Econometrics; Statistics; Economics; Mathematics; Biology","score_opus":0.8831522603204187,"score_gpt":0.6579785674833427,"score_spread":0.225173692837076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232692662","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":[0.93693703,0.00026945598,0.015605278,0.0011405142,0.00026393821,0.0022141594,0.043246325,0.000041023268,0.000282277],"genre_scores_gemma":[0.99514765,0.00028174394,0.0014994664,0.00004575045,0.00023568579,0.000017298058,0.0025717702,0.000024461062,0.00017618191],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.982129,0.005161783,0.0024553172,0.0027587572,0.0069834264,0.00051175844],"domain_scores_gemma":[0.975024,0.011126251,0.0023605959,0.0070723374,0.004250291,0.00016655287],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.057754625,0.0002661044,0.00065144605,0.0005068453,0.00047220814,0.004021866,0.009866968,0.00014199392,0.00017577634],"category_scores_gemma":[0.07254955,0.0002168137,0.000038963575,0.0021753707,0.0016743742,0.0035916101,0.07439256,0.0015584858,0.0000969143],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041309455,0.0061085243,0.7211722,0.005255202,0.001731413,0.0004566196,0.08665153,0.0013562579,0.00015492654,0.016880238,0.021536639,0.1345655],"study_design_scores_gemma":[0.0005340114,0.0016569062,0.65111434,0.00066372874,0.00006157928,0.0000052887044,0.17265694,0.011628572,0.00021946112,0.018718328,0.14198208,0.0007587741],"about_ca_topic_score_codex":0.0032041967,"about_ca_topic_score_gemma":0.002486871,"teacher_disagreement_score":0.13380674,"about_ca_system_score_codex":0.000039027746,"about_ca_system_score_gemma":0.00055492774,"threshold_uncertainty_score":0.9970121},"labels":[],"label_agreement":null},{"id":"W4235765738","doi":"10.1007/978-0-387-39940-9_2404","title":"Data Utility Measures","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.2837700046111019,"score_gpt":0.39175607703186327,"score_spread":0.10798607242076136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235765738","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000036467131,0.0047202534,0.0054094717,0.00019338139,0.0024341526,0.00089370157,0.06294834,0.00007836294,0.9233187],"genre_scores_gemma":[0.000675593,0.004433983,0.0008978794,0.0001536051,0.0010409431,0.000011710563,0.014101504,0.00005491482,0.9786299],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9897843,0.00039499233,0.0027116537,0.0019396347,0.0047628162,0.00040659372],"domain_scores_gemma":[0.9847097,0.0011884822,0.0016823501,0.011665743,0.00048179142,0.00027194858],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014015507,0.0005647298,0.0014115183,0.0005347864,0.00012802819,0.0002485458,0.0068641854,0.0003051913,0.0013574503],"category_scores_gemma":[0.0036610113,0.0004489084,0.00020669901,0.00017931986,0.00026481523,0.0012281332,0.0030242836,0.00048453498,0.0019123487],"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":[0.000029500778,0.000060578175,0.000020432613,0.00015398883,0.00009991459,0.00004799399,0.000049839764,0.0000030790843,0.000001486687,0.09112633,0.786902,0.12150484],"study_design_scores_gemma":[0.00020821285,0.00004390073,0.000063324995,0.0003547863,0.00013331861,0.0000071451736,0.00014827032,0.0001588958,0.0000011525692,0.008140484,0.9903058,0.00043475197],"about_ca_topic_score_codex":0.00037970778,"about_ca_topic_score_gemma":0.000528076,"teacher_disagreement_score":0.20340374,"about_ca_system_score_codex":0.00004413521,"about_ca_system_score_gemma":0.0003012154,"threshold_uncertainty_score":0.9997963},"labels":[],"label_agreement":null},{"id":"W4236290949","doi":"10.4018/9781609602000.ch023","title":"Do You Know Where Your Data Is?","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Alberta","funders":"","keywords":"Need to know; Computer science; Data science; Computer security","score_opus":0.28092519451972603,"score_gpt":0.40100844440042255,"score_spread":0.12008324988069652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236290949","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003785229,0.0017794111,0.0010992531,0.0005878546,0.0014840794,0.00042532227,0.0083441,0.000117528696,0.98615867],"genre_scores_gemma":[0.0015259935,0.00010795959,0.0007852035,0.0025591315,0.00048689204,0.0000068256563,0.00009657419,0.000043849243,0.99438757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99408394,0.000084460604,0.0010052188,0.0019386258,0.002390386,0.00049738545],"domain_scores_gemma":[0.9914606,0.00012227832,0.0006860679,0.0071480675,0.0002734693,0.0003094763],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025152247,0.0005696011,0.0007708849,0.00015486439,0.0001773676,0.00090785907,0.0074535497,0.00047696504,0.004544926],"category_scores_gemma":[0.00029694813,0.0004592222,0.00026216637,0.00005064505,0.00026283684,0.0004004188,0.0055608163,0.0003700535,0.018913876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016840833,0.000008408261,0.000005201379,0.00001028207,0.00006126708,0.00004070217,0.00006126365,5.0194224e-8,1.2539637e-7,0.5026705,0.3983103,0.098815024],"study_design_scores_gemma":[0.00013137837,0.000029663657,0.000009419251,0.00008200498,0.000062076935,0.000007571888,0.00006589761,0.0000032888013,9.3069923e-7,0.4622522,0.53706867,0.00028688376],"about_ca_topic_score_codex":0.00032639538,"about_ca_topic_score_gemma":0.00074487634,"teacher_disagreement_score":0.13875836,"about_ca_system_score_codex":0.00010202482,"about_ca_system_score_gemma":0.00021531696,"threshold_uncertainty_score":0.99978596},"labels":[],"label_agreement":null},{"id":"W4237174812","doi":"10.2139/ssrn.3254297","title":"Entity Set Expansion with Semantic Features of Knowledge Graphs","year":2018,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Natural language processing; Information retrieval; Set (abstract data type); Artificial intelligence; Programming language","score_opus":0.04820797742969012,"score_gpt":0.3650064786949731,"score_spread":0.316798501265283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237174812","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":[0.95081306,0.002662318,0.035937246,0.0010204624,0.0006194309,0.0002200047,0.00001574809,0.00003347429,0.008678281],"genre_scores_gemma":[0.9942834,0.00072153896,0.00014509876,0.00008192198,0.00014276525,0.0000014789333,0.0000035836879,0.000008909899,0.0046112994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99678266,0.00031136334,0.00046737242,0.00030274063,0.0010121217,0.0011237399],"domain_scores_gemma":[0.99845225,0.0001682985,0.0003505707,0.00051106483,0.00043206048,0.00008575695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008363786,0.00013509043,0.0002606172,0.00034647243,0.00027991275,0.00014842958,0.0009360074,0.000049926217,0.00015573841],"category_scores_gemma":[0.00034881226,0.00008364355,0.00011366082,0.0007663506,0.00024598037,0.00046552744,0.00016595403,0.000655537,0.00016936418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030192026,0.0002735006,0.002994338,0.000015990276,0.0002436722,0.000005931239,0.002007936,0.000005558538,0.0006636792,0.8481337,0.021828769,0.123525],"study_design_scores_gemma":[0.0008783095,0.0014190053,0.010915117,0.00005653585,0.000069231755,0.00022185236,0.008103083,0.000045251414,0.0012733315,0.95152855,0.025273332,0.00021641515],"about_ca_topic_score_codex":0.00010213343,"about_ca_topic_score_gemma":0.00904975,"teacher_disagreement_score":0.12330859,"about_ca_system_score_codex":0.00012026701,"about_ca_system_score_gemma":0.00080529536,"threshold_uncertainty_score":0.5049973},"labels":[],"label_agreement":null},{"id":"W4237245205","doi":"10.21203/rs.2.22164/v1","title":"Innovative use of data sources: A Cross-sectional study of Data Linkage Practices across European Countries","year":2020,"lang":"en","type":"preprint","venue":"Research Square","topic":"Data Quality and Management","field":"Decision Sciences","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":"National Research Council Canada; Institute of Health Economics","funders":"Norwegian Institute of Public Health; Helsedirektoratet; Institut National de la Santé et de la Recherche Médicale; European Commission","keywords":"Linkage (software); Cross-sectional study; Cross-sectional data; Geography; Statistics; Mathematics; Biology; Genetics","score_opus":0.8684068958353723,"score_gpt":0.6619126168745204,"score_spread":0.20649427896085193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237245205","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":[0.8914055,0.00028164845,0.004022582,0.0013294555,0.00038742775,0.0030136541,0.09831263,0.00007066421,0.0011764131],"genre_scores_gemma":[0.98858714,0.0002316275,0.0015110755,0.000089088164,0.00033780493,0.000029654175,0.008185785,0.000042089432,0.0009857351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9723002,0.0085413875,0.0029595061,0.0034915914,0.011994293,0.0007130287],"domain_scores_gemma":[0.9624895,0.013582367,0.0035862778,0.013214093,0.0069210967,0.00020668714],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.07747904,0.00032904465,0.00084478734,0.00064503157,0.00053130864,0.0043097218,0.018718144,0.00017858675,0.00038006328],"category_scores_gemma":[0.09394451,0.00026390768,0.00007064842,0.0030398234,0.0013617607,0.0050363024,0.11065619,0.0020840322,0.00027367732],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018795452,0.004257397,0.83698803,0.0033146113,0.0015236139,0.00033970422,0.034773283,0.0007183538,0.000057759942,0.002344585,0.101729214,0.012073918],"study_design_scores_gemma":[0.0009180538,0.00066554255,0.6029779,0.00031191017,0.000029435942,0.0000018289621,0.045325335,0.0015974735,0.000028250442,0.001414882,0.34638682,0.00034257022],"about_ca_topic_score_codex":0.004564086,"about_ca_topic_score_gemma":0.0020988067,"teacher_disagreement_score":0.24465762,"about_ca_system_score_codex":0.00007004918,"about_ca_system_score_gemma":0.0008678833,"threshold_uncertainty_score":0.9999813},"labels":[],"label_agreement":null},{"id":"W4237720795","doi":"10.1002/(sici)1097-4571(2000)51:8<774::aid-asi90>3.0.co;2-p","title":"Using clustering strategies for creating authority files","year":2000,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada; Smithsonian Astrophysical Observatory; National Aeronautics and Space Administration; National Radio Astronomy Observatory; National Science Foundation","keywords":"Computer science; String (physics); Matching (statistics); Word (group theory); Information retrieval; Cluster analysis; Categorization; Spelling; String searching algorithm; Quality (philosophy); Metadata; Data mining; Artificial intelligence; Pattern matching; World Wide Web","score_opus":0.19143348053855952,"score_gpt":0.45290997536841127,"score_spread":0.26147649482985175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237720795","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":[0.3320829,0.00000841731,0.6633872,0.0013315172,0.00038781646,0.00031936396,0.00007986581,0.000010851291,0.0023920883],"genre_scores_gemma":[0.78436315,0.000021518514,0.21224117,0.0029335343,0.00016169042,0.000007075422,0.0000013635598,0.0000040940326,0.00026641387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973643,0.000038397186,0.00087689376,0.000103953535,0.0013814972,0.0002349476],"domain_scores_gemma":[0.99656487,0.0006096166,0.0016390663,0.00029934302,0.000814749,0.000072330695],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010306357,0.00007940277,0.00021262979,0.00010481258,0.0010075936,0.0012815667,0.0015542683,0.0000148921745,0.000028963434],"category_scores_gemma":[0.0015897665,0.000047554277,0.00044869568,0.0013510722,0.0007466259,0.0078204265,0.00015062839,0.000090978865,0.000004491732],"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":[0.00021630844,0.000053712884,0.00029576823,0.00006780053,0.000072618466,1.06178845e-7,0.02706285,0.14118987,0.0019791918,0.017025901,0.038650144,0.7733857],"study_design_scores_gemma":[0.00067987276,0.00028361197,0.00456704,0.000069279005,0.000056036442,0.000030751144,0.15099718,0.4814226,0.00043108282,0.019723594,0.34149364,0.0002453065],"about_ca_topic_score_codex":0.000036176923,"about_ca_topic_score_gemma":0.0000032853268,"teacher_disagreement_score":0.77314043,"about_ca_system_score_codex":0.000115626695,"about_ca_system_score_gemma":0.00038651787,"threshold_uncertainty_score":0.9997552},"labels":[],"label_agreement":null},{"id":"W4240833016","doi":"10.1007/bf03405034","title":"Development of a Computer Linkage System for a Blood Recipient Notification Program in Nova Scotia","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Public Health","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Health Canada","funders":"","keywords":"Nova scotia; Medical record; Record linkage; Data file; Medicine; Computer science; Nova (rocket); Linkage (software); Medical emergency; Database; Geography; Surgery; Environmental health; Engineering; Population; Biology","score_opus":0.38003217666380074,"score_gpt":0.4087639461078232,"score_spread":0.028731769444022448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240833016","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":[0.6412812,0.0008960623,0.3079832,0.042008914,0.0034993694,0.0027991724,0.00018647638,0.000026279038,0.0013193333],"genre_scores_gemma":[0.9116061,0.0000036960225,0.08763594,0.0005121578,0.000106674626,0.000008543925,0.000011417226,0.0000074221684,0.00010804345],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965319,0.00030149356,0.0018507597,0.0002148827,0.00062670314,0.0004742367],"domain_scores_gemma":[0.9969615,0.00020514659,0.0009913138,0.00032059496,0.0005790499,0.0009423968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015311708,0.000090265596,0.00036550636,0.0011391198,0.00010380803,0.0002546869,0.00071117724,0.00004993627,0.00009556426],"category_scores_gemma":[0.0009077051,0.00007444685,0.00007363001,0.00087568024,0.00005240081,0.0003259031,0.00002642622,0.00013255513,0.000030154657],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029029568,0.00022979916,0.0025547852,0.0001653622,0.000034540542,0.000012644693,0.007631014,0.000029091185,0.0000023734642,0.0059428504,0.021485174,0.9619095],"study_design_scores_gemma":[0.0016864516,0.0006152284,0.03311358,0.0004710037,0.000010796609,0.000047228626,0.0061494512,0.003491098,0.00003086029,0.00016113745,0.9540172,0.0002059295],"about_ca_topic_score_codex":0.0029323504,"about_ca_topic_score_gemma":0.16272938,"teacher_disagreement_score":0.96170354,"about_ca_system_score_codex":0.0005210673,"about_ca_system_score_gemma":0.0026279865,"threshold_uncertainty_score":0.85254866},"labels":[],"label_agreement":null},{"id":"W4241033854","doi":"10.1007/978-1-4939-7131-2_100333","title":"Entity Extraction","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Extraction (chemistry); Computer science; Chromatography; Chemistry","score_opus":0.34082901758318324,"score_gpt":0.4610012396116445,"score_spread":0.12017222202846128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241033854","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006758412,0.000025253825,0.020227484,0.00043289442,0.0012597897,0.00012539254,0.000050091432,0.00005497184,0.97781736],"genre_scores_gemma":[0.00016789162,0.000048698337,0.00072094105,0.0007009143,0.00034697205,0.0000015426432,0.000039639515,0.000009486822,0.9979639],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99746895,0.000027780396,0.00048760648,0.0005143135,0.0013882027,0.000113141854],"domain_scores_gemma":[0.99818164,0.0002467079,0.0002776248,0.0010312656,0.00019731012,0.00006546831],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025598428,0.00014105836,0.0002170172,0.00022199056,0.000086942695,0.00036280253,0.00071738125,0.00015683768,0.17944528],"category_scores_gemma":[0.00033392853,0.00010229656,0.00013749559,0.00003349266,0.000108027045,0.0003779916,0.00036560002,0.00013004246,0.07638179],"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":[0.0000038455732,0.000005036484,6.418809e-7,0.0000016893246,0.000010000644,0.000002592703,0.000013352793,4.148107e-8,7.360694e-7,0.41011578,0.55472505,0.035121202],"study_design_scores_gemma":[0.000025270148,0.000019259107,0.000017851984,0.0000055930595,0.000009709216,8.5655785e-7,0.000024452684,0.000005263026,0.000005895135,0.38497195,0.6148322,0.000081637554],"about_ca_topic_score_codex":0.000031995263,"about_ca_topic_score_gemma":0.00039564856,"teacher_disagreement_score":0.103063494,"about_ca_system_score_codex":0.00003195017,"about_ca_system_score_gemma":0.00002389034,"threshold_uncertainty_score":0.9243374},"labels":[],"label_agreement":null},{"id":"W4241632110","doi":"10.23889/ijpds.v4i2.1133","title":"Population Data BC: Supporting population data science in British Columbia","year":2020,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Quebec Population Health Research Network; University of British Columbia","funders":"","keywords":"Computer science; Data access; Linkage (software); Variety (cybernetics); Data quality; Identifier; Data science; Data management; Linked data; Record linkage; Population; Database; World Wide Web; Service (business); Business","score_opus":0.4131892460550775,"score_gpt":0.5216265395244426,"score_spread":0.10843729346936509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241632110","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":[0.8865519,0.000059636164,0.07598428,0.012562612,0.009467637,0.0012822434,0.013604172,0.0001284257,0.00035910864],"genre_scores_gemma":[0.96462756,0.00004099073,0.01679803,0.0010562412,0.0007358834,0.0000047791646,0.01654906,0.000017573191,0.00016990687],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9874048,0.00019683733,0.0023742411,0.0025281806,0.0068186345,0.00067730335],"domain_scores_gemma":[0.9926067,0.00047402378,0.0016762879,0.0036342263,0.0011583152,0.00045042348],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.027868325,0.00018510043,0.00037867462,0.00071954814,0.0013694743,0.012668324,0.028264605,0.00007032599,0.00042489826],"category_scores_gemma":[0.04174124,0.00023355822,0.000050937906,0.0030168635,0.0003963596,0.04263052,0.011638212,0.00035372857,0.000060076487],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047279314,0.0001217217,0.7225228,0.000012098623,0.00001622124,0.000035400695,0.00014836839,0.0016016827,0.0001611422,0.0019422541,0.033598654,0.23979239],"study_design_scores_gemma":[0.00048272713,0.000029140227,0.6200442,0.00005824766,0.000014402856,0.00004048931,0.0003823851,0.3510511,0.0000020421237,0.0063117584,0.021352189,0.00023136432],"about_ca_topic_score_codex":0.05802133,"about_ca_topic_score_gemma":0.1004933,"teacher_disagreement_score":0.3494494,"about_ca_system_score_codex":0.00035526612,"about_ca_system_score_gemma":0.0004666633,"threshold_uncertainty_score":0.9999306},"labels":[],"label_agreement":null},{"id":"W4242139153","doi":"10.1504/ijmso.2019.099839","title":"A data exchange solution for emergency response systems based on the EDXL-RESCUER ontology","year":2019,"lang":"en","type":"article","venue":"International Journal of Metadata Semantics and Ontologies","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; European Commission","keywords":"Interoperability; Computer science; Ontology; Semantic interoperability; Data exchange; Emergency response; Information exchange; Computer security; Database; World Wide Web; Medical emergency; Telecommunications; Medicine","score_opus":0.36351123738029595,"score_gpt":0.46071758606612306,"score_spread":0.09720634868582712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242139153","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":[0.1603979,0.003442416,0.63888717,0.17428523,0.017648485,0.0010793571,0.0034242952,0.000034725814,0.000800398],"genre_scores_gemma":[0.9928711,0.000565527,0.0033444976,0.00089690345,0.00027268982,0.000008623047,0.00009234982,0.000008883291,0.0019394102],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99684536,0.0005810125,0.0008422356,0.0003108995,0.0012536645,0.00016684619],"domain_scores_gemma":[0.9938297,0.003718921,0.0007789549,0.00095959165,0.00066998834,0.000042812444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012885555,0.000121425976,0.00032016027,0.0002973983,0.000095673,0.00047556628,0.0030998592,0.000058316622,0.0000979837],"category_scores_gemma":[0.0089423,0.00006617867,0.000093622664,0.00010407163,0.00008635562,0.0010085747,0.0006544573,0.00013417992,0.000019807025],"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":[0.008398331,0.00054662133,0.008855596,0.00009515653,0.0011772495,0.00010104426,0.0005247696,0.0010220167,0.0009959728,0.1940286,0.743793,0.040461633],"study_design_scores_gemma":[0.001045564,0.00046443753,0.012050798,0.00007675182,0.00009024903,0.000044350974,0.0020135825,0.096212536,0.000035618075,0.006687088,0.88112205,0.00015696896],"about_ca_topic_score_codex":0.000061525236,"about_ca_topic_score_gemma":0.0002855271,"teacher_disagreement_score":0.8324732,"about_ca_system_score_codex":0.000023505767,"about_ca_system_score_gemma":0.00007118226,"threshold_uncertainty_score":0.9994058},"labels":[],"label_agreement":null},{"id":"W4243007898","doi":"10.4018/978-1-4666-2044-5.ch011","title":"Data Management and Data Administration","year":2013,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Timeline; Quarter (Canadian coin); Perception; Subject matter; Set (abstract data type); Data management; Data science; Knowledge management; Political science; Public relations; Computer science; Psychology; Geography; Data mining","score_opus":0.2949578727367357,"score_gpt":0.4209749095604416,"score_spread":0.1260170368237059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243007898","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000007798218,0.00028264459,0.0026740949,0.00056586845,0.0005165771,0.0006682096,0.011532138,0.000064628315,0.98368806],"genre_scores_gemma":[0.0073735635,0.00009013014,0.006589699,0.001989386,0.00033210052,0.000013704472,0.0024702235,0.000032660726,0.98110855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99516094,0.0000588365,0.0008630406,0.0019321938,0.0017144108,0.00027055212],"domain_scores_gemma":[0.9903343,0.00013602452,0.00044214004,0.008802885,0.00009193505,0.00019271986],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0022882582,0.0003545096,0.000432011,0.00010588217,0.00013810923,0.0012722659,0.0063400296,0.00019566585,0.0005887394],"category_scores_gemma":[0.00017769146,0.00029520915,0.000042515294,0.000030196476,0.00018721892,0.0006588907,0.01174165,0.00016368566,0.003161615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009130083,0.0000059050585,0.0000015059663,0.000017137016,0.000059280464,0.000034040662,0.000003791285,6.142768e-8,5.3471645e-8,0.56368804,0.33253407,0.10364696],"study_design_scores_gemma":[0.000119855256,0.000026439098,0.000054219556,0.0000388026,0.0000826051,0.000008292057,0.0000437536,0.00010229122,1.8570023e-7,0.40341973,0.5959095,0.00019434855],"about_ca_topic_score_codex":0.000058196147,"about_ca_topic_score_gemma":0.00058722566,"teacher_disagreement_score":0.2633754,"about_ca_system_score_codex":0.00004707778,"about_ca_system_score_gemma":0.00007927605,"threshold_uncertainty_score":0.99995},"labels":[],"label_agreement":null},{"id":"W4243870196","doi":"10.1007/978-1-4939-7131-2_100039","title":"Aspect or Facet Mining","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Facet (psychology); Geology; Computer science; Mining engineering; Psychology; Social psychology","score_opus":0.44505886852049,"score_gpt":0.44800967471884373,"score_spread":0.0029508061983537504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243870196","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000099929475,0.000036928763,0.004908993,0.0008501962,0.00074074144,0.00018324368,0.00011910215,0.0000798368,0.99307096],"genre_scores_gemma":[0.00008331407,0.000035445275,0.00341245,0.0020419988,0.00033282628,0.0000026564633,0.000034012664,0.000019521365,0.99403775],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99670756,0.000036600693,0.0006795875,0.00073822704,0.0016281436,0.00020987394],"domain_scores_gemma":[0.9975611,0.00050408964,0.0003023564,0.0013672425,0.00016116425,0.0001040307],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0028227998,0.00023760555,0.00042585479,0.00029586995,0.000104941784,0.0004897535,0.0014188263,0.00017371736,0.23517571],"category_scores_gemma":[0.0008427062,0.00013892318,0.00014590802,0.00006471312,0.00016527508,0.00022587871,0.0008685804,0.00012094471,0.041294284],"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":[0.000008894499,0.000003964202,5.272264e-7,0.0000031500488,0.00002628763,0.000018663271,0.00011820014,1.3433932e-7,2.1803909e-7,0.2450834,0.7201884,0.03454816],"study_design_scores_gemma":[0.00008606711,0.00008044113,0.000008505008,0.000027967233,0.000017484255,0.000002796257,0.00037435998,0.000014126086,0.00000448758,0.14649792,0.8526863,0.00019954568],"about_ca_topic_score_codex":0.000015718504,"about_ca_topic_score_gemma":0.0006243097,"teacher_disagreement_score":0.19388142,"about_ca_system_score_codex":0.000029764537,"about_ca_system_score_gemma":0.00006599907,"threshold_uncertainty_score":0.95945215},"labels":[],"label_agreement":null},{"id":"W4244656168","doi":"10.1109/edocw.2019.00004","title":"Table of Contents","year":2019,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Table (database); Computer science; Database","score_opus":0.2766879689188622,"score_gpt":0.43200925537921075,"score_spread":0.15532128646034854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244656168","genre_codex":"other","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":[0.18185131,0.000014255065,0.0068169497,0.0009000661,0.0003773615,0.00013741483,0.00001751,0.000013090859,0.80987203],"genre_scores_gemma":[0.82873356,0.0000014779945,0.00039458112,0.000565696,0.0000033408382,5.3933906e-7,0.0000015162668,8.04757e-7,0.17029849],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99908125,0.000030006104,0.00020817397,0.00011949333,0.0004992241,0.00006187378],"domain_scores_gemma":[0.999284,0.00016621061,0.000059586546,0.00039895222,0.00007190468,0.000019309433],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011647546,0.000022982906,0.0000914996,0.00004525819,0.0000082136075,0.000034118108,0.00037990668,0.000009668846,0.0086890785],"category_scores_gemma":[0.00028999103,0.000014181711,0.000022053575,0.00017772739,0.000015014835,0.00019236929,0.00015074034,0.000013137643,0.004759603],"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":[0.000017132003,0.000083406754,0.026263641,0.000007909784,0.000014496629,5.9846684e-7,0.00011153062,0.000023837736,0.0016404522,0.4629409,0.4788997,0.029996404],"study_design_scores_gemma":[0.00024582774,0.000035274283,0.011503683,0.000003095173,0.0000016452179,1.2911397e-7,0.0013344038,0.00027244858,0.0023433699,0.018804844,0.96541494,0.00004035184],"about_ca_topic_score_codex":0.00012408815,"about_ca_topic_score_gemma":0.000021337783,"teacher_disagreement_score":0.64688224,"about_ca_system_score_codex":0.0000018470807,"about_ca_system_score_gemma":0.0000053017334,"threshold_uncertainty_score":0.9960153},"labels":[],"label_agreement":null},{"id":"W4245895410","doi":"10.4018/9781599048574.ch055","title":"Statistical Data and Metadata Quality Assessment","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardization; Quality (philosophy); Metadata; Product (mathematics); Data quality; Summary statistics; Computer science; Business; Statistics; Service (business); Marketing; World Wide Web; Mathematics","score_opus":0.4417883249660065,"score_gpt":0.4803543658407542,"score_spread":0.03856604087474769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245895410","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000006025538,0.00016683499,0.09278925,0.00019902388,0.00048066737,0.00035341366,0.03128406,0.000054249973,0.87466645],"genre_scores_gemma":[0.039495368,0.00009102854,0.046635326,0.004780968,0.0005062625,0.000025999387,0.002157733,0.00008936438,0.90621793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.993812,0.00028397658,0.001365136,0.0017790744,0.0023928632,0.0003669056],"domain_scores_gemma":[0.99288034,0.00078443985,0.0006085193,0.0052219043,0.00016600483,0.00033877412],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0067377645,0.0004421905,0.0009073014,0.0000949027,0.000155045,0.0010586698,0.0036873783,0.00025779064,0.0009544708],"category_scores_gemma":[0.00090013933,0.00034860024,0.00008735965,0.000026685348,0.00045305712,0.00053362775,0.006703454,0.00033787475,0.0006336891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002363944,0.000016669563,0.000032816133,0.000020006804,0.00012493198,0.000044214798,0.00001492609,2.9656787e-8,2.3470837e-7,0.824083,0.09307929,0.08256027],"study_design_scores_gemma":[0.00013786006,0.000032291493,0.0007536406,0.000017785349,0.00010280673,0.0000052918913,0.000030204263,0.00001092496,2.1866853e-7,0.55266607,0.44600654,0.0002363784],"about_ca_topic_score_codex":0.0005926373,"about_ca_topic_score_gemma":0.0010113658,"teacher_disagreement_score":0.35292727,"about_ca_system_score_codex":0.00009195185,"about_ca_system_score_gemma":0.00026417754,"threshold_uncertainty_score":0.9999783},"labels":[],"label_agreement":null},{"id":"W4245953805","doi":"10.1007/978-0-387-39940-9_2382","title":"Data Quality Benchmarking","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmarking; Quality (philosophy); Computer science; Business; Physics","score_opus":0.2811221040659851,"score_gpt":0.4236949266335831,"score_spread":0.142572822567598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245953805","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009584449,0.0028222832,0.005522152,0.00020595017,0.003278456,0.0008492215,0.051725116,0.000072803,0.93551445],"genre_scores_gemma":[0.00027256052,0.0038010357,0.002466768,0.0002175891,0.0020839826,0.000012206972,0.024816323,0.00006328311,0.9662663],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98872614,0.0005111048,0.0036591613,0.002075834,0.0045764185,0.0004513535],"domain_scores_gemma":[0.98356014,0.0020908401,0.0027454833,0.01094187,0.00039447023,0.00026716915],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.018452741,0.000595795,0.0016097933,0.0006232294,0.00015060953,0.0003031398,0.006627435,0.00032441216,0.0015265387],"category_scores_gemma":[0.0028100563,0.0004953635,0.00022905183,0.00020787978,0.0002194851,0.0013860455,0.0037233906,0.00052935735,0.0013983101],"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":[0.000024427964,0.00005550223,0.000027703147,0.00025273356,0.00010482901,0.000049731683,0.00007256316,0.000010486149,0.0000027323265,0.27709603,0.6183558,0.10394746],"study_design_scores_gemma":[0.00023299598,0.00005407452,0.00009379068,0.0005447801,0.000107296764,0.0000062978356,0.0001788571,0.00015520571,6.5422233e-7,0.007498657,0.99058163,0.0005457532],"about_ca_topic_score_codex":0.00062564557,"about_ca_topic_score_gemma":0.0005070885,"teacher_disagreement_score":0.37222585,"about_ca_system_score_codex":0.00006969549,"about_ca_system_score_gemma":0.00027209005,"threshold_uncertainty_score":0.9997498},"labels":[],"label_agreement":null},{"id":"W4246320142","doi":"10.4018/978-1-4666-0927-3.ch016","title":"Managing Demographic Data Inconsistencies in Healthcare Information Systems","year":2012,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Data Quality and Management","field":"Decision Sciences","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":"Athabasca University","funders":"","keywords":"Computer science; Workflow; XML; Information system; Disparate system; RDF; Data exchange; DICOM; Database; Data science; Information retrieval; World Wide Web; Semantic Web; Engineering","score_opus":0.17316906449221955,"score_gpt":0.3654270627057529,"score_spread":0.19225799821353337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246320142","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029747685,0.002502571,0.0010284088,0.0009719624,0.0014760222,0.00077189214,0.0023973647,0.000097060496,0.990725],"genre_scores_gemma":[0.9221219,0.00039184856,0.00094199984,0.007815425,0.0006805994,0.00007983085,0.0012503141,0.00006569183,0.06665241],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99521583,0.00015755593,0.001591898,0.000609597,0.0019533336,0.00047180173],"domain_scores_gemma":[0.9956661,0.00022128111,0.00082644663,0.0028522655,0.00022673859,0.00020720116],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047225333,0.0003622666,0.0006471854,0.0006111873,0.00014996497,0.0008035171,0.0026779838,0.0003189486,0.000021313448],"category_scores_gemma":[0.00028896134,0.0003151402,0.000114042254,0.00013219372,0.00015444927,0.0014050531,0.0022408566,0.00033807915,0.0010285397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013526183,0.0000042342967,0.00037390436,0.0001244451,0.00003238013,0.00001236444,0.000092899354,0.0000072500707,2.8380185e-8,0.9113582,0.012059755,0.075921044],"study_design_scores_gemma":[0.00017550301,0.000019651778,0.00048884156,0.000278802,0.000036252473,0.000017809018,0.00054077257,0.00017994504,6.77015e-8,0.4206405,0.57729876,0.00032307362],"about_ca_topic_score_codex":0.0024915037,"about_ca_topic_score_gemma":0.0038466793,"teacher_disagreement_score":0.92407256,"about_ca_system_score_codex":0.00021621262,"about_ca_system_score_gemma":0.00016579218,"threshold_uncertainty_score":0.9999301},"labels":[],"label_agreement":null},{"id":"W4247644046","doi":"10.1007/978-1-4939-7131-2_100238","title":"Data Mash-Ups","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.6487458488491252,"score_gpt":0.4840009790531912,"score_spread":0.164744869795934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247644046","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.6106192e-7,0.000074520816,0.010977438,0.001256778,0.00089407316,0.00017261853,0.0021555333,0.00006567678,0.9844029],"genre_scores_gemma":[0.000011607283,0.00008573936,0.0025931369,0.002773817,0.00046011154,0.000001076537,0.00093043706,0.000018791809,0.99312526],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959801,0.00003807571,0.0007226398,0.0011515227,0.001916048,0.00019164388],"domain_scores_gemma":[0.9924399,0.00047515146,0.00029700037,0.0065179146,0.00015981859,0.00011016172],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0049502747,0.00022135806,0.0003678649,0.00023464994,0.00008913993,0.0005087478,0.0059169354,0.00017506111,0.16089532],"category_scores_gemma":[0.0007452548,0.00014975795,0.00008364913,0.000048775626,0.00021265198,0.0005177154,0.005614631,0.00015650222,0.10366888],"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":[0.00000254094,0.0000036585297,4.5343378e-7,0.000002227809,0.000018153698,0.000005982556,0.000011708732,2.8509998e-8,5.87868e-8,0.36285535,0.6069498,0.030150026],"study_design_scores_gemma":[0.000042617514,0.000016006568,0.000004305485,0.000011608145,0.00001735179,0.0000010811846,0.00004217329,0.000031990967,3.954079e-7,0.34363502,0.6560567,0.0001407318],"about_ca_topic_score_codex":0.000020756845,"about_ca_topic_score_gemma":0.00054780627,"teacher_disagreement_score":0.057226438,"about_ca_system_score_codex":0.000016826127,"about_ca_system_score_gemma":0.000052268155,"threshold_uncertainty_score":0.99946153},"labels":[],"label_agreement":null},{"id":"W4248646218","doi":"10.1007/978-981-10-7847-7_8","title":"Conclusion","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Crowdsourcing; Analytics; Data science; Computer science; World Wide Web","score_opus":0.314498482960396,"score_gpt":0.43832979866986777,"score_spread":0.12383131570947176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248646218","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000214833,0.0000461825,0.005831822,0.0010240998,0.0007443164,0.00014005585,0.000062728934,0.00005196948,0.99209666],"genre_scores_gemma":[0.000073879026,0.000041556523,0.00061406917,0.0028879724,0.00028028863,0.0000010186698,0.00004020793,0.000011786198,0.9960492],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972424,0.000025327261,0.0005204873,0.0005282948,0.0015610771,0.00012239652],"domain_scores_gemma":[0.9979589,0.00034612592,0.00022819712,0.0011810338,0.00020704055,0.00007872245],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0025058,0.00015697065,0.00027370342,0.00019444326,0.00010213094,0.00023143706,0.0011093444,0.00015837235,0.1883382],"category_scores_gemma":[0.000334834,0.000102103964,0.00012669023,0.000030291592,0.00016610032,0.00014810284,0.0014107826,0.00010105354,0.0849425],"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":[0.0000023024595,0.0000017560777,1.4253135e-7,0.000001032568,0.000005888088,0.0000032839148,0.000026878204,3.242182e-8,3.6957064e-7,0.44567218,0.5263274,0.02795879],"study_design_scores_gemma":[0.000037406575,0.00002239932,0.0000019151241,0.000009510328,0.0000061290752,5.538577e-7,0.000027348007,0.000007426049,0.000003707099,0.42087674,0.57892114,0.00008571478],"about_ca_topic_score_codex":0.000011382568,"about_ca_topic_score_gemma":0.00010346544,"teacher_disagreement_score":0.10339571,"about_ca_system_score_codex":0.000022691707,"about_ca_system_score_gemma":0.000029678995,"threshold_uncertainty_score":0.91577},"labels":[],"label_agreement":null},{"id":"W4249269717","doi":"10.1007/978-0-387-39940-9_2384","title":"Data Quality Measurement","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Quality (philosophy); Physics","score_opus":0.414846341116501,"score_gpt":0.42206371298250933,"score_spread":0.007217371866008349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249269717","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000031403906,0.004761224,0.0063587003,0.00036216594,0.0027650145,0.0011185423,0.044722255,0.00007974233,0.93982923],"genre_scores_gemma":[0.00044439785,0.003752528,0.0013165791,0.0002525854,0.0013418802,0.000020887865,0.0115956655,0.000073520525,0.98120195],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9839837,0.0006092365,0.0038722656,0.0020669864,0.009019279,0.00044855886],"domain_scores_gemma":[0.9831904,0.0009284961,0.0026212796,0.012036148,0.0009233854,0.00030027158],"candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.031688932,0.00062074,0.0016400935,0.00055876165,0.00013102504,0.00026289234,0.006772084,0.00029246806,0.0010050457],"category_scores_gemma":[0.0050192764,0.0005016447,0.00023649102,0.00018260692,0.00020174563,0.0011399986,0.0030216633,0.00047639548,0.0021406708],"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":[0.00003266402,0.00008811158,0.000011051962,0.000277009,0.00014739935,0.000033111293,0.000056437697,0.0000068766835,0.000006985226,0.21795775,0.72537774,0.056004833],"study_design_scores_gemma":[0.0003108876,0.00005750084,0.000072613475,0.00056189497,0.00013742452,0.000004228007,0.00019054033,0.000047097445,0.0000017982705,0.007363675,0.9907067,0.0005456725],"about_ca_topic_score_codex":0.0006145689,"about_ca_topic_score_gemma":0.00078499696,"teacher_disagreement_score":0.2653289,"about_ca_system_score_codex":0.00014120407,"about_ca_system_score_gemma":0.0004228183,"threshold_uncertainty_score":0.99990815},"labels":[],"label_agreement":null},{"id":"W4249958738","doi":"10.1007/978-0-387-39940-9_2347","title":"Data Deduplication","year":2009,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Database Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data deduplication; Computer science; Database","score_opus":0.21490546097654822,"score_gpt":0.39464753395498214,"score_spread":0.17974207297843392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249958738","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003706767,0.0031737085,0.0076622423,0.0003004046,0.0015459226,0.000871599,0.0337375,0.0000629108,0.952642],"genre_scores_gemma":[0.0001390537,0.003880562,0.001444948,0.00019472286,0.00092782325,0.000015887019,0.0240696,0.000044391734,0.969283],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99317354,0.00016513362,0.0021104761,0.0014793898,0.002797374,0.0002741147],"domain_scores_gemma":[0.9873815,0.00085218454,0.0016974293,0.009552355,0.0003354809,0.00018105941],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006680399,0.00039535694,0.00090256106,0.00051302,0.00009073846,0.00019119987,0.0053163865,0.0002318418,0.0007486915],"category_scores_gemma":[0.0016100705,0.00032633814,0.00012155267,0.00016258079,0.00013484125,0.0011073796,0.0020285049,0.00030467648,0.0028960896],"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":[0.000010496541,0.00003466515,0.000005787407,0.00009350398,0.00004560245,0.000013941613,0.000030173023,0.000006326612,0.0000031141626,0.23403238,0.6947393,0.070984714],"study_design_scores_gemma":[0.00015360555,0.000037186648,0.00003072571,0.0002794591,0.0000964646,0.000006539655,0.000092096845,0.00022061507,0.0000012815419,0.008305746,0.9904449,0.00033135523],"about_ca_topic_score_codex":0.00019235544,"about_ca_topic_score_gemma":0.00016169272,"teacher_disagreement_score":0.29570562,"about_ca_system_score_codex":0.000046790028,"about_ca_system_score_gemma":0.00019261472,"threshold_uncertainty_score":0.9999189},"labels":[],"label_agreement":null},{"id":"W4251706394","doi":"10.1007/978-1-4614-6170-8_100362","title":"Data Mash-ups","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mashup; Computer science; World Wide Web","score_opus":0.5876439455935591,"score_gpt":0.46426003717551917,"score_spread":0.12338390841803998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251706394","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1613612e-7,0.00006578828,0.062173404,0.0018513299,0.0006691186,0.00015178525,0.0011334744,0.000062735744,0.93389225],"genre_scores_gemma":[0.0000401226,0.00007788688,0.0019088949,0.0038429187,0.0002901563,0.0000011977478,0.0009812238,0.000019217567,0.9928384],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99600697,0.000052645588,0.0007498429,0.0010985981,0.0019071173,0.00018484237],"domain_scores_gemma":[0.9922052,0.0007572995,0.00031578247,0.0065039746,0.00010355536,0.00011418545],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005961908,0.00022448589,0.0004279693,0.00023038528,0.00007712816,0.00047446354,0.005703293,0.00017146206,0.038127724],"category_scores_gemma":[0.000875604,0.00015241808,0.00009200545,0.000038628248,0.000115074115,0.0002812476,0.0045707813,0.00019222686,0.051080115],"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":[0.0000014058353,0.000001812934,4.9011123e-7,0.0000025860127,0.000011640657,0.0000031330214,0.0000032040857,1.966809e-7,4.1663597e-8,0.45187798,0.4670053,0.08109217],"study_design_scores_gemma":[0.00005216279,0.000011434572,0.0000058786663,0.000011928051,0.000018860965,0.0000010022715,0.000015818347,0.0000907596,2.119634e-7,0.2825137,0.71712065,0.00015759481],"about_ca_topic_score_codex":0.000025061905,"about_ca_topic_score_gemma":0.00040644995,"teacher_disagreement_score":0.2501153,"about_ca_system_score_codex":0.000014153819,"about_ca_system_score_gemma":0.000036773312,"threshold_uncertainty_score":0.99967635},"labels":[],"label_agreement":null},{"id":"W4251836994","doi":"10.1007/978-1-4757-3283-2_6","title":"Experimental Analyses","year":2001,"lang":"en","type":"book-chapter","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Ranking (information retrieval); Variety (cybernetics); Computer science; Software; Data mining; Data science; Diversity (politics); Information retrieval; Artificial intelligence; Programming language","score_opus":0.5945501731855667,"score_gpt":0.5331326257667598,"score_spread":0.061417547418806895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251836994","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000545987,0.00044367486,0.0037592123,0.00035576796,0.00033068948,0.00012324715,0.00004374202,0.00005673828,0.99488145],"genre_scores_gemma":[0.0016191152,0.000053627722,0.00040772645,0.0014180386,0.00014567211,0.0000031830148,0.00005284822,0.000014743706,0.996285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969179,0.00002959629,0.00062294863,0.00061228353,0.0016593438,0.000157909],"domain_scores_gemma":[0.9982199,0.00025070715,0.00022562718,0.0011232044,0.000080297265,0.00010024611],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010065612,0.0002194721,0.0003837783,0.00034515373,0.000078641286,0.00033906772,0.0010505896,0.00012494113,0.104987435],"category_scores_gemma":[0.00011419617,0.00014967032,0.00024575158,0.00006307614,0.00010413594,0.00021789366,0.00057313644,0.00011468066,0.01654991],"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":[0.0000044301864,0.000014737354,6.454898e-7,7.6770874e-7,0.000035139503,0.000025127789,0.00002451106,0.0000016631848,0.000015781072,0.5563824,0.42856482,0.014929984],"study_design_scores_gemma":[0.00007385605,0.00002944671,0.000003761649,0.0000073193037,0.000018112034,0.000002425126,0.00025451032,0.000010876968,0.00020827616,0.11307147,0.88613915,0.0001808067],"about_ca_topic_score_codex":0.000051693885,"about_ca_topic_score_gemma":0.00004573915,"teacher_disagreement_score":0.4575743,"about_ca_system_score_codex":0.000037912887,"about_ca_system_score_gemma":0.00002206943,"threshold_uncertainty_score":0.9842158},"labels":[],"label_agreement":null},{"id":"W4251956775","doi":"10.1007/978-0-85729-277-3_3","title":"Specification Qualities","year":2011,"lang":"en","type":"book-chapter","venue":"Texts in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Formal specification; Formal methods; Software engineering; Software requirements specification; Software development process; Programming language; Software development; Software; Software design","score_opus":0.3559857135491262,"score_gpt":0.4049652110917449,"score_spread":0.048979497542618655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251956775","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006350555,0.0001322292,0.20776716,0.0004484683,0.0020106554,0.0002789959,0.000030383106,0.000066393055,0.7892022],"genre_scores_gemma":[0.0207324,0.00017028926,0.027078329,0.0016449924,0.00062419416,0.000011745163,0.00001861594,0.000030652194,0.9496888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99472916,0.000070150825,0.0009935359,0.0012795705,0.0025697497,0.00035780444],"domain_scores_gemma":[0.99656224,0.00046472522,0.00047239824,0.0020898313,0.00028625433,0.00012453526],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00925193,0.0002514934,0.00039099203,0.0011734937,0.00017854579,0.00071542384,0.0044828444,0.00011335889,0.0016005943],"category_scores_gemma":[0.0002269645,0.00020716962,0.00009019016,0.00040050285,0.0012191554,0.0009319181,0.0016398159,0.0002588922,0.004012308],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027697893,0.000014326982,0.0000069127327,0.000004497991,0.0000018253181,0.0000074916397,0.0008394613,0.000013937261,8.855166e-7,0.662463,0.011544463,0.32510042],"study_design_scores_gemma":[0.000060116552,0.000031385225,0.0006348237,0.000053009295,0.0000022750514,0.0000025094605,0.00001662489,0.0004810131,0.000011948066,0.56380016,0.4346919,0.00021421196],"about_ca_topic_score_codex":0.00004509814,"about_ca_topic_score_gemma":0.000093304996,"teacher_disagreement_score":0.42314744,"about_ca_system_score_codex":0.00012835614,"about_ca_system_score_gemma":0.00019484515,"threshold_uncertainty_score":0.9993121},"labels":[],"label_agreement":null},{"id":"W4255857053","doi":"10.32920/ryerson.14639367","title":"ORCID IDs in the open knowledge era","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Toronto Metropolitan University","funders":"","keywords":"Metadata; Identifier; World Wide Web; Interoperability; Computer science; Unique identifier; Outreach; Political science; Programming language","score_opus":0.530129337104347,"score_gpt":0.55318074981532,"score_spread":0.023051412710972996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255857053","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004848192,0.0003298872,0.0092619555,0.014218275,0.0013862328,0.0009444757,0.00004040783,0.000022366456,0.9689482],"genre_scores_gemma":[0.79402053,0.0002866699,0.01022878,0.015255699,0.0003318997,0.00043182488,0.0003567788,0.000023481844,0.17906435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956581,0.0013626743,0.0007755393,0.0009196111,0.001064857,0.00021919007],"domain_scores_gemma":[0.9955326,0.0012196242,0.00016647282,0.0028692498,0.00016340733,0.000048676273],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.017331118,0.00017460281,0.00041495424,0.00019134785,0.00009169287,0.005029863,0.010044125,0.0001293212,0.006035502],"category_scores_gemma":[0.0018028909,0.0000943072,0.00012736634,0.0007108102,0.00006589555,0.0003823977,0.021096049,0.00055845303,0.0013100031],"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":[0.00000912354,0.00032305336,0.00026737803,0.000028793538,0.000026196209,0.000045239867,0.006031595,0.00007959077,0.0000023289797,0.22127293,0.6413461,0.13056764],"study_design_scores_gemma":[0.00020283589,0.000013377865,0.00811844,0.00005886256,0.000011064475,0.0000014960001,0.016254753,0.00039022326,0.000025247833,0.13753797,0.83716965,0.00021605426],"about_ca_topic_score_codex":0.0015483582,"about_ca_topic_score_gemma":0.013977572,"teacher_disagreement_score":0.78988385,"about_ca_system_score_codex":0.00003917883,"about_ca_system_score_gemma":0.00036486666,"threshold_uncertainty_score":0.9994676},"labels":[],"label_agreement":null},{"id":"W4256290989","doi":"10.1002/essoar.10503497.2","title":"N/A","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Western University","funders":"","keywords":"World Wide Web; Email authentication; Electronic mail; Computer science","score_opus":0.6549000826400283,"score_gpt":0.5294346348873289,"score_spread":0.1254654477526994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256290989","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003884199,0.000040030875,0.2365945,0.055482153,0.0014881948,0.00022257183,0.00010314462,0.00014541665,0.7055356],"genre_scores_gemma":[0.7102608,0.000084632025,0.03845674,0.04655115,0.00097536226,0.00006142298,0.00027902453,0.000030038751,0.20330083],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99749035,0.0001319036,0.00043775843,0.0006231164,0.0012157492,0.000101154634],"domain_scores_gemma":[0.9982424,0.0002758122,0.00014189133,0.0011753035,0.000072632174,0.000091969916],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020381003,0.00009925217,0.00023294812,0.00008696075,0.000029194496,0.00062278315,0.001958842,0.00007625585,0.0055087027],"category_scores_gemma":[0.001968826,0.000067205845,0.00012139743,0.0001687702,0.000030897412,0.000075674834,0.006216771,0.00022711589,0.012245349],"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":[0.0000022626575,0.000009750492,0.00002571776,0.000007689771,0.000010810859,0.0000060169323,0.00009946363,0.00003682602,0.0000018473343,0.13412666,0.8213364,0.044336572],"study_design_scores_gemma":[0.000021324904,0.000003797206,0.00034627906,0.000002512474,0.000003651283,7.273499e-8,0.00016497416,0.0005129022,0.000014658965,0.43552387,0.5633435,0.00006244308],"about_ca_topic_score_codex":0.00007228403,"about_ca_topic_score_gemma":0.00003500811,"teacher_disagreement_score":0.70987236,"about_ca_system_score_codex":0.000010467406,"about_ca_system_score_gemma":0.000045165394,"threshold_uncertainty_score":0.99540037},"labels":[],"label_agreement":null},{"id":"W4280497177","doi":"10.1007/s00146-022-01456-5","title":"Indexing, enriching, and understanding Brazilian missing person cases from data of distributed repositories on the web","year":2022,"lang":"en","type":"article","venue":"AI & Society","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":"Cape Breton University","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Linked data; Process (computing); World Wide Web; Government (linguistics); Data science; Semantic Web; Data quality; Missing data; Quality (philosophy); Data discovery; Search engine indexing; Publishing; Information retrieval; Domain (mathematical analysis); Knowledge management; Metadata; Engineering; Political science","score_opus":0.3405926389921211,"score_gpt":0.40482843763498494,"score_spread":0.06423579864286383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280497177","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":[0.88423425,0.0010321623,0.043236185,0.05589356,0.001576316,0.0005665632,0.010870891,0.00012198439,0.0024681045],"genre_scores_gemma":[0.99747103,0.00002679345,0.00024523976,0.0016806812,0.000058874844,0.0000033507604,0.00032277656,0.0000058935325,0.00018535716],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9976971,0.00034709874,0.00029573686,0.00046326258,0.0010299277,0.00016684011],"domain_scores_gemma":[0.9964622,0.0021701143,0.00021396254,0.0010750126,0.000030054698,0.00004860934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035113632,0.00009809405,0.00016933367,0.000022365288,0.0012136819,0.00040133146,0.0010324393,0.00002862208,0.00022157993],"category_scores_gemma":[0.0012568635,0.000067556895,0.00007434059,0.00038642887,0.00019084473,0.00035798398,0.0012941335,0.00023986617,0.0000018022824],"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":[0.000041763687,0.00010991122,0.0076343203,0.000013860405,0.00014523159,0.000017671082,0.024026241,0.000061826104,0.0004967253,0.022316022,0.94136375,0.0037726578],"study_design_scores_gemma":[0.00056629634,0.00016365352,0.006140341,0.00004859056,0.0001034846,0.00001095638,0.56773645,0.020701576,0.00017712169,0.031760678,0.37227175,0.00031910534],"about_ca_topic_score_codex":0.0009962112,"about_ca_topic_score_gemma":0.00020176597,"teacher_disagreement_score":0.56909204,"about_ca_system_score_codex":0.000118392396,"about_ca_system_score_gemma":0.00006400082,"threshold_uncertainty_score":0.93347824},"labels":[],"label_agreement":null},{"id":"W4282961702","doi":"10.18438/eblip30115","title":"Librarian-Lead Faculty Learning Communities Offer Opportunities for Collaboration","year":2022,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information literacy; Curriculum; Medical education; Literacy; Library science; Psychology; Sociology; Computer science; Pedagogy; Medicine","score_opus":0.2672568174698916,"score_gpt":0.39513025646328365,"score_spread":0.12787343899339204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282961702","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010217344,0.0006355906,0.13345434,0.80362856,0.0010992187,0.0020849216,0.0015020111,0.00052593317,0.046852045],"genre_scores_gemma":[0.53413147,0.0013910069,0.02642282,0.40625173,0.00018136368,0.0010148328,0.0067244256,0.000032914246,0.023849431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99659085,0.0014883444,0.0006986605,0.00014336062,0.0009178963,0.00016090638],"domain_scores_gemma":[0.99036384,0.00828417,0.0007180029,0.00038386145,0.0001718822,0.00007827049],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0046641612,0.000121451056,0.00016177843,0.00036552158,0.0013747262,0.0025863298,0.00062036037,0.00003630311,0.0013491345],"category_scores_gemma":[0.0052293376,0.00011113637,0.000038251197,0.00067431864,0.00008361165,0.31053996,0.00059163786,0.00025950128,0.000036391557],"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":[0.0009174045,0.000062308565,0.0001567173,0.00008461239,0.000022036653,0.0000024304295,0.003797207,0.0051970067,0.000008693612,0.67980164,0.21068394,0.099265985],"study_design_scores_gemma":[0.00027454898,0.0002807489,0.00026840638,0.000021460211,0.000016587632,0.0000039077313,0.1672454,0.015483946,0.00012513711,0.0011039625,0.8150505,0.00012543084],"about_ca_topic_score_codex":0.000011420104,"about_ca_topic_score_gemma":2.0645315e-7,"teacher_disagreement_score":0.6786977,"about_ca_system_score_codex":0.0000143287925,"about_ca_system_score_gemma":0.0002914381,"threshold_uncertainty_score":0.9999254},"labels":[],"label_agreement":null},{"id":"W4283449126","doi":"10.1145/3530190.3534829","title":"Note: Leveraging Artificial Intelligence to build a Data Catalog and support research on the Sustainable Development Goals","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Western University; Université de Montréal","funders":"","keywords":"Metadata; Computer science; Prosperity; Sustainable development; Data science; Sustainability; Big data; World Wide Web; Political science; Data mining","score_opus":0.6059346502404944,"score_gpt":0.5244392208282098,"score_spread":0.0814954294122846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283449126","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":[0.15185586,0.00008807528,0.45432615,0.29211935,0.0010553527,0.0050586793,0.0005592796,0.00019415686,0.094743095],"genre_scores_gemma":[0.9591441,0.0000038033177,0.002460681,0.0050821053,0.000038818707,0.00012298976,0.000099429606,0.000008455315,0.03303958],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.994629,0.00067999004,0.000536606,0.00087253784,0.002738751,0.0005431139],"domain_scores_gemma":[0.9951691,0.0024594036,0.000060667968,0.0019820721,0.00019779876,0.00013098227],"candidate_categories":["metaresearch","sts","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.04310535,0.00010114818,0.000143695,0.0004215154,0.0016944665,0.00087074284,0.0036429898,0.000016472177,0.0031472247],"category_scores_gemma":[0.004172776,0.0000652572,0.000014908685,0.0015759056,0.000113583046,0.00036010658,0.013844822,0.00031253137,0.00080027775],"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":[0.000060084065,0.000109866596,0.000045022007,0.0000066730927,0.000008907177,0.000064426225,0.004306969,0.00025625783,0.00001679601,0.48864797,0.28738987,0.21908715],"study_design_scores_gemma":[0.000016509983,0.000086622575,0.00024493184,0.000002535387,0.0000017289834,0.0000027288336,0.07877689,0.0006132512,0.0009211017,0.060687765,0.8585357,0.00011023144],"about_ca_topic_score_codex":0.0005862127,"about_ca_topic_score_gemma":0.00040817613,"teacher_disagreement_score":0.8072883,"about_ca_system_score_codex":0.0001407101,"about_ca_system_score_gemma":0.00031223785,"threshold_uncertainty_score":0.9999777},"labels":[],"label_agreement":null},{"id":"W4283574083","doi":"10.1016/j.jclinepi.2022.06.006","title":"Record linkage and big data—enhancing information and improving design","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Linkage (software); Record linkage; Computer science; Data science; Observational study; Population; Value (mathematics); Data mining; Medicine; Statistics; Mathematics; Environmental health; Biology","score_opus":0.7736697826487204,"score_gpt":0.5786307282052613,"score_spread":0.19503905444345915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283574083","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":[0.09185232,0.0004296252,0.8900619,0.014090845,0.003186614,0.00013783116,0.00004529113,0.000007787535,0.00018776004],"genre_scores_gemma":[0.76932234,0.0032883491,0.18381453,0.04119122,0.0019577518,0.0000074216464,0.000038260332,0.000013521988,0.00036659202],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98240364,0.010045117,0.0064663035,0.00031767928,0.00053497805,0.00023227287],"domain_scores_gemma":[0.8851509,0.10686593,0.006622736,0.00084314914,0.00021986719,0.0002973977],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23586325,0.00008251047,0.0010425587,0.00022060782,0.0001940132,0.00006809966,0.0009193707,0.00008157671,0.0000846136],"category_scores_gemma":[0.27506512,0.000057491492,0.00009379388,0.00018274254,0.0001553712,0.0010564221,0.0018072816,0.0007144938,0.000010241561],"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":[0.00016342779,0.000024857181,0.0122785885,0.000009186863,0.00002416267,0.0000074450377,0.000085793625,0.00015102736,0.0000035732287,0.0011282766,0.025238536,0.9608851],"study_design_scores_gemma":[0.0012192486,0.0014634291,0.077584326,0.000019215047,0.00005764367,0.00013405299,0.0018720573,0.02437746,0.0000018826338,0.10633928,0.7867826,0.00014878633],"about_ca_topic_score_codex":0.000053096956,"about_ca_topic_score_gemma":0.000024820276,"teacher_disagreement_score":0.96073633,"about_ca_system_score_codex":0.000015217795,"about_ca_system_score_gemma":0.00013705356,"threshold_uncertainty_score":0.7868396},"labels":[],"label_agreement":null},{"id":"W4283831618","doi":"10.21083/partnership.v17i1.6779","title":"Practices Before Policy: Research Data Management Behaviours in Canada","year":2022,"lang":"en","type":"article","venue":"Partnership The Canadian Journal of Library and Information Practice and Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Okanagan University College; University of British Columbia, Okanagan Campus; Western University; University of Toronto; University of British Columbia; Queen's University; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada; Canadian Institutes of Health Research","keywords":"RDM; Data management plan; Multidisciplinary approach; Agency (philosophy); Data management; Funding Agency; Knowledge management; Service (business); Survey data collection; Science policy; Data science; Public relations; Political science; Business; Computer science; Sociology; Marketing; Public administration; Social science; Database","score_opus":0.45755055852737964,"score_gpt":0.5160546254667507,"score_spread":0.0585040669393711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283831618","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":[0.08236357,0.0013035936,0.000008272597,0.8022877,0.0002930928,0.00070085336,0.00028184697,0.0000037854313,0.11275726],"genre_scores_gemma":[0.99113846,0.000686089,0.00014456171,0.0060578785,0.000116007446,0.000015398451,0.000069893926,0.0000058011224,0.0017659353],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911366,0.0042951507,0.00076548464,0.00018810359,0.0031031703,0.0005114647],"domain_scores_gemma":[0.9931442,0.004535339,0.00070365594,0.00078286405,0.00029443004,0.00053951656],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":["metaresearch","scholarly_communication"],"category_scores_codex":[0.048425093,0.000076789125,0.00014204644,0.001966863,0.0018388897,0.0021595072,0.0024078616,0.00002795907,0.00031173532],"category_scores_gemma":[0.008552262,0.000052124687,0.000015507225,0.0025510564,0.00030164944,0.030224256,0.001601342,0.0014939541,0.00000949653],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032916322,0.00003653996,0.01351522,0.000043322754,0.000061633364,0.00036856392,0.009354684,0.00016581599,1.16353625e-7,0.43446213,0.45289347,0.088769354],"study_design_scores_gemma":[0.00021712767,0.000110315785,0.0132849,0.000013106334,0.000007786695,0.00012600404,0.13052016,0.0002690391,0.0000011124731,0.007223979,0.8481755,0.000050929186],"about_ca_topic_score_codex":0.7087664,"about_ca_topic_score_gemma":0.80337924,"teacher_disagreement_score":0.90877485,"about_ca_system_score_codex":0.00022534853,"about_ca_system_score_gemma":0.009358189,"threshold_uncertainty_score":0.99979913},"labels":[],"label_agreement":null},{"id":"W4285178284","doi":"10.18653/v1/2022.deelio-1","title":"Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures","year":2022,"lang":"en","type":"paratext","venue":"","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":"University of British Columbia","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Deep learning; Artificial intelligence; Computer science; Extraction (chemistry); Machine learning; Chemistry","score_opus":0.10579495292610251,"score_gpt":0.40898478142943545,"score_spread":0.3031898285033329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285178284","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01384155,0.0052219406,0.2443038,0.0025938111,0.00495791,0.0039325636,0.000068757996,0.00017698221,0.7249027],"genre_scores_gemma":[0.22711746,0.0016619192,0.00167721,0.0005098356,0.00069176656,0.00063778873,0.00044660678,0.000085097825,0.76717234],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960275,0.0003983745,0.0010157832,0.0009774056,0.0012356339,0.00034528555],"domain_scores_gemma":[0.9932956,0.004775394,0.0010957015,0.00032727007,0.00042492014,0.00008109899],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006288426,0.00038293324,0.0005875556,0.00083560287,0.0008926286,0.0007685481,0.0009241252,0.00018952003,0.0038694704],"category_scores_gemma":[0.005475483,0.00024266337,0.00020032178,0.00070934766,0.00016027458,0.00029841118,0.0006793689,0.0016037747,0.00043747664],"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":[0.00037970702,0.000115852185,0.000021344955,0.00012029753,0.00008209009,4.6679125e-7,0.0070930505,0.0069071194,0.00027522215,0.0043892297,0.14783499,0.83278066],"study_design_scores_gemma":[0.00034526002,0.00057578506,0.00021015672,0.00011144276,0.00006909103,0.000004054811,0.032735184,0.012816281,0.0003051618,0.0029222528,0.9495784,0.00032694748],"about_ca_topic_score_codex":0.000053424432,"about_ca_topic_score_gemma":0.00093595387,"teacher_disagreement_score":0.83245367,"about_ca_system_score_codex":0.000101953876,"about_ca_system_score_gemma":0.000044722292,"threshold_uncertainty_score":0.9970411},"labels":[],"label_agreement":null},{"id":"W4285325594","doi":"10.1109/hpcc-dss-smartcity-dependsys53884.2021.00025","title":"Message from the DIKW 2021 General Chairs","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Regina","funders":"Zayed University; Southern Methodist University; Nihon University","keywords":"Computer science; Telecommunications; Library science; Computer security; Operations research; Engineering","score_opus":0.18359957351730186,"score_gpt":0.40852648183886836,"score_spread":0.2249269083215665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285325594","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10948911,0.00086825073,0.059657738,0.11649075,0.002147863,0.00021578903,0.00044954836,0.00006245747,0.7106185],"genre_scores_gemma":[0.41305465,0.00019248357,0.0052693295,0.029519634,0.0007627628,0.00001689248,0.00017479372,0.0000114007535,0.55099803],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979789,0.00031019477,0.00028915328,0.00037221372,0.00089986384,0.00014966803],"domain_scores_gemma":[0.9978365,0.0008966458,0.000053626467,0.0010743244,0.00008658342,0.000052340292],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0017433775,0.00006939443,0.00012644565,0.000018824283,0.00014179847,0.0004912391,0.0008201146,0.000025451349,0.03410701],"category_scores_gemma":[0.0010317317,0.000035852638,0.000081662474,0.00034393338,0.0000527351,0.00016404588,0.0006857667,0.00006843932,0.002315904],"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":[0.0000028631432,0.00003448193,0.0005436541,3.3721238e-7,0.000019886967,0.00002970614,0.0003047591,0.000020236625,0.00018809723,0.11322823,0.81108207,0.07454569],"study_design_scores_gemma":[0.0001195633,0.000004296862,0.008635678,0.000002195475,0.0000074157606,5.4989266e-7,0.0036370924,0.00037703855,0.0009859778,0.050847683,0.93531233,0.00007015914],"about_ca_topic_score_codex":0.0006030893,"about_ca_topic_score_gemma":0.0019395475,"teacher_disagreement_score":0.30356553,"about_ca_system_score_codex":0.000008427167,"about_ca_system_score_gemma":0.000032584594,"threshold_uncertainty_score":0.9984609},"labels":[],"label_agreement":null},{"id":"W4285335450","doi":"10.14778/3494124.3494149","title":"Ember","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"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; Joins; Schema (genetic algorithms); Context (archaeology); Code (set theory); Information retrieval; Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.14569448175843022,"score_gpt":0.38625044455308555,"score_spread":0.24055596279465533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285335450","genre_codex":"other","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":[0.40125245,0.00031275986,0.00026590438,0.028313095,0.0013686477,0.0005097799,0.000044472054,0.000057740494,0.56787515],"genre_scores_gemma":[0.9674962,0.000029763456,0.0013860769,0.0013606643,0.00006237678,0.000018442566,0.0000011414002,0.0000063186676,0.029638993],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977883,0.000016972948,0.0004301266,0.0003109235,0.0012832199,0.00017046872],"domain_scores_gemma":[0.9988625,0.000120243756,0.00023858955,0.00031222502,0.00041631577,0.000050094055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017498882,0.00008337014,0.00017010682,0.00005396444,0.000096120886,0.00018215316,0.001006377,0.000024441402,0.00066612894],"category_scores_gemma":[0.0015655471,0.000048218102,0.00013489154,0.0006024831,0.000071193106,0.00025271895,0.0011002491,0.00007328689,0.00017525165],"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":[0.000022604734,0.00029209678,0.0067584496,0.00005124116,0.00007451925,0.000002271176,0.0011799654,0.000013204485,0.022831721,0.44697928,0.4881496,0.033645038],"study_design_scores_gemma":[0.00033984127,0.000023287874,0.007295904,0.000036280824,0.000028410883,0.000008421216,0.0034987936,0.000047074947,0.19152468,0.14425294,0.65282774,0.00011665757],"about_ca_topic_score_codex":0.000016777569,"about_ca_topic_score_gemma":0.000008547709,"teacher_disagreement_score":0.56624377,"about_ca_system_score_codex":0.000026989946,"about_ca_system_score_gemma":0.000026741482,"threshold_uncertainty_score":0.7293645},"labels":[],"label_agreement":null},{"id":"W4285582215","doi":"10.15868/socialsector.40379","title":"The Data Assembly: The Responsible Data Re-Use Framework","year":2020,"lang":"en","type":"report","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Mount Allison University","funders":"Henry Luce Foundation","keywords":"Computer science","score_opus":0.8301770159171185,"score_gpt":0.5768168267993399,"score_spread":0.2533601891177786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285582215","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000822385,0.0024913498,0.07005435,0.34637168,0.010801553,0.0019254847,0.018258702,0.00033592797,0.5497527],"genre_scores_gemma":[0.0011643431,0.034658946,0.023333583,0.023402404,0.004661913,0.00006885936,0.019764239,0.00016470153,0.892781],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9823409,0.002251128,0.00201996,0.0029306326,0.009841265,0.0006161704],"domain_scores_gemma":[0.8412856,0.0701467,0.0020883295,0.08496793,0.0011330204,0.00037840707],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.07306641,0.0004166928,0.0006891515,0.00014808876,0.0011373697,0.007954704,0.04776182,0.00036394817,0.0013004625],"category_scores_gemma":[0.25248155,0.00017340973,0.00013552463,0.0016541452,0.00039408385,0.002065997,0.052777473,0.0014603982,0.0034289365],"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":[0.000042828502,0.00002247333,0.000031058942,0.000010821932,0.000141686,0.00002867469,0.000055050637,0.0000011231303,2.5676948e-7,0.023765424,0.9285621,0.04733851],"study_design_scores_gemma":[0.00004711478,0.000021422637,0.0004288692,0.000059594386,0.00012936733,0.0000068277354,0.0015485089,0.0007352439,0.0000013858322,0.033021998,0.9637359,0.0002637822],"about_ca_topic_score_codex":0.0015515845,"about_ca_topic_score_gemma":0.008046887,"teacher_disagreement_score":0.34302828,"about_ca_system_score_codex":0.00006750907,"about_ca_system_score_gemma":0.0027226354,"threshold_uncertainty_score":0.9996125},"labels":[],"label_agreement":null},{"id":"W4287455910","doi":"10.1007/978-3-031-12670-3_17","title":"Discovery of Keys for Graphs","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data deduplication; Theoretical computer science; Key (lock); Graph; Modular decomposition; Object (grammar); Pathwidth; Artificial intelligence; Computer security; Line graph","score_opus":0.09635541844843103,"score_gpt":0.35710321165896763,"score_spread":0.2607477932105366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287455910","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":[0.00009822517,0.00015388802,0.988787,0.00097294716,0.002029666,0.0004983772,0.00021503247,0.000019481195,0.0072254064],"genre_scores_gemma":[0.561445,0.00028799498,0.39798102,0.011343303,0.0010344511,0.00014905531,0.00022867597,0.00013544367,0.027395027],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952286,0.000055287517,0.0008207253,0.0012132,0.0023382804,0.00034391033],"domain_scores_gemma":[0.9951382,0.0026203112,0.0005127086,0.0014688717,0.00020290042,0.00005698891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005158552,0.00025854833,0.00053871755,0.0011075482,0.00021537469,0.00042764263,0.0037487962,0.000099883444,0.00022261533],"category_scores_gemma":[0.00088482955,0.00020305996,0.00024208766,0.0007055175,0.0008141176,0.0007268924,0.0020566478,0.00030360062,0.000015769388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027434331,0.000040420895,0.000039105693,0.000041545,0.000014496712,0.00001048778,0.00043297067,0.0089349,0.00004274214,0.40141767,0.0011355166,0.5878627],"study_design_scores_gemma":[0.000176252,0.00018396536,0.00007323898,0.000052549345,0.000010139135,0.00000275302,0.0000016757293,0.0074543,0.00028062734,0.9173114,0.0741903,0.0002628262],"about_ca_topic_score_codex":0.000037091435,"about_ca_topic_score_gemma":0.00012622112,"teacher_disagreement_score":0.59080595,"about_ca_system_score_codex":0.00009226978,"about_ca_system_score_gemma":0.00024661832,"threshold_uncertainty_score":0.8280545},"labels":[],"label_agreement":null},{"id":"W4287901858","doi":"10.5281/zenodo.3611327","title":"CESSDA ERIC Persistent Identifier Policy 2019","year":2020,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Identifier; Genealogy; Computer science; History; Programming language","score_opus":0.291310094241864,"score_gpt":0.3978849953402161,"score_spread":0.1065749010983521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287901858","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015673325,0.00040711355,0.003336065,0.0090624215,0.001192547,0.00087734393,0.0033114012,0.000802867,0.9808535],"genre_scores_gemma":[0.112706624,0.00858233,0.0008749174,0.0046178345,0.0077427453,4.694113e-7,0.056578342,0.010696423,0.7982003],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99101126,0.0011174375,0.0010772577,0.0013997041,0.004788586,0.0006057502],"domain_scores_gemma":[0.99416745,0.0001196987,0.0007092378,0.0018686648,0.0026689784,0.00046598425],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0070485165,0.00034069314,0.00054807845,0.001058266,0.0022642028,0.0056336066,0.0055412143,0.00019236372,0.045622535],"category_scores_gemma":[0.016673991,0.00031520936,0.00037510457,0.0023527301,0.00028730993,0.00060371915,0.007852444,0.0006590731,0.10683136],"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":[0.00002328441,0.00007735231,6.2804713e-7,0.000106608706,0.00011611387,0.000027625547,0.0005746024,0.000019025587,0.000043914977,0.0020033072,0.882122,0.11488555],"study_design_scores_gemma":[0.00022878,0.00015735456,0.00027296136,0.000057633937,0.00005777888,0.00008636826,0.0009149892,0.00006834587,0.0000129717355,0.0008391467,0.9969706,0.0003330504],"about_ca_topic_score_codex":0.00026294755,"about_ca_topic_score_gemma":0.0000022535605,"teacher_disagreement_score":0.1826532,"about_ca_system_score_codex":0.0006269115,"about_ca_system_score_gemma":0.00007622045,"threshold_uncertainty_score":0.99993},"labels":[],"label_agreement":null},{"id":"W4288088430","doi":"","title":"Data Interoperability Assessment Towards the Resilience of Data Exchange Systems","year":2019,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Berger (Canada)","funders":"","keywords":"Interoperability; Computer science; Resilience (materials science); Data exchange; Semantic interoperability; Data science; Database; World Wide Web","score_opus":0.2178816663540311,"score_gpt":0.39189918402393886,"score_spread":0.17401751766990775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288088430","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":[0.011580475,0.0070757815,0.7785769,0.07546819,0.0038515518,0.002987094,0.016581561,0.00012219402,0.10375626],"genre_scores_gemma":[0.84269637,0.0063056136,0.054115877,0.00039268238,0.00010959256,0.00011938075,0.011727628,0.00007134711,0.08446153],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9499785,0.039796785,0.002662494,0.003538411,0.0033160425,0.0007077684],"domain_scores_gemma":[0.93783194,0.011560429,0.0023600862,0.043585036,0.0043814774,0.00028105403],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.123976655,0.0005736126,0.0010667496,0.00023799633,0.0005903982,0.0020829893,0.036103103,0.00033724826,0.00095275335],"category_scores_gemma":[0.0151895,0.00043114784,0.00020468047,0.0011073269,0.0016510464,0.0018246067,0.06461378,0.0011531857,0.00036550264],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047375677,0.0022148103,0.0037127063,0.001644446,0.00038026914,0.0000068557592,0.011176779,0.0005993381,0.0002329503,0.3250072,0.08417528,0.570802],"study_design_scores_gemma":[0.00045005835,0.0000015902128,0.01236825,0.0031382963,0.00016224806,0.0000075620164,0.0035258862,0.24280618,0.00032297624,0.002515961,0.73418766,0.0005133104],"about_ca_topic_score_codex":0.021187888,"about_ca_topic_score_gemma":0.010715277,"teacher_disagreement_score":0.83111584,"about_ca_system_score_codex":0.00025870907,"about_ca_system_score_gemma":0.001340889,"threshold_uncertainty_score":0.9999605},"labels":[],"label_agreement":null},{"id":"W4288870185","doi":"10.1007/978-3-031-01865-7_7","title":"Profiling Non-Relational Data","year":2019,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Computer science; Relational database; XML; Big data; Data type; Data science; Data mining; World Wide Web; Programming language","score_opus":0.38729458902149144,"score_gpt":0.40962350864797265,"score_spread":0.022328919626481203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288870185","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000023774987,0.00031727744,0.021713093,0.0026034906,0.0014302896,0.0018349676,0.016708184,0.000113739596,0.9552766],"genre_scores_gemma":[0.0011239046,0.0006733661,0.0130790565,0.003391396,0.0006715358,0.00004629557,0.027844315,0.00015960562,0.9530105],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9889292,0.000191776,0.0015003504,0.0040066596,0.004810438,0.00056157],"domain_scores_gemma":[0.97380686,0.002864663,0.00095089205,0.022094864,0.00012457134,0.00015813622],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.008362029,0.0007842016,0.00096234964,0.0010679804,0.00029961826,0.0010083604,0.017840682,0.00033657602,0.006507755],"category_scores_gemma":[0.0021200783,0.00061862404,0.00017844627,0.0001954573,0.00017212653,0.0012586098,0.01855476,0.0006192611,0.017994028],"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":[0.00005904352,0.000051533672,0.000004794743,0.00010512471,0.0005296001,0.000042447176,0.000008525432,0.00019977725,7.130486e-7,0.32840657,0.5070807,0.16351119],"study_design_scores_gemma":[0.00020360477,0.000035459983,0.00014815795,0.00031644822,0.0004167624,0.0000016811509,0.00005552093,0.002345416,0.000010711556,0.033690214,0.96208674,0.0006893088],"about_ca_topic_score_codex":0.000019279383,"about_ca_topic_score_gemma":0.00010585538,"teacher_disagreement_score":0.45500603,"about_ca_system_score_codex":0.00013613432,"about_ca_system_score_gemma":0.00013375565,"threshold_uncertainty_score":0.9996265},"labels":[],"label_agreement":null},{"id":"W4288917651","doi":"10.1007/978-3-031-01865-7_8","title":"Data Profiling Tools","year":2019,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Computer science; Visualization; Data science; Data mining; Operating system","score_opus":0.4881953596693671,"score_gpt":0.4276409553592674,"score_spread":0.06055440431009973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288917651","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000015525188,0.00048151263,0.0073031476,0.0026624366,0.0014888095,0.0021376198,0.036900725,0.00018200812,0.94884217],"genre_scores_gemma":[0.00056231127,0.0015111245,0.008096152,0.0048858016,0.0006385421,0.000054896598,0.026180938,0.0001960059,0.95787424],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9877042,0.00029462198,0.0016819354,0.004786574,0.0048245722,0.0007080807],"domain_scores_gemma":[0.9621809,0.0037303972,0.0010178492,0.032771643,0.00011681315,0.00018235884],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.010357936,0.00092673907,0.0012310715,0.001065484,0.00028225756,0.0024035398,0.027912157,0.00035573283,0.0062382496],"category_scores_gemma":[0.0042095217,0.0007142229,0.00020396065,0.00021122901,0.00018327078,0.0017870574,0.02644856,0.0006607452,0.018900812],"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":[0.000052763393,0.00004235543,0.0000010539645,0.00012029404,0.00043812304,0.000063222105,0.000005686564,0.00004380261,7.278577e-7,0.23770505,0.4354103,0.32611662],"study_design_scores_gemma":[0.00017646073,0.000045826968,0.000036749072,0.0003631163,0.0004851092,0.0000021013266,0.00008366065,0.00051037373,0.000026115822,0.037221815,0.9602462,0.0008024698],"about_ca_topic_score_codex":0.00001700284,"about_ca_topic_score_gemma":0.00015398985,"teacher_disagreement_score":0.52483594,"about_ca_system_score_codex":0.00013777414,"about_ca_system_score_gemma":0.00011179197,"threshold_uncertainty_score":0.9995309},"labels":[],"label_agreement":null},{"id":"W4289533864","doi":"10.1109/icde53745.2022.00248","title":"Effective Explanations for Entity Resolution Models","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 38th International Conference on Data Engineering (ICDE)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"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 Toronto","funders":"Science for Equity, Empowerment and Development Division","keywords":"Computer science; Counterfactual thinking; Trustworthiness; Probabilistic logic; Classifier (UML); Artificial intelligence; Machine learning; Task (project management); Resolution (logic); Matching (statistics); Data mining","score_opus":0.41086171946325595,"score_gpt":0.4345066269760401,"score_spread":0.02364490751278414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289533864","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":[0.003465981,0.000031289826,0.9616903,0.004021814,0.0053672167,0.00093486,0.01827106,0.0001426315,0.006074857],"genre_scores_gemma":[0.9801638,0.000045473866,0.0052702874,0.00057606224,0.0003405281,0.00072606065,0.007735271,0.000029115668,0.005113382],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966371,0.00014386982,0.00049115275,0.00076911505,0.0017148186,0.00024393944],"domain_scores_gemma":[0.99758315,0.0007137189,0.00018972668,0.0011888989,0.00024294342,0.000081559425],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033610319,0.000166178,0.00019930003,0.0004955466,0.00028564545,0.00034856284,0.0031791315,0.000034008743,0.0016748073],"category_scores_gemma":[0.0013226534,0.00016974399,0.00007779745,0.0003762704,0.000027728265,0.0011294526,0.0012164164,0.00027991243,0.000106858555],"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":[0.000109452296,0.00016823183,0.000011010488,0.000011338429,0.00010745825,0.0000071812556,0.00021134797,0.2639377,0.00033875727,0.55370104,0.17206877,0.009327682],"study_design_scores_gemma":[0.00034967402,0.000084387066,0.00013408845,0.0000100188145,0.0000122653155,0.0000029928658,0.0003405451,0.7333299,0.000050011797,0.013745926,0.25177985,0.00016033287],"about_ca_topic_score_codex":0.00008819513,"about_ca_topic_score_gemma":0.00006949608,"teacher_disagreement_score":0.97669786,"about_ca_system_score_codex":0.00024815113,"about_ca_system_score_gemma":0.00006556305,"threshold_uncertainty_score":0.9992378},"labels":[],"label_agreement":null},{"id":"W4292572073","doi":"10.48550/arxiv.1312.7373","title":"Extending Contexts with Ontologies for Multidimensional Data Quality\\n Assessment","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Carleton University","funders":"","keywords":"Computer science; Datalog; Context (archaeology); Quality (philosophy); Data quality; Quality assessment; Information retrieval; Database; Data mining; Data science; Evaluation methods; Engineering","score_opus":0.6327342795842864,"score_gpt":0.39462611012385806,"score_spread":0.23810816946042834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292572073","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":[0.16327873,0.00009490767,0.8270624,0.0010003772,0.0009795392,0.0016604068,0.0024812133,0.0001807737,0.003261593],"genre_scores_gemma":[0.96155524,0.000077636985,0.025038958,0.0003366056,0.00008520267,0.000010609885,0.0010512802,0.000024903076,0.011819561],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99497306,0.00064042764,0.00070596056,0.002561094,0.00062762963,0.0004918256],"domain_scores_gemma":[0.99054605,0.0030392092,0.00095895276,0.0046313955,0.0006204347,0.0002039669],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005370511,0.00042058813,0.00078993523,0.0003767463,0.00034868624,0.00039346563,0.0042494335,0.00024644024,0.00034081878],"category_scores_gemma":[0.0013496901,0.0003383384,0.00019122948,0.000375934,0.00034925406,0.0011468438,0.007894994,0.00045677662,0.00019862967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028903765,0.0003373352,0.0045816046,0.00013401727,0.00042772977,0.000101681435,0.00014349935,0.026466532,0.000019997458,0.9084561,0.04774198,0.011300519],"study_design_scores_gemma":[0.0042845733,0.0003699515,0.045502104,0.0003809385,0.000550229,0.0000058781798,0.008089029,0.3058515,0.00003568582,0.3509122,0.28191814,0.0020997638],"about_ca_topic_score_codex":0.0007543245,"about_ca_topic_score_gemma":0.0014452953,"teacher_disagreement_score":0.8020235,"about_ca_system_score_codex":0.00020240113,"about_ca_system_score_gemma":0.00032261416,"threshold_uncertainty_score":0.99990684},"labels":[],"label_agreement":null},{"id":"W4292735752","doi":"10.5281/zenodo.6111560","title":"Research Data Canada's 2013 Infrastructure Report","year":2013,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Université Laval","keywords":"Data science; Computer science; Business","score_opus":0.3393149948349254,"score_gpt":0.4226062867898235,"score_spread":0.0832912919548981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292735752","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041613763,0.0005248821,0.002184009,0.009542604,0.0021472692,0.0018480917,0.010526672,0.0005765647,0.9722338],"genre_scores_gemma":[0.04837671,0.0068378616,0.0020008606,0.0014980616,0.0060251397,9.842923e-7,0.29665273,0.009980285,0.62862736],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9803662,0.0025640894,0.0016820175,0.0024630344,0.011828133,0.0010965765],"domain_scores_gemma":[0.9783401,0.00047467538,0.000974282,0.008875711,0.010692541,0.000642687],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.034430057,0.00041233722,0.0006691365,0.0011591854,0.004201662,0.0067948285,0.01637947,0.0003319096,0.09765543],"category_scores_gemma":[0.04172557,0.0003617078,0.00009569827,0.0024091774,0.00055255345,0.001084664,0.029196158,0.0018798377,0.02510604],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011905519,0.000044228404,0.000002270349,0.00007897056,0.00007980033,0.0002699035,0.00009831727,0.000023479382,0.000010333325,0.0005870675,0.83071035,0.16808335],"study_design_scores_gemma":[0.0001722122,0.00007076042,0.0009454826,0.00007041572,0.000026930818,0.0006404532,0.0010703471,0.00018466324,0.0000057201128,0.0014231488,0.99500895,0.00038090802],"about_ca_topic_score_codex":0.21666329,"about_ca_topic_score_gemma":0.010836469,"teacher_disagreement_score":0.34360638,"about_ca_system_score_codex":0.0013451774,"about_ca_system_score_gemma":0.0005698752,"threshold_uncertainty_score":0.9998835},"labels":[],"label_agreement":null},{"id":"W4293162521","doi":"10.1007/978-3-031-01865-7","title":"Data Profiling","year":2019,"lang":"en","type":"book","venue":"Synthesis lectures on data management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Metadata; Computer science; Data science; Research data; World Wide Web; Data curation; Operating system","score_opus":0.4345880521667448,"score_gpt":0.4454418407113966,"score_spread":0.010853788544651799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293162521","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000012498698,0.0005940887,0.008694728,0.00236543,0.0020530045,0.002297109,0.035753127,0.00020870296,0.94803256],"genre_scores_gemma":[0.00011933768,0.00077100826,0.0060128565,0.0039155185,0.00067244365,0.000075009724,0.03261295,0.00014051348,0.9556804],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98597026,0.00066272035,0.0016965843,0.0052924007,0.0055595646,0.0008184701],"domain_scores_gemma":[0.9552925,0.0040051206,0.0010658638,0.039331775,0.000114814764,0.00018989488],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.013610947,0.0009136091,0.0012848651,0.001257517,0.0002945078,0.0019569395,0.03777334,0.0003673314,0.003236155],"category_scores_gemma":[0.005112842,0.0006961924,0.00018825111,0.00046859484,0.00018645907,0.0013909884,0.032896105,0.0007316042,0.019326104],"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":[0.000056927787,0.00009038895,0.0000017167833,0.00024052443,0.00052685477,0.000071138355,0.000009299678,0.00007012799,4.6116435e-7,0.043178137,0.7421225,0.21363194],"study_design_scores_gemma":[0.00018961783,0.00004313553,0.000031518815,0.0003725532,0.000519564,0.0000018360998,0.00011004564,0.0010167013,0.000018187082,0.025714824,0.97120106,0.0007809812],"about_ca_topic_score_codex":0.000018739835,"about_ca_topic_score_gemma":0.00014977634,"teacher_disagreement_score":0.22907856,"about_ca_system_score_codex":0.0002514999,"about_ca_system_score_gemma":0.00024142313,"threshold_uncertainty_score":0.9995489},"labels":[],"label_agreement":null},{"id":"W4293242898","doi":"10.23889/ijpds.v7i3.2105","title":"Public Engagement and other Essential Requirements for Data Trusts, Data Repositories and Other Data Collaborations.","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick; University of British Columbia; University of Toronto","funders":"","keywords":"Stakeholder engagement; Data governance; Documentation; Stewardship (theology); Stakeholder; Data management; Corporate governance; Directive; Public engagement; Public consultation; Test (biology); Computer science; Business; Political science; Engineering; Data quality; Public relations; Operations management; Database; Finance; Law","score_opus":0.6550036183699004,"score_gpt":0.5352410799770353,"score_spread":0.1197625383928651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293242898","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":[0.023831455,0.0007117204,0.5725599,0.040839653,0.022216538,0.002961951,0.33604315,0.00009368686,0.0007419521],"genre_scores_gemma":[0.79081,0.0001683936,0.121884786,0.005549961,0.002834376,0.00010335347,0.07625374,0.00006402305,0.002331369],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.993439,0.00028516306,0.0010486554,0.0016155457,0.0033168804,0.0002947556],"domain_scores_gemma":[0.9922219,0.000662947,0.0009164131,0.005359395,0.00066865707,0.00017067707],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.028374372,0.00014957461,0.0001907847,0.00049979595,0.002294542,0.0051016402,0.01870518,0.000025047135,0.00022133408],"category_scores_gemma":[0.011608844,0.00013064599,0.000015096149,0.000673215,0.00029114212,0.014242206,0.0266436,0.00015619765,0.0000034313373],"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":[0.00035824114,0.00039730416,0.036232114,0.00002227717,0.00029666992,0.000009026008,0.0005753921,0.0001724803,0.00039962918,0.14727324,0.70455724,0.10970641],"study_design_scores_gemma":[0.0006665357,0.00004247423,0.002027968,0.0000095273,0.000038380513,0.000038030103,0.0011411132,0.1396458,0.0000060413845,0.006920848,0.8493141,0.00014916994],"about_ca_topic_score_codex":0.00032257597,"about_ca_topic_score_gemma":0.0006112507,"teacher_disagreement_score":0.76697856,"about_ca_system_score_codex":0.000105032,"about_ca_system_score_gemma":0.00036800568,"threshold_uncertainty_score":0.9995451},"labels":[],"label_agreement":null},{"id":"W4293243715","doi":"10.23889/ijpds.v7i3.2077","title":"Analysing Siamese Neural Network Architectures for Computing Name Similarity.","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Guelph","funders":"","keywords":"Similarity (geometry); Computer science; Classifier (UML); False positive paradox; Artificial intelligence; String metric; Artificial neural network; Random forest; Similitude; False positives and false negatives; Set (abstract data type); Machine learning; Pattern recognition (psychology); Data mining; String searching algorithm; Pattern matching","score_opus":0.2782177487324201,"score_gpt":0.5106037761682547,"score_spread":0.23238602743583459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293243715","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":[0.27509695,0.00009608599,0.6992705,0.011610349,0.010762718,0.0006318418,0.002284129,0.000049731043,0.00019769785],"genre_scores_gemma":[0.9677878,0.0000015326136,0.028767914,0.0016722338,0.00090530724,0.000008665075,0.00063224783,0.000008250809,0.00021604403],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944961,0.00019511355,0.00089696504,0.00067727064,0.0033574225,0.00037709574],"domain_scores_gemma":[0.9965632,0.0011482952,0.000778234,0.0007244835,0.0006561311,0.00012966518],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01694581,0.00011643021,0.0001904095,0.00060978066,0.002467159,0.0018791666,0.0068138726,0.000016075159,0.00017532219],"category_scores_gemma":[0.006043157,0.00009992385,0.0001303243,0.0008947331,0.00014021223,0.0012295324,0.002741666,0.00023273376,0.0000036105769],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012432504,0.000051865474,0.01074011,0.0000021043952,0.000039605507,0.000005322761,0.00019787726,0.80004853,0.000034244753,0.011517566,0.024053928,0.1531845],"study_design_scores_gemma":[0.00036220637,0.00005589077,0.018498404,0.0000067240103,0.000015977035,0.00005693482,0.0003757065,0.8098908,0.0000031931902,0.060384225,0.110222,0.00012791311],"about_ca_topic_score_codex":0.000082907136,"about_ca_topic_score_gemma":0.00008549764,"teacher_disagreement_score":0.69269085,"about_ca_system_score_codex":0.00017856614,"about_ca_system_score_gemma":0.00012443132,"threshold_uncertainty_score":0.99915695},"labels":[],"label_agreement":null},{"id":"W4294243313","doi":"10.23889/ijpds.v7i3.1962","title":"A proposed approach for standardized reporting of data linkage processes and results.","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linkage (software); Record linkage; Computer science; Linked data; Population; Data science; Information retrieval; Data mining; Readability; Medicine","score_opus":0.5125041464715098,"score_gpt":0.5428579715218413,"score_spread":0.030353825050331573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294243313","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":[0.017457291,0.0000911537,0.94452274,0.0033307679,0.0015449487,0.0010229895,0.031589054,0.000022197224,0.00041885002],"genre_scores_gemma":[0.75684744,0.000020618365,0.23590769,0.00017158067,0.00020436897,0.000020607093,0.006416657,0.000008181715,0.00040283182],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99315023,0.000094625866,0.0024492163,0.00082139025,0.0033032815,0.00018124591],"domain_scores_gemma":[0.9918025,0.000739334,0.0043823323,0.0013017317,0.0016887088,0.00008539608],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05103772,0.00008346187,0.00022229993,0.00045012924,0.0008590074,0.00088404457,0.006725245,0.000014883513,0.000019544264],"category_scores_gemma":[0.07579295,0.000065320004,0.00003310964,0.0007029386,0.00017729268,0.0048324624,0.004130147,0.00011406396,2.5457433e-7],"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":[0.0059731696,0.0011968088,0.013935383,0.00033439827,0.00034325075,0.000028717894,0.0033320899,0.01270308,0.0028507214,0.054566525,0.1642205,0.74051535],"study_design_scores_gemma":[0.003919468,0.00033116867,0.0058322875,0.00005667195,0.000065213186,0.00022995779,0.005229995,0.43843213,0.0002862372,0.04650584,0.49874792,0.00036310856],"about_ca_topic_score_codex":0.00006844195,"about_ca_topic_score_gemma":0.000027969678,"teacher_disagreement_score":0.74015224,"about_ca_system_score_codex":0.00007204648,"about_ca_system_score_gemma":0.00048888545,"threshold_uncertainty_score":0.9986488},"labels":[],"label_agreement":null},{"id":"W4294243567","doi":"10.23889/ijpds.v7i3.1782","title":"Data on Patient Record Trajectory for Linkage (DataPRinT Linkage).","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Linkage (software); Computer science; Data mining; Table (database); Key (lock); Medical diagnosis; Process (computing); Medical record; Health care; Record linkage; Information retrieval; Data science; Computer security; Medicine; Political science","score_opus":0.4308056502261164,"score_gpt":0.5122798057911399,"score_spread":0.08147415556502347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294243567","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":[0.14074223,0.000114072056,0.64453757,0.024659086,0.05348919,0.0028910395,0.1319569,0.00013956179,0.0014703225],"genre_scores_gemma":[0.9164508,0.000060573533,0.054106664,0.0052750194,0.0015409528,0.00012155135,0.020599853,0.000035660785,0.0018089075],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99244416,0.00019835998,0.0012127474,0.00125414,0.0045370962,0.00035349317],"domain_scores_gemma":[0.99414223,0.0011649794,0.0009479825,0.002841748,0.0007167674,0.00018626527],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01718742,0.00015610264,0.00020337425,0.0008331821,0.0015513302,0.0015848781,0.016583357,0.00002756258,0.00052877615],"category_scores_gemma":[0.009897495,0.00013329,0.00008936032,0.0006209705,0.00013244599,0.00484185,0.006654784,0.00030876286,0.000045144152],"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":[0.0004378703,0.00040958938,0.0011790607,0.000006345108,0.000059820784,0.000015183608,0.0002367361,0.0074491906,0.00019036677,0.028849114,0.2833042,0.6778625],"study_design_scores_gemma":[0.000586903,0.00024760322,0.0045678373,0.000015044808,0.000013533917,0.000026841086,0.00062490604,0.09449528,0.000025947027,0.016399182,0.8828146,0.00018235562],"about_ca_topic_score_codex":0.00010311247,"about_ca_topic_score_gemma":0.0001383535,"teacher_disagreement_score":0.77570856,"about_ca_system_score_codex":0.00031918104,"about_ca_system_score_gemma":0.00027374583,"threshold_uncertainty_score":0.9997485},"labels":[],"label_agreement":null},{"id":"W4294834616","doi":"10.31219/osf.io/pa5fx","title":"Understanding the Challenges Associated with Finding and Accessing Restricted Data in Canada: A Mixed Methods Study","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"National Research Council Canada; University of Saskatchewan; McMaster University Medical Centre; McMaster University; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Discoverability; Custodians; Metadata; Data access; Computer science; Documentation; Consistency (knowledge bases); Information retrieval; Data element; Data management; Data discovery; Data collection; Rubric; Data science; Data mining; World Wide Web; Database; Geography; Statistics; Mathematics","score_opus":0.7837340661535428,"score_gpt":0.5285062507486068,"score_spread":0.255227815404936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294834616","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":[0.6748665,0.0039603906,0.23528065,0.03344957,0.0041602845,0.00756949,0.0017863344,0.00026710104,0.03865968],"genre_scores_gemma":[0.9972844,0.00016125025,0.0019039875,0.00017397072,0.000015672013,0.00005656492,0.00013394516,0.000016538375,0.00025364084],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9891447,0.0059396722,0.0008634826,0.0014304273,0.0022618386,0.00035989418],"domain_scores_gemma":[0.9862269,0.010112028,0.0007179363,0.0028044384,0.00006002723,0.00007867679],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.028384496,0.0002680022,0.0006066342,0.00042669507,0.00051910226,0.001060008,0.0041749156,0.000067128,0.00021006212],"category_scores_gemma":[0.007331492,0.00015833126,0.000021529337,0.0011286396,0.00007319669,0.0003973314,0.0185731,0.0008873796,3.7601828e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005808175,0.0022565827,0.24353777,0.0003521997,0.004751333,0.0018267748,0.06974717,0.014996745,0.000006236838,0.06309026,0.08158254,0.5172716],"study_design_scores_gemma":[0.0006819349,0.000060418188,0.32524073,0.00010918483,0.00012556434,0.0000014907012,0.6377186,0.012685322,5.631978e-7,0.021162912,0.001803714,0.00040953117],"about_ca_topic_score_codex":0.6538165,"about_ca_topic_score_gemma":0.99151707,"teacher_disagreement_score":0.56797147,"about_ca_system_score_codex":0.001358986,"about_ca_system_score_gemma":0.001441031,"threshold_uncertainty_score":0.999977},"labels":[],"label_agreement":null},{"id":"W4295878695","doi":"10.1162/qss_a_00211","title":"Assessing the quality of bibliographic data sources for measuring international research collaboration","year":2022,"lang":"en","type":"article","venue":"Quantitative Science Studies","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":"Université de Montréal","funders":"","keywords":"Computer science; Data science; Quality (philosophy); Digital library; Data quality; Information retrieval; Conceptual framework; Metric (unit); Engineering","score_opus":0.9238412134420332,"score_gpt":0.7257074572657539,"score_spread":0.19813375617627926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295878695","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":[0.93793625,0.0028685164,0.02290242,0.027467953,0.0025772797,0.0012026023,0.0010792153,0.000034255027,0.003931494],"genre_scores_gemma":[0.9952641,0.00012670447,0.004207525,0.00011012646,0.000031506926,0.00009758058,0.000015649206,0.000003283281,0.00014351578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9904249,0.0017829029,0.0007391174,0.0007402979,0.006025782,0.00028705236],"domain_scores_gemma":[0.97565424,0.016114464,0.00076929026,0.0015401321,0.005874872,0.000046971105],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.13792866,0.00007812503,0.00022216242,0.002603617,0.0037792183,0.001015887,0.0048956405,0.000007858378,0.000028967914],"category_scores_gemma":[0.05603263,0.00004930538,0.00004797191,0.017008753,0.0032785728,0.003045732,0.004982365,0.00014821586,0.0000057136576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019426199,0.00033038977,0.020508012,0.00006142253,0.00029540792,0.0000011280382,0.04541436,0.0020082593,0.009219865,0.8452355,0.05691098,0.019820387],"study_design_scores_gemma":[0.00021989705,0.00016370395,0.037543613,0.000015024216,0.000009911826,2.725601e-7,0.8053657,0.003295567,0.00067114254,0.11139558,0.041212644,0.00010697581],"about_ca_topic_score_codex":0.0001001873,"about_ca_topic_score_gemma":0.00032525248,"teacher_disagreement_score":0.7599513,"about_ca_system_score_codex":0.00007011552,"about_ca_system_score_gemma":0.00026955022,"threshold_uncertainty_score":0.99943393},"labels":[],"label_agreement":null},{"id":"W4301135710","doi":"10.1145/3487553.3524263","title":"VisPaD: Visualization and Pattern Discovery for Fighting Human Trafficking","year":2022,"lang":"en","type":"article","venue":"Companion Proceedings of the Web Conference 2022","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Visualization; Identification (biology); Cluster (spacecraft); Domain (mathematical analysis); Data science; Space (punctuation); Task (project management); Data visualization; Data mining; Human–computer interaction; Engineering","score_opus":0.12123217389918489,"score_gpt":0.3699951522064527,"score_spread":0.2487629783072678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301135710","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":[0.990825,0.000029847353,0.0051355264,0.001284049,0.00038905372,0.0005581238,0.00013924055,0.000037762566,0.0016014217],"genre_scores_gemma":[0.9979235,0.0000055689848,0.000043149503,0.0002971709,0.00003955531,0.000074205505,0.000020078956,0.000010091337,0.0015866634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977981,0.000058872567,0.0005486537,0.0004292725,0.0009777729,0.00018735371],"domain_scores_gemma":[0.9986634,0.00023460438,0.0006093126,0.00019714456,0.0002578787,0.00003764749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028629962,0.00012089556,0.00024331143,0.00016636189,0.00085670233,0.0005228634,0.0011977305,0.000021741063,0.00025227582],"category_scores_gemma":[0.0005114435,0.00009107315,0.0000899722,0.00046606478,0.00009884567,0.000618116,0.0015367462,0.00013253445,0.0000016833407],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039333747,0.00019530013,0.012572528,0.00015165638,0.000039330396,2.2860034e-7,0.0042853034,0.00007393361,0.03793327,0.87694484,0.045601305,0.022162974],"study_design_scores_gemma":[0.0039475863,0.0010367224,0.04944158,0.0003686182,0.0002210075,0.00002471843,0.124852486,0.20006572,0.017201789,0.25779116,0.34371787,0.0013307167],"about_ca_topic_score_codex":0.000015597723,"about_ca_topic_score_gemma":0.000012250607,"teacher_disagreement_score":0.6191537,"about_ca_system_score_codex":0.000038632515,"about_ca_system_score_gemma":0.00003781171,"threshold_uncertainty_score":0.65891486},"labels":[],"label_agreement":null},{"id":"W4301605997","doi":"10.23889/ijpds.v7i1.1757","title":"A scoping review of preprocessing methods for unstructured text data to assess data quality","year":2022,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":30,"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 Manitoba; George & Fay Yee Centre for Healthcare Innovation; Manitoba Health","funders":"Canada Research Chairs","keywords":"Computer science; Preprocessor; Punctuation; Data quality; Data pre-processing; Stop words; Information retrieval; Lexical analysis; Natural language processing; Artificial intelligence; Data mining","score_opus":0.9239911994930267,"score_gpt":0.7624971008446532,"score_spread":0.1614940986483735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301605997","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.775133e-7,0.50871915,0.45906195,0.00053468277,0.003809113,0.001991975,0.0258214,0.000012734808,0.00004884132],"genre_scores_gemma":[7.113046e-7,0.6736616,0.2973722,0.0004914062,0.0003421187,0.000062115716,0.027946467,0.000019748732,0.00010366798],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9858254,0.0013752916,0.004651135,0.0027198945,0.005014746,0.0004135255],"domain_scores_gemma":[0.9694701,0.008737557,0.0073152576,0.012089778,0.002060535,0.00032680912],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.119293615,0.0003425022,0.00166487,0.0011385233,0.0007887261,0.0021248998,0.0544372,0.00007620063,0.00041845653],"category_scores_gemma":[0.15512058,0.0002622833,0.00022184687,0.002136638,0.0001927214,0.009437866,0.025450964,0.0003545998,0.0000074438117],"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":[0.00001638609,0.00003557527,0.0000031983682,0.015165743,0.00007216633,7.1137333e-7,0.000015818116,0.000017344075,9.618203e-7,0.0012809657,0.014333921,0.9690572],"study_design_scores_gemma":[0.00014764289,0.00002282537,0.000014626487,0.06427237,0.00024886287,0.000049237944,0.000057191693,0.003803544,4.46795e-7,0.0025340237,0.9285659,0.0002832889],"about_ca_topic_score_codex":0.000085950196,"about_ca_topic_score_gemma":0.0000698519,"teacher_disagreement_score":0.9687739,"about_ca_system_score_codex":0.00027663723,"about_ca_system_score_gemma":0.0027547234,"threshold_uncertainty_score":0.99998295},"labels":[],"label_agreement":null},{"id":"W4302335021","doi":"","title":"A Big Step Forward: It’s Time for a Database of Evidence Summaries in Library and","year":2016,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; Concordia University; University of Alberta","funders":"","keywords":"Database; Computer science; Data science; Information retrieval","score_opus":0.683002680968158,"score_gpt":0.6234343031518965,"score_spread":0.05956837781626145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302335021","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":[0.8507852,0.04780895,0.03876381,0.033515107,0.0021967979,0.005929614,0.007535211,0.00011236384,0.013352964],"genre_scores_gemma":[0.9000368,0.0720382,0.006999877,0.0035421788,0.0003245912,0.00024743937,0.00006718194,0.00009582585,0.016647913],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958306,0.0005392506,0.0014838709,0.00061786757,0.001197851,0.00033053622],"domain_scores_gemma":[0.9908609,0.0067265895,0.001061745,0.0009570442,0.00018460635,0.00020913061],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0073185177,0.00021942194,0.00081372407,0.0012248219,0.00012220633,0.0015402959,0.0043987967,0.000065821216,0.005805685],"category_scores_gemma":[0.0062974365,0.00012849197,0.00013465776,0.0011691244,0.00031542845,0.015989864,0.0036371113,0.000114711605,0.00002689032],"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":[0.001160743,0.00026300646,0.18480167,0.00021760816,0.000108100285,0.000024129853,0.00024783082,0.0000051667907,0.02306636,0.002568495,0.5276949,0.25984204],"study_design_scores_gemma":[0.002304839,0.00007606559,0.31942356,0.0047768685,0.00011617831,0.000007326976,0.0006826374,0.00029836307,0.022005765,0.09438106,0.55518067,0.00074664946],"about_ca_topic_score_codex":0.00023358944,"about_ca_topic_score_gemma":0.00012267598,"teacher_disagreement_score":0.25909537,"about_ca_system_score_codex":0.000020007443,"about_ca_system_score_gemma":0.00016866086,"threshold_uncertainty_score":0.9994962},"labels":[],"label_agreement":null},{"id":"W4306317280","doi":"10.1145/3511808.3557673","title":"Probing the Robustness of Pre-trained Language Models for Entity Matching","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information &amp; Knowledge Management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"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 Alberta","funders":"","keywords":"Robustness (evolution); Computer science; Spurious relationship; Machine learning; Software deployment; Artificial intelligence; Training set; Data modeling; Data mining; Database; Software engineering","score_opus":0.15254733957015623,"score_gpt":0.3846648573911663,"score_spread":0.23211751782101006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306317280","genre_codex":"other","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":[0.22621213,0.000034959536,0.19894972,0.014525772,0.0038444402,0.0054124678,0.00083862134,0.00013973033,0.55004215],"genre_scores_gemma":[0.9870851,0.000010636499,0.0030726846,0.00024880306,0.000051090363,0.0004601219,0.0000761438,0.000007960501,0.008987467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99686956,0.000046704314,0.0010067311,0.00024272522,0.0016432769,0.0001909966],"domain_scores_gemma":[0.9970588,0.00023150425,0.0011323406,0.00051469036,0.0010305294,0.000032097705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004558297,0.00016165442,0.00021522274,0.00040925064,0.00041572878,0.00041258452,0.0044810805,0.000027241449,0.0003302906],"category_scores_gemma":[0.0008270525,0.00010564143,0.0001783285,0.00052229007,0.00009992437,0.0015189783,0.0032486876,0.00017788951,0.000026917764],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002042132,0.00016532684,0.000028316614,0.0002484307,0.00012261244,2.4261496e-8,0.014245321,0.018179517,0.000112026806,0.93375325,0.017637819,0.015303162],"study_design_scores_gemma":[0.0024119136,0.0001618744,0.0013035475,0.0003902251,0.00015660223,0.0000054445372,0.12053072,0.17646834,0.00085623964,0.40662882,0.29047832,0.0006079737],"about_ca_topic_score_codex":0.000021247479,"about_ca_topic_score_gemma":0.000029765764,"teacher_disagreement_score":0.76087296,"about_ca_system_score_codex":0.00014042914,"about_ca_system_score_gemma":0.000038242004,"threshold_uncertainty_score":0.8327037},"labels":[],"label_agreement":null},{"id":"W4307174368","doi":"10.5281/zenodo.7243921","title":"Deliverable 1.6 Data Governance Framework","year":2020,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Horizon 2020 Framework Programme","keywords":"Deliverable; Corporate governance; Data governance; Process management; Computer science; Business; Systems engineering; Engineering; Finance; Marketing; Data quality","score_opus":0.4122397577623883,"score_gpt":0.41663312835974364,"score_spread":0.004393370597355339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307174368","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028074293,0.0007070728,0.049143698,0.0064864564,0.0011567534,0.00074529875,0.013604732,0.0008903297,0.9272376],"genre_scores_gemma":[0.14792897,0.056641616,0.030179657,0.013607334,0.015870068,6.1201894e-7,0.32661185,0.02779413,0.38136578],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9909484,0.00094035396,0.0009651106,0.0017882771,0.0048364033,0.0005215],"domain_scores_gemma":[0.9919099,0.0003044565,0.00078224915,0.0045213704,0.0021309585,0.00035106536],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.009351674,0.00030335377,0.0005176449,0.00022584744,0.002204841,0.004656343,0.013085051,0.00022919368,0.06649248],"category_scores_gemma":[0.04566444,0.0002862691,0.000113354516,0.001465027,0.000232484,0.00095350505,0.020277396,0.0009892926,0.077783585],"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":[0.000023090604,0.00005763285,7.485201e-7,0.00006826388,0.000058886548,0.00003108854,0.0001867692,0.000013539772,0.0000063378607,0.006140813,0.77006,0.22335283],"study_design_scores_gemma":[0.0001514166,0.00009598149,0.00019192437,0.000109417546,0.000039818828,0.000047055477,0.00027099886,0.00037108795,0.0000062830863,0.0033274821,0.9950747,0.00031386333],"about_ca_topic_score_codex":0.00012907236,"about_ca_topic_score_gemma":0.0000028835973,"teacher_disagreement_score":0.5458718,"about_ca_system_score_codex":0.00033668344,"about_ca_system_score_gemma":0.0000469288,"threshold_uncertainty_score":0.99995893},"labels":[],"label_agreement":null},{"id":"W4308752211","doi":"10.1002/bdm.2307","title":"Meta‐informational cue inconsistency and judgment of information accuracy: Spotlight on intelligence analysis","year":2022,"lang":"en","type":"article","venue":"Journal of Behavioral Decision Making","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of Ontario; Government of Canada; Defence Research and Development Canada","funders":"","keywords":"Credibility; Reliability (semiconductor); Psychology; Computer science; Social psychology; Information quality; Quality (philosophy); Cognitive psychology; Natural language processing; Information system","score_opus":0.25537479457183065,"score_gpt":0.45268452003447074,"score_spread":0.19730972546264008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308752211","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":[0.7592959,0.00031063138,0.23718295,0.000900719,0.00085891,0.00030822615,0.0002341331,0.000012210082,0.0008963562],"genre_scores_gemma":[0.9884812,0.000037959675,0.010907713,0.00050212035,0.000016280215,0.0000063078824,0.000009860017,0.0000034443788,0.000035064346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9929978,0.00026814063,0.002623358,0.00016153896,0.003798485,0.00015067977],"domain_scores_gemma":[0.9945153,0.0015747736,0.002763584,0.00044123927,0.00061395817,0.00009115424],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008691698,0.00014439768,0.0006220968,0.0023270058,0.0002719886,0.00030313386,0.0009350239,0.000036583864,0.0018028534],"category_scores_gemma":[0.0008950435,0.000102062884,0.000494375,0.0018330141,0.00005891373,0.002349505,0.0007124312,0.00029189876,0.000021473554],"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":[0.00058087305,0.00035439467,0.0028185935,0.000010352548,0.0007851437,0.000027204977,0.0028479588,0.059287526,0.000023018316,0.013411547,0.0038774507,0.9159759],"study_design_scores_gemma":[0.0034895511,0.006507377,0.23922455,0.000378076,0.024972262,0.0006091426,0.08099983,0.050321255,0.0012739977,0.27747,0.31280836,0.0019456032],"about_ca_topic_score_codex":0.000014513696,"about_ca_topic_score_gemma":0.000013103307,"teacher_disagreement_score":0.9140303,"about_ca_system_score_codex":0.00011791789,"about_ca_system_score_gemma":0.00008493637,"threshold_uncertainty_score":0.9991096},"labels":[],"label_agreement":null},{"id":"W4309421654","doi":"10.31223/x5h07q","title":"Community recommendations for geochemical data, services and analytical capabilities in the 21st century","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"HORIZON EUROPE Framework Programme; Cambridge Trust; Eidgenössische Technische Hochschule Zürich; Gates Cambridge Trust; Nuclear Safety and Security Commission; Deutsche Forschungsgemeinschaft; Bill and Melinda Gates Foundation; European Commission; Geochemical Society; National Aeronautics and Space Administration; Natural Environment Research Council; Science Foundation Ireland; National Science Foundation","keywords":"Data science; Variety (cybernetics); Computer science; Data sharing; Data quality; Earth science; Outreach; Data curation; Quality (philosophy); Political science; Service (business); Business; Artificial intelligence","score_opus":0.3850553958374082,"score_gpt":0.47515712563240603,"score_spread":0.09010172979499781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309421654","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":[0.29359412,0.0014166529,0.0043384642,0.46336564,0.0033688196,0.007353495,0.06024955,0.00024262679,0.16607061],"genre_scores_gemma":[0.86854607,0.0025758604,0.017189432,0.03417942,0.0004232236,0.0013980052,0.070425496,0.000050882096,0.00521163],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957894,0.001817686,0.00076161785,0.0006276119,0.0007866979,0.00021695922],"domain_scores_gemma":[0.98938215,0.0065922234,0.00017904268,0.003708411,0.00008334937,0.000054802167],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.018390063,0.00016641294,0.00033739954,0.00017990678,0.00045369193,0.000788936,0.005494163,0.000094342344,0.0015389352],"category_scores_gemma":[0.001731808,0.00010810135,0.000071536924,0.00025590364,0.00019670892,0.0003107725,0.015050557,0.00096339645,0.000009998077],"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":[0.0000871184,0.0012335972,0.0031734782,0.0007150324,0.0001376475,0.0000021577664,0.022983564,0.00007197426,0.0000012049607,0.43391377,0.46648863,0.07119184],"study_design_scores_gemma":[0.0001243317,0.000016381044,0.0012517007,0.000012250654,0.000027824524,7.3430675e-7,0.20995003,0.0036826164,5.030927e-7,0.11646107,0.668357,0.000115526374],"about_ca_topic_score_codex":0.0053071696,"about_ca_topic_score_gemma":0.0075571476,"teacher_disagreement_score":0.57495195,"about_ca_system_score_codex":0.00004731716,"about_ca_system_score_gemma":0.000057058096,"threshold_uncertainty_score":0.9998866},"labels":[],"label_agreement":null},{"id":"W4309617049","doi":"10.1145/3571281","title":"Efficiently Cleaning Structured Event Logs: A Graph Repair Approach","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","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":"Simon Fraser University","funders":"Beijing National Research Center For Information Science And Technology; National Natural Science Foundation of China","keywords":"Computer science; Workflow; Event (particle physics); Pruning; Data mining; Graph; Profiling (computer programming); Information retrieval; Theoretical computer science; Database; Programming language","score_opus":0.11679595709416458,"score_gpt":0.35897822892552084,"score_spread":0.24218227183135627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309617049","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":[0.009426407,0.00025694203,0.9766492,0.00040243688,0.003217915,0.0012736254,0.0063290126,0.000424474,0.0020199372],"genre_scores_gemma":[0.99131215,0.000013613272,0.0043960162,0.00042837326,0.000065088156,0.0004227625,0.0005775493,0.000028971428,0.0027555074],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99336386,0.0013303277,0.0010241437,0.0011261149,0.002727783,0.00042777462],"domain_scores_gemma":[0.99491006,0.0006978599,0.0003144542,0.0038078288,0.00009119069,0.00017860868],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.006514168,0.0002537365,0.0003957864,0.0007524402,0.0013073109,0.00027657722,0.0022303027,0.00004586341,0.0008134438],"category_scores_gemma":[0.0004147896,0.00021756743,0.0003174985,0.0018732569,0.00008820976,0.00042233584,0.00021483855,0.00049361284,0.00019454381],"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":[0.000536886,0.0025119146,0.00012515136,0.00026310002,0.00056906365,0.00012182899,0.0034137687,0.77707064,0.00047766796,0.02937876,0.13830233,0.047228917],"study_design_scores_gemma":[0.0019629227,0.0005214039,0.0003274187,0.00006897005,0.00019563844,0.00017329857,0.06328368,0.05944963,0.00015046407,0.0020557586,0.8708953,0.00091548136],"about_ca_topic_score_codex":0.00056761334,"about_ca_topic_score_gemma":0.000067476576,"teacher_disagreement_score":0.98188573,"about_ca_system_score_codex":0.0001570881,"about_ca_system_score_gemma":0.000069767644,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W4309836268","doi":"10.23889/ijpds.v7i4.1755","title":"Validating a novel deterministic privacy-preserving record linkage between administrative &amp; clinical data: applications in stroke research","year":2022,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ted Rogers Centre for Heart Research; Indoc Research; University Health Network; University of Toronto; Health Sciences Centre; Ontario Brain Institute; Heart and Stroke Foundation; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; University of Toronto; Ontario Ministry of Health and Long-Term Care; Government of Ontario; Department of Medicine, University of Toronto; Ontario Brain Institute; Heart and Stroke Foundation of Canada","keywords":"Record linkage; Linkage (software); Computer science; Medical record; Stroke (engine); Data science; Medicine; Engineering; Genetics; Gene; Biology; Environmental health; Internal medicine","score_opus":0.8808373577486144,"score_gpt":0.6882838280011057,"score_spread":0.19255352974750872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309836268","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":[0.34877247,0.0000331565,0.609324,0.007706007,0.004499306,0.0017497698,0.026847279,0.000047132384,0.0010208917],"genre_scores_gemma":[0.93915176,0.000017179336,0.0536749,0.00018791227,0.00084984757,0.00007649742,0.0051920763,0.000013463533,0.0008363769],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.98899704,0.0008802238,0.002225126,0.0014706752,0.005942395,0.00048451428],"domain_scores_gemma":[0.9836115,0.009209928,0.001374432,0.004045782,0.0014501251,0.00030819935],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.074597135,0.00014139549,0.00029191258,0.0012901521,0.00189623,0.002310759,0.024463499,0.000047594265,0.00025208713],"category_scores_gemma":[0.049950123,0.00012951242,0.00006958383,0.0017633335,0.00035570553,0.0055440464,0.018923897,0.0009803541,0.000033435605],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025853037,0.0011016782,0.6440929,0.00001864894,0.00011922713,0.000026135855,0.0010894261,0.0016419396,0.0004156381,0.027719803,0.036165755,0.28735027],"study_design_scores_gemma":[0.000968633,0.00015453536,0.18700662,0.0000428254,0.000021808624,0.000031389394,0.003191502,0.058750357,0.0000073467636,0.03917782,0.7103605,0.000286627],"about_ca_topic_score_codex":0.0003552016,"about_ca_topic_score_gemma":0.00075649266,"teacher_disagreement_score":0.67419475,"about_ca_system_score_codex":0.00037635464,"about_ca_system_score_gemma":0.00072272914,"threshold_uncertainty_score":0.9994032},"labels":[],"label_agreement":null},{"id":"W4310153872","doi":"10.1007/s13042-022-01686-5","title":"MORE: Toward Improving Author Name Disambiguation in Academic Knowledge Graphs","year":2022,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"International Science and Technology Cooperation Programme; National Key Research and Development Program of China","keywords":"Computer science; Embedding; Cluster analysis; Artificial intelligence; Graph; Graph embedding; Representation (politics); Similarity (geometry); Hierarchical clustering; Feature learning; Machine learning; Task (project management); Data mining; Theoretical computer science; Image (mathematics)","score_opus":0.08535776253208069,"score_gpt":0.42558615324482046,"score_spread":0.3402283907127398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310153872","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":[0.9707275,0.005309106,0.007464955,0.013422082,0.0019399071,0.000105612286,0.000037149497,0.000018477009,0.0009752258],"genre_scores_gemma":[0.99657965,0.00031656248,0.0005287974,0.00021624455,0.00011494144,0.0000029948574,0.00001355398,0.000007921338,0.0022193538],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969273,0.0004854287,0.00080107374,0.00019287391,0.0014624428,0.00013085792],"domain_scores_gemma":[0.9984496,0.0005375717,0.000628783,0.00008567733,0.00022747346,0.00007085946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005398422,0.00009388833,0.00018294407,0.00056473794,0.00010617374,0.00015909428,0.0008307124,0.000035356465,0.00026817448],"category_scores_gemma":[0.0024232464,0.0000799195,0.00008013385,0.0002731723,0.000055725195,0.00023989799,0.0006139562,0.00095780956,0.0000100217],"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":[0.00028359093,0.0002496536,0.11264206,0.000011273526,0.00009466945,0.00010717991,0.013783333,0.014570399,0.00044284534,0.02250196,0.0033059032,0.8320071],"study_design_scores_gemma":[0.0032018945,0.00075353036,0.12100575,0.00010603551,0.00006424116,0.00039610238,0.015685277,0.18266684,0.0000934226,0.08445354,0.5911038,0.00046955212],"about_ca_topic_score_codex":0.00011246953,"about_ca_topic_score_gemma":0.000023214445,"teacher_disagreement_score":0.8315376,"about_ca_system_score_codex":0.00009579493,"about_ca_system_score_gemma":0.000053335938,"threshold_uncertainty_score":0.41612592},"labels":[],"label_agreement":null},{"id":"W4312036666","doi":"10.2196/preprints.44331","title":"Optimizing Patient Record Linkage in a Master Patient Index Using Machine Learning: Algorithm Development and Validation (Preprint)","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Hamilton Health Sciences; McMaster University; Population Health Research Institute; University of Toronto","funders":"","keywords":"Computer science; Matching (statistics); Record linkage; Population; Software; Machine learning; Linkage (software); Interface (matter); Artificial intelligence; Set (abstract data type); Data mining; Programming language; Medicine; Operating system","score_opus":0.16978250935429592,"score_gpt":0.35992108858677824,"score_spread":0.1901385792324823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312036666","genre_codex":"empirical","genre_gemma":"methods","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":[0.6575446,0.0001726222,0.33610997,0.0003042965,0.0011053914,0.0015436177,0.000067174515,0.00010056232,0.0030517543],"genre_scores_gemma":[0.45397407,0.00015618191,0.5415155,0.0008520401,0.000057380046,0.00037994666,0.0006750537,0.0000721861,0.0023176146],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99263304,0.0011551136,0.0020364472,0.0016722871,0.0020745299,0.00042855338],"domain_scores_gemma":[0.99727243,0.0004256201,0.0009918343,0.0009973553,0.0001567246,0.00015606232],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053299568,0.0004283621,0.0006329089,0.0010217365,0.00031365038,0.0008581755,0.00080905546,0.00019311091,0.0024638288],"category_scores_gemma":[0.00067953055,0.00038274593,0.00011321801,0.0005250188,0.000051952786,0.00036906239,0.011968746,0.0011852564,0.000046110785],"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":[0.00004627971,0.00022503741,0.014089161,0.000059029153,0.000052516294,0.0000513101,0.012662058,0.07284756,0.000008300683,0.00008901961,0.00015013461,0.8997196],"study_design_scores_gemma":[0.0009884603,0.00024187453,0.004139515,0.0002955887,0.00003563958,0.000009511429,0.019921344,0.63693434,0.0007026095,0.0052825124,0.33009258,0.0013560083],"about_ca_topic_score_codex":0.0013632971,"about_ca_topic_score_gemma":0.00031287386,"teacher_disagreement_score":0.8983636,"about_ca_system_score_codex":0.0004958296,"about_ca_system_score_gemma":0.00018499175,"threshold_uncertainty_score":0.99986243},"labels":[],"label_agreement":null},{"id":"W4312333616","doi":"10.1115/ipc2022-87872","title":"Structured, Systematic Threat Based Approach to Evaluate and Improve Data Quality to Facilitate Digital Transformation","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Dynamic Systems Analysis (Canada)","funders":"","keywords":"Computer science; Data quality; Data governance; Pipeline (software); Asset (computer security); Quality (philosophy); Data science; Risk analysis (engineering); Cloud computing; Data mining; Process management; Computer security; Engineering; Operations management","score_opus":0.4426005142575988,"score_gpt":0.43085171282932977,"score_spread":0.011748801428269007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312333616","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":[0.043801326,0.000028891576,0.91800773,0.0040561743,0.00029130143,0.003789158,0.008732363,0.000097205986,0.021195877],"genre_scores_gemma":[0.99084,3.6133292e-7,0.0037059041,0.0018095829,0.000009921077,0.00020541623,0.0006407113,0.000006979795,0.0027811131],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99487007,0.00070150633,0.0010065851,0.0008216573,0.0023556908,0.0002445208],"domain_scores_gemma":[0.99698365,0.0005862591,0.00013330186,0.0019957654,0.00010144717,0.00019955436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013176241,0.00016191165,0.00039955266,0.00023760567,0.00029263864,0.000929922,0.0016958984,0.000020328222,0.00023869066],"category_scores_gemma":[0.0016753267,0.0001116129,0.000049086186,0.00065183855,0.000030180932,0.0013693875,0.001339485,0.000089212896,0.00015110768],"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":[0.0019569658,0.0014903945,0.0005783386,0.020274937,0.0005451965,0.000010185134,0.07501588,0.06018092,0.0012161266,0.21013844,0.16080172,0.46779087],"study_design_scores_gemma":[0.005558054,0.001446675,0.004678704,0.00020891392,0.0003171413,0.00002234987,0.22703987,0.5375162,0.000284411,0.075016506,0.14543131,0.0024798585],"about_ca_topic_score_codex":0.0001781011,"about_ca_topic_score_gemma":0.00008402118,"teacher_disagreement_score":0.9470387,"about_ca_system_score_codex":0.000063911786,"about_ca_system_score_gemma":0.00004240429,"threshold_uncertainty_score":0.8967259},"labels":[],"label_agreement":null},{"id":"W4312347912","doi":"10.2196/39967","title":"Optimizing the Quality of Clinical Data in an Australian Aged Care and Disability Service to Improve Care Delivery and Clinical Outcomes: Protocol for an Agile Lean Six Sigma Study","year":2022,"lang":"en","type":"article","venue":"JMIR Research Protocols","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Documentation; Service delivery framework; Medicine; Agile software development; Health care; Quality (philosophy); Quality management; Process management; Service (business); Operations management; Business; Computer science; Engineering","score_opus":0.8856366775879874,"score_gpt":0.7578436878248014,"score_spread":0.12779298976318598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312347912","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31527635,3.705532e-7,0.000017787786,0.0006263718,0.000013575377,0.68295527,0.0010607461,0.000018879846,0.000030651405],"genre_scores_gemma":[0.15890126,6.614268e-8,0.0010981055,0.00021745412,0.0000639818,0.839565,0.00008259627,0.000018325607,0.000053202926],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9744514,0.016321225,0.0031206661,0.0022573725,0.003181844,0.0006674891],"domain_scores_gemma":[0.98441917,0.008568351,0.0005041092,0.0051088273,0.000929401,0.000470158],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0987264,0.00024856877,0.0009138639,0.00017285424,0.00084485556,0.0006718752,0.004831492,0.000116372554,0.00009014476],"category_scores_gemma":[0.00949171,0.00016665066,0.000121351004,0.0009825171,0.0006265617,0.0011284046,0.009722022,0.0010181778,0.000003183615],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048796427,0.00486638,0.87435025,0.0009309478,0.00003473868,0.000005587363,0.014746359,0.000045902747,0.000021172571,0.000098415025,0.0020587617,0.09796181],"study_design_scores_gemma":[0.006823993,0.012166033,0.6624529,0.00008994801,0.0000062505246,2.2422846e-7,0.2604738,0.00034625817,0.0000071676754,0.00046100465,0.056914996,0.0002574274],"about_ca_topic_score_codex":0.0025038521,"about_ca_topic_score_gemma":0.040511817,"teacher_disagreement_score":0.24572743,"about_ca_system_score_codex":0.00011595548,"about_ca_system_score_gemma":0.00034331722,"threshold_uncertainty_score":0.9988518},"labels":[],"label_agreement":null},{"id":"W4312438866","doi":"10.1007/978-3-031-16990-8_4","title":"Data Preprocessing","year":2022,"lang":"en","type":"book-chapter","venue":"International series in management science/operations research/International series in operations research & management science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; York University","funders":"","keywords":"Preprocessor; Software portability; Computer science; Raw data; Data pre-processing; Context (archaeology); Usability; Data quality; Task (project management); Data mining; Precondition; Data processing; Database; Artificial intelligence; Human–computer interaction; Engineering; Programming language","score_opus":0.4274617544225517,"score_gpt":0.5633610717969169,"score_spread":0.13589931737436517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312438866","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007808603,0.00016334999,0.0015285617,0.03242613,0.0046705175,0.0042336187,0.0012996988,0.00013728238,0.95475996],"genre_scores_gemma":[0.06139928,0.0074310736,0.017138159,0.00052872556,0.0005151611,0.0018730419,0.0020473879,0.00012266566,0.9089445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.95040286,0.0010439388,0.0034772938,0.006540122,0.035944656,0.0025911087],"domain_scores_gemma":[0.9859889,0.00080179784,0.0002790558,0.0071964953,0.0051613166,0.0005724009],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"category_scores_codex":[0.09803984,0.0008577964,0.0007958891,0.024841586,0.0072110095,0.016226511,0.04348985,0.00021322494,0.018436244],"category_scores_gemma":[0.008639766,0.0008574274,0.0001825523,0.011856309,0.013665223,0.026520943,0.05247046,0.0029927993,0.0016601386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021365957,0.0004670163,0.00013250251,0.00006205833,0.00012572056,0.00046933812,0.0008444872,0.07232182,0.00009322654,0.8964115,0.013559367,0.015299316],"study_design_scores_gemma":[0.0008036817,0.00015210698,0.0014525646,0.0003888881,0.000016458644,0.00003302123,0.010334063,0.04996751,0.000043564527,0.07596786,0.85997343,0.00086682575],"about_ca_topic_score_codex":0.0013110823,"about_ca_topic_score_gemma":0.015764987,"teacher_disagreement_score":0.8464141,"about_ca_system_score_codex":0.006842192,"about_ca_system_score_gemma":0.0017132165,"threshold_uncertainty_score":0.99971086},"labels":[],"label_agreement":null},{"id":"W4312989454","doi":"10.14778/3554821.3554864","title":"CERTEM","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","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 Toronto","funders":"","keywords":"Counterfactual thinking; Computer science; Debugging; Order (exchange); Matching (statistics); State (computer science); Artificial intelligence; Programming language; Epistemology; Mathematics; Philosophy","score_opus":0.15111650697305168,"score_gpt":0.36334862928504613,"score_spread":0.21223212231199445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312989454","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":[0.53809255,0.0002681255,0.00020710441,0.045273386,0.0028318563,0.0017611758,0.00020573886,0.00012971419,0.41123036],"genre_scores_gemma":[0.98736215,0.000005397933,0.00023851325,0.0009930928,0.00003097232,0.00008245711,9.2624504e-7,0.000005511134,0.01128096],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970824,0.000027909195,0.00043657777,0.0002919813,0.0019832933,0.00017785195],"domain_scores_gemma":[0.99910545,0.00011003951,0.0003467173,0.00027720293,0.00011902891,0.000041532097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033835822,0.000080759426,0.0001556302,0.00011181532,0.00033136888,0.00010189803,0.0021313764,0.00001009337,0.00083877996],"category_scores_gemma":[0.00048715516,0.00004940535,0.00012511532,0.0006803476,0.00006181779,0.00019040935,0.002684553,0.00011771538,0.000055046767],"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":[0.000058427693,0.00034138578,0.0037109056,0.000025704463,0.00004996509,6.4963194e-7,0.0019254583,0.00010779127,0.0065438417,0.30644527,0.65225214,0.028538445],"study_design_scores_gemma":[0.00033387492,0.000091145674,0.0034412453,0.0000060549437,0.000017886538,0.0000054992192,0.007972308,0.00017091559,0.008237335,0.09827807,0.8813429,0.00010279608],"about_ca_topic_score_codex":0.00004756431,"about_ca_topic_score_gemma":0.0000022901604,"teacher_disagreement_score":0.44926962,"about_ca_system_score_codex":0.00007334291,"about_ca_system_score_gemma":0.000016999908,"threshold_uncertainty_score":0.91840523},"labels":[],"label_agreement":null},{"id":"W4313347193","doi":"10.1007/978-3-031-18223-5_6","title":"Recommendations for Data Discovery, Sensemaking and Reuse","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on information concepts, retrieval, and services","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Metadata; Sensemaking; Variety (cybernetics); Documentation; Data science; Reuse; Computer science; Data discovery; Work (physics); World Wide Web; Knowledge management; Engineering","score_opus":0.15843408841646722,"score_gpt":0.3893312965759483,"score_spread":0.23089720815948106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313347193","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013262499,0.008318362,0.026328316,0.10162267,0.0062832446,0.009078322,0.081911296,0.0007234094,0.7644081],"genre_scores_gemma":[0.13095859,0.079884045,0.027334467,0.1713569,0.0038949565,0.00084187917,0.089238055,0.0007099229,0.49578118],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964588,0.00014993353,0.001194256,0.000706791,0.0012352902,0.00025489155],"domain_scores_gemma":[0.9912848,0.0050529414,0.0011656682,0.002174293,0.00021240563,0.00010988399],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0033876176,0.00039081316,0.00058040605,0.0005604978,0.00090107456,0.00214971,0.0019044257,0.00022006642,0.0013629233],"category_scores_gemma":[0.0026364843,0.0003165603,0.000105161576,0.00014031575,0.00015740299,0.0041701198,0.0018551669,0.00030953035,0.000053883894],"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":[0.0009995953,0.000030363964,0.000009459873,0.0008221644,0.00038595506,0.0000025260206,0.0059459335,0.000069402115,0.000004449318,0.3517081,0.2095418,0.43048024],"study_design_scores_gemma":[0.0002571166,0.000098587625,0.000022198925,0.00015624298,0.0001253327,0.00000469988,0.001984985,0.0012246501,0.000031084066,0.033126324,0.9625956,0.00037320657],"about_ca_topic_score_codex":0.0000783371,"about_ca_topic_score_gemma":0.00015039218,"teacher_disagreement_score":0.7530538,"about_ca_system_score_codex":0.000058665402,"about_ca_system_score_gemma":0.00008045896,"threshold_uncertainty_score":0.99992865},"labels":[],"label_agreement":null},{"id":"W4313347268","doi":"10.1007/978-3-031-18223-5_3","title":"Data Needs","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on information concepts, retrieval, and services","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Geography","score_opus":0.11148555734705928,"score_gpt":0.3599012098088728,"score_spread":0.24841565246181352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313347268","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016041294,0.001598652,0.0004699834,0.003455026,0.001260172,0.0007985035,0.008618031,0.00018694212,0.98345226],"genre_scores_gemma":[0.10274945,0.028369732,0.0014162882,0.12916678,0.0028015045,0.00018410855,0.03290433,0.000380317,0.7020275],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942808,0.00019856013,0.0014706646,0.0006524184,0.0030731708,0.00032436277],"domain_scores_gemma":[0.9926389,0.0029330268,0.0012874154,0.002701697,0.00026116526,0.00017779334],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0039775204,0.00051013986,0.0007384618,0.0011258582,0.00068046455,0.0015830846,0.0035754328,0.00033159903,0.016197124],"category_scores_gemma":[0.0012941526,0.00040011626,0.00015268075,0.00033363377,0.00021075906,0.0032585429,0.0019219423,0.0005508857,0.0012243914],"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":[0.00078485714,0.000031804502,0.000009311342,0.00050258695,0.0003720103,0.00000719647,0.004484234,0.00019916771,0.000002353287,0.3992824,0.18174654,0.41257754],"study_design_scores_gemma":[0.00019285695,0.00009650221,0.00004543366,0.00009529774,0.000104242165,0.0000046395894,0.0022839857,0.0004895568,0.000030597992,0.016931767,0.97926426,0.000460849],"about_ca_topic_score_codex":0.000070413575,"about_ca_topic_score_gemma":0.00008907186,"teacher_disagreement_score":0.7975177,"about_ca_system_score_codex":0.00007664437,"about_ca_system_score_gemma":0.00012359644,"threshold_uncertainty_score":0.9998451},"labels":[],"label_agreement":null},{"id":"W4313424566","doi":"10.2196/38922","title":"A Privacy-Preserving Distributed Medical Data Integration Security System for Accuracy Assessment of Cancer Screening: Development Study of Novel Data Integration System","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology","keywords":"Computer science; System integration; Cancer; Information privacy; Data integration; Data mining; Computer security; Medicine; Database","score_opus":0.31563900577634946,"score_gpt":0.505430718105667,"score_spread":0.18979171232931752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313424566","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":[0.10365208,0.000020018932,0.8864068,0.0007052573,0.0005835688,0.0024641552,0.0059196167,0.00007020155,0.0001783133],"genre_scores_gemma":[0.9735796,0.000005413115,0.01647219,0.000114764225,0.00005483857,0.00052721385,0.009223194,0.000010349937,0.000012447371],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98595357,0.00047493263,0.0039610346,0.00047344508,0.008827961,0.00030903448],"domain_scores_gemma":[0.99146086,0.002113518,0.0021259664,0.0034461706,0.0005673433,0.0002861201],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.022808801,0.00022239515,0.0007213762,0.00028617046,0.00034864142,0.00018004632,0.009594385,0.00012152557,0.00023730299],"category_scores_gemma":[0.010751315,0.00016165858,0.00005407549,0.0009810426,0.00009955901,0.0017032623,0.015360079,0.00050166226,0.0000017510532],"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":[0.000698636,0.010316219,0.005613454,0.008231175,0.0015970763,0.000025064131,0.089869544,0.0013422202,0.000033403878,0.033031374,0.2294111,0.6198307],"study_design_scores_gemma":[0.0017287149,0.00015126643,0.0010074385,0.0005523807,0.000058392106,0.0000047987182,0.20026475,0.7734352,0.000021152451,0.000018295525,0.022616513,0.0001410995],"about_ca_topic_score_codex":0.0005910154,"about_ca_topic_score_gemma":0.0011773783,"teacher_disagreement_score":0.8699346,"about_ca_system_score_codex":0.00032583807,"about_ca_system_score_gemma":0.0012571819,"threshold_uncertainty_score":0.99758154},"labels":[],"label_agreement":null},{"id":"W4315630458","doi":"10.1109/globecom48099.2022.10001041","title":"Efficient Information Sharing in ICT Supply Chain Social Network via Table Structure Recognition","year":2022,"lang":"en","type":"article","venue":"GLOBECOM 2022 - 2022 IEEE Global Communications Conference","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"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":"Mitacs","keywords":"Computer science; Table (database); Supply chain; Information sharing; Representation (politics); Structuring; Process (computing); Data mining; Artificial intelligence; World Wide Web","score_opus":0.11417516000948796,"score_gpt":0.3601949135115256,"score_spread":0.24601975350203764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315630458","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":[0.67905885,0.0020391461,0.10847661,0.036781367,0.009168993,0.0071284883,0.040477112,0.00096482236,0.115904614],"genre_scores_gemma":[0.99359006,0.00006513753,0.0016750024,0.0014214835,0.000060594222,0.00028718766,0.0026974115,0.000008877142,0.0001942732],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99448705,0.0013558946,0.0013042295,0.00057254435,0.0016833195,0.00059699366],"domain_scores_gemma":[0.99621075,0.00032938918,0.0006562967,0.002368499,0.00032315633,0.00011192715],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047160597,0.00026302075,0.00040127302,0.0002930779,0.0020088463,0.00067596766,0.0053197993,0.000091587746,0.004161419],"category_scores_gemma":[0.00041426794,0.00029124855,0.00011822008,0.00394182,0.00017980837,0.00072159606,0.0051343776,0.00077184034,0.00022793734],"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":[0.0003200575,0.00083932996,0.009978635,0.00004396609,0.0001264144,0.000011979028,0.005947338,0.14545287,0.000122011625,0.1989271,0.20022081,0.4380095],"study_design_scores_gemma":[0.0013746617,0.00015250877,0.019943302,0.000038748465,0.000056454857,0.000028977256,0.01392719,0.4096759,0.0000129486025,0.2267041,0.32716084,0.00092436024],"about_ca_topic_score_codex":0.0017016684,"about_ca_topic_score_gemma":0.0039715273,"teacher_disagreement_score":0.43708512,"about_ca_system_score_codex":0.0008106751,"about_ca_system_score_gemma":0.00024242647,"threshold_uncertainty_score":0.999954},"labels":[],"label_agreement":null},{"id":"W4318185132","doi":"10.1109/bigdata55660.2022.10020719","title":"From Data Warehouse to Lakehouse: A Comparative Review","year":2022,"lang":"en","type":"review","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Data warehouse; Computer science; Big data; Data science; Unstructured data; Data management; Data extraction; Analytics; Strengths and weaknesses; Data transformation; Data virtualization; Database; Data mining; Cloud computing","score_opus":0.9445247924110595,"score_gpt":0.5941263284283097,"score_spread":0.35039846398274976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318185132","genre_codex":"dataset","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.4829404e-7,0.45608628,0.004004519,0.0021729474,0.009992622,0.0015395446,0.52148074,0.00010096643,0.004622118],"genre_scores_gemma":[0.0000029208466,0.60721445,0.00043149482,0.0028948393,0.0015518144,0.00017462394,0.38533476,0.000050449184,0.0023446302],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97974664,0.002583426,0.0033330678,0.006373909,0.0072983913,0.0006645376],"domain_scores_gemma":[0.9574002,0.004158267,0.0022596095,0.035281073,0.00039333847,0.0005075001],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012021707,0.0010835255,0.0033660799,0.0009694112,0.00038338167,0.002031271,0.0844325,0.00020239461,0.018055383],"category_scores_gemma":[0.009123594,0.0008831522,0.00024101867,0.0018470454,0.00021904576,0.0026327898,0.06154928,0.0015585796,0.01191348],"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":[0.000020784662,0.00015718206,2.5254454e-7,0.0004495791,0.00032789877,0.00006297513,0.00003756451,8.5131984e-7,7.606146e-8,0.0007144516,0.5003039,0.49792445],"study_design_scores_gemma":[0.00026607176,0.00007629258,0.0000017329043,0.00914134,0.0006437727,0.000016156719,0.00030455462,0.00057533634,1.5896894e-7,0.00075039355,0.9872922,0.00093202636],"about_ca_topic_score_codex":0.0012387198,"about_ca_topic_score_gemma":0.0045828274,"teacher_disagreement_score":0.49699244,"about_ca_system_score_codex":0.00031306178,"about_ca_system_score_gemma":0.0014855758,"threshold_uncertainty_score":0.99936193},"labels":[],"label_agreement":null},{"id":"W4318187137","doi":"10.1109/bigdata55660.2022.10020293","title":"Entity Matching with AUC-Based Fairness","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Matching (statistics); Statistics; Mathematics","score_opus":0.6664563814827509,"score_gpt":0.4557380255016488,"score_spread":0.21071835598110206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318187137","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":[0.037671443,0.000051204417,0.58079004,0.029684363,0.02680365,0.0012514273,0.27326807,0.0003333516,0.050146453],"genre_scores_gemma":[0.9421769,0.000027335718,0.0008851946,0.0030008208,0.00055055844,0.00007188579,0.049754392,0.000024431656,0.0035085245],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911465,0.00060547673,0.00076645956,0.0019078131,0.005200207,0.00037355564],"domain_scores_gemma":[0.9922483,0.0006265891,0.000530135,0.0061526997,0.0002854757,0.00015681979],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0063508744,0.00028675687,0.0003435746,0.0005316997,0.00058336137,0.0013517684,0.016823674,0.000042586566,0.0060702134],"category_scores_gemma":[0.0008768787,0.00024246966,0.000050077742,0.00072403037,0.00017429804,0.0017404582,0.0084126005,0.00057270017,0.00070077024],"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":[0.00079204363,0.0010272501,0.0013144709,0.000024888837,0.00025435557,0.00025650262,0.00021745198,0.0016403192,0.00039331007,0.09533767,0.5560572,0.34268454],"study_design_scores_gemma":[0.0011599958,0.00017693636,0.0013182109,0.00004421529,0.00003428354,0.000015264332,0.002329668,0.036200147,0.00009883745,0.012399021,0.9457222,0.0005011918],"about_ca_topic_score_codex":0.0011803901,"about_ca_topic_score_gemma":0.0030879127,"teacher_disagreement_score":0.90450543,"about_ca_system_score_codex":0.00015164698,"about_ca_system_score_gemma":0.0005706901,"threshold_uncertainty_score":0.99968493},"labels":[],"label_agreement":null},{"id":"W4319163363","doi":"10.1016/j.infoandorg.2023.100450","title":"Data governance and digital innovation: A translational account of practitioner issues for IS research","year":2023,"lang":"en","type":"article","venue":"Information and Organization","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Data governance; Corporate governance; Leverage (statistics); Scholarship; Process (computing); Knowledge management; Translational research; Public relations; Political science; Service (business); Sociology; Business; Data quality; Computer science; Marketing; Medicine","score_opus":0.3347722549072698,"score_gpt":0.48715743105209824,"score_spread":0.15238517614482844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319163363","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":[0.25944152,0.00021550854,0.5615006,0.14907847,0.0006745018,0.0025421176,0.018956218,0.00026154405,0.007329524],"genre_scores_gemma":[0.98975235,0.00029127428,0.001307684,0.0007809163,0.000066971166,0.000008680583,0.0066931653,0.000006045957,0.0010929365],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985683,0.000022940387,0.00046352745,0.00012873339,0.000742916,0.00007358207],"domain_scores_gemma":[0.9979367,0.00034112504,0.00019884319,0.00025274194,0.0012536569,0.000016918124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025592241,0.00004220411,0.000071861235,0.00027202853,0.00016199089,0.0005456806,0.00021734777,0.00003416511,0.000120803736],"category_scores_gemma":[0.0042944094,0.00003610558,0.0000044300537,0.0023369486,0.000060546463,0.0069713593,0.00018237362,0.000035736317,0.00009568306],"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":[0.000030262016,0.000023975736,0.004512237,0.00008872481,0.000015605054,9.208885e-8,0.0045965547,0.000045453526,0.00004782995,0.37805915,0.45672193,0.15585817],"study_design_scores_gemma":[0.00034727273,0.000023574039,0.046151903,0.000012302402,0.00000336431,0.0000012293009,0.0023554105,0.009273476,0.00019714535,0.024942746,0.9166271,0.000064474654],"about_ca_topic_score_codex":0.000008768035,"about_ca_topic_score_gemma":0.0000050855533,"teacher_disagreement_score":0.7303108,"about_ca_system_score_codex":0.000006985772,"about_ca_system_score_gemma":0.00004775832,"threshold_uncertainty_score":0.526201},"labels":[],"label_agreement":null},{"id":"W4320024352","doi":"10.1109/bigdata55660.2022.10020258","title":"Review of Publically Available Health Big Data Sets","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Health informatics; Public health informatics; Computer science; Informatics; Usability; Data science; Dashboard; Data mining; Information retrieval; World Wide Web; Public health; Medicine; Health policy; International health; Engineering","score_opus":0.8077064389291911,"score_gpt":0.5061207953285485,"score_spread":0.30158564360064266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024352","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001490502,0.005669428,0.0188944,0.11308918,0.02354572,0.0015441999,0.79181635,0.00014336422,0.04514833],"genre_scores_gemma":[0.025111338,0.070449896,0.0025733763,0.073307976,0.002118886,0.00016579134,0.80585146,0.000081982,0.020339303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9871895,0.0013284273,0.0021439143,0.0028614919,0.005934084,0.0005425894],"domain_scores_gemma":[0.9789383,0.0009062659,0.0015668478,0.01765819,0.00061887724,0.00031151433],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.022832815,0.00034461226,0.0007724446,0.0006014536,0.00041365082,0.0007487819,0.038791616,0.000054727014,0.013330643],"category_scores_gemma":[0.0076445923,0.0003099359,0.00007111667,0.0013102505,0.00021712077,0.0024261512,0.035109952,0.0006791715,0.001720524],"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":[0.000046300007,0.00028333158,0.00003851975,0.00015143456,0.00007721219,0.000011252767,0.000017220764,0.0000022420993,0.000018642999,0.006074741,0.6461211,0.34715798],"study_design_scores_gemma":[0.00046444836,0.00014757545,0.00011679161,0.0005437565,0.000029547151,0.000016262404,0.00030931755,0.006916731,0.000007550864,0.0019215718,0.9892234,0.0003030168],"about_ca_topic_score_codex":0.0013941182,"about_ca_topic_score_gemma":0.0017527373,"teacher_disagreement_score":0.34685498,"about_ca_system_score_codex":0.00016477212,"about_ca_system_score_gemma":0.0016151189,"threshold_uncertainty_score":0.99993527},"labels":[],"label_agreement":null},{"id":"W4320924434","doi":"10.1007/978-3-031-25448-2_54","title":"Improving Maintenance Data Quality: Application of Natural Language Processing to Asset Management","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in mechanical engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hydro-Québec; Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Asset (computer security); Asset management; Quality (philosophy); Data quality; Business; Computer security; Finance; Marketing","score_opus":0.07670199170063244,"score_gpt":0.3735223383615675,"score_spread":0.29682034666093504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320924434","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":[0.00003120731,0.00028129978,0.9959897,0.00058435835,0.00044448444,0.00067887874,0.00024302668,0.00015141716,0.0015956598],"genre_scores_gemma":[0.7637233,0.00010798323,0.20406859,0.0018428437,0.0007547079,0.00018827194,0.0018436544,0.00037622033,0.027094407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958477,0.000040234998,0.0011655955,0.0011785438,0.001390586,0.00037735305],"domain_scores_gemma":[0.9964111,0.00090691785,0.00038903303,0.0021016682,0.00009808811,0.000093211944],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004281417,0.0003475395,0.00065958255,0.0005799218,0.00003776128,0.0001486421,0.0024296185,0.00023661455,0.000025396574],"category_scores_gemma":[0.0037646713,0.0003008645,0.00009760494,0.00048451874,0.000021293452,0.00022142635,0.002373048,0.0006026912,0.00009645387],"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":[0.000025390154,0.000014335245,7.288858e-7,0.0005383627,0.000041672603,0.0000328101,0.00011979874,0.010279487,0.0017071189,0.09219643,0.00018503537,0.89485884],"study_design_scores_gemma":[0.0006963701,0.00007899263,0.00010342278,0.0017057029,0.00013429449,0.000006406281,0.0001759498,0.85633916,0.0012273605,0.074377686,0.06365588,0.0014988008],"about_ca_topic_score_codex":0.00007846345,"about_ca_topic_score_gemma":0.00036088732,"teacher_disagreement_score":0.89336,"about_ca_system_score_codex":0.000115386676,"about_ca_system_score_gemma":0.000023929562,"threshold_uncertainty_score":0.9999443},"labels":[],"label_agreement":null},{"id":"W4322500097","doi":"10.36713/epra12492","title":"IMPORTANCE OF DATA INTEGRITY IN PHARMACEUTICAL INDUSTRY","year":2023,"lang":"en","type":"article","venue":"EPRA International Journal of Economics Business and Management Studies","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data integrity; Metadata; Scientific integrity; Business; Computer science; Data science; Data retention; Personal Integrity; Computer security; Risk analysis (engineering); Engineering; World Wide Web","score_opus":0.532101745288129,"score_gpt":0.5177898149369912,"score_spread":0.01431193035113787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322500097","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":[0.9665669,0.00059365213,0.0009886917,0.027530797,0.0017648363,0.0001491595,0.00011696551,0.0000076015776,0.0022813578],"genre_scores_gemma":[0.9650613,0.031944152,0.0014770529,0.0007659271,0.00017122886,0.0000042156817,0.000023190087,0.000006858197,0.0005460867],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981557,0.00006345324,0.0010536786,0.00026337197,0.00034652566,0.0001172341],"domain_scores_gemma":[0.99816054,0.00043647166,0.00062752847,0.00032184293,0.00041736182,0.000036270012],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006303918,0.00009324024,0.00032710118,0.00065001345,0.000030637046,0.000103887854,0.0014317685,0.00003375345,0.000040607083],"category_scores_gemma":[0.0011269937,0.000073285475,0.000036212175,0.00040271482,0.00016638423,0.0010953567,0.0023964422,0.00019171812,0.000011694548],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003848492,0.00042170633,0.17764783,0.00019069487,0.0022888016,0.00039750745,0.0007716809,0.002765462,0.0000068825625,0.24241075,0.10247164,0.4702422],"study_design_scores_gemma":[0.001677322,0.000031440562,0.5745782,0.0002447204,0.00008584563,0.000019230265,0.012727473,0.0036808827,0.000018946712,0.10270542,0.30399173,0.00023875384],"about_ca_topic_score_codex":0.00001480159,"about_ca_topic_score_gemma":0.00012928032,"teacher_disagreement_score":0.47000346,"about_ca_system_score_codex":0.000045964556,"about_ca_system_score_gemma":0.000023892811,"threshold_uncertainty_score":0.2988495},"labels":[],"label_agreement":null},{"id":"W4327523276","doi":"10.2139/ssrn.4385455","title":"Next-Generation Data Governance","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute on Governance","funders":"","keywords":"Corporate governance; Business; Accounting; Finance","score_opus":0.3451412591577748,"score_gpt":0.42382953442411975,"score_spread":0.07868827526634492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327523276","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":[0.38575172,0.010686893,0.42355976,0.133638,0.010235811,0.0010257533,0.00063084136,0.0006643644,0.033806883],"genre_scores_gemma":[0.9509315,0.010465047,0.00018781864,0.0006934464,0.0010576418,0.0000032101207,0.00017128783,0.000014748051,0.036475327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962084,0.00021779121,0.00046963952,0.00040421096,0.001348652,0.0013512601],"domain_scores_gemma":[0.9983289,0.0001822066,0.00025538937,0.0010789734,0.00008831687,0.00006620264],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01927831,0.00009191984,0.00013798969,0.00011872251,0.00029976785,0.0006349341,0.0024290986,0.0000349085,0.00018083103],"category_scores_gemma":[0.0019093789,0.000069622714,0.000051487958,0.000879641,0.000033357916,0.0017209214,0.0006014649,0.0006512613,0.002662143],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008394686,0.000018908602,0.0001160731,7.4406825e-7,0.000033485376,0.0000055747405,0.00005320871,0.000100186284,0.00026228643,0.4800562,0.18533401,0.33401093],"study_design_scores_gemma":[0.00023986628,0.00006190972,0.00086176867,0.000003755821,0.000011277107,0.000042776846,0.001656773,0.009596502,0.000023775294,0.43889517,0.548491,0.00011543069],"about_ca_topic_score_codex":0.000053177147,"about_ca_topic_score_gemma":0.0024704782,"teacher_disagreement_score":0.56517977,"about_ca_system_score_codex":0.00022888908,"about_ca_system_score_gemma":0.0007744519,"threshold_uncertainty_score":0.9981144},"labels":[],"label_agreement":null},{"id":"W4366549947","doi":"10.1145/3544548.3580868","title":"Governor: Turning Open Government Data Portals into Interactive Databases","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"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","keywords":"Upload; Governor; Computer science; World Wide Web; Open data; Government (linguistics); Database; TRACE (psycholinguistics); Engineering","score_opus":0.5390147190723072,"score_gpt":0.5428906721109037,"score_spread":0.003875953038596447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366549947","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032580663,0.00007834277,0.06965495,0.029425282,0.0029222213,0.0019432658,0.010644545,0.0005180056,0.85223275],"genre_scores_gemma":[0.7185138,0.0002402936,0.014228222,0.008730786,0.00027702568,0.0000849451,0.0049193427,0.000045918918,0.25295967],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995469,0.00023397879,0.0006709461,0.0010521286,0.0022923432,0.000281616],"domain_scores_gemma":[0.9941429,0.0018456948,0.00030596138,0.0035153427,0.000059743357,0.00013037624],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.00858006,0.0001483179,0.0002793194,0.00007539764,0.00019520843,0.0012767701,0.0066118613,0.000020497744,0.0040587704],"category_scores_gemma":[0.005370876,0.00010555164,0.000039677376,0.0008304591,0.000059471455,0.004570723,0.024047539,0.00011411736,0.007458485],"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":[0.000031295218,0.00005821013,0.00066002435,0.000004398725,0.000045460758,0.000037151414,0.00031816657,0.00003132007,0.00009679126,0.016022023,0.8722847,0.110410444],"study_design_scores_gemma":[0.00020132565,0.000024081972,0.0022673274,0.000020553633,0.000013366224,0.0000013755181,0.014506913,0.0040796204,0.0002589432,0.004868835,0.9735925,0.00016515086],"about_ca_topic_score_codex":0.0020780715,"about_ca_topic_score_gemma":0.0037022254,"teacher_disagreement_score":0.6859331,"about_ca_system_score_codex":0.000083251456,"about_ca_system_score_gemma":0.000047764865,"threshold_uncertainty_score":0.99976},"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":"W4366959045","doi":"10.1109/wi-iat55865.2022.00014","title":"SMAT: String Matching in Action Theory","year":2022,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Lakehead University","funders":"","keywords":"String metric; String searching algorithm; Computer science; Heuristics; Edit distance; Approximate string matching; Commentz-Walter algorithm; Matching (statistics); Levenshtein distance; Formalism (music); String (physics); Pattern matching; Artificial intelligence; Theoretical computer science; Mathematics; Theoretical physics; Physics","score_opus":0.33880310067949526,"score_gpt":0.46709783886259926,"score_spread":0.128294738183104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366959045","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":[0.77617544,0.000020221667,0.10708802,0.002087331,0.00078260526,0.00017640855,0.00001509031,0.000074224,0.11358065],"genre_scores_gemma":[0.9825419,0.0000018743468,0.00035631593,0.0007817337,0.000012508147,0.000012047144,0.000003547816,0.0000021242265,0.016287908],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99843675,0.00038588975,0.00023385976,0.00018985348,0.0006541437,0.000099527795],"domain_scores_gemma":[0.9991779,0.00046958242,0.00005252251,0.00027405604,0.000007915068,0.000018045146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007931492,0.000034248827,0.0000664912,0.00019238748,0.00015158847,0.00011657545,0.00042891758,0.0000067011483,0.00573918],"category_scores_gemma":[0.00022097588,0.000027484486,0.000023710705,0.00039935482,0.000008876453,0.0003103919,0.00060778,0.00009994431,0.00019750344],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019132704,0.000040802795,0.0003642807,0.0000017412473,0.000002611838,0.000005838767,0.00092751626,0.002369441,0.000094589945,0.8046829,0.005858328,0.18563282],"study_design_scores_gemma":[0.00015820372,0.000016063708,0.005438639,0.0000015013011,0.0000013876394,0.0000016054917,0.045045182,0.00050389784,0.00010041164,0.74286175,0.205801,0.000070356684],"about_ca_topic_score_codex":0.00018672284,"about_ca_topic_score_gemma":0.00022591239,"teacher_disagreement_score":0.2063665,"about_ca_system_score_codex":0.000044288,"about_ca_system_score_gemma":0.000009743066,"threshold_uncertainty_score":0.9951697},"labels":[],"label_agreement":null},{"id":"W4367551721","doi":"10.1155/2023/8707205","title":"Mapping Relationship Discovery of Multidimensional Architectures in Autonomous Transportation System Based on Text-Matching Model","year":2023,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Innovation-Driven Project of Central South University; National Key Research and Development Program of China; Central South University","keywords":"Computer science; Matching (statistics); Data mining; Artificial intelligence; Similarity (geometry); Masking (illustration); Word (group theory); Similitude; Information retrieval; Natural language processing; Image (mathematics)","score_opus":0.07180389518918914,"score_gpt":0.3482732900291737,"score_spread":0.27646939483998456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367551721","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":[0.72785145,0.00001342671,0.27130234,0.0003077124,0.00019138634,0.00016035899,0.000110407935,0.000019946476,0.00004295052],"genre_scores_gemma":[0.9823627,0.000004699512,0.017360518,0.000059165202,0.000022136197,0.0000068250206,0.000120994155,0.000012144784,0.000050828963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99637324,0.00014768561,0.0017047671,0.00025107936,0.0013561392,0.00016710849],"domain_scores_gemma":[0.9972271,0.0012351322,0.0010650684,0.00022373295,0.00019392169,0.000055049717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026675158,0.00013801445,0.000366558,0.0012588416,0.0000787278,0.000033590826,0.0002545137,0.0000592475,0.000004246945],"category_scores_gemma":[0.00026890924,0.00011265084,0.00018920448,0.0010522949,0.00003835335,0.0007590353,0.0000022998486,0.00024108459,0.000005499183],"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":[0.00032710645,0.000072524366,0.0044188937,0.000091011854,0.000010306967,0.000033345714,0.00449407,0.97878885,0.0018139831,0.006142263,0.000022389922,0.0037852754],"study_design_scores_gemma":[0.0015404318,0.00011481363,0.8595645,0.0006014557,0.00002376534,0.0000010926715,0.008096159,0.112636186,0.0005965911,0.016614262,0.000060570088,0.00015021779],"about_ca_topic_score_codex":0.00002173831,"about_ca_topic_score_gemma":0.0002741485,"teacher_disagreement_score":0.86615264,"about_ca_system_score_codex":0.000080443635,"about_ca_system_score_gemma":0.00011775728,"threshold_uncertainty_score":0.4593768},"labels":[],"label_agreement":null},{"id":"W4368249689","doi":"10.1007/978-3-031-21147-8_24","title":"Sailing the Data Sea to Advance Research on the Sustainable Development Goals","year":2023,"lang":"en","type":"book-chapter","venue":"Philosophical studies series","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Western University; Université de Montréal","funders":"","keywords":"Metadata; Prosperity; Data science; Sustainable development; Sustainability; Computer science; Open data; Work (physics); World Wide Web; Political science; Engineering","score_opus":0.7781077524468246,"score_gpt":0.5436658511501645,"score_spread":0.2344419012966601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4368249689","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005400101,0.002126698,0.000088140725,0.649965,0.0006824563,0.0018940867,0.00040079828,0.00013497732,0.34465384],"genre_scores_gemma":[0.0038048641,0.0032847233,0.00033357454,0.007159204,0.0011105821,0.00034113685,0.00011238868,0.000081679056,0.98377186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99097455,0.00050821,0.0010875061,0.0016050312,0.0049519157,0.0008727898],"domain_scores_gemma":[0.98117065,0.012712761,0.00025013086,0.0044293287,0.00128455,0.00015259099],"candidate_categories":["metaresearch","sts","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0243149,0.00045698247,0.00073662505,0.00032465573,0.0032004504,0.00074632536,0.0069826604,0.00014205909,0.00022061885],"category_scores_gemma":[0.021449957,0.00021890132,0.000103862316,0.00071037613,0.0013706638,0.0004334374,0.02119229,0.0011202086,0.0057761753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091371054,0.000014693161,0.0000014587679,0.000050634935,0.00020237241,0.00006517549,0.00091617357,0.000027081951,1.15839015e-7,0.7834297,0.20904626,0.0061549577],"study_design_scores_gemma":[0.000031163738,0.00006338411,0.000019785593,0.000097966215,0.000011191754,5.371861e-7,0.0060863164,0.0000016781061,0.0000034577708,0.4826039,0.51093024,0.00015039866],"about_ca_topic_score_codex":0.000025806567,"about_ca_topic_score_gemma":0.00041646208,"teacher_disagreement_score":0.6428058,"about_ca_system_score_codex":0.00025234476,"about_ca_system_score_gemma":0.000163816,"threshold_uncertainty_score":0.99839},"labels":[],"label_agreement":null},{"id":"W4376869324","doi":"10.18280/isi.280207","title":"A Schema Integration Approach for Big Data Analysis","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Schema matching; NoSQL; Computer science; Data integration; Star schema; Schema (genetic algorithms); Conceptual schema; Database schema; Information schema; Schema evolution; Data mining; Schema migration; Information retrieval; Data science; Big data; Semi-structured model; Database design","score_opus":0.29287249228606804,"score_gpt":0.39120524986390676,"score_spread":0.09833275757783871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376869324","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":[0.0067952843,0.000012468573,0.9808017,0.00018593472,0.00039528697,0.0005057173,0.0007035131,0.00019778346,0.010402335],"genre_scores_gemma":[0.94927716,0.000023078432,0.02656776,0.00042866866,0.00021661475,0.00021932262,0.022050949,0.000009537615,0.0012069055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739206,0.00011164796,0.0010068772,0.0003226843,0.00090885983,0.00025789771],"domain_scores_gemma":[0.99720705,0.0004242371,0.00043803814,0.0014561476,0.00040740837,0.000067138506],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007989397,0.00013124921,0.0002850836,0.0014137616,0.00031725282,0.001163621,0.0013115095,0.00007723133,0.000028376186],"category_scores_gemma":[0.0059719253,0.00010275815,0.00012409849,0.0048806183,0.000088535715,0.005475838,0.00054560654,0.00006520182,0.00047342174],"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":[0.000047241163,0.00003060704,0.00051982387,0.00011369095,0.0002672204,4.0170704e-7,0.003941567,0.0031666546,0.000024134659,0.019242618,0.093536526,0.8791095],"study_design_scores_gemma":[0.00040381437,0.00004912189,0.006166896,0.000018195282,0.00021936515,0.0000016330739,0.01634694,0.7699723,0.0001500407,0.030396411,0.17600803,0.00026721097],"about_ca_topic_score_codex":0.000075608565,"about_ca_topic_score_gemma":0.00007084526,"teacher_disagreement_score":0.95423394,"about_ca_system_score_codex":0.00007566305,"about_ca_system_score_gemma":0.000051611285,"threshold_uncertainty_score":0.9998733},"labels":[],"label_agreement":null},{"id":"W4378349663","doi":"10.1093/eurpub/ckab164.515","title":"Country experiences with data linkage initiatives","year":2021,"lang":"en","type":"article","venue":"European Journal of Public Health","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Microdata (statistics); Identifier; Government (linguistics); Record linkage; Health care; Linkage (software); Medicine; Census; Environmental health; Political science; Computer science; Population","score_opus":0.5558074311327259,"score_gpt":0.4778533447731891,"score_spread":0.07795408635953682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378349663","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":[0.10959018,0.0037638145,0.6542601,0.10522545,0.0021813784,0.00021164725,0.00031270678,0.00005384189,0.124400884],"genre_scores_gemma":[0.9792609,0.00045181054,0.0092583215,0.009515479,0.0005153916,5.126229e-7,0.0000622919,0.000017290806,0.0009179629],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98677355,0.009072372,0.0013457363,0.00040550056,0.0020335813,0.00036928337],"domain_scores_gemma":[0.99603343,0.0005796661,0.0011341115,0.0011519128,0.0006411749,0.00045973258],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05949043,0.000107187785,0.00032554625,0.0002085627,0.00021482928,0.00094399427,0.0023778395,0.000010021541,0.0007356776],"category_scores_gemma":[0.006125748,0.00006666027,0.000037479578,0.00092047337,0.00016598891,0.0026871762,0.00073206064,0.00027185216,0.00011552249],"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":[0.000019360426,0.0005112788,0.0015191446,0.000043946224,0.00013101533,0.0022627437,0.05842279,0.00001070959,0.000006462581,0.008268781,0.2779563,0.65084743],"study_design_scores_gemma":[0.00042136412,0.0003075403,0.0136020705,0.000051538507,0.0000035182466,0.00016045115,0.14335479,0.000034080495,0.0000049910864,0.000095924726,0.84187496,0.0000887772],"about_ca_topic_score_codex":0.0000055353844,"about_ca_topic_score_gemma":0.000034585024,"teacher_disagreement_score":0.86967075,"about_ca_system_score_codex":0.000035516543,"about_ca_system_score_gemma":0.0013705785,"threshold_uncertainty_score":0.9684525},"labels":[],"label_agreement":null},{"id":"W4378782364","doi":"10.2196/44567","title":"Migrating a Well-Established Longitudinal Cohort Database From Oracle SQL to Research Electronic Data Entry (REDCap): Data Management Research and Design Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Electronic data capture; Computer science; Data quality; Database; Data management; Electronic data; SQL; Information retrieval; Data collection; Data mining; Metric (unit); Engineering; Statistics","score_opus":0.6685705021262548,"score_gpt":0.6015098240105905,"score_spread":0.0670606781156643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378782364","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":[0.92849725,0.00075756066,0.015769009,0.010146409,0.0004821965,0.021789622,0.009402269,0.00038211484,0.012773585],"genre_scores_gemma":[0.98003477,0.0011060896,0.0026666836,0.000078513964,0.00028832862,0.0016356887,0.0069051897,0.000077018776,0.0072077303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.95498073,0.014889943,0.001760678,0.0045279865,0.019799436,0.0040412275],"domain_scores_gemma":[0.96511173,0.018068343,0.00018760358,0.013445164,0.0023365365,0.0008506417],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.24813664,0.00039695177,0.000694721,0.00481932,0.0030640785,0.004907969,0.016511131,0.00012776736,0.000973666],"category_scores_gemma":[0.011437886,0.00032464982,0.000040549494,0.016779585,0.0009773123,0.0067337817,0.06904036,0.0028831507,0.008732522],"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":[0.0007968618,0.0013992338,0.007731598,0.0000985278,0.00031904213,0.0003686462,0.00850148,0.00001749756,0.00007894857,0.0038108737,0.94685006,0.030027224],"study_design_scores_gemma":[0.0031217579,0.0034604685,0.1329654,0.0004138916,0.00004985702,0.000007947308,0.37486786,0.040635232,0.0002191796,0.035084732,0.40825948,0.00091422],"about_ca_topic_score_codex":0.00540543,"about_ca_topic_score_gemma":0.0047067106,"teacher_disagreement_score":0.5385906,"about_ca_system_score_codex":0.0004967987,"about_ca_system_score_gemma":0.0005623385,"threshold_uncertainty_score":0.99993956},"labels":[],"label_agreement":null},{"id":"W4381572165","doi":"10.2196/44331","title":"Optimizing Patient Record Linkage in a Master Patient Index Using Machine Learning: Algorithm Development and Validation","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","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":true,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute; University of Toronto","funders":"Strong; Bill and Melinda Gates Foundation; United States Agency for International Development","keywords":"Computer science; Matching (statistics); Machine learning; Population; Software; Linkage (software); Record linkage; Artificial intelligence; Interface (matter); Bayesian optimization; Set (abstract data type); Data mining; Programming language; Medicine; Operating system","score_opus":0.33027613605812656,"score_gpt":0.4740721920281339,"score_spread":0.14379605597000733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381572165","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":[0.980693,0.00003715136,0.016840404,0.0003573755,0.00013990328,0.0007716509,0.000027898483,0.00004750842,0.0010851074],"genre_scores_gemma":[0.98828477,0.000053179316,0.010666949,0.00007102556,0.000020285926,0.00017443878,0.00011516333,0.000017638777,0.0005965814],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945183,0.0012277804,0.0008630813,0.00045504305,0.0023625926,0.00057319447],"domain_scores_gemma":[0.99822927,0.00081714743,0.00020236138,0.00030513838,0.00031173372,0.00013436883],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008347609,0.00014754487,0.0002379529,0.0016205902,0.00044881259,0.00051576016,0.0003567064,0.00007311092,0.000119233875],"category_scores_gemma":[0.00065608183,0.000116562944,0.000035097688,0.002303352,0.00010334751,0.0010434913,0.0015718079,0.000556029,0.00036396418],"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":[0.000047896905,0.000112314,0.0038730418,0.000037214937,0.000015146816,0.000029804063,0.068583064,0.0008101581,0.000037862334,0.00010436894,0.00096469285,0.92538446],"study_design_scores_gemma":[0.0011638885,0.0006540258,0.016525282,0.00025988955,0.0000026590503,0.0000050877647,0.06933504,0.6874129,0.0020671524,0.0034374306,0.2186852,0.00045145198],"about_ca_topic_score_codex":0.00014568814,"about_ca_topic_score_gemma":0.00007120748,"teacher_disagreement_score":0.92493296,"about_ca_system_score_codex":0.00022955335,"about_ca_system_score_gemma":0.000082865176,"threshold_uncertainty_score":0.4973487},"labels":[],"label_agreement":null},{"id":"W4381938374","doi":"10.2196/44310","title":"Normal Workflow and Key Strategies for Data Cleaning Toward Real-World Data: Viewpoint","year":2023,"lang":"en","type":"article","venue":"Interactive Journal of Medical Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workflow; Data quality; Computer science; Data science; Data governance; Data mining; Process (computing); Data virtualization; Data set; Data management; Key (lock); Quality (philosophy); Data cleansing; Database; Engineering; Computer security; Artificial intelligence","score_opus":0.7111703779494515,"score_gpt":0.6382519355459901,"score_spread":0.07291844240346135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381938374","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":[0.14531769,0.0011708128,0.2725326,0.5429013,0.0059495657,0.0018218684,0.0018669675,0.00010878448,0.02833042],"genre_scores_gemma":[0.97518486,0.008130921,0.008486907,0.001670389,0.0027234862,0.000019169314,0.00032851487,0.000045676043,0.003410055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888952,0.0012849511,0.0011568926,0.00057255157,0.0075647673,0.00052568474],"domain_scores_gemma":[0.9709289,0.025035597,0.0005214918,0.0016097518,0.001287718,0.00061654864],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09282124,0.000115533454,0.000444045,0.0010708766,0.00020852314,0.0012388017,0.0066165207,0.000060374772,0.00057502085],"category_scores_gemma":[0.06404767,0.000075879645,0.00006176149,0.0014311569,0.0005088947,0.0035466119,0.0075104134,0.0012827384,0.00015469661],"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":[0.00052087667,0.00006880919,0.00013233254,0.000031308806,0.00009211714,0.00022840012,0.00094768853,0.0000053628423,0.000016095879,0.007600079,0.48833928,0.5020177],"study_design_scores_gemma":[0.00086030917,0.0004625425,0.004517656,0.00051772175,0.000021245556,0.000036731934,0.036267255,0.031763066,0.000026545666,0.05847815,0.866923,0.00012580628],"about_ca_topic_score_codex":0.00045531036,"about_ca_topic_score_gemma":0.0021486378,"teacher_disagreement_score":0.8298672,"about_ca_system_score_codex":0.00006639009,"about_ca_system_score_gemma":0.00070226233,"threshold_uncertainty_score":0.999798},"labels":[],"label_agreement":null},{"id":"W4383175845","doi":"10.5281/zenodo.8107872","title":"Data Remediation as Collaborative Process","year":2023,"lang":"en","type":"paratext","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Process (computing); Computer science; Environmental remediation; Process management; Process engineering; Engineering; Operating system; Contamination","score_opus":0.28152297107503876,"score_gpt":0.4339006903726039,"score_spread":0.15237771929756516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383175845","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00012849698,0.00020242902,0.005350461,0.0048299637,0.0018333775,0.0013983608,0.02851584,0.0007841493,0.9569569],"genre_scores_gemma":[0.005665011,0.00198518,0.00028008714,0.001155133,0.0017049697,4.1379133e-7,0.3163085,0.0043226937,0.668578],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99273974,0.0014781448,0.0008759447,0.0015927509,0.0028185605,0.00049485115],"domain_scores_gemma":[0.9930538,0.0003001615,0.0006827511,0.0030210589,0.0026919157,0.0002503087],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0077199615,0.00029021243,0.00042177507,0.0008544899,0.0025299748,0.004965253,0.009319845,0.00020238633,0.09902575],"category_scores_gemma":[0.017520947,0.00027063905,0.00005672019,0.0036328179,0.0002864925,0.0012081282,0.00900859,0.00053298724,0.6797977],"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":[0.000048215068,0.00006963906,4.110912e-8,0.00007425877,0.00006073879,0.000011927744,0.00093851495,0.000083793726,0.000019523612,0.0017830291,0.91912633,0.077784],"study_design_scores_gemma":[0.0002990922,0.00014697656,0.00002036561,0.000059842787,0.000025873738,0.000009618076,0.0029247457,0.00035218615,0.00003074896,0.002132163,0.99370223,0.00029614303],"about_ca_topic_score_codex":0.000025818988,"about_ca_topic_score_gemma":0.0000043023915,"teacher_disagreement_score":0.580772,"about_ca_system_score_codex":0.00016482653,"about_ca_system_score_gemma":0.000041860672,"threshold_uncertainty_score":0.9999746},"labels":[],"label_agreement":null},{"id":"W4384524480","doi":"10.51964/hlcs15759","title":"Introduction: Content, Design and Structure of Major Databases with Historical Longitudinal Population Data","year":2023,"lang":"en","type":"article","venue":"Historical Life Course Studies","topic":"Data Quality and Management","field":"Decision Sciences","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":"Université du Québec à Chicoutimi","funders":"","keywords":"Linkage (software); Data science; Crowdsourcing; Computer science; Database; Population; Information retrieval; World Wide Web; Sociology","score_opus":0.5645442949893535,"score_gpt":0.43977901725878454,"score_spread":0.124765277730569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384524480","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":[0.14309004,0.10272695,0.41979244,0.29162544,0.032047007,0.004724176,0.003966508,0.0014828446,0.0005445943],"genre_scores_gemma":[0.9538645,0.0015881936,0.023465931,0.00037942905,0.0028846925,0.00003370182,0.00072747207,0.000046980596,0.017009072],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99668723,0.00027189642,0.0006640106,0.00085465505,0.0012941733,0.00022800342],"domain_scores_gemma":[0.9968247,0.0010470989,0.00035479869,0.0012644615,0.00037773792,0.0001312442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017827847,0.00018743261,0.0005943865,0.0002239315,0.00029301693,0.00004383586,0.00060072757,0.00003580963,0.00006810984],"category_scores_gemma":[0.005555424,0.00012504263,0.00003340344,0.0009571941,0.00017917785,0.00063365017,0.0008680952,0.00012621353,0.00002586792],"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":[0.00017892868,0.000078365265,0.011812918,0.000042625554,0.00018420146,0.00001623574,0.00021161043,0.000086022774,0.000027931117,0.0058392477,0.9780908,0.003431077],"study_design_scores_gemma":[0.00074859196,0.00035478905,0.079314515,0.000034233253,0.00045323445,0.000011762894,0.002404233,0.00048319416,0.000013069873,0.0023814756,0.91343904,0.0003618436],"about_ca_topic_score_codex":0.00048803582,"about_ca_topic_score_gemma":0.00031951684,"teacher_disagreement_score":0.8107745,"about_ca_system_score_codex":0.0003646422,"about_ca_system_score_gemma":0.000049233116,"threshold_uncertainty_score":0.66507626},"labels":[],"label_agreement":null},{"id":"W4384525924","doi":"10.3390/s23146443","title":"Empowering Patient Similarity Networks through Innovative Data-Quality-Aware Federated Profiling","year":2023,"lang":"en","type":"article","venue":"Sensors","topic":"Data Quality and Management","field":"Decision Sciences","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":"Humber Polytechnic","funders":"","keywords":"Computer science; Data mining; Data quality; Quality assurance; Profiling (computer programming); Outlier; Classifier (UML); Data integrity; Metadata; Machine learning; Artificial intelligence; Database; Engineering","score_opus":0.36624541897583285,"score_gpt":0.49565355172024805,"score_spread":0.1294081327444152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384525924","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":[0.93551755,0.000043124746,0.04274582,0.0047523696,0.0021620875,0.0009981672,0.0011157618,0.00078476046,0.011880353],"genre_scores_gemma":[0.99317575,0.000035297155,0.0016711832,0.001880881,0.00014517117,0.000015324098,0.0016597576,0.000026641846,0.0013900087],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951067,0.00070637517,0.0011186849,0.001057679,0.0014761306,0.0005344088],"domain_scores_gemma":[0.99611425,0.0012213092,0.00038446853,0.0016710428,0.00052301073,0.00008594356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005883192,0.00022663931,0.00040014114,0.00018515323,0.0004995663,0.0006167264,0.0011390136,0.00011014004,0.00016833162],"category_scores_gemma":[0.004023704,0.0001841444,0.00005596383,0.0035972213,0.00012502406,0.000830128,0.0020881365,0.00033052458,0.00077616685],"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":[0.0003948204,0.00051336107,0.009585452,0.0001479829,0.00052200165,0.0005078879,0.015122612,0.1534747,0.0003493101,0.0475928,0.57795876,0.1938303],"study_design_scores_gemma":[0.0010875403,0.00019638836,0.011852934,0.0001114539,0.00003414716,0.0000054696397,0.07800837,0.36925006,0.0019278362,0.016706357,0.51947045,0.0013489989],"about_ca_topic_score_codex":0.00023605445,"about_ca_topic_score_gemma":0.00013805841,"teacher_disagreement_score":0.21577537,"about_ca_system_score_codex":0.000045997513,"about_ca_system_score_gemma":0.00005711291,"threshold_uncertainty_score":0.9976313},"labels":[],"label_agreement":null},{"id":"W4385269654","doi":"10.1109/wimob58348.2023.10187831","title":"UbiSecE: UbiLab’s Secure Cloud Environment for Public Health Research in Microsoft Azure","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Waterloo","funders":"","keywords":"Cloud computing; Corporate governance; Computer security; Public health; Computer science; Business; Medicine","score_opus":0.8048605200246887,"score_gpt":0.5722741108240867,"score_spread":0.23258640920060192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385269654","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":[0.09810885,0.000879588,0.04592863,0.8232243,0.0023137478,0.006403587,0.0012493982,0.0004894357,0.02140248],"genre_scores_gemma":[0.75786144,0.0016393389,0.0062755444,0.015424671,0.0006678184,0.00093056465,0.00077039754,0.000080094476,0.21635015],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943591,0.00084698864,0.0007857235,0.0008500558,0.0021475875,0.0010105851],"domain_scores_gemma":[0.9962383,0.00219219,0.0001091601,0.0010861773,0.000101586964,0.0002725847],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.04149767,0.00012805186,0.00028509897,0.00087543746,0.00033206822,0.0005345075,0.0013672232,0.00008412721,0.0010688554],"category_scores_gemma":[0.0017679407,0.000097104974,0.000086543485,0.0020920886,0.00015799174,0.0003720261,0.0010411653,0.00025759978,0.0052327076],"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":[0.00001144708,0.00012562485,0.00055592856,0.000040227205,0.0000071740114,0.0000044260396,0.0012538271,0.000050493534,0.000031495907,0.04581847,0.89235044,0.059750468],"study_design_scores_gemma":[0.00042398722,0.00011426608,0.0041725026,0.00001027006,6.117426e-7,5.0755347e-7,0.0063028303,0.00043756835,0.000023436234,0.039171863,0.94923663,0.00010550859],"about_ca_topic_score_codex":0.00018353217,"about_ca_topic_score_gemma":0.0010418992,"teacher_disagreement_score":0.80779964,"about_ca_system_score_codex":0.00020286892,"about_ca_system_score_gemma":0.00017590456,"threshold_uncertainty_score":0.9998443},"labels":[],"label_agreement":null},{"id":"W4385571965","doi":"10.18653/v1/2023.findings-acl.604","title":"AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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":"Metadata; Computer science; Field (mathematics); Metadata repository; Table (database); Information retrieval; Dimension (graph theory); Data element; Data type; Data mining; World Wide Web","score_opus":0.6644636814897413,"score_gpt":0.5129623906594967,"score_spread":0.15150129083024466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385571965","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008263984,0.00033391555,0.7549451,0.0022739926,0.00035730487,0.000340826,0.23867527,0.00011574204,0.0021314318],"genre_scores_gemma":[0.23142852,0.00021001716,0.05582472,0.0032801875,0.000086873086,0.000033615983,0.63373566,0.000047452944,0.07535296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959547,0.00030765793,0.000991989,0.0011137692,0.0012873509,0.00034456988],"domain_scores_gemma":[0.99262667,0.0026213254,0.00029721312,0.004199003,0.000109612076,0.00014615506],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008955189,0.00017210336,0.00057756645,0.00087424583,0.00018588617,0.00048916246,0.0035344416,0.0000667496,0.00443495],"category_scores_gemma":[0.003754933,0.00012639635,0.00010403168,0.0062500653,0.000094306735,0.0024871067,0.004888348,0.0001117152,0.00058362423],"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":[0.00001599627,0.00013378092,0.00037316943,0.000010687984,0.0006778303,0.0000055183455,0.000053494703,0.00014862457,0.0001235411,0.0042636176,0.99295396,0.0012397773],"study_design_scores_gemma":[0.0006508278,0.0000461522,0.000473937,0.000011230012,0.00086057873,5.35326e-7,0.0038030753,0.23137292,0.00032274463,0.0031846806,0.7589609,0.00031241612],"about_ca_topic_score_codex":0.0014047677,"about_ca_topic_score_gemma":0.0047516017,"teacher_disagreement_score":0.6991204,"about_ca_system_score_codex":0.000032747263,"about_ca_system_score_gemma":0.00006908165,"threshold_uncertainty_score":0.99647516},"labels":[],"label_agreement":null},{"id":"W4385796912","doi":"10.5281/zenodo.8213503","title":"ARDC survey on cloud services usage in research","year":2023,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cloud computing; Computer science; Survey research; Data science; World Wide Web; Business; Operating system","score_opus":0.6484422039557307,"score_gpt":0.49571621073802463,"score_spread":0.15272599321770608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385796912","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073173107,0.00017023238,0.00027835966,0.0018894374,0.0021238816,0.0018172099,0.007388545,0.0011047014,0.97791034],"genre_scores_gemma":[0.33345047,0.010042026,0.00019947861,0.0014739874,0.0043378645,0.0000015490916,0.105215296,0.015229725,0.5300496],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9798813,0.0075660893,0.0013233044,0.0017920182,0.008415945,0.0010213838],"domain_scores_gemma":[0.99058765,0.0015675337,0.00047780917,0.0027091056,0.0043218983,0.0003360309],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.08747341,0.0003484381,0.0006373144,0.0029683027,0.0023918936,0.004984128,0.0072397124,0.00031115033,0.019758867],"category_scores_gemma":[0.031165786,0.00032095276,0.00013890692,0.0055637937,0.00036376473,0.00044465848,0.009202058,0.0016269812,0.14083916],"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":[0.000096612115,0.00018287104,0.000032365562,0.00015186,0.000041787098,0.00011024585,0.0006874808,0.000054261036,0.00001105774,0.0010990734,0.9055384,0.09199401],"study_design_scores_gemma":[0.0003049854,0.00024739525,0.01837009,0.00022968039,0.0000072064304,0.000012793085,0.0011294377,0.00008338415,0.000009348085,0.0018699002,0.9774259,0.0003098819],"about_ca_topic_score_codex":0.002973098,"about_ca_topic_score_gemma":0.0003992835,"teacher_disagreement_score":0.44786072,"about_ca_system_score_codex":0.0007768034,"about_ca_system_score_gemma":0.00005726265,"threshold_uncertainty_score":0.99992424},"labels":[],"label_agreement":null},{"id":"W4385816875","doi":"10.1007/978-3-031-24498-8","title":"Data Governance and Policy in Africa","year":2023,"lang":"en","type":"book","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Consortium pour la recherche économique en Afrique; University of Cape Town; National Research Foundation; Göteborgs Universitet; European Commission; Department of Science and Technology, Ministry of Science and Technology, India; University of Oxford; Japan International Cooperation Agency; International Development Research Centre; University of Fort Hare; African Union; International Fine Particle Research Institute; Government of the Republic of Kenya","keywords":"Corporate governance; Political science; Public administration; Data governance; Business; Economics; Economy; Finance; Data quality","score_opus":0.4414745369931295,"score_gpt":0.46369257914321055,"score_spread":0.022218042150081052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385816875","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.081409e-7,0.00027078175,0.0002961169,0.0053814887,0.00018958143,0.00014776536,0.002943341,0.000038592098,0.99073154],"genre_scores_gemma":[0.000020885656,0.00094395917,0.0002321198,0.0006772367,0.00014723254,0.000003395532,0.00026182234,0.000011445486,0.9977019],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972544,0.00006874591,0.0004969102,0.00081611756,0.0011543519,0.00020948969],"domain_scores_gemma":[0.99638623,0.0010064238,0.00018746861,0.002335269,0.000023135082,0.00006150017],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00397314,0.00013262672,0.00029939087,0.00026798414,0.0000326227,0.00030996546,0.0027550608,0.0000980912,0.00046631708],"category_scores_gemma":[0.0034167084,0.00009816215,0.000022474684,0.0004446978,0.00008831475,0.00040965286,0.0050430265,0.00015525782,0.003164059],"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":[0.000001652414,0.000004637551,0.0000033223419,0.000007639299,0.0000041598537,0.000012783991,0.000039193867,3.5658059e-7,2.8685271e-8,0.25683337,0.69915766,0.043935183],"study_design_scores_gemma":[0.00006668515,0.000005723375,0.000585346,0.000024759347,0.0000028023653,3.37389e-7,0.000058892158,0.000087673645,3.4336406e-8,0.2461474,0.7529311,0.000089255394],"about_ca_topic_score_codex":0.0003557021,"about_ca_topic_score_gemma":0.0051190336,"teacher_disagreement_score":0.05377343,"about_ca_system_score_codex":0.00006430735,"about_ca_system_score_gemma":0.00023610219,"threshold_uncertainty_score":0.9976121},"labels":[],"label_agreement":null},{"id":"W4386399195","doi":"10.2307/jj.6445824.13","title":"An Overview of the BALSAC Population Database.","year":2023,"lang":"en","type":"book-chapter","venue":"Radboud University Press eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Université de Montréal; Université du Québec à Chicoutimi; McGill University; Université Laval","keywords":"Database; Computer science","score_opus":0.4115540489772465,"score_gpt":0.39047241864154,"score_spread":0.021081630335706536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386399195","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000112837035,0.00016159382,0.0006397366,0.000078922654,0.00091508846,0.00060809153,0.003316896,0.00009734928,0.99406946],"genre_scores_gemma":[0.0011878661,0.00025946528,0.000085300766,0.00007871154,0.0000585426,3.213311e-7,0.00023305492,0.000021547807,0.9980752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708205,0.0002635298,0.0004245531,0.0005839892,0.0014764963,0.00016938639],"domain_scores_gemma":[0.9965769,0.00032459846,0.00061941217,0.0022266842,0.00016169024,0.000090707734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014305259,0.00021324668,0.00040113655,0.00023600998,0.00022473084,0.00012224236,0.0024329491,0.00017487032,0.00010790149],"category_scores_gemma":[0.00010043387,0.00016861498,0.00022065168,0.00004416094,0.00018657534,0.0003067048,0.0014616142,0.00023215773,0.000049316914],"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":[0.00002190797,0.000010322143,0.000008604047,0.0000451699,0.000049342398,0.00001218875,0.000092280556,0.00006646607,0.0000050513527,0.97266084,0.02030194,0.0067258957],"study_design_scores_gemma":[0.00017834282,0.000021539654,0.00061072584,0.00014993537,0.00013046422,6.54967e-7,0.00012174505,0.00023929925,0.000011008276,0.01673079,0.9816099,0.0001956024],"about_ca_topic_score_codex":0.0012448265,"about_ca_topic_score_gemma":0.00027136956,"teacher_disagreement_score":0.96130794,"about_ca_system_score_codex":0.00006304213,"about_ca_system_score_gemma":0.00005086046,"threshold_uncertainty_score":0.6875919},"labels":[],"label_agreement":null},{"id":"W4386399277","doi":"10.2307/jj.6445824.4","title":"Introduction:","year":2023,"lang":"en","type":"book-chapter","venue":"Radboud University Press eBooks","topic":"Data Quality and Management","field":"Decision Sciences","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":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science","score_opus":0.19240006459690023,"score_gpt":0.3137238721674182,"score_spread":0.12132380757051797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386399277","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014646836,0.000031985197,0.0013785692,0.0008110032,0.0015871446,0.0002886513,0.00037676093,0.00025494045,0.9952695],"genre_scores_gemma":[0.00001843264,0.000111612964,0.00010173415,0.00007971091,0.00086327567,4.152431e-7,0.000076420125,0.000029435163,0.998719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969235,0.00010650827,0.0003733153,0.00093453866,0.0014089028,0.000253218],"domain_scores_gemma":[0.99735373,0.00034814718,0.00035192742,0.001565219,0.00023287929,0.00014811769],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012565028,0.00027334067,0.0004292635,0.00046678967,0.00027839674,0.00031798918,0.001691738,0.00026353355,0.00050971715],"category_scores_gemma":[0.0001427696,0.00027683406,0.00022488461,0.000033064945,0.00027755325,0.00020717696,0.0014090046,0.00037469703,0.0017634371],"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":[0.000020403471,0.000003199281,7.0841615e-8,0.000007176769,0.000054905,0.000081687285,0.000044943714,0.0000225158,4.426988e-7,0.5769859,0.41509953,0.0076791975],"study_design_scores_gemma":[0.0002023108,0.000026875336,0.000004375278,0.00001857568,0.000087541186,0.0000032979135,0.00020937876,0.000043922544,0.000004545402,0.018686026,0.98042566,0.000287473],"about_ca_topic_score_codex":0.00010385981,"about_ca_topic_score_gemma":0.000028554341,"teacher_disagreement_score":0.56532615,"about_ca_system_score_codex":0.00010820262,"about_ca_system_score_gemma":0.00006328782,"threshold_uncertainty_score":0.9999684},"labels":[],"label_agreement":null},{"id":"W43864256","doi":"","title":"ptafflist - Utilisation des données du site du Gouvernement du Canada","year":2005,"lang":"fr","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.108488946171131,"score_gpt":0.31258719403150376,"score_spread":0.20409824786037276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W43864256","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":[0.366356,0.0034551162,0.048117317,0.3109998,0.008644962,0.0010702554,0.0009226004,0.00016924672,0.26026472],"genre_scores_gemma":[0.86057657,0.002066172,0.0033538875,0.010123356,0.0011815093,0.000019709352,0.00011309076,0.00001703845,0.12254866],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956073,0.00037709673,0.00093562703,0.0006856578,0.0018321002,0.0005621864],"domain_scores_gemma":[0.9976624,0.0007120129,0.00025351834,0.0007727495,0.00029911025,0.00030015863],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003497172,0.00028229476,0.0003084899,0.00012509245,0.0007010682,0.00079113577,0.0009567585,0.00008377833,0.020629799],"category_scores_gemma":[0.0011852339,0.00024169935,0.00011098758,0.00052493566,0.00038870354,0.0015611168,0.0006491885,0.00011837328,0.0019883213],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018066019,0.00020995206,0.005505807,0.000035234458,0.00003847753,0.000029219922,0.0014154104,0.0005967999,0.000006781823,0.08648851,0.6860567,0.21959905],"study_design_scores_gemma":[0.00046358976,0.000052370757,0.014592168,0.000036583504,0.00005050983,0.000008702217,0.0058034263,0.013049494,0.00014709405,0.002101306,0.9633909,0.00030388715],"about_ca_topic_score_codex":0.83183676,"about_ca_topic_score_gemma":0.9899795,"teacher_disagreement_score":0.49422058,"about_ca_system_score_codex":0.0009917474,"about_ca_system_score_gemma":0.00057678175,"threshold_uncertainty_score":0.9987888},"labels":[],"label_agreement":null},{"id":"W4386528130","doi":"10.5281/zenodo.8322584","title":"Tracing data: A survey investigating disciplinary differences in data citation","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Université de Montréal; University of Ottawa","funders":"","keywords":"Citation; Tracing; Discipline; Computer science; Survey data collection; Data science; Library science; Statistics; Programming language; Sociology; Mathematics; Social science","score_opus":0.6841979718495724,"score_gpt":0.4488876378466068,"score_spread":0.23531033400296564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386528130","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":[0.8958413,0.000105098006,0.03207925,0.01091777,0.0007341731,0.0015121007,0.014994297,0.0020350616,0.041780945],"genre_scores_gemma":[0.9610243,0.0000411957,0.00037819264,0.000104960614,0.00007496833,3.8534985e-8,0.037121806,0.00029236736,0.00096217636],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99509543,0.0018362227,0.00058221666,0.0009627091,0.0011807166,0.00034268186],"domain_scores_gemma":[0.99639726,0.000666742,0.00019608437,0.0023259933,0.00028148023,0.00013241364],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.019279914,0.000114079405,0.00018954025,0.00062755955,0.0014401284,0.0022775216,0.006380027,0.000040132836,0.0016487087],"category_scores_gemma":[0.024715265,0.00010282895,0.000015292617,0.0033226418,0.00018404388,0.0019355548,0.014369379,0.00022121183,0.008277807],"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":[0.000037620084,0.00012769329,0.0011427796,0.00005550336,0.000026141239,0.000026312704,0.0045564673,0.0001691459,0.00024417022,0.0026042585,0.7164872,0.2745227],"study_design_scores_gemma":[0.00061011955,0.00010944129,0.4170845,0.00010665546,0.000011915579,0.000011685792,0.009870643,0.076905906,0.000016450891,0.008852194,0.48604974,0.00037077043],"about_ca_topic_score_codex":0.00014855935,"about_ca_topic_score_gemma":0.00007849107,"teacher_disagreement_score":0.4159417,"about_ca_system_score_codex":0.000044664073,"about_ca_system_score_gemma":0.000006902468,"threshold_uncertainty_score":0.99985987},"labels":[],"label_agreement":null},{"id":"W4386733095","doi":"10.2139/ssrn.4563380","title":"Using Network Science to Provide Insights into the Structure of Event Knowledge","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Western University","funders":"","keywords":"Event (particle physics); Data science; Computer science; Knowledge management; Physics","score_opus":0.12326988137027868,"score_gpt":0.4293816548885598,"score_spread":0.3061117735182811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386733095","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":[0.6720521,0.007783013,0.3046729,0.005106714,0.007983175,0.0016556411,0.000025252957,0.00006974462,0.0006514416],"genre_scores_gemma":[0.99549407,0.00073460565,0.0011246882,0.00018187755,0.0008686346,0.0000043585487,0.000004012648,0.00002511394,0.0015626294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922779,0.0006500083,0.0013075746,0.0008782727,0.002675959,0.002210254],"domain_scores_gemma":[0.9960685,0.00047400026,0.0010226343,0.0014737776,0.00077478174,0.00018633864],"candidate_categories":["open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02211941,0.00029982787,0.0005157683,0.0007205447,0.0009382824,0.00077255425,0.0058249803,0.00013607874,0.000026865819],"category_scores_gemma":[0.0024938087,0.00017568325,0.00024587076,0.002582905,0.00038935235,0.00036323364,0.0051769577,0.0030473622,0.00007593926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010657272,0.00010289749,0.0003293745,0.000064553555,0.00036929725,0.000006869992,0.013963265,0.199499,0.0017780394,0.59770966,0.0059451116,0.18012539],"study_design_scores_gemma":[0.00011512105,0.00010622723,0.00039542344,0.00015537706,0.00005391447,0.00001698643,0.0043759593,0.0029291878,0.00021324602,0.9670968,0.024324575,0.00021719854],"about_ca_topic_score_codex":0.00046131853,"about_ca_topic_score_gemma":0.01620693,"teacher_disagreement_score":0.36938715,"about_ca_system_score_codex":0.0015935253,"about_ca_system_score_gemma":0.011067619,"threshold_uncertainty_score":0.999554},"labels":[],"label_agreement":null},{"id":"W4386942653","doi":"10.48550/arxiv.2309.10880","title":"Classifying Organizations for Food System Ontologies using Natural Language Processing","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Science Foundation","keywords":"Computer science; Artificial intelligence; Natural language processing; Government (linguistics); Information retrieval; Data science","score_opus":0.48326968158249645,"score_gpt":0.3328273787771146,"score_spread":0.15044230280538184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386942653","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":[0.22388576,0.00023681787,0.7713999,0.00017727497,0.0016717683,0.00078633823,0.00046765397,0.00068555784,0.00068888307],"genre_scores_gemma":[0.9934418,0.000009984726,0.002181664,0.00004911371,0.000110099776,0.000002208446,0.00012601605,0.000031197415,0.004047924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755585,0.00021081654,0.0004430664,0.0011493231,0.00027983915,0.00036112184],"domain_scores_gemma":[0.99717146,0.0006230701,0.0005671025,0.0009806438,0.0005737215,0.00008402236],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014040029,0.0002608196,0.00044006546,0.0005512122,0.0005210483,0.0005978233,0.0017008274,0.00021862432,0.000014696917],"category_scores_gemma":[0.0016930513,0.00025082607,0.00017456936,0.001563542,0.00011664104,0.00050599454,0.002200014,0.00031662112,0.000083419094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019156882,0.00022129415,0.00589397,0.003452279,0.0007466208,0.00050134736,0.007429107,0.61131996,0.00023588522,0.3469679,0.009577739,0.013462342],"study_design_scores_gemma":[0.0004967622,0.00003837861,0.0007187832,0.0004018483,0.0002637076,0.0000037602636,0.05297006,0.9266939,0.000067053115,0.016149204,0.0016266239,0.00056991656],"about_ca_topic_score_codex":0.00013733734,"about_ca_topic_score_gemma":0.00083654514,"teacher_disagreement_score":0.76955605,"about_ca_system_score_codex":0.00036020094,"about_ca_system_score_gemma":0.00025167182,"threshold_uncertainty_score":0.9999944},"labels":[],"label_agreement":null},{"id":"W4387012786","doi":"10.18438/eblip30382","title":"Continuing Education and Data Training Initiatives are Needed to Positively Impact Academic Librarians Providing Data Services","year":2023,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical education; Government (linguistics); Likert scale; Computer science; Psychology; Medicine","score_opus":0.23970072358886668,"score_gpt":0.4603316262883908,"score_spread":0.22063090269952412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387012786","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":[0.2936513,0.0016363931,0.02407887,0.6631455,0.00091783615,0.0027062315,0.0044386904,0.00091800024,0.008507162],"genre_scores_gemma":[0.78105646,0.0027600657,0.012831437,0.19726172,0.0002963977,0.0000523289,0.005348773,0.000023769473,0.00036903372],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970973,0.0006411026,0.00077385415,0.00053707924,0.0007032915,0.00024735526],"domain_scores_gemma":[0.9903748,0.0072363527,0.0008477824,0.0012169835,0.00009082891,0.00023325146],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.005889652,0.00017202777,0.00021968031,0.00061443157,0.00030313365,0.0032552914,0.0019126136,0.00007853837,0.000079555095],"category_scores_gemma":[0.014592488,0.00014285727,0.000016691227,0.0015122669,0.0000556854,0.55787706,0.0027108763,0.0002636276,0.00014583273],"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":[0.0009007714,0.00006783051,0.0042841844,0.0004341476,0.00007813941,0.000009633408,0.029616276,0.00025604738,0.00016466578,0.04168378,0.13518709,0.78731745],"study_design_scores_gemma":[0.00032368387,0.00011911901,0.06460765,0.0015607012,0.00006217062,0.000016970691,0.24421959,0.04984405,0.00013191577,0.00056864484,0.63820356,0.0003419094],"about_ca_topic_score_codex":0.00004026305,"about_ca_topic_score_gemma":4.3862426e-7,"teacher_disagreement_score":0.7869755,"about_ca_system_score_codex":0.0000068969744,"about_ca_system_score_gemma":0.00029766845,"threshold_uncertainty_score":0.9977794},"labels":[],"label_agreement":null},{"id":"W4387267360","doi":"10.21900/j.alise.2023.1266","title":"Data Literacy Proficiency and Its Importance","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ALISE Annual Conference","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Information literacy; Literacy; Perception; Psychology; Rank (graph theory); Association (psychology); Library science; Survey data collection; Medical education; Computer science; Medicine; Mathematics; Pedagogy; Statistics","score_opus":0.2659070268639109,"score_gpt":0.4312554664129052,"score_spread":0.1653484395489943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387267360","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":[0.9820487,0.0001645607,0.000025769183,0.008044351,0.00019959,0.0004003202,0.0010044924,0.00007274967,0.00803947],"genre_scores_gemma":[0.99430114,0.00012775933,0.00012396259,0.00036356534,0.000036681588,0.000011367882,0.00001633235,0.000006069732,0.005013146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99747,0.000021790323,0.00053919555,0.0006252349,0.0010872311,0.00025651057],"domain_scores_gemma":[0.99757385,0.00021557118,0.0004101572,0.0006534364,0.0010663328,0.000080622885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003963563,0.0001248026,0.0002194292,0.0001396957,0.00016500917,0.00045464002,0.0039129434,0.00003827963,0.000070784394],"category_scores_gemma":[0.0052232267,0.000076484874,0.00003497433,0.0012679718,0.00015240554,0.002621054,0.0040653716,0.00011264508,0.00010163974],"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":[0.00009415173,0.00015669815,0.04605214,0.0003168491,0.000056060075,0.000004968354,0.020097662,0.0000025111763,0.004858469,0.4480243,0.43246835,0.04786784],"study_design_scores_gemma":[0.0008548782,0.0002220486,0.21191306,0.0003820418,0.000104199076,0.000017877386,0.03499388,0.020100595,0.0065899915,0.2675034,0.4564774,0.00084061635],"about_ca_topic_score_codex":0.000014360618,"about_ca_topic_score_gemma":0.000006045022,"teacher_disagreement_score":0.18052088,"about_ca_system_score_codex":0.0000057410425,"about_ca_system_score_gemma":0.000048575457,"threshold_uncertainty_score":0.72712874},"labels":[],"label_agreement":null},{"id":"W4387846857","doi":"10.1145/3583780.3615046","title":"SAND: Semantic Annotation of Numeric Data in Web Tables","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Information retrieval; Semantic Web; Annotation; Semantic Web Stack; Semantic annotation; Graph; Margin (machine learning); Knowledge graph; Social Semantic Web; Schema (genetic algorithms); Natural language processing; Artificial intelligence; Machine learning; Theoretical computer science","score_opus":0.32976674592286453,"score_gpt":0.4672587250817268,"score_spread":0.13749197915886224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387846857","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":[0.8893638,0.00012901225,0.029660877,0.0086328965,0.00081889686,0.0005784303,0.00085568574,0.00019330542,0.06976709],"genre_scores_gemma":[0.9931678,0.00006327723,0.00073119847,0.00019041885,0.000011484484,0.0000027222998,0.00026581218,0.0000027265812,0.0055645714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843407,0.00010895949,0.00040469386,0.00028030493,0.00065650226,0.0001154779],"domain_scores_gemma":[0.9983678,0.00053098553,0.00008973467,0.0009522237,0.000038410097,0.000020831498],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004390383,0.00004294744,0.0001315889,0.00033052583,0.000022639448,0.00007382222,0.0009414548,0.000015650014,0.0007316124],"category_scores_gemma":[0.0014815051,0.00003110915,0.000013608248,0.001831122,0.000031397343,0.0005915565,0.0006560191,0.000026361673,0.0010406484],"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":[0.000021430398,0.00012503444,0.018937394,0.000046725254,0.000016507307,0.000015218192,0.0008499478,0.0005548375,0.0012362563,0.022819065,0.769596,0.18578158],"study_design_scores_gemma":[0.0009939009,0.00006796263,0.16120228,0.000054218573,0.00001803348,0.0000011052931,0.016673526,0.23321041,0.0007031323,0.07689877,0.5098777,0.00029896083],"about_ca_topic_score_codex":0.00041127508,"about_ca_topic_score_gemma":0.0013474659,"teacher_disagreement_score":0.2597183,"about_ca_system_score_codex":0.0000043298633,"about_ca_system_score_gemma":0.00002519407,"threshold_uncertainty_score":0.99973714},"labels":[],"label_agreement":null},{"id":"W4387846873","doi":"10.1145/3583780.3615172","title":"Product Entity Matching via Tabular Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Serialization; ENCODE; Transformer; Data mining; Matching (statistics); Benchmark (surveying); Entity linking; Task (project management); Product (mathematics); Artificial intelligence; Information retrieval; Natural language processing; Machine learning; Knowledge base; Programming language","score_opus":0.48078262262889726,"score_gpt":0.492133428387495,"score_spread":0.01135080575859776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387846873","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":[0.1604108,0.00013148294,0.6651023,0.047324955,0.004828068,0.0011471581,0.0006606304,0.0015593584,0.118835256],"genre_scores_gemma":[0.84746253,0.00006088258,0.0092695365,0.0025869594,0.00038889775,0.0000126940595,0.0009611046,0.000018963729,0.1392384],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997511,0.00013347018,0.00033984162,0.0006553279,0.0011574366,0.00020291498],"domain_scores_gemma":[0.9967785,0.00024757328,0.0000673099,0.0027996793,0.000050186834,0.000056786153],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.009536238,0.00006770335,0.00012482463,0.00016239138,0.00014070046,0.00043058078,0.0024954944,0.000014445613,0.001912097],"category_scores_gemma":[0.0015495694,0.000047302372,0.000025996851,0.0010232608,0.000035711604,0.001119453,0.003177383,0.00006129738,0.017339963],"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":[0.0000026679863,0.000030169122,0.00047742008,0.0000068574727,0.000012100183,0.000012669322,0.00013408037,0.000039650226,0.0001860885,0.016732289,0.87781066,0.10455535],"study_design_scores_gemma":[0.000070510214,0.0000054800125,0.0053345724,0.0000026155556,0.000005750599,6.2586554e-7,0.00077686476,0.0027084376,0.0001594035,0.1040865,0.8867544,0.00009485109],"about_ca_topic_score_codex":0.00041407224,"about_ca_topic_score_gemma":0.000493516,"teacher_disagreement_score":0.6870518,"about_ca_system_score_codex":0.000006869638,"about_ca_system_score_gemma":0.00001622126,"threshold_uncertainty_score":0.9990003},"labels":[],"label_agreement":null},{"id":"W4387860452","doi":"10.1002/pra2.868","title":"(Talking About) Failing Better in Research: The First Rule of Failure Club Is…You Don’t Talk about Failure Club","year":2023,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of British Columbia; McGill University","funders":"","keywords":"Journal club; Mentorship; Publishing; Club; Public relations; Research integrity; Psychology; Engineering ethics; Sociology; Political science; Medical education; Engineering; Medicine","score_opus":0.08120058587441907,"score_gpt":0.37832501646006544,"score_spread":0.29712443058564636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387860452","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":[0.8733343,0.00002143885,0.00007026863,0.121863276,0.00018500445,0.0009160274,0.000069901966,0.00007543373,0.003464364],"genre_scores_gemma":[0.9986516,0.00003497216,0.0003263485,0.0005593459,0.00001831703,0.00007986343,0.0000037489187,0.0000038876196,0.00032187748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995853,0.000017459377,0.00093622814,0.00027432028,0.0024698854,0.00044907883],"domain_scores_gemma":[0.9951155,0.0005970273,0.0011449778,0.00029695663,0.0028155595,0.000029935845],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.024129312,0.000102657534,0.0002319081,0.0018960874,0.0008420363,0.0005265691,0.0021825337,0.00017796358,0.000008812003],"category_scores_gemma":[0.017086495,0.00006406843,0.00006361708,0.009283807,0.00078321254,0.0036632752,0.0012106799,0.00030497072,0.00003063295],"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":[0.000052926353,0.0000795086,0.22436678,0.0003632439,0.00006237365,1.6281865e-7,0.027687889,0.00008502455,0.0051478357,0.41436282,0.20955792,0.11823351],"study_design_scores_gemma":[0.0007341877,0.00007501398,0.05040099,0.00013447918,0.000013979925,0.0000019544552,0.060737442,0.0039028483,0.017674852,0.14889735,0.7172424,0.00018448703],"about_ca_topic_score_codex":0.000032972883,"about_ca_topic_score_gemma":0.00009654021,"teacher_disagreement_score":0.50768447,"about_ca_system_score_codex":0.00016445514,"about_ca_system_score_gemma":0.000094229275,"threshold_uncertainty_score":0.991193},"labels":[],"label_agreement":null},{"id":"W4388095942","doi":"10.5267/j.ijdns.2023.9.022","title":"Web-based information system framework for the digitization of historical databases and endowments","year":2023,"lang":"en","type":"article","venue":"International Journal of Data and Network Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Digitization; Computer science; World Wide Web; Inheritance (genetic algorithm); Web application; Population; Graph; Data science; Database","score_opus":0.21510516184672646,"score_gpt":0.43539972690260986,"score_spread":0.2202945650558834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388095942","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":[0.012479736,0.00017117134,0.98026735,0.0038236822,0.002313433,0.00016282898,0.00065879663,0.000010480751,0.0001125534],"genre_scores_gemma":[0.9870852,0.00024018383,0.011958275,0.00035036524,0.00025387236,0.0000028976126,0.0000822788,0.0000019061116,0.000025008794],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977046,0.000041930223,0.0005673764,0.00013681056,0.0014463844,0.00010288868],"domain_scores_gemma":[0.9965063,0.0020017822,0.0005869053,0.00031751348,0.00053465803,0.00005288446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069545167,0.000048072987,0.000112342466,0.00024719417,0.00016389224,0.00036956242,0.0017240274,0.000013089747,0.0000049922446],"category_scores_gemma":[0.0034175538,0.000028828763,0.000020423637,0.00061604736,0.00017132354,0.0028741828,0.000616778,0.000054010918,0.0000028921695],"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":[0.00038224686,0.000057918092,0.016646449,0.000057754933,0.000101427424,0.00000747078,0.000534875,0.007035895,0.00006936911,0.2365412,0.18723023,0.55133516],"study_design_scores_gemma":[0.0009572009,0.00011659168,0.017820299,0.0003094106,0.00004559791,0.000025431134,0.0015636651,0.38954803,0.00007082013,0.01074396,0.5786843,0.00011470791],"about_ca_topic_score_codex":0.000010927857,"about_ca_topic_score_gemma":0.0000046587747,"teacher_disagreement_score":0.9746055,"about_ca_system_score_codex":0.000050350332,"about_ca_system_score_gemma":0.00011301375,"threshold_uncertainty_score":0.4091378},"labels":[],"label_agreement":null},{"id":"W4388494637","doi":"10.1049/pbpc063e_ch7","title":"Visualization tools for personal knowledge graphs","year":2023,"lang":"en","type":"book-chapter","venue":"Institution of Engineering and Technology eBooks","topic":"Data Quality and Management","field":"Decision Sciences","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":"Cape Breton University","funders":"","keywords":"Computer science; Visualization; Information visualization; Graph drawing; Focus (optics); Knowledge graph; Data science; Human–computer interaction; Knowledge management; Information retrieval; Data mining","score_opus":0.12444921563194548,"score_gpt":0.3504058782548951,"score_spread":0.2259566626229496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388494637","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036619636,0.0023867032,0.34564298,0.0009205652,0.0053209215,0.0029728808,0.0014912139,0.0028210487,0.6347817],"genre_scores_gemma":[0.33490202,0.00033480654,0.0017296213,0.000054584205,0.00017979107,0.000191213,0.00024675368,0.00009636396,0.6622648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872065,0.000005316802,0.00049059093,0.00037656675,0.00026336714,0.00014353398],"domain_scores_gemma":[0.9989566,0.000309243,0.00018895676,0.00026546014,0.00024423926,0.000035475183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007629869,0.00018418474,0.00034300017,0.001353601,0.00009479091,0.0000657706,0.0002878029,0.0004074671,0.000009672466],"category_scores_gemma":[0.0009929702,0.00017214376,0.00009106014,0.00011073273,0.00028180805,0.00009882208,0.00019074077,0.00015057335,0.000032556905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049644727,0.0000048139364,0.0000011686375,0.00007684997,0.000045004643,0.0000018857529,0.0000678808,0.00001552993,0.00008486379,0.9258617,0.00088644406,0.07294889],"study_design_scores_gemma":[0.00028692433,0.000104604485,0.000008674902,0.00023477412,0.00004884319,0.0000055368737,0.00006921773,0.003978374,0.0003426781,0.23062746,0.7640617,0.00023121486],"about_ca_topic_score_codex":0.0000015546431,"about_ca_topic_score_gemma":0.0000116053725,"teacher_disagreement_score":0.76317525,"about_ca_system_score_codex":0.000022580496,"about_ca_system_score_gemma":0.000053574495,"threshold_uncertainty_score":0.70198184},"labels":[],"label_agreement":null},{"id":"W4388963821","doi":"10.48550/arxiv.2311.13517","title":"Learning-Based Relaxation of Completeness Requirements for Data Entry Forms","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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 Ottawa","funders":"BNP Paribas Cardif","keywords":"Completeness (order theory); Computer science; Field (mathematics); Lacquer; Data mining; Artificial intelligence; Machine learning; Mathematics","score_opus":0.649970621585224,"score_gpt":0.3571455270505782,"score_spread":0.2928250945346458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388963821","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":[0.092766084,0.00001125208,0.90208375,0.00046634415,0.0009197789,0.0009652532,0.0014457622,0.00014511801,0.001196652],"genre_scores_gemma":[0.98675674,0.000050267117,0.0005315418,0.000097783275,0.00003887346,0.000002741096,0.0033982438,0.000021330134,0.009102473],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693006,0.00029340657,0.00064565835,0.0013813679,0.0004674243,0.00028206795],"domain_scores_gemma":[0.9943928,0.0011458357,0.0011890421,0.002776468,0.00040292356,0.00009288932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045943926,0.00021783359,0.00045986183,0.00049157365,0.0001925014,0.000137177,0.003827339,0.00018667681,0.00009633],"category_scores_gemma":[0.0024614427,0.00021288336,0.00019116284,0.0007222203,0.00015066747,0.0005520416,0.0044211405,0.00026337785,0.0001745086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006132597,0.00036326365,0.01812363,0.0006896928,0.00033953713,0.000047903242,0.0002350895,0.83359295,0.000029511983,0.09450283,0.04561412,0.0058482126],"study_design_scores_gemma":[0.0013535323,0.00014672773,0.004274046,0.00018272776,0.00020042685,1.2588369e-7,0.0011766895,0.7703267,0.00007492047,0.17278181,0.04908618,0.00039614964],"about_ca_topic_score_codex":0.0002781754,"about_ca_topic_score_gemma":0.00027473658,"teacher_disagreement_score":0.9015522,"about_ca_system_score_codex":0.00010341187,"about_ca_system_score_gemma":0.00016838478,"threshold_uncertainty_score":0.86811316},"labels":[],"label_agreement":null},{"id":"W4389205106","doi":"10.51224/srxiv.353","title":"PubMed search filter for efficiently retrieving exercise training studies","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Training (meteorology); Computer science; Filter (signal processing); Information retrieval; Computer vision; Geography","score_opus":0.8329623756291038,"score_gpt":0.5367704814240526,"score_spread":0.2961918942050512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389205106","genre_codex":"methods","genre_gemma":"other","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":[0.06959939,0.0047901142,0.75988895,0.055673834,0.03786798,0.02511035,0.00401093,0.0029522378,0.04010621],"genre_scores_gemma":[0.3434047,0.0018913803,0.031591587,0.0025660077,0.0013765785,0.0053872247,0.0006294209,0.0001979026,0.6129552],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935714,0.00027274707,0.0012710519,0.0016188046,0.0024407255,0.00082525454],"domain_scores_gemma":[0.99161726,0.005388183,0.00031623465,0.001808708,0.0006872074,0.00018243045],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.028574329,0.00032888737,0.00093638693,0.00079289573,0.0003241706,0.0012728248,0.0024775758,0.00019580833,0.00018389305],"category_scores_gemma":[0.014881309,0.00023874418,0.00039877655,0.00083443563,0.00018888275,0.00023580495,0.007011885,0.000418088,0.0005465912],"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":[0.00006924144,0.00006409918,0.000070542344,0.00043958056,0.00023740823,0.000015481788,0.010737821,0.002636816,0.0000022875265,0.0055236365,0.50536114,0.47484192],"study_design_scores_gemma":[0.0017721183,0.00016640163,0.006121868,0.0014616955,0.00038605285,0.0000017777496,0.2029721,0.019665278,0.0005649739,0.288725,0.47607487,0.00208787],"about_ca_topic_score_codex":0.000049375267,"about_ca_topic_score_gemma":0.00009863576,"teacher_disagreement_score":0.72829735,"about_ca_system_score_codex":0.00011164087,"about_ca_system_score_gemma":0.00012781176,"threshold_uncertainty_score":0.99976397},"labels":[],"label_agreement":null},{"id":"W4389327349","doi":"10.1130/abs/2023am-393822","title":"CORRELATING MULTI-PROXY DATA ACROSS MULTIPLE BASINS IN WALDEN POND (MA, USA): EVIDENCE OF SUDDEN ONSET EVENTS AND HUMAN IMPACT","year":2023,"lang":"en","type":"article","venue":"Abstracts with programs - Geological Society of America","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; McMaster University","funders":"","keywords":"Proxy (statistics); Geology; Physical geography; Climatology; Geography; Computer science; Machine learning","score_opus":0.30149014474322877,"score_gpt":0.47146020407533373,"score_spread":0.16997005933210496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389327349","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":[0.9969574,0.00008717425,0.0009935773,0.0007331164,0.00003677836,0.00078084884,0.0003161338,0.000056662466,0.000038267055],"genre_scores_gemma":[0.9799597,0.00010697892,0.019247085,0.00016376705,0.000014577386,0.000028023793,0.00023943903,0.000011531998,0.00022887654],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99559265,0.0002859159,0.00119138,0.0009515918,0.0012824127,0.0006960223],"domain_scores_gemma":[0.9949161,0.0025487342,0.0010009906,0.0011638683,0.00018101741,0.000189291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005709656,0.00026759482,0.000711614,0.0000654813,0.0002481609,0.00013042598,0.0016335716,0.00016526064,0.00010895269],"category_scores_gemma":[0.0029473489,0.00017318812,0.00016038436,0.0014644244,0.0013472926,0.0009246529,0.0020088283,0.0003877652,0.000052080304],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012988735,0.0005284363,0.9206993,0.00008391247,0.00008826008,0.000019111712,0.0031665342,0.001152544,0.00011428551,0.000005372318,0.0018113822,0.072201006],"study_design_scores_gemma":[0.000959282,0.0009317335,0.9687508,0.00024206238,0.000021913367,0.0000052030878,0.011345434,0.015748192,0.000022047972,0.0002629073,0.0014758997,0.0002345452],"about_ca_topic_score_codex":0.0084184185,"about_ca_topic_score_gemma":0.0016606682,"teacher_disagreement_score":0.07196646,"about_ca_system_score_codex":0.000041116706,"about_ca_system_score_gemma":0.00007494649,"threshold_uncertainty_score":0.9981846},"labels":[],"label_agreement":null},{"id":"W4389386408","doi":"10.1145/3635708","title":"Learning-based Relaxation of Completeness Requirements for Data Entry Forms","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Ottawa","funders":"BNP Paribas Cardif; Université du Luxembourg","keywords":"Completeness (order theory); Computer science; Field (mathematics); Artificial intelligence; Machine learning; Data mining","score_opus":0.5502892581731978,"score_gpt":0.47503419077972964,"score_spread":0.07525506739346821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389386408","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":[0.01276107,0.000023376644,0.98567957,0.0004934619,0.00046014058,0.00020194426,0.00020655082,0.00016899484,0.0000049018863],"genre_scores_gemma":[0.25692028,0.00009761665,0.74102,0.00023010236,0.00003721582,0.000108654254,0.0005859643,0.000032313426,0.00096781744],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984218,0.000245747,0.000425925,0.00040122197,0.00030714352,0.00019815637],"domain_scores_gemma":[0.989589,0.009231166,0.00013215735,0.0009060179,0.00008907444,0.000052582713],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006153193,0.000105710715,0.00027162954,0.00039476555,0.00012956395,0.000029208353,0.0006504996,0.0000785886,0.00002881877],"category_scores_gemma":[0.013746993,0.000091026464,0.000056638695,0.00050166104,0.0000448981,0.00020604902,0.00004927591,0.00012226493,0.000013287241],"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":[0.00023182311,0.00009413299,0.00060494547,0.00025632454,0.00015805975,0.00000242771,0.00048672434,0.39017555,0.0007389207,0.0015426031,0.0017333111,0.6039752],"study_design_scores_gemma":[0.00491807,0.001738249,0.019814517,0.0002289346,0.00040773652,0.0000110992805,0.0022539285,0.46508914,0.009232403,0.028667258,0.46668822,0.00095046137],"about_ca_topic_score_codex":0.00002136789,"about_ca_topic_score_gemma":0.000010492121,"teacher_disagreement_score":0.6030247,"about_ca_system_score_codex":0.000012788165,"about_ca_system_score_gemma":0.00002208521,"threshold_uncertainty_score":0.99456066},"labels":[],"label_agreement":null},{"id":"W4389519304","doi":"10.18653/v1/2023.crac-sharedtask.5","title":"McGill at CRAC 2023: Multilingual Generalization of Entity-Ranking Coreference Resolution Models","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"Canadian Institute for Advanced Research; Nvidia","keywords":"Coreference; Computer science; Task (project management); Ranking (information retrieval); Generalization; Preprocessor; Natural language processing; Artificial intelligence; F1 score; Encoder; Resolution (logic); Machine learning; Information retrieval","score_opus":0.4044293887468424,"score_gpt":0.44015659461111,"score_spread":0.035727205864267586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389519304","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":[0.74056315,0.000047304766,0.21105982,0.0007432348,0.0010284804,0.0004569195,0.00047400684,0.0002683724,0.045358703],"genre_scores_gemma":[0.96900094,0.00010798323,0.00224329,0.00024274831,0.000030566203,0.000007809768,0.00017633819,0.0000068144805,0.028183494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973412,0.00019266414,0.00061116955,0.00041575418,0.0012350176,0.00020416046],"domain_scores_gemma":[0.9986,0.00033323548,0.00020285926,0.00054860424,0.000264401,0.000050923692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031714523,0.00008938916,0.00017729217,0.00032328774,0.00022505925,0.00006424074,0.0005238953,0.00005418928,0.000656975],"category_scores_gemma":[0.0009912177,0.000072264476,0.00006653438,0.0011079219,0.00005910772,0.0005643734,0.0006631873,0.000045920082,0.0007503096],"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":[0.00011717093,0.00017215237,0.0016860468,0.00006314426,0.000049714956,0.000012113047,0.0012863522,0.21706983,0.0071372464,0.49130479,0.19762224,0.0834792],"study_design_scores_gemma":[0.00044266682,0.00004563653,0.004426344,0.000025888407,0.000017868126,7.8292845e-7,0.00082451495,0.8003722,0.0056098225,0.12178868,0.06623349,0.00021212707],"about_ca_topic_score_codex":0.00056588836,"about_ca_topic_score_gemma":0.0014171428,"teacher_disagreement_score":0.5833023,"about_ca_system_score_codex":0.000043498112,"about_ca_system_score_gemma":0.000015168904,"threshold_uncertainty_score":0.96439624},"labels":[],"label_agreement":null},{"id":"W4389615820","doi":"10.23889/ijpds.v8i1.2153","title":"De-identification of Free Text Data containing Personal Health Information: A Scoping Review of Reviews","year":2023,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"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 Manitoba; George & Fay Yee Centre for Healthcare Innovation; Manitoba Health","funders":"Canadian Institutes of Health Research","keywords":"Health Insurance Portability and Accountability Act; Identification (biology); Computer science; Protected health information; Information retrieval; MEDLINE; Personally identifiable information; Digital library; Data science; World Wide Web; Medicine; Confidentiality; Public health; Nursing; Health education","score_opus":0.7026193400916434,"score_gpt":0.6308973187983484,"score_spread":0.07172202129329497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389615820","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.649742e-7,0.9250688,0.05741154,0.0011832913,0.0022805717,0.0017910029,0.012197019,0.000014259278,0.00005314205],"genre_scores_gemma":[0.000005274331,0.98431915,0.004617844,0.0004737379,0.00023154015,0.0000310523,0.010214936,0.00001095169,0.000095484735],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9875827,0.0005568905,0.0066171163,0.0007229413,0.0042162123,0.00030417836],"domain_scores_gemma":[0.98135316,0.0013995569,0.011864572,0.0033798777,0.001826005,0.00017680512],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07437966,0.00022600382,0.0014526079,0.0013589668,0.00033256708,0.000942666,0.018078167,0.00006471051,0.00011772373],"category_scores_gemma":[0.065756746,0.00017383139,0.00025891868,0.0017979313,0.00022182544,0.009249598,0.0042995503,0.00024999474,0.00006816018],"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":[0.0000059103154,0.000019442978,0.000008429448,0.027133722,0.00004269615,4.79978e-7,0.00009950463,0.0000041315157,1.17543735e-7,0.0024432684,0.03728007,0.93296224],"study_design_scores_gemma":[0.00013054423,0.000028470955,0.000038085498,0.22073941,0.000094870455,0.00003741265,0.00009098175,0.0020462496,1.1335901e-7,0.000857024,0.7758035,0.0001333251],"about_ca_topic_score_codex":0.00014992968,"about_ca_topic_score_gemma":0.00007457093,"teacher_disagreement_score":0.9328289,"about_ca_system_score_codex":0.00029084267,"about_ca_system_score_gemma":0.0025606304,"threshold_uncertainty_score":0.9872345},"labels":[],"label_agreement":null},{"id":"W4389986082","doi":"10.51952/9781529233551.ch006","title":"Experiments in Practice: New Directions in Municipal Data Policy and Governance","year":2023,"lang":"en","type":"book-chapter","venue":"Bristol University Press eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corporate governance; Public administration; Political science; Business; Environmental planning; Geography; Finance","score_opus":0.3036909657686982,"score_gpt":0.41267996682332714,"score_spread":0.10898900105462894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389986082","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004205091,0.0002906221,0.00007950636,0.00049150415,0.00021890797,0.00038459682,0.0008382856,0.00005119944,0.9976033],"genre_scores_gemma":[0.000435872,0.0012795031,0.00030824088,0.00016762593,0.00007074735,5.2358916e-7,0.00007397128,0.000020230706,0.9976433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99738437,0.00017309922,0.00041181434,0.00094249466,0.00083949644,0.00024872817],"domain_scores_gemma":[0.99691445,0.00071689667,0.00041550674,0.0017569931,0.00005525388,0.00014092062],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011468021,0.00022359232,0.00038975614,0.0005026078,0.00011691889,0.00018254036,0.0020732784,0.00018779995,0.000023635483],"category_scores_gemma":[0.0010794348,0.00025865049,0.00004654356,0.000086875654,0.0001764171,0.0007635048,0.004329328,0.00037794528,0.000058172092],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001429904,0.00003717492,0.000008804669,0.000013476897,0.000058253634,0.00059625576,0.0014196157,0.000010316577,9.72712e-7,0.89321446,0.059057236,0.045440458],"study_design_scores_gemma":[0.0006108106,0.000016367208,0.0001978489,0.000112416215,0.00003679733,0.0000048949496,0.0008834116,0.000118999,0.0000014832387,0.0033087605,0.9944684,0.00023983532],"about_ca_topic_score_codex":0.05079364,"about_ca_topic_score_gemma":0.013217722,"teacher_disagreement_score":0.93541116,"about_ca_system_score_codex":0.00028320245,"about_ca_system_score_gemma":0.00023385734,"threshold_uncertainty_score":0.9999866},"labels":[],"label_agreement":null},{"id":"W4390245620","doi":"10.1016/j.datak.2023.102274","title":"Mining Keys for Graphs","year":2023,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Data deduplication; Theoretical computer science; Identification (biology); Data mining; Pruning; Database","score_opus":0.3915863678661295,"score_gpt":0.45612684361496436,"score_spread":0.06454047574883487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390245620","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":[0.036285207,0.00097127573,0.92995983,0.00208795,0.009235888,0.0013068663,0.005426869,0.002074137,0.0126519585],"genre_scores_gemma":[0.6081954,0.0005172615,0.27274084,0.00094600033,0.0045168153,0.0009858274,0.031681042,0.00050744414,0.07990935],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982215,0.000032910866,0.00041366107,0.000590915,0.00038635003,0.0003546488],"domain_scores_gemma":[0.9966078,0.0015499732,0.000055878798,0.0016106992,0.00007792504,0.000097748634],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004567647,0.00013131872,0.00020627533,0.00046921187,0.000109486595,0.00026203826,0.002229502,0.00004161456,0.00007234562],"category_scores_gemma":[0.004466019,0.00011692486,0.00005973463,0.0013795267,0.000019908366,0.00066435273,0.001509854,0.00006850877,0.0015328354],"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":[0.0000045760644,0.000023946304,0.00008389208,0.000055799053,0.000033361637,0.0000050958697,0.00051834463,0.00017652418,0.00018465552,0.022172429,0.72205603,0.25468534],"study_design_scores_gemma":[0.00014161725,0.000010317399,0.00052290445,0.00001627418,0.0000086979335,4.8556456e-7,0.00037129913,0.35582313,0.000057400153,0.0013434913,0.641587,0.000117367104],"about_ca_topic_score_codex":0.0000046527007,"about_ca_topic_score_gemma":0.000034737885,"teacher_disagreement_score":0.657219,"about_ca_system_score_codex":0.0000138819805,"about_ca_system_score_gemma":0.000021148533,"threshold_uncertainty_score":0.9992446},"labels":[],"label_agreement":null},{"id":"W4390690778","doi":"10.3138/jmvfh-2022-0071","title":"Studying military and Veteran health using a life-course approach: Lessons learned from a Canadian record linkage study","year":2024,"lang":"en","type":"article","venue":"Journal of Military Veteran and Family Health","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Veterans Affairs Canada; Public Health Agency of Canada","funders":"","keywords":"Stakeholder; Life course approach; Linkage (software); Public relations; Resource (disambiguation); Political science; Psychology; Computer science","score_opus":0.4195636312155331,"score_gpt":0.4607801025808845,"score_spread":0.04121647136535139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390690778","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":[0.854796,0.12686123,0.0020979575,0.01404729,0.0010547857,0.0006700545,0.00038333438,0.000024874602,0.000064498694],"genre_scores_gemma":[0.96858776,0.013717459,0.008231955,0.008927488,0.00042960743,0.000004782594,0.000018251905,0.000031975385,0.000050740568],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99308044,0.002097101,0.0020879698,0.0008734315,0.0011768686,0.0006841739],"domain_scores_gemma":[0.9964637,0.0008362696,0.00031374267,0.00062760425,0.00013426546,0.0016244026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.014165944,0.00033523302,0.0010897447,0.00092255813,0.00070792873,0.00020480245,0.0006019842,0.000086330656,0.000024928038],"category_scores_gemma":[0.00037842782,0.00026318646,0.00017624583,0.000607668,0.00012633146,0.0008620309,0.00020659817,0.00080635137,0.000008945289],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050805253,0.0010502664,0.015995326,0.00057547993,0.0006847917,0.0006944985,0.10093461,0.00020543631,0.00003134189,0.00010223256,0.029731566,0.8494864],"study_design_scores_gemma":[0.005046452,0.008706916,0.53271943,0.0014296065,0.00038280344,0.00023472853,0.33760348,0.034948174,1.8840983e-7,0.007032962,0.07086159,0.0010336619],"about_ca_topic_score_codex":0.30535248,"about_ca_topic_score_gemma":0.088376276,"teacher_disagreement_score":0.84845275,"about_ca_system_score_codex":0.00024607973,"about_ca_system_score_gemma":0.001931079,"threshold_uncertainty_score":0.99998206},"labels":[],"label_agreement":null},{"id":"W4391018115","doi":"10.1145/3593579","title":"Record Fusion via Inference and Data Augmentation","year":2024,"lang":"en","type":"article","venue":"ACM / IMS Journal of Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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 Waterloo","funders":"","keywords":"Computer science; Inference; Probabilistic logic; Sensor fusion; Data mining; Fusion; Data source; Artificial intelligence; Machine learning","score_opus":0.5120775299749007,"score_gpt":0.5555716160536497,"score_spread":0.04349408607874894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391018115","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":[0.32441798,0.0029277839,0.638906,0.023143008,0.0070650117,0.00038969438,0.001602311,0.00006096902,0.0014872738],"genre_scores_gemma":[0.9360951,0.0016236736,0.06111645,0.0005506846,0.00023564689,5.995909e-7,0.00012070581,0.000006784798,0.00025034454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956779,0.00013254953,0.0008170487,0.00078008126,0.0023717186,0.00022072987],"domain_scores_gemma":[0.9937635,0.0014162299,0.00039194658,0.003944189,0.00028853441,0.000195585],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.023029098,0.00009981575,0.00018500177,0.00052378944,0.000249898,0.0021482504,0.013045885,0.000024412657,0.00021986366],"category_scores_gemma":[0.013065709,0.000066036926,0.000018409373,0.001635967,0.0004944185,0.020372694,0.011141012,0.00019807312,0.00013622841],"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":[0.0000150459155,0.000024639925,0.0007443671,0.000010812121,0.000008265724,0.000034559365,0.00024307918,0.000003262378,0.0035319233,0.0012052095,0.035587765,0.95859104],"study_design_scores_gemma":[0.00059464935,0.00043091175,0.025150346,0.0004010677,0.0001107794,0.00033672794,0.0029948768,0.0630696,0.0007013286,0.11329627,0.7924813,0.00043213659],"about_ca_topic_score_codex":0.00007799401,"about_ca_topic_score_gemma":0.00009017748,"teacher_disagreement_score":0.9581589,"about_ca_system_score_codex":0.00003375756,"about_ca_system_score_gemma":0.00032350203,"threshold_uncertainty_score":0.9988876},"labels":[],"label_agreement":null},{"id":"W4391054937","doi":"10.14778/3632093.3632096","title":"Blocker and Matcher Can Mutually Benefit: A Co-Learning Framework for Low-Resource Entity Resolution","year":2023,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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":"Vector Institute; University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Resource (disambiguation); Noise (video); Selection (genetic algorithm); Machine learning; Artificial intelligence; Resolution (logic); Data mining","score_opus":0.07733140174241149,"score_gpt":0.3638194075327134,"score_spread":0.2864880057903019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391054937","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":[0.98065096,0.00007711705,0.0011062153,0.011151741,0.0002963744,0.0012148896,0.00011032599,0.00014355224,0.0052488334],"genre_scores_gemma":[0.98705167,0.000054781427,0.0032541668,0.0005706783,0.000118952674,0.0001367552,0.000011205743,0.000021001642,0.00878079],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762446,0.00002290538,0.00049097894,0.00045093586,0.0010769072,0.00033383287],"domain_scores_gemma":[0.99863416,0.00046091896,0.00037828847,0.00022707996,0.00021494034,0.000084591724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039013666,0.00014366173,0.00024236266,0.00017956608,0.00035030325,0.00028268638,0.00077806617,0.00007797755,0.000049041246],"category_scores_gemma":[0.002621769,0.00009840118,0.000119416334,0.00068343146,0.00012699267,0.00018666708,0.00076587615,0.00017258496,0.000031713647],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037458443,0.0003127596,0.016926423,0.0005899199,0.00025288362,0.0000015910371,0.015736988,0.0006259845,0.008565363,0.6782655,0.21925876,0.059089243],"study_design_scores_gemma":[0.0011831772,0.0002653645,0.022419779,0.0003744437,0.00011229366,0.0000039141987,0.01934921,0.0031659456,0.018065942,0.40382552,0.5308076,0.0004268277],"about_ca_topic_score_codex":0.000057461435,"about_ca_topic_score_gemma":0.000021910007,"teacher_disagreement_score":0.31154883,"about_ca_system_score_codex":0.000051150488,"about_ca_system_score_gemma":0.000014849927,"threshold_uncertainty_score":0.40126836},"labels":[],"label_agreement":null},{"id":"W4391092916","doi":"10.1109/bigdata59044.2023.10386157","title":"Leveraging Knowledge Graphs for Matching Heterogeneous Entities and Explanation","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Knowledge graph; Matching (statistics); Data science; Information retrieval; Mathematics","score_opus":0.27236666365209145,"score_gpt":0.43350352874008075,"score_spread":0.1611368650879893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391092916","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":[0.8189833,0.00024228818,0.16173384,0.0020956486,0.0010287612,0.00046172022,0.00005871064,0.0003138932,0.015081817],"genre_scores_gemma":[0.9839099,0.000057678604,0.0008737452,0.00028015953,0.000027564934,0.00002847856,0.000033389162,0.000005106984,0.014783995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990818,0.000050579107,0.00022164782,0.00023802319,0.000273431,0.00013453075],"domain_scores_gemma":[0.99903643,0.0006547245,0.00004318827,0.00018012583,0.000051853956,0.000033650944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002065233,0.000055691904,0.0000914782,0.00028522508,0.00018038052,0.0003536517,0.00020201926,0.000016280914,0.000090942405],"category_scores_gemma":[0.00022494626,0.00004309398,0.000038644113,0.00027678293,0.000023428503,0.00029812352,0.00018373615,0.000019345893,0.00019990571],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018900519,0.000038046262,0.0005391407,0.00007291588,0.00004577215,0.000006162328,0.011053576,0.00036777472,0.00024358432,0.58532286,0.188617,0.21367429],"study_design_scores_gemma":[0.00028006808,0.000027015903,0.0014238746,0.000010673355,0.0000081503795,0.0000023835985,0.011916172,0.00855301,0.00049635855,0.7925916,0.18455422,0.0001365293],"about_ca_topic_score_codex":0.00003562408,"about_ca_topic_score_gemma":0.00015414764,"teacher_disagreement_score":0.21353775,"about_ca_system_score_codex":0.000006742968,"about_ca_system_score_gemma":0.000005984676,"threshold_uncertainty_score":0.34102714},"labels":[],"label_agreement":null},{"id":"W4391093649","doi":"10.1109/bigdata59044.2023.10386776","title":"Unstructured Transportation Safety Board Findings Categorization Using the Knowledge Graph Pipeline","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Categorization; Computer science; Pipeline (software); Graph; Knowledge graph; Data science; Information retrieval; Artificial intelligence; Theoretical computer science; Programming language","score_opus":0.14575456692883001,"score_gpt":0.40316707886037756,"score_spread":0.25741251193154757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391093649","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":[0.11523887,0.000028298384,0.87135375,0.0041881376,0.001367498,0.00047687886,0.00016366997,0.00026696696,0.006915952],"genre_scores_gemma":[0.9903997,0.00003369046,0.0007730992,0.00037663063,0.00007934874,0.000004774314,0.000253996,0.000009284554,0.0080694705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980966,0.00014899857,0.00054751127,0.00033015892,0.00068739656,0.00018932504],"domain_scores_gemma":[0.9989104,0.0003548722,0.000102623504,0.00042883432,0.0001570907,0.000046124103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027949756,0.00010165232,0.00014003704,0.00027413163,0.00033651222,0.00020738259,0.0005349893,0.00004803506,0.0005504574],"category_scores_gemma":[0.00031752948,0.000058874895,0.000079277495,0.0025531107,0.000073073425,0.0003939592,0.000046392623,0.00007195248,0.00032677292],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121865094,0.00007922764,0.0039486974,0.000040560422,0.000063641266,0.000010048047,0.014122935,0.017562859,0.0026881478,0.517214,0.22668889,0.21745916],"study_design_scores_gemma":[0.0010767182,0.00004161757,0.17597166,0.000020809033,0.00010552546,0.0000016633657,0.016982296,0.0948162,0.0019393241,0.2317669,0.47677135,0.00050594757],"about_ca_topic_score_codex":0.00017101291,"about_ca_topic_score_gemma":0.0012044752,"teacher_disagreement_score":0.8751608,"about_ca_system_score_codex":0.000021994976,"about_ca_system_score_gemma":0.00003263911,"threshold_uncertainty_score":0.6027122},"labels":[],"label_agreement":null},{"id":"W4391358403","doi":"10.1002/joom.1294","title":"Vendor selection in the wake of data breaches: A longitudinal study","year":2024,"lang":"en","type":"article","venue":"Journal of Operations Management","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Wake; Vendor; Selection (genetic algorithm); Business; Longitudinal data; Computer science; Operations management; Operations research; Marketing; Data mining; Economics; Artificial intelligence; Mathematics","score_opus":0.4863857178479917,"score_gpt":0.523023495877093,"score_spread":0.03663777802910123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391358403","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":[0.54210407,0.0016714368,0.41095,0.022625769,0.0021626283,0.0031509292,0.00016344135,0.000040266415,0.017131472],"genre_scores_gemma":[0.99554014,0.000060250888,0.0033075523,0.00010987592,0.0000979706,0.000010431324,0.0000073103147,0.0000041406306,0.00086234795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969144,0.00041763607,0.0009946107,0.00025010327,0.0013199874,0.00010329053],"domain_scores_gemma":[0.9988227,0.0002773435,0.00014301257,0.0005995289,0.00013378686,0.000023626804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012220027,0.00007932474,0.0001844517,0.0006250224,0.00009377544,0.00068656873,0.0016944166,0.000013500238,0.00016203133],"category_scores_gemma":[0.00023006617,0.000045279852,0.00005954715,0.001259372,0.00003121405,0.0013596796,0.00039275346,0.00016314034,0.000043093067],"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":[0.0001633365,0.0063061635,0.01390023,0.00019928506,0.0014237497,0.0008265911,0.022613032,0.02634127,0.00008956216,0.120396495,0.3309315,0.47680876],"study_design_scores_gemma":[0.0021224325,0.0016429716,0.3116259,0.0003258443,0.0008420998,0.00022142984,0.1488558,0.045294188,0.000022194688,0.008756889,0.47993138,0.00035884583],"about_ca_topic_score_codex":0.00009342134,"about_ca_topic_score_gemma":0.0011036899,"teacher_disagreement_score":0.4764499,"about_ca_system_score_codex":0.000044318273,"about_ca_system_score_gemma":0.00004566071,"threshold_uncertainty_score":0.6620598},"labels":[],"label_agreement":null},{"id":"W4391491066","doi":"10.2196/51560","title":"Frameworks, Dimensions, Definitions of Aspects, and Assessment Methods for the Appraisal of Quality of Health Data for Secondary Use: Comprehensive Overview of Reviews","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Terminology; Quality (philosophy); Data quality; Computer science; Ambiguity; Data science; Health care; Preprint; Systematic review; Management science; Knowledge management; MEDLINE; Engineering; World Wide Web","score_opus":0.6628416497360395,"score_gpt":0.6389503575125496,"score_spread":0.023891292223489957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391491066","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":[0.00062121893,0.024049193,0.964058,0.0042336197,0.0004240716,0.0019076597,0.0044714976,0.000010815315,0.00022392355],"genre_scores_gemma":[0.0071608974,0.038449157,0.9495259,0.0037363407,0.000038417245,0.00017787606,0.0008822415,0.000012220572,0.000016952154],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9938735,0.00085809885,0.00377792,0.00018214672,0.0011419706,0.00016640732],"domain_scores_gemma":[0.95839685,0.038165174,0.001579181,0.0014026801,0.00034835385,0.00010773211],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025243811,0.0001204754,0.0010023862,0.00012707649,0.00007667935,0.000049024475,0.00095901464,0.00012675565,0.000102531616],"category_scores_gemma":[0.01233276,0.000069023634,0.0001657831,0.00044434553,0.0004651925,0.00052404054,0.0009270347,0.00031748821,0.0000010430969],"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":[0.0000146724315,0.000110408655,0.000010630336,0.008031039,0.00010641738,4.4220258e-8,0.0015730078,0.000002261901,0.000004438032,0.44500703,0.07467221,0.47046787],"study_design_scores_gemma":[0.000476076,0.00023989247,0.0015697208,0.0015584995,0.0000927998,0.0000016503385,0.0070015346,0.027046021,0.000020910464,0.05831239,0.90358317,0.0000973613],"about_ca_topic_score_codex":0.00005876673,"about_ca_topic_score_gemma":0.000025863386,"teacher_disagreement_score":0.82891095,"about_ca_system_score_codex":0.000012664781,"about_ca_system_score_gemma":0.00053027825,"threshold_uncertainty_score":0.99598676},"labels":[],"label_agreement":null},{"id":"W4391725330","doi":"10.14722/ndss.2024.23014","title":"Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":21,"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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overconfidence effect; Inference; Computer security; Computer science; Artificial intelligence; Psychology; Social psychology","score_opus":0.2179136209609521,"score_gpt":0.4373605369772627,"score_spread":0.21944691601631058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391725330","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":[0.104476824,0.0012463405,0.69177127,0.008746517,0.0031216429,0.0008651743,0.00047090097,0.0009739318,0.18832742],"genre_scores_gemma":[0.97396904,0.00006242809,0.0009204963,0.0029384154,0.000117568605,0.000029010116,0.00003810622,0.0000139793765,0.021910938],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956563,0.00022018976,0.0008949094,0.0008816643,0.001963465,0.00038343968],"domain_scores_gemma":[0.99658614,0.0021633697,0.00016031269,0.0007534281,0.00016895696,0.0001677752],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0051428434,0.00021274236,0.00026769532,0.0002181508,0.00024479374,0.0025314458,0.0009582082,0.000105412415,0.0028958092],"category_scores_gemma":[0.0018298773,0.0001651054,0.0001190132,0.0007189403,0.00013083426,0.0019735186,0.0004491477,0.00030042883,0.0009035946],"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":[0.0000145659205,0.000046594567,0.0019743275,0.00015386702,0.0000919185,0.0000394718,0.0145043535,0.00016444825,0.0018490269,0.1704867,0.66954,0.14113472],"study_design_scores_gemma":[0.00046958865,0.00017679403,0.0007812589,0.00088832184,0.00010240758,0.000028814278,0.053776726,0.085559204,0.01415903,0.062312324,0.78090954,0.00083601876],"about_ca_topic_score_codex":0.0016707374,"about_ca_topic_score_gemma":0.00028083593,"teacher_disagreement_score":0.86949223,"about_ca_system_score_codex":0.00009430124,"about_ca_system_score_gemma":0.00009673211,"threshold_uncertainty_score":0.9998743},"labels":[],"label_agreement":null},{"id":"W4391826396","doi":"10.14283/jfa.2024.18","title":"Identifying Frailty in Administrative Databases: A Narrative Review","year":2024,"lang":"en","type":"review","venue":"The Journal of Frailty & Aging","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":"Université Laval","funders":"","keywords":"Narrative; Database; Computer science; Data science; Art; Literature","score_opus":0.6798674861213438,"score_gpt":0.6021681501844243,"score_spread":0.07769933593691958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391826396","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004027236,0.9920288,0.0024315414,0.0019868051,0.0010728623,0.00074233755,0.00019951965,0.000013650235,0.0015204925],"genre_scores_gemma":[0.000019150848,0.9963519,0.0004925719,0.00079982146,0.0003129588,0.000016199761,0.000031579617,0.00003061427,0.0019452116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9888756,0.0036217896,0.004063951,0.00053908175,0.0024915943,0.0004079583],"domain_scores_gemma":[0.9915744,0.0031055561,0.0034841027,0.0013663161,0.00030826175,0.00016136188],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.031018425,0.0005313602,0.0028872706,0.00083791034,0.00020680745,0.000567693,0.0036343706,0.000089785404,0.00052872644],"category_scores_gemma":[0.005239613,0.00026524928,0.00092943024,0.002459302,0.000203641,0.0012399338,0.0011717352,0.0020167395,0.00053066615],"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":[0.0000064269093,0.0000450655,4.1998769e-7,0.012458488,0.000299319,0.00031640104,0.0047489116,0.0000011433489,2.0403124e-7,0.0010030426,0.15086094,0.8302596],"study_design_scores_gemma":[0.00009614792,0.000040684452,0.000002913791,0.15182684,0.0014358133,0.0002662055,0.00462166,0.000003506069,3.7918056e-7,0.0028609317,0.8386135,0.00023141985],"about_ca_topic_score_codex":0.00006755127,"about_ca_topic_score_gemma":0.00031337215,"teacher_disagreement_score":0.83002824,"about_ca_system_score_codex":0.00023691021,"about_ca_system_score_gemma":0.0008514809,"threshold_uncertainty_score":0.99998},"labels":[],"label_agreement":null},{"id":"W4392144211","doi":"10.1007/s42081-023-00228-9","title":"Making statistical inferences about linkage errors","year":2024,"lang":"en","type":"article","venue":"Japanese Journal of Statistics and Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Linkage (software); Computer science; Statistics; Psychology; Mathematics; Biology; Genetics","score_opus":0.3100787365167909,"score_gpt":0.507185537428243,"score_spread":0.1971068009114521,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392144211","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":[0.08638734,0.00033774565,0.90705305,0.001126648,0.0010309928,0.00008980541,0.00214886,0.000017286966,0.001808249],"genre_scores_gemma":[0.90680283,0.0001438064,0.092667826,0.00021682773,0.00007213785,4.6280957e-7,0.00001598243,0.0000035646751,0.00007654348],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959859,0.00011354608,0.0008907782,0.00049147644,0.0022414832,0.00027678005],"domain_scores_gemma":[0.9959038,0.0025382743,0.00026248285,0.00065559783,0.0004066756,0.00023316866],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.014199977,0.00010875498,0.00023920024,0.0004545134,0.00030337423,0.0023197716,0.002375354,0.00002104215,0.0002795537],"category_scores_gemma":[0.010252716,0.0000671402,0.000017454255,0.0010386552,0.001037619,0.003212779,0.0010931528,0.0002016365,0.00006878788],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003007498,0.00006129793,0.0017819761,0.00005111123,0.000020422922,0.00041545398,0.002698347,0.00006015069,0.00049694354,0.6661867,0.017919919,0.31027758],"study_design_scores_gemma":[0.00054289924,0.0006304069,0.15408412,0.00036411142,0.00011262395,0.00057171704,0.016547687,0.22569469,0.00004641189,0.42798722,0.17285162,0.0005664948],"about_ca_topic_score_codex":0.000033765664,"about_ca_topic_score_gemma":0.00004304297,"teacher_disagreement_score":0.8204155,"about_ca_system_score_codex":0.000021878333,"about_ca_system_score_gemma":0.00029448065,"threshold_uncertainty_score":0.99871594},"labels":[],"label_agreement":null},{"id":"W4392869771","doi":"10.1007/978-3-031-56060-6_18","title":"LaQuE: Enabling Entity Search at Scale","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; University of Waterloo","funders":"","keywords":"Computer science; Scale (ratio); Information retrieval; Data science; Cartography","score_opus":0.11652703004926346,"score_gpt":0.38104999362034464,"score_spread":0.2645229635710812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392869771","genre_codex":"methods","genre_gemma":"other","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":[0.0005536362,0.0007515449,0.94811416,0.0024058544,0.003653604,0.0004011595,0.00006892048,0.00011256255,0.04393854],"genre_scores_gemma":[0.37284368,0.0007163431,0.17518537,0.0147904195,0.005183234,0.000041549807,0.00014657485,0.00024690817,0.43084592],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99258983,0.00007135806,0.0007804162,0.0021101495,0.003808564,0.0006396662],"domain_scores_gemma":[0.9961747,0.0013104683,0.00017057233,0.0018480502,0.0002957363,0.00020048427],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007991929,0.000374843,0.0005136773,0.0014276453,0.00038076146,0.0019628287,0.0039356267,0.00023702373,0.000820884],"category_scores_gemma":[0.0004443103,0.0002861687,0.00019093156,0.0011298978,0.0011004613,0.0005747884,0.0059561995,0.0008058933,0.0031184147],"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":[0.000015642141,0.00003495247,0.00012098653,0.00009554261,0.00001957826,0.0002012183,0.0015167774,0.01174295,0.00011710606,0.04329756,0.002439468,0.9403982],"study_design_scores_gemma":[0.00014670822,0.00008186293,0.00010479756,0.00034740832,0.000016849868,0.000025965604,0.000002627414,0.0475149,0.0011086885,0.6809699,0.2690881,0.0005922269],"about_ca_topic_score_codex":0.000084939355,"about_ca_topic_score_gemma":0.0011797321,"teacher_disagreement_score":0.939806,"about_ca_system_score_codex":0.0004327182,"about_ca_system_score_gemma":0.00026493057,"threshold_uncertainty_score":0.99995905},"labels":[],"label_agreement":null},{"id":"W4393327679","doi":"10.1016/j.knosys.2024.111678","title":"Better entity matching with transformers through ensembles","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Transformer; Computer science; Matching (statistics); Artificial intelligence; Data mining; Engineering; Mathematics; Electrical engineering; Statistics; Voltage","score_opus":0.12214234167731597,"score_gpt":0.3903886435702951,"score_spread":0.26824630189297916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393327679","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":[0.06334736,0.0037842751,0.82744515,0.002554261,0.004229384,0.0008580278,0.00018526253,0.00044979007,0.09714649],"genre_scores_gemma":[0.9917038,0.000010072858,0.0005220514,0.00028531035,0.00028709183,0.00007446808,0.000034742498,0.000029469655,0.007053004],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964525,0.00046919784,0.0007287091,0.0007605383,0.0011915665,0.00039746103],"domain_scores_gemma":[0.99795765,0.0010010063,0.00009466302,0.00067659945,0.00015979641,0.00011028814],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038725683,0.0002512492,0.00040177672,0.00030295746,0.00023535785,0.0016158512,0.0006982654,0.000085217725,0.0002661247],"category_scores_gemma":[0.00008541359,0.00016033759,0.00017524352,0.001002575,0.00012795729,0.0009036984,0.00006392358,0.0002009285,0.003230161],"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":[0.00037239966,0.00081928726,0.0015369474,0.0052291243,0.00082544546,0.00049295375,0.028197052,0.0029121211,0.0022559199,0.22649278,0.5488985,0.18196745],"study_design_scores_gemma":[0.00047525045,0.00010708392,0.0001449383,0.0006475974,0.00006737745,0.000010089489,0.0039159902,0.0049719266,0.00087639765,0.004840201,0.9835816,0.00036156195],"about_ca_topic_score_codex":0.00040789897,"about_ca_topic_score_gemma":0.0008232193,"teacher_disagreement_score":0.9283564,"about_ca_system_score_codex":0.00009789805,"about_ca_system_score_gemma":0.00017361161,"threshold_uncertainty_score":0.9994206},"labels":[],"label_agreement":null},{"id":"W4393370844","doi":"10.29173/jchla29751","title":"Review of 'Data-Driven Decisions: A Practical Toolkit for Librarians and Information Professionals'","year":2024,"lang":"en","type":"article","venue":"Journal of the Canadian Health Libraries Association / Journal de l Association de bilbiothèques de la santé du Canada","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Data science; Knowledge management; World Wide Web","score_opus":0.05294237714436072,"score_gpt":0.39841301689478775,"score_spread":0.345470639750427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393370844","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004688534,0.27329478,0.01972093,0.6885301,0.004812064,0.0016313441,0.0058317585,0.000045534445,0.0014449605],"genre_scores_gemma":[0.09945285,0.5126146,0.06830834,0.31254238,0.0041452614,0.00005053349,0.00031711353,0.00010397188,0.002464907],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917948,0.0031233435,0.0022806888,0.00018338488,0.0020086784,0.0006090728],"domain_scores_gemma":[0.9732417,0.019566182,0.0046211863,0.0003876983,0.0013611828,0.00082208664],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033451293,0.00017025956,0.00057928695,0.0004520371,0.0007117155,0.0025776424,0.0011735525,0.000253083,0.00016336828],"category_scores_gemma":[0.08960773,0.000121100995,0.0002103436,0.00084793573,0.000044654826,0.007887439,0.00019384429,0.00086864864,0.0000019704835],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000025893478,0.000021390373,0.0053008744,0.0003439061,0.00019919132,0.000015233328,0.0008260312,0.00003309313,5.2619083e-7,0.010331579,0.97336286,0.009539416],"study_design_scores_gemma":[0.00033986924,0.00006707236,0.011040888,0.0022646764,0.00010250257,0.0002568248,0.0008361252,0.0016991135,0.0000037907607,0.017403657,0.9658625,0.00012295725],"about_ca_topic_score_codex":0.026189648,"about_ca_topic_score_gemma":0.11057418,"teacher_disagreement_score":0.3759877,"about_ca_system_score_codex":0.006813618,"about_ca_system_score_gemma":0.0509969,"threshold_uncertainty_score":0.9984578},"labels":[],"label_agreement":null},{"id":"W4393476016","doi":"10.5281/zenodo.10247175","title":"StreamMapper Membership Tables for GD-1 and Pal 5","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Computer science","score_opus":0.23191240980410538,"score_gpt":0.3766317142646174,"score_spread":0.144719304460512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393476016","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028310502,0.00005937218,0.00080664345,0.0013838467,0.00031783254,0.00076678576,0.9914376,0.00030605853,0.0048935534],"genre_scores_gemma":[0.00009404046,0.0002426569,0.00012985269,0.00031230578,0.00026715558,2.1550994e-7,0.9919683,0.0007118613,0.006273665],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959245,0.0006335531,0.00061999675,0.0010089091,0.0013036452,0.00050943857],"domain_scores_gemma":[0.9970067,0.0004461719,0.0003070068,0.0013102329,0.0006778246,0.0002520732],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00591789,0.0002562724,0.00037077794,0.0006308729,0.0021052246,0.0036629087,0.0029755603,0.00016571286,0.016271602],"category_scores_gemma":[0.008811291,0.00023008318,0.000096203876,0.0008705136,0.00026716504,0.00039678047,0.0042576664,0.0003115045,0.042887345],"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":[0.00005307809,0.00006086375,1.4755555e-7,0.00015467784,0.000050488925,0.000010493056,0.00012463331,0.000007430364,0.0000067262395,0.001966853,0.9589745,0.038590137],"study_design_scores_gemma":[0.00040389522,0.00016670441,0.000027753644,0.000035404813,0.00004404012,0.000013110476,0.00088525127,0.000058830152,0.0000060823145,0.0028403746,0.99525946,0.0002590942],"about_ca_topic_score_codex":0.00017911526,"about_ca_topic_score_gemma":0.000029517572,"teacher_disagreement_score":0.038331043,"about_ca_system_score_codex":0.00007949587,"about_ca_system_score_gemma":0.0000074478758,"threshold_uncertainty_score":0.9995379},"labels":[],"label_agreement":null},{"id":"W4393482895","doi":"10.5281/zenodo.831804","title":"Replication Package For How The R Community Creates And Curates Knowledge: An Extended Study Of Stack Overflow And Mailing Lists","year":2017,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Victoria","funders":"","keywords":"Replication (statistics); Stack (abstract data type); Computer science; World Wide Web; Data science; Biology; Operating system; Virology","score_opus":0.28101975437067334,"score_gpt":0.43084575850810003,"score_spread":0.1498260041374267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393482895","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031305697,0.00021096056,0.0005758648,0.0007352486,0.00011832045,0.0023025165,0.9635799,0.00012345932,0.0010480438],"genre_scores_gemma":[0.12857033,0.0004182344,0.000084103565,0.000056263518,0.0001091754,6.624517e-7,0.86937714,0.00036162045,0.0010224833],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99562854,0.0023642802,0.00045204628,0.00069413654,0.0006260945,0.00023492805],"domain_scores_gemma":[0.9934824,0.00063327857,0.00063140277,0.004075441,0.0010444238,0.00013306212],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009978983,0.00020430762,0.00034174533,0.00025392853,0.0048543597,0.004304276,0.0035970556,0.00008915064,0.00046101783],"category_scores_gemma":[0.013826189,0.00015159066,0.00003895403,0.00026955517,0.00045468612,0.00070883916,0.004278881,0.00039959347,0.0001887875],"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":[0.00008539161,0.0005022353,0.0000037759562,0.00014781204,0.00005293401,0.0000011699119,0.002264248,8.599034e-7,0.00005746381,0.00024011196,0.9454431,0.05120091],"study_design_scores_gemma":[0.00056606473,0.00086376973,0.0020062742,0.00004104652,0.00006560373,0.000008075101,0.00926787,0.00012922654,0.000035521603,0.001026539,0.98582685,0.00016315859],"about_ca_topic_score_codex":0.0001898249,"about_ca_topic_score_gemma":0.00008687512,"teacher_disagreement_score":0.09726463,"about_ca_system_score_codex":0.00003784696,"about_ca_system_score_gemma":0.0000062863573,"threshold_uncertainty_score":0.9967294},"labels":[],"label_agreement":null},{"id":"W4393496653","doi":"10.5281/zenodo.1303406","title":"Assisting The Appraisal Of E-Mail Records With Automatic Classification","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Ottawa","funders":"","keywords":"Computer science; Data mining","score_opus":0.18887021048498925,"score_gpt":0.38195591701409737,"score_spread":0.19308570652910811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393496653","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019100054,0.000020577532,0.004666516,0.0013356495,0.0003726913,0.00065398467,0.96493757,0.00025661828,0.027565422],"genre_scores_gemma":[0.0020481464,0.000050560633,0.0004611063,0.00016016998,0.00026042465,1.4949705e-7,0.99577653,0.00045849898,0.0007844191],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946822,0.0015213704,0.00080910564,0.00068987656,0.0019820887,0.0003153788],"domain_scores_gemma":[0.9946821,0.00067735894,0.0009755393,0.0021915874,0.0013586051,0.000114861425],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008018317,0.00020936602,0.00031955144,0.00041227488,0.0019581104,0.0018505048,0.0046269195,0.00011001163,0.019316163],"category_scores_gemma":[0.014634158,0.00013663025,0.00007403794,0.0013276034,0.00064568187,0.00034450408,0.002439675,0.0003751765,0.010558142],"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":[0.000032443026,0.00009331221,5.44471e-7,0.00007901613,0.000050975774,0.0000027843266,0.00016006401,0.00000393065,0.000012060864,0.0006430114,0.93000364,0.06891821],"study_design_scores_gemma":[0.0002036702,0.00027003558,0.0004480058,0.00007887427,0.00005234073,0.000024329422,0.00066717516,0.0004923973,0.000008211544,0.00025947805,0.9973286,0.00016687554],"about_ca_topic_score_codex":0.00008163708,"about_ca_topic_score_gemma":0.000011374293,"teacher_disagreement_score":0.068751335,"about_ca_system_score_codex":0.0000866216,"about_ca_system_score_gemma":0.000014549052,"threshold_uncertainty_score":0.9993412},"labels":[],"label_agreement":null},{"id":"W4393520745","doi":"10.5281/zenodo.8200678","title":"OpenAlex Author Name Disambiguation V3 Data - Disambiguation Model","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"OpenAlex","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.4820321125774946,"score_gpt":0.44476936927281047,"score_spread":0.037262743304684154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393520745","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023943327,0.000038268092,0.025614874,0.0030064175,0.00054834154,0.0009727594,0.9650159,0.000954895,0.0038246298],"genre_scores_gemma":[0.00019209701,0.00025395743,0.00030704442,0.00035559712,0.00032130335,2.5613556e-7,0.98984313,0.0012821838,0.0074444236],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910929,0.0015450201,0.001250993,0.0019639437,0.0035060507,0.0006410451],"domain_scores_gemma":[0.9921137,0.00029331492,0.00074533484,0.005480812,0.0010380527,0.0003287761],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012755338,0.00039801703,0.000502179,0.0009634974,0.0030157624,0.006330061,0.012345995,0.00025488544,0.009475511],"category_scores_gemma":[0.01873715,0.000377501,0.00011641444,0.00190382,0.00030019684,0.0018485244,0.017571859,0.00067267905,0.21686445],"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":[0.000047340283,0.0001652099,6.57782e-8,0.00007767517,0.0000609928,0.000013198786,0.00017709905,0.00073299167,0.000011151515,0.0010986726,0.920554,0.07706162],"study_design_scores_gemma":[0.0003631945,0.00009696136,0.000058327052,0.00006346629,0.00007802695,0.000011237628,0.00041375557,0.026745414,0.0000024115361,0.003454411,0.9682992,0.00041358988],"about_ca_topic_score_codex":0.0002941412,"about_ca_topic_score_gemma":0.000030378065,"teacher_disagreement_score":0.20738895,"about_ca_system_score_codex":0.0002607848,"about_ca_system_score_gemma":0.000024759038,"threshold_uncertainty_score":0.9998677},"labels":[],"label_agreement":null},{"id":"W4393556446","doi":"10.5281/zenodo.1303407","title":"Assisting The Appraisal Of E-Mail Records With Automatic Classification","year":2018,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Ottawa","funders":"","keywords":"Computer science; Data mining; Information retrieval","score_opus":0.18887021048498925,"score_gpt":0.38195591701409737,"score_spread":0.19308570652910811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393556446","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019100054,0.000020577532,0.004666516,0.0013356495,0.0003726913,0.00065398467,0.96493757,0.00025661828,0.027565422],"genre_scores_gemma":[0.0020481464,0.000050560633,0.0004611063,0.00016016998,0.00026042465,1.4949705e-7,0.99577653,0.00045849898,0.0007844191],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946822,0.0015213704,0.00080910564,0.00068987656,0.0019820887,0.0003153788],"domain_scores_gemma":[0.9946821,0.00067735894,0.0009755393,0.0021915874,0.0013586051,0.000114861425],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008018317,0.00020936602,0.00031955144,0.00041227488,0.0019581104,0.0018505048,0.0046269195,0.00011001163,0.019316163],"category_scores_gemma":[0.014634158,0.00013663025,0.00007403794,0.0013276034,0.00064568187,0.00034450408,0.002439675,0.0003751765,0.010558142],"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":[0.000032443026,0.00009331221,5.44471e-7,0.00007901613,0.000050975774,0.0000027843266,0.00016006401,0.00000393065,0.000012060864,0.0006430114,0.93000364,0.06891821],"study_design_scores_gemma":[0.0002036702,0.00027003558,0.0004480058,0.00007887427,0.00005234073,0.000024329422,0.00066717516,0.0004923973,0.000008211544,0.00025947805,0.9973286,0.00016687554],"about_ca_topic_score_codex":0.00008163708,"about_ca_topic_score_gemma":0.000011374293,"teacher_disagreement_score":0.068751335,"about_ca_system_score_codex":0.0000866216,"about_ca_system_score_gemma":0.000014549052,"threshold_uncertainty_score":0.9993412},"labels":[],"label_agreement":null},{"id":"W4393677160","doi":"10.5281/zenodo.1324412","title":"Dataset for: Exploring the experiences of academic libraries with research data management: a meta-ethnographic analysis of qualitative studies","year":2018,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Carleton University; University of Toronto","funders":"","keywords":"Ethnography; Qualitative research; Meta-analysis; Qualitative property; Data management; Qualitative analysis; Sociology; Data science; Library science; World Wide Web; Computer science; Database; Social science; Medicine; Anthropology","score_opus":0.9542500389912101,"score_gpt":0.654501081881029,"score_spread":0.2997489571101811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393677160","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002740742,0.0037260226,0.000014347099,0.00017993251,0.000094076284,0.0010504582,0.99487716,0.000008637927,0.000021976999],"genre_scores_gemma":[0.0000665872,0.0007590472,0.00041204874,0.00011439463,0.00005897135,0.0034870605,0.9949799,0.000012458368,0.00010951788],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98973155,0.0023593146,0.0016159718,0.0015272354,0.0042624525,0.00050348707],"domain_scores_gemma":[0.970875,0.018819414,0.0016768725,0.00736727,0.0011689893,0.00009242682],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.016329147,0.00040424927,0.0017087989,0.00262742,0.00049349654,0.00035413314,0.013401414,0.00013446606,0.018769765],"category_scores_gemma":[0.021087954,0.00020855764,0.00032683453,0.0079976,0.0010292191,0.0021984354,0.010409585,0.00050886406,0.00012313577],"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":[0.00009545782,0.00004529068,2.607892e-7,0.0007926881,0.019320503,0.0000039181887,0.027546184,0.000007688485,3.165071e-8,0.00012402849,0.95177865,0.00028528526],"study_design_scores_gemma":[0.00009876818,0.0001255667,0.000006295977,0.0004921269,0.0046242643,1.3472828e-7,0.27568415,0.000020077454,0.000011793639,0.0009516109,0.7178099,0.00017530896],"about_ca_topic_score_codex":0.00008202856,"about_ca_topic_score_gemma":0.0008342656,"teacher_disagreement_score":0.24813795,"about_ca_system_score_codex":0.000015680573,"about_ca_system_score_gemma":0.00009189722,"threshold_uncertainty_score":0.99759406},"labels":[],"label_agreement":null},{"id":"W4393689549","doi":"10.5281/zenodo.8189450","title":"OpenAlex Authors and Affiliations, V2","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"OpenAlex","funders":"","keywords":"Geology","score_opus":0.22124788760444838,"score_gpt":0.3903120854090305,"score_spread":0.16906419780458212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393689549","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029389717,0.00006292353,0.00056773506,0.0024047592,0.00041291522,0.00054707733,0.98678994,0.00045908013,0.008726179],"genre_scores_gemma":[0.00004939324,0.00055224996,0.00009435948,0.00035019364,0.00017628541,8.248345e-8,0.9883012,0.00063339213,0.009842823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951215,0.0011265661,0.00067743525,0.0009872075,0.0016738962,0.00041341805],"domain_scores_gemma":[0.9969021,0.00026065746,0.0003459271,0.0015613154,0.00064736325,0.00028262098],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007100963,0.00023266941,0.00032736597,0.0008825361,0.0025605308,0.004735184,0.003752851,0.00016016644,0.016965985],"category_scores_gemma":[0.010855178,0.00021490213,0.00007525585,0.0014887138,0.00025798992,0.0004888399,0.0072344225,0.000470555,0.17666525],"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":[0.000017468255,0.000057700086,1.034163e-7,0.00005319847,0.000038789956,0.000020974914,0.00012007938,0.000009897542,0.000004404638,0.0014221098,0.95534545,0.042909797],"study_design_scores_gemma":[0.00022739655,0.00009725394,0.00015017012,0.000036258833,0.000029697301,0.000020789736,0.00055570464,0.00006501376,0.000001943739,0.0013787997,0.99719936,0.00023762292],"about_ca_topic_score_codex":0.0001362992,"about_ca_topic_score_gemma":0.000010419058,"teacher_disagreement_score":0.15969926,"about_ca_system_score_codex":0.000096450356,"about_ca_system_score_gemma":0.0000072754506,"threshold_uncertainty_score":0.998738},"labels":[],"label_agreement":null},{"id":"W4393717180","doi":"10.5281/zenodo.7555363","title":"A dataset from a survey investigating disciplinary differences in data citation","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Ottawa; Université de Montréal","funders":"","keywords":"Citation; Discipline; Data science; Information retrieval; Computer science; Library science; Sociology; Social science","score_opus":0.5749845184576483,"score_gpt":0.43616563722372576,"score_spread":0.13881888123392255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393717180","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006657566,0.000035560057,0.00040955297,0.0008546799,0.00032866377,0.00050078286,0.9967476,0.00018160176,0.00027578365],"genre_scores_gemma":[0.0004251965,0.00015927143,0.0001244292,0.00019659444,0.00014904367,1.1847812e-7,0.9982652,0.00044963506,0.00023049832],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99092543,0.00373293,0.00107541,0.0016872478,0.0021106245,0.0004683846],"domain_scores_gemma":[0.99335057,0.001420372,0.0005893459,0.004023308,0.0003840479,0.0002323806],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.013898496,0.00029286003,0.00048109976,0.0010149234,0.0014983584,0.004135063,0.010967996,0.0001628795,0.0056337286],"category_scores_gemma":[0.03510141,0.0002685714,0.000037851252,0.0026221797,0.00033040694,0.0011111777,0.022393038,0.0006504412,0.061783653],"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":[0.00003166454,0.00011220017,0.000014796989,0.00004475355,0.00003798103,0.000031784308,0.00024540976,0.000008841506,0.000004880675,0.000039607334,0.9890459,0.010382169],"study_design_scores_gemma":[0.00029930173,0.00006455775,0.013502832,0.00011503025,0.000021534845,0.0000030454128,0.00084588217,0.0007177711,4.3809433e-7,0.0020465879,0.982086,0.00029700444],"about_ca_topic_score_codex":0.004757983,"about_ca_topic_score_gemma":0.0012049282,"teacher_disagreement_score":0.056149922,"about_ca_system_score_codex":0.00011253672,"about_ca_system_score_gemma":0.00001624947,"threshold_uncertainty_score":0.99997663},"labels":[],"label_agreement":null},{"id":"W4393735424","doi":"10.5281/zenodo.8189449","title":"OpenAlex Authors and Affiliations, V2","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"OpenAlex","funders":"","keywords":"Geography; Geology","score_opus":0.22124788760444838,"score_gpt":0.3903120854090305,"score_spread":0.16906419780458212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393735424","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000029389717,0.00006292353,0.00056773506,0.0024047592,0.00041291522,0.00054707733,0.98678994,0.00045908013,0.008726179],"genre_scores_gemma":[0.00004939324,0.00055224996,0.00009435948,0.00035019364,0.00017628541,8.248345e-8,0.9883012,0.00063339213,0.009842823],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951215,0.0011265661,0.00067743525,0.0009872075,0.0016738962,0.00041341805],"domain_scores_gemma":[0.9969021,0.00026065746,0.0003459271,0.0015613154,0.00064736325,0.00028262098],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007100963,0.00023266941,0.00032736597,0.0008825361,0.0025605308,0.004735184,0.003752851,0.00016016644,0.016965985],"category_scores_gemma":[0.010855178,0.00021490213,0.00007525585,0.0014887138,0.00025798992,0.0004888399,0.0072344225,0.000470555,0.17666525],"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":[0.000017468255,0.000057700086,1.034163e-7,0.00005319847,0.000038789956,0.000020974914,0.00012007938,0.000009897542,0.000004404638,0.0014221098,0.95534545,0.042909797],"study_design_scores_gemma":[0.00022739655,0.00009725394,0.00015017012,0.000036258833,0.000029697301,0.000020789736,0.00055570464,0.00006501376,0.000001943739,0.0013787997,0.99719936,0.00023762292],"about_ca_topic_score_codex":0.0001362992,"about_ca_topic_score_gemma":0.000010419058,"teacher_disagreement_score":0.15969926,"about_ca_system_score_codex":0.000096450356,"about_ca_system_score_gemma":0.0000072754506,"threshold_uncertainty_score":0.998738},"labels":[],"label_agreement":null},{"id":"W4393777015","doi":"10.5281/zenodo.4096182","title":"Data Literacies &amp; Practices in Higher Education: Educators' Perspectives","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Windsor","funders":"","keywords":"Mathematics education; Sociology; Pedagogy; Computer science; Psychology","score_opus":0.43746757453122126,"score_gpt":0.4565183782044062,"score_spread":0.019050803673184957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393777015","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023492683,0.00053064886,0.00004849998,0.016143799,0.0007951695,0.00052494276,0.95311266,0.00018718146,0.028633606],"genre_scores_gemma":[0.00023431348,0.0006231795,0.00027175422,0.0010565304,0.0008127008,1.3818617e-7,0.98870754,0.00042607513,0.00786776],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99383,0.001736564,0.00078050274,0.0016190129,0.0016490929,0.00038478622],"domain_scores_gemma":[0.9938201,0.0003376365,0.000982972,0.0037340014,0.0008571044,0.00026823874],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.004422871,0.00028554662,0.00038312955,0.0008569341,0.0011926368,0.0060985214,0.0097429305,0.0001389192,0.09105148],"category_scores_gemma":[0.019267837,0.00026876808,0.000062808576,0.001984201,0.000271131,0.0018878527,0.010802212,0.0007582061,0.08800107],"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":[0.00004529742,0.0004994422,5.3468034e-7,0.00009592233,0.000042266962,0.000009295913,0.0013508508,0.0000016168266,0.0000035075116,0.0025029434,0.9754202,0.020028159],"study_design_scores_gemma":[0.00016051126,0.00006256518,0.00017062397,0.00006047451,0.000032288925,0.00002013608,0.0050866297,0.0000045246197,4.3188854e-7,0.0009150972,0.99319834,0.0002883811],"about_ca_topic_score_codex":0.0001559641,"about_ca_topic_score_gemma":0.000019111487,"teacher_disagreement_score":0.035594888,"about_ca_system_score_codex":0.00020187629,"about_ca_system_score_gemma":0.000055001063,"threshold_uncertainty_score":0.99997646},"labels":[],"label_agreement":null},{"id":"W4393829228","doi":"10.5281/zenodo.8200679","title":"OpenAlex Author Name Disambiguation V3 Data - Disambiguation Model","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"OpenAlex","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Information retrieval; Linguistics; Philosophy","score_opus":0.4820321125774946,"score_gpt":0.44476936927281047,"score_spread":0.037262743304684154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393829228","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023943327,0.000038268092,0.025614874,0.0030064175,0.00054834154,0.0009727594,0.9650159,0.000954895,0.0038246298],"genre_scores_gemma":[0.00019209701,0.00025395743,0.00030704442,0.00035559712,0.00032130335,2.5613556e-7,0.98984313,0.0012821838,0.0074444236],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910929,0.0015450201,0.001250993,0.0019639437,0.0035060507,0.0006410451],"domain_scores_gemma":[0.9921137,0.00029331492,0.00074533484,0.005480812,0.0010380527,0.0003287761],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012755338,0.00039801703,0.000502179,0.0009634974,0.0030157624,0.006330061,0.012345995,0.00025488544,0.009475511],"category_scores_gemma":[0.01873715,0.000377501,0.00011641444,0.00190382,0.00030019684,0.0018485244,0.017571859,0.00067267905,0.21686445],"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":[0.000047340283,0.0001652099,6.57782e-8,0.00007767517,0.0000609928,0.000013198786,0.00017709905,0.00073299167,0.000011151515,0.0010986726,0.920554,0.07706162],"study_design_scores_gemma":[0.0003631945,0.00009696136,0.000058327052,0.00006346629,0.00007802695,0.000011237628,0.00041375557,0.026745414,0.0000024115361,0.003454411,0.9682992,0.00041358988],"about_ca_topic_score_codex":0.0002941412,"about_ca_topic_score_gemma":0.000030378065,"teacher_disagreement_score":0.20738895,"about_ca_system_score_codex":0.0002607848,"about_ca_system_score_gemma":0.000024759038,"threshold_uncertainty_score":0.9998677},"labels":[],"label_agreement":null},{"id":"W4394049725","doi":"10.5281/zenodo.4096183","title":"Data Literacies &amp; Practices in Higher Education: Educators' Perspectives","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Windsor","funders":"","keywords":"Sociology; Mathematics education; Pedagogy; Psychology","score_opus":0.43746757453122126,"score_gpt":0.4565183782044062,"score_spread":0.019050803673184957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394049725","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023492683,0.00053064886,0.00004849998,0.016143799,0.0007951695,0.00052494276,0.95311266,0.00018718146,0.028633606],"genre_scores_gemma":[0.00023431348,0.0006231795,0.00027175422,0.0010565304,0.0008127008,1.3818617e-7,0.98870754,0.00042607513,0.00786776],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99383,0.001736564,0.00078050274,0.0016190129,0.0016490929,0.00038478622],"domain_scores_gemma":[0.9938201,0.0003376365,0.000982972,0.0037340014,0.0008571044,0.00026823874],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.004422871,0.00028554662,0.00038312955,0.0008569341,0.0011926368,0.0060985214,0.0097429305,0.0001389192,0.09105148],"category_scores_gemma":[0.019267837,0.00026876808,0.000062808576,0.001984201,0.000271131,0.0018878527,0.010802212,0.0007582061,0.08800107],"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":[0.00004529742,0.0004994422,5.3468034e-7,0.00009592233,0.000042266962,0.000009295913,0.0013508508,0.0000016168266,0.0000035075116,0.0025029434,0.9754202,0.020028159],"study_design_scores_gemma":[0.00016051126,0.00006256518,0.00017062397,0.00006047451,0.000032288925,0.00002013608,0.0050866297,0.0000045246197,4.3188854e-7,0.0009150972,0.99319834,0.0002883811],"about_ca_topic_score_codex":0.0001559641,"about_ca_topic_score_gemma":0.000019111487,"teacher_disagreement_score":0.035594888,"about_ca_system_score_codex":0.00020187629,"about_ca_system_score_gemma":0.000055001063,"threshold_uncertainty_score":0.99997646},"labels":[],"label_agreement":null},{"id":"W4394081635","doi":"10.6084/m9.figshare.23878644","title":"Data Canada Study 1","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.65019135127114,"score_gpt":0.5022475106843322,"score_spread":0.14794384058680787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394081635","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.217003e-8,0.000029609011,6.3324045e-8,0.00026142842,0.0007591146,0.00052784604,0.9980947,0.000033569933,0.0002936092],"genre_scores_gemma":[5.4076844e-7,0.0000028726106,0.0000020209707,0.0008337623,0.000248839,0.000100526486,0.99249583,0.000011862438,0.006303717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942738,0.00028641097,0.0006632808,0.0012069587,0.0032657809,0.00030376896],"domain_scores_gemma":[0.9897521,0.0018249775,0.0003722911,0.007752579,0.00015811104,0.00013991246],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0014435046,0.00023600341,0.00040184267,0.00019280783,0.00014841076,0.000689716,0.011694452,0.00009216447,0.44462836],"category_scores_gemma":[0.035396405,0.00018577091,0.000037070036,0.00082617626,0.0000042896886,0.000302866,0.011019504,0.00031250378,0.25749663],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015161388,0.00004713888,3.1004996e-7,0.00004304425,0.00003851249,0.00031355728,0.0000037987127,0.000001819012,6.231259e-10,1.9204478e-7,0.99780595,0.001744133],"study_design_scores_gemma":[0.000087834065,0.00002035719,0.0003667769,0.0001603213,0.00002116759,6.0110955e-7,0.0004963129,0.000014695175,1.6414498e-8,0.0000280683,0.99857944,0.0002244177],"about_ca_topic_score_codex":0.4878124,"about_ca_topic_score_gemma":0.99009794,"teacher_disagreement_score":0.50228554,"about_ca_system_score_codex":0.000070684626,"about_ca_system_score_gemma":0.0008510284,"threshold_uncertainty_score":0.9969792},"labels":[],"label_agreement":null},{"id":"W4394433341","doi":"10.6084/m9.figshare.13229081","title":"DATA Cognition and Social Information Use Morinay et al. 2020 FrontiersEcoEvol","year":2020,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Uppsala Universitet; Université de Lyon; Ministère de l'Enseignement Supérieur et de la Recherche; Agence Nationale de la Recherche","keywords":"Cognition; Psychology; Cognitive psychology; Cognitive science; Computer science; Data science; Neuroscience","score_opus":0.410437204575108,"score_gpt":0.43221580861264414,"score_spread":0.02177860403753612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394433341","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.6975773e-7,0.00001903232,0.00003940926,0.0038283342,0.0002350819,0.00040570265,0.9952654,0.000032626478,0.00017424069],"genre_scores_gemma":[0.0000021480587,0.00005647055,0.00008642835,0.026072506,0.0001306699,0.000059127196,0.9734917,0.000006132683,0.00009477108],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99703777,0.00023660943,0.0006238528,0.0005982109,0.0013145916,0.0001889658],"domain_scores_gemma":[0.9975213,0.00048475628,0.00059033744,0.0010952066,0.00020801829,0.00010038514],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007224815,0.00022738687,0.0003345824,0.00016225169,0.00018104029,0.0020963817,0.0018333037,0.00016754813,0.08621724],"category_scores_gemma":[0.01185502,0.00020555245,0.00005400302,0.00028440513,0.000016946382,0.005450313,0.0035657936,0.00037905652,0.037881456],"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":[0.00001703684,0.000014431759,2.0372701e-7,0.00013219025,0.000030182899,0.000011777402,0.0000637092,4.3524815e-7,2.801095e-8,0.000004373953,0.9953539,0.004371777],"study_design_scores_gemma":[0.0002435197,0.000023359104,0.00015548787,0.00015581917,0.00003804188,0.0000019727024,0.00026434258,0.00015083559,2.510664e-7,0.0001167988,0.9986066,0.00024292248],"about_ca_topic_score_codex":0.000040443625,"about_ca_topic_score_gemma":0.00018941757,"teacher_disagreement_score":0.048335787,"about_ca_system_score_codex":0.000020139456,"about_ca_system_score_gemma":0.000080305,"threshold_uncertainty_score":0.9989395},"labels":[],"label_agreement":null},{"id":"W4394936107","doi":"10.5465/amj.2024.4002","title":"Mobilizing New Sources of Data: Opportunities and Recommendations","year":2024,"lang":"en","type":"article","venue":"Academy of Management Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Business; Data science; Environmental science; Computer science","score_opus":0.5236404761192961,"score_gpt":0.4822428565995527,"score_spread":0.04139761951974341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394936107","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":[0.06686721,0.040148173,0.18773228,0.5596981,0.0030741484,0.0015252129,0.00083102204,0.00023934987,0.13988447],"genre_scores_gemma":[0.73157525,0.0992972,0.074054755,0.0045494945,0.001096952,0.000010814647,0.00009014101,0.00006295352,0.089262426],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975132,0.00016958412,0.0009344927,0.00031054157,0.0009129111,0.0001592863],"domain_scores_gemma":[0.99866074,0.00055067736,0.00033093567,0.00031065583,0.00002991903,0.000117067495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007299729,0.0001003426,0.00022712693,0.0006264853,0.00011794299,0.00038270737,0.001375244,0.00003793576,0.000616682],"category_scores_gemma":[0.00016565944,0.00007681269,0.000058167818,0.00036019564,0.00012823695,0.0018059934,0.0013177715,0.00021428351,0.000019448527],"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":[0.000006269654,0.000017672826,0.00006187739,0.000068144465,0.00013932587,0.000007615586,0.00033767536,0.000013007789,0.000008142208,0.14038216,0.29289925,0.5660589],"study_design_scores_gemma":[0.00015449351,0.000024402449,0.0007968556,0.00018739616,0.00009704516,0.000020909267,0.009107011,0.0004960293,0.000042668526,0.11875021,0.870246,0.000076958684],"about_ca_topic_score_codex":0.000011970402,"about_ca_topic_score_gemma":0.0000024284604,"teacher_disagreement_score":0.6647081,"about_ca_system_score_codex":0.000011001121,"about_ca_system_score_gemma":0.000026796664,"threshold_uncertainty_score":0.6752235},"labels":[],"label_agreement":null},{"id":"W4395098146","doi":"10.1007/978-981-97-2242-6_16","title":"Class Ratio and Its Implications for Reproducibility and Performance in Record Linkage","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Record linkage; Pairwise comparison; Matching (statistics); Linkage (software); Classifier (UML); Data mining; Class (philosophy); Test data; Artificial intelligence; Information retrieval; Statistics; Mathematics","score_opus":0.13093958025310867,"score_gpt":0.3785712184593527,"score_spread":0.24763163820624404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395098146","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":[0.009416672,0.0014204747,0.96842283,0.013688763,0.0013976243,0.0015596537,0.00012247497,0.000058044472,0.0039134556],"genre_scores_gemma":[0.94110936,0.00064335513,0.04853477,0.0025593268,0.0004879239,0.000091851674,0.000026443613,0.000032511864,0.006514464],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958366,0.000033817018,0.00070118293,0.0026534186,0.00049543014,0.00027954503],"domain_scores_gemma":[0.99644035,0.0013816879,0.0001762374,0.0017235597,0.00019572461,0.00008242594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008950124,0.00022648668,0.00036276254,0.00062633515,0.00017895584,0.00067468523,0.0010162641,0.00014331254,0.000011612045],"category_scores_gemma":[0.0016957511,0.00017958898,0.000043324257,0.0005233794,0.0004194511,0.0005282181,0.0011417377,0.00036144062,0.000019445053],"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":[0.000012541578,0.000014234667,0.0009805091,0.00011919058,0.0000039085376,0.0000022190852,0.00052173383,0.00058807945,0.000028315608,0.050527994,0.00012269255,0.9470786],"study_design_scores_gemma":[0.00018006768,0.00017026383,0.013582823,0.00023887049,0.000010483732,0.0000098529445,0.0000014411338,0.15819483,0.00012449543,0.7849451,0.042188007,0.0003538075],"about_ca_topic_score_codex":0.000009753757,"about_ca_topic_score_gemma":0.00045660997,"teacher_disagreement_score":0.9467248,"about_ca_system_score_codex":0.0000896132,"about_ca_system_score_gemma":0.00013646422,"threshold_uncertainty_score":0.73234266},"labels":[],"label_agreement":null},{"id":"W4396561978","doi":"10.1201/9781003258254","title":"The Data Preparation Journey","year":2024,"lang":"en","type":"book","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Victoria","funders":"","keywords":"Computer science","score_opus":0.5389770882399062,"score_gpt":0.532252402529568,"score_spread":0.006724685710338241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396561978","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.9246704e-8,0.0009631841,0.005099757,0.0066721584,0.0017988334,0.00022576234,0.00037287397,0.000054299868,0.98481303],"genre_scores_gemma":[0.000005504704,0.00034787343,0.00016334288,0.0007192714,0.00040062328,0.0000046207415,0.00069003477,0.00000933352,0.9976594],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99670225,0.00013362538,0.00063148886,0.00067553914,0.0017238249,0.00013324506],"domain_scores_gemma":[0.9940223,0.0014719571,0.00018928564,0.004175047,0.00009347648,0.000047929385],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010563991,0.00012316435,0.00016290163,0.00010218575,0.00020714925,0.0030522791,0.004897568,0.00008776051,0.0013116879],"category_scores_gemma":[0.0015960303,0.000056627894,0.000063532854,0.00012763782,0.00008781885,0.0004825197,0.003434786,0.00022231929,0.025218183],"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":[0.0000027374467,0.0000021499293,2.7867424e-8,0.000003515473,0.000021973075,0.0000023808714,0.000030350115,8.081486e-7,2.6977666e-8,0.25837833,0.70298654,0.038571186],"study_design_scores_gemma":[0.00001274583,0.000008165375,7.516177e-7,0.000012050624,0.000020891755,9.0900335e-7,0.00008255696,0.00060106756,2.2602786e-7,0.35001373,0.6491922,0.000054690907],"about_ca_topic_score_codex":0.000012072655,"about_ca_topic_score_gemma":0.00072603906,"teacher_disagreement_score":0.0916354,"about_ca_system_score_codex":0.000040244962,"about_ca_system_score_gemma":0.00038540596,"threshold_uncertainty_score":0.99960124},"labels":[],"label_agreement":null},{"id":"W4396577082","doi":"10.61737/gdbg7853","title":"Définitions et usages de l’IA en santé - Fiche 1","year":2022,"lang":"fr","type":"report","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Humanities; Art","score_opus":0.37945299070058497,"score_gpt":0.5254114740594544,"score_spread":0.14595848335886946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396577082","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004334447,0.0015306312,0.036108438,0.015787648,0.0035655294,0.0005341873,0.0030375554,0.00013280427,0.9388698],"genre_scores_gemma":[0.0027584017,0.01719729,0.009885385,0.006959237,0.0004853495,0.00021338733,0.0016210547,0.000041171475,0.96083874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99005497,0.0028476664,0.0015234849,0.0012080497,0.003659769,0.00070605206],"domain_scores_gemma":[0.9901171,0.0068620266,0.000605162,0.0018835907,0.00024113007,0.00029101464],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.025660811,0.00043032854,0.0007264854,0.0005658339,0.00071830396,0.0009760014,0.0024831467,0.00030841253,0.2745391],"category_scores_gemma":[0.008295943,0.0003725776,0.00047177103,0.0010733457,0.00027942928,0.0006439109,0.0029771675,0.0010481927,0.004120528],"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":[0.0000065395034,0.0003001786,0.0003162621,0.00007953826,0.00014436812,0.00025306013,0.0014719202,0.00019322195,0.000007968796,0.124587394,0.73486525,0.13777429],"study_design_scores_gemma":[0.00014861189,0.00009526742,0.004165013,0.00005666474,0.00017304772,0.000094856514,0.0104684485,0.00014042738,0.000012987887,0.0387333,0.945458,0.00045336716],"about_ca_topic_score_codex":0.0032085131,"about_ca_topic_score_gemma":0.0028045813,"teacher_disagreement_score":0.27041858,"about_ca_system_score_codex":0.0005195751,"about_ca_system_score_gemma":0.001995419,"threshold_uncertainty_score":0.9998726},"labels":[],"label_agreement":null},{"id":"W4396767755","doi":"10.23977/acss.2024.080307","title":"Research on an Automatic Table Generation Model Based on Entity Attribute Relations","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Table (database); Computer science; Natural language processing; Information retrieval; Data mining; Artificial intelligence","score_opus":0.3452929619656378,"score_gpt":0.4932424078717301,"score_spread":0.14794944590609233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396767755","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":[0.030733442,0.0013432871,0.9646167,0.00048004967,0.0010490273,0.0004062867,0.00007481078,0.00006322393,0.001233153],"genre_scores_gemma":[0.9960039,0.00006235672,0.0027140614,0.00018955515,0.00021041518,0.000056116984,0.000043320382,0.0000072941443,0.00071297697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99651045,0.000905544,0.00053913525,0.0006028154,0.0012195249,0.00022252934],"domain_scores_gemma":[0.9977656,0.0014457582,0.00006339978,0.0005170874,0.00013179421,0.000076367156],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008969428,0.00010650813,0.00021094609,0.000538733,0.00023297139,0.0013018677,0.00035641968,0.00005090684,0.000032080145],"category_scores_gemma":[0.00010477629,0.00007919473,0.0000296729,0.0008267593,0.000049818285,0.0012306327,0.00009504512,0.00018081898,0.00013535155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040051013,0.00007059055,0.00009919837,0.000047174068,0.0000036377642,0.000008337101,0.00015087008,0.90586936,0.000015126073,0.041583635,0.0095857475,0.042562313],"study_design_scores_gemma":[0.000121515965,0.0001944656,0.000091676666,0.00021585604,0.00000232118,6.6381665e-7,0.00009896804,0.9725469,0.000013435911,0.008466338,0.018155573,0.00009229065],"about_ca_topic_score_codex":0.000043080658,"about_ca_topic_score_gemma":0.00010179039,"teacher_disagreement_score":0.96527046,"about_ca_system_score_codex":0.000064897955,"about_ca_system_score_gemma":0.000053728632,"threshold_uncertainty_score":0.9997349},"labels":[],"label_agreement":null},{"id":"W4398141288","doi":"10.23889/ijpds.v9i1.2378","title":"Semantically Interoperable Census Data: Unlocking the Semantics of Census Data Using Ontologies and Linked Data","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Tata Consultancy Services","keywords":"Census; Computer science; Ontology; Data science; Population; Data mining; American Community Survey; Interoperability; Geography; Information retrieval; World Wide Web","score_opus":0.68581780609668,"score_gpt":0.5772460683615351,"score_spread":0.10857173773514484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398141288","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":[0.1397323,0.001543058,0.70231,0.041516487,0.02148393,0.0010313794,0.09192959,0.00011821622,0.00033502743],"genre_scores_gemma":[0.9446987,0.00037848353,0.044696,0.00032690237,0.00052912114,8.0089313e-7,0.009200721,0.000014626903,0.00015467065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945123,0.00016573095,0.0011535437,0.0012747971,0.0025988885,0.00029473737],"domain_scores_gemma":[0.99172205,0.0014640013,0.00050345884,0.0055886335,0.0006184864,0.00010339878],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.019227069,0.00015258131,0.00023842577,0.0003744753,0.0005647307,0.0038436665,0.024864037,0.00004382437,0.000038437054],"category_scores_gemma":[0.016471587,0.00009560419,0.00002523013,0.0007080874,0.0005843548,0.0115946205,0.026887704,0.00026721685,0.000008503472],"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":[0.00031153933,0.00031455402,0.01938727,0.00015512871,0.0006500749,0.00016952514,0.00083176576,0.005452796,0.0022810404,0.09968516,0.2818421,0.58891904],"study_design_scores_gemma":[0.00016658942,0.000017644492,0.004377576,0.00015257963,0.000066539906,0.00014795236,0.00058980857,0.7979875,0.000010441829,0.006960326,0.18940373,0.00011927742],"about_ca_topic_score_codex":0.00064141833,"about_ca_topic_score_gemma":0.0006273429,"teacher_disagreement_score":0.8049664,"about_ca_system_score_codex":0.00006463717,"about_ca_system_score_gemma":0.00020461692,"threshold_uncertainty_score":0.9971904},"labels":[],"label_agreement":null},{"id":"W4398180243","doi":"10.1007/s00778-024-00847-y","title":"Discovering approximate implicit domain orders through order dependencies","year":2024,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; York University; University of Waterloo","funders":"","keywords":"Computer science; Domain (mathematical analysis); Order (exchange); Data mining; Theoretical computer science; Mathematics; Business","score_opus":0.13203993517966403,"score_gpt":0.4151772800383418,"score_spread":0.2831373448586778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398180243","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":[0.1957649,0.001721779,0.73569643,0.039669383,0.0028108952,0.00027293627,0.00004807636,0.00012198453,0.023893626],"genre_scores_gemma":[0.98553294,0.00045236447,0.006881802,0.0019590356,0.0006289249,0.000008130974,0.000003658604,0.000029731524,0.0045033926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99711156,0.00027820293,0.0005554371,0.00029852337,0.0013867844,0.00036948247],"domain_scores_gemma":[0.9985407,0.0005980427,0.00013165879,0.0005670225,0.000089540525,0.00007304237],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006603232,0.00014613965,0.0001906151,0.00013586483,0.0005182965,0.0028831125,0.0014306657,0.000035328525,0.001002899],"category_scores_gemma":[0.0005151496,0.000071916664,0.00013814372,0.0008709646,0.00014647795,0.0013251614,0.00051478326,0.0004017562,0.0006925345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009060428,0.00009372886,0.00023645663,0.000058149366,0.0003760916,0.00034598683,0.028478723,0.003271715,0.0016066278,0.59979296,0.25212196,0.113527015],"study_design_scores_gemma":[0.00014929533,0.000030443665,0.00022556582,0.000044541826,0.000024167426,0.00028016596,0.015817802,0.0010324664,0.00012249907,0.5741414,0.40799484,0.0001368329],"about_ca_topic_score_codex":0.000085488406,"about_ca_topic_score_gemma":0.00008479601,"teacher_disagreement_score":0.78976804,"about_ca_system_score_codex":0.000049777984,"about_ca_system_score_gemma":0.00009127191,"threshold_uncertainty_score":0.9999103},"labels":[],"label_agreement":null},{"id":"W4398370825","doi":"10.7910/dvn/krogfv","title":"Replication Data for: Service Representation in a Federal System: A Field Experiment","year":2018,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Replication (statistics); Representation (politics); Field (mathematics); Service (business); Computer science; Business; Political science; Mathematics; Statistics","score_opus":0.2563692904441717,"score_gpt":0.45251321404726,"score_spread":0.1961439236030883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398370825","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025395035,0.0000017616476,0.002778723,0.00021942609,0.0010768167,0.0014082592,0.9941172,0.000046518177,0.00032592425],"genre_scores_gemma":[0.000032185475,0.00004282098,0.0015439007,0.001956048,0.00038731363,0.0002927044,0.9953973,0.0000141266655,0.00033357614],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99417037,0.00045667717,0.0013187899,0.002288643,0.0014087387,0.0003568082],"domain_scores_gemma":[0.98040116,0.0010152549,0.00078117935,0.01738902,0.00029575595,0.00011764116],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.006764069,0.00029717144,0.0005406401,0.00043069106,0.00020224585,0.00087809743,0.0059464187,0.00025318962,0.0027700958],"category_scores_gemma":[0.0068844287,0.0002675794,0.000076927805,0.0006678955,0.000046193407,0.00151599,0.00412259,0.00019501291,0.026391152],"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":[0.00018481012,0.00010753265,0.0000064557184,0.00019798242,0.000035757304,0.000013427834,0.000080295526,0.0000035741741,0.000008288461,0.00023575914,0.99812746,0.0009986629],"study_design_scores_gemma":[0.00065980013,0.000072744355,0.000024342198,0.00015305086,0.000046556135,0.000005349637,0.0017542784,0.001115142,0.000042698226,0.00027457016,0.99556816,0.0002833161],"about_ca_topic_score_codex":0.0064632515,"about_ca_topic_score_gemma":0.008065966,"teacher_disagreement_score":0.023621056,"about_ca_system_score_codex":0.00016768744,"about_ca_system_score_gemma":0.00013615844,"threshold_uncertainty_score":0.99997765},"labels":[],"label_agreement":null},{"id":"W4398613456","doi":"10.7910/dvn/gl5ccd/5igdeu","title":"iolinks_exec","year":2018,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Data Quality and Management","field":"Decision Sciences","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":"Statistics Canada; Université du Québec à Montréal","funders":"","keywords":"Replication (statistics); Computer science; Database; Biology; Virology","score_opus":0.11876681155733702,"score_gpt":0.3832193626359284,"score_spread":0.26445255107859134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398613456","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002062934,7.4769747e-7,0.00031816558,0.000035682,0.0029752234,0.00030413902,0.9936524,0.00005736495,0.002654224],"genre_scores_gemma":[9.379689e-7,0.00018624251,0.00046801483,0.002750744,0.0009421672,0.000020618294,0.9894944,0.00001581546,0.0061210934],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99388134,0.0004752259,0.0011037706,0.0013593981,0.0026604582,0.00051982375],"domain_scores_gemma":[0.99132293,0.0006834053,0.0006445005,0.006784185,0.00028975366,0.00027522523],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0057928506,0.00041451395,0.000660102,0.000584905,0.00024619585,0.001004632,0.005838388,0.00036884155,0.20653632],"category_scores_gemma":[0.0060363803,0.000325224,0.00023214905,0.0006289217,0.0003719255,0.00080095563,0.0037055756,0.0004325444,0.8428237],"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":[0.00003103839,0.00008474534,8.559726e-7,0.000026301945,0.00005320253,0.00008096681,0.000014435054,7.8021236e-7,5.424246e-7,0.0003181453,0.99782693,0.0015620711],"study_design_scores_gemma":[0.0002706898,0.00006215907,0.000015497242,0.00003743079,0.00009078895,0.000006911625,0.000095657524,0.00001351688,0.0000036760944,0.0023729377,0.9966292,0.000401537],"about_ca_topic_score_codex":0.00055915775,"about_ca_topic_score_gemma":0.00085296144,"teacher_disagreement_score":0.63628733,"about_ca_system_score_codex":0.00006821805,"about_ca_system_score_gemma":0.00015788007,"threshold_uncertainty_score":0.99992},"labels":[],"label_agreement":null},{"id":"W4398749752","doi":"10.7910/dvn/gl5ccd/p3ylfa","title":"main_iolinks.cpp","year":2018,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Data Quality and Management","field":"Decision Sciences","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":"Statistics Canada; Université du Québec à Montréal","funders":"","keywords":"Replication (statistics); Computer science; Biology; Virology","score_opus":0.11743043908432159,"score_gpt":0.38104419894002906,"score_spread":0.26361375985570745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398749752","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002415458,9.1099287e-7,0.00048118143,0.000048018715,0.003348353,0.000359455,0.9927938,0.000064599604,0.002901251],"genre_scores_gemma":[0.0000010650247,0.0002193538,0.00071155507,0.003241212,0.0010461494,0.000025834888,0.9878781,0.000019258036,0.006857467],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99322814,0.0005865445,0.0012141631,0.0015085107,0.002848672,0.000613975],"domain_scores_gemma":[0.99052465,0.0008667355,0.00070247985,0.007290336,0.00030022443,0.00031556244],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0070968135,0.00046761017,0.0007167502,0.000647197,0.00028909853,0.0011242223,0.0063366783,0.00041584417,0.2162294],"category_scores_gemma":[0.006674717,0.00037260962,0.00025559665,0.0007092831,0.00043495107,0.0008529127,0.004191933,0.00049286237,0.83112293],"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":[0.00003655894,0.00009518537,0.0000013198947,0.000034342243,0.00006487977,0.00010606039,0.000017041468,0.0000010250717,5.4129924e-7,0.00048583138,0.99775517,0.0014020529],"study_design_scores_gemma":[0.00031999787,0.000067340145,0.000021374024,0.00004649996,0.000102628015,0.00000843614,0.00014029925,0.00001552529,0.0000031587492,0.003356011,0.99546194,0.00045679955],"about_ca_topic_score_codex":0.00051852665,"about_ca_topic_score_gemma":0.00085300393,"teacher_disagreement_score":0.6148935,"about_ca_system_score_codex":0.00008655541,"about_ca_system_score_gemma":0.00017249685,"threshold_uncertainty_score":0.9999127},"labels":[],"label_agreement":null},{"id":"W4399419098","doi":"10.1177/14604582241259336","title":"Building ontology-based temporal databases for data reuse: An applied example on hospital organizational structures","year":2024,"lang":"en","type":"article","venue":"Health Informatics Journal","topic":"Data Quality and Management","field":"Decision Sciences","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":"Université de Sherbrooke","funders":"","keywords":"Computer science; Ontology; Interoperability; Database; Data modeling; Temporal database; Data quality; Information retrieval; Data warehouse; Relational database; Data model (GIS); Data science; Data mining; World Wide Web; Artificial intelligence","score_opus":0.3993119407378315,"score_gpt":0.5042411380466737,"score_spread":0.1049291973088422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399419098","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":[0.009808723,0.00012346283,0.973792,0.011071562,0.0019125161,0.00060795073,0.002312504,0.0001018465,0.0002694178],"genre_scores_gemma":[0.14384395,0.00004062096,0.84034777,0.010667579,0.0008706859,0.000015027004,0.0041323085,0.00003356061,0.000048478247],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960087,0.0001260961,0.001752662,0.0003050793,0.0013853419,0.00042211855],"domain_scores_gemma":[0.99565136,0.0010297738,0.000685208,0.002098138,0.000207173,0.00032833737],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.009300239,0.00017942135,0.00030881786,0.0004925241,0.0006896886,0.0013549844,0.00304797,0.00005182241,0.00028085193],"category_scores_gemma":[0.003560995,0.00013016575,0.000042362884,0.00047685218,0.00007446166,0.0019241943,0.0006912348,0.0003542915,0.000065312284],"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":[0.00006734762,0.0000940064,0.0002076601,0.0002656712,0.00003805158,0.000005487862,0.002026425,0.0011437538,0.0000020681564,0.33186185,0.59085363,0.07343404],"study_design_scores_gemma":[0.00060196087,0.00038892985,0.000460826,0.00008236505,0.000015047441,0.00003388549,0.0019485215,0.07261308,0.000019037332,0.09030829,0.8333163,0.0002116983],"about_ca_topic_score_codex":0.000051619783,"about_ca_topic_score_gemma":0.000090280635,"teacher_disagreement_score":0.24246272,"about_ca_system_score_codex":0.000119980614,"about_ca_system_score_gemma":0.0010392745,"threshold_uncertainty_score":0.9996817},"labels":[],"label_agreement":null},{"id":"W4399496685","doi":"10.2139/ssrn.4821693","title":"An Introduction to International Data Governance Design","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for International Governance Innovation","funders":"","keywords":"Corporate governance; Business; Accounting; Political science; Computer science; Finance","score_opus":0.13604214927573285,"score_gpt":0.4327472587361949,"score_spread":0.296705109460462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399496685","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":[0.0014154658,0.000734112,0.9248397,0.069043815,0.003198316,0.0001083168,0.000051581854,0.00004998629,0.0005587136],"genre_scores_gemma":[0.95631343,0.0027139825,0.007511612,0.0013206439,0.008630178,0.0000083371515,0.0001140894,0.00003202884,0.023355693],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965482,0.00025529033,0.0004208699,0.0006142254,0.001302077,0.000859389],"domain_scores_gemma":[0.9985494,0.0001566141,0.00009648189,0.0009803936,0.000117223055,0.000099910656],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019862587,0.000098524324,0.00011156043,0.00019062788,0.00013069343,0.0012927273,0.003086216,0.000028964967,0.00046060872],"category_scores_gemma":[0.001335476,0.00007501608,0.00003963849,0.00051891216,0.000025153118,0.0024391,0.00035349536,0.0007326619,0.00092767476],"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":[0.000036681282,0.000031330856,0.000012182433,7.2271945e-7,0.000054983233,0.0000054245206,0.00008509778,0.0005451154,0.00014306659,0.4618104,0.14697951,0.39029548],"study_design_scores_gemma":[0.00007201166,0.00013756711,0.000120402634,0.0000053317194,0.000010448828,0.0001213703,0.00072470645,0.006375587,0.00002904718,0.32378268,0.66853654,0.00008433114],"about_ca_topic_score_codex":0.000030218427,"about_ca_topic_score_gemma":0.00044535135,"teacher_disagreement_score":0.954898,"about_ca_system_score_codex":0.00054912566,"about_ca_system_score_gemma":0.00082173105,"threshold_uncertainty_score":0.9998502},"labels":[],"label_agreement":null},{"id":"W4399828472","doi":"10.32920/26060791","title":"Data Governance. Enablers, Inhibitors, Practices, and Outcomes","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Toronto Metropolitan University","funders":"","keywords":"Corporate governance; Business; Data governance; Process management; Knowledge management; Computer science; Finance; Data quality; Marketing","score_opus":0.39699396160423256,"score_gpt":0.4907735664996202,"score_spread":0.09377960489538761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828472","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013352289,0.02032716,0.0050376737,0.30356994,0.027477246,0.00298212,0.024912056,0.0009604923,0.601381],"genre_scores_gemma":[0.23364829,0.012763183,0.035492342,0.014388879,0.0024527956,0.00014816513,0.0044265394,0.00016621036,0.6965136],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99422866,0.00026498255,0.000979422,0.0020678765,0.0021786503,0.00028040487],"domain_scores_gemma":[0.992197,0.0013807439,0.0011639174,0.005018185,0.000098738456,0.00014141739],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00989279,0.00031500097,0.0005585805,0.0001590198,0.00009304339,0.0033689062,0.0040076445,0.00020528375,0.0012218527],"category_scores_gemma":[0.011217941,0.00020453367,0.00008691324,0.00029606398,0.00012860942,0.0009327091,0.05069949,0.000770708,0.0017128902],"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":[0.000006270691,0.000040200535,0.0008242495,0.00012647614,0.00011028972,0.000032937864,0.000098432094,0.0000050799654,9.610499e-7,0.052691903,0.89622074,0.049842443],"study_design_scores_gemma":[0.00009142136,0.000008640599,0.0012988102,0.00007074012,0.00008338413,0.000002383014,0.0006704703,0.0011262348,0.000005157995,0.13400663,0.8623864,0.00024972315],"about_ca_topic_score_codex":0.0021402861,"about_ca_topic_score_gemma":0.0022895394,"teacher_disagreement_score":0.28918108,"about_ca_system_score_codex":0.000047778016,"about_ca_system_score_gemma":0.00021257672,"threshold_uncertainty_score":0.9996912},"labels":[],"label_agreement":null},{"id":"W4399828482","doi":"10.32920/26060791.v1","title":"Data Governance. Enablers, Inhibitors, Practices, and Outcomes","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Toronto Metropolitan University","funders":"","keywords":"Corporate governance; Business; Data governance; Knowledge management; Process management; Computer science; Finance; Marketing; Data quality","score_opus":0.39699396160423256,"score_gpt":0.4907735664996202,"score_spread":0.09377960489538761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828482","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013352289,0.02032716,0.0050376737,0.30356994,0.027477246,0.00298212,0.024912056,0.0009604923,0.601381],"genre_scores_gemma":[0.23364829,0.012763183,0.035492342,0.014388879,0.0024527956,0.00014816513,0.0044265394,0.00016621036,0.6965136],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99422866,0.00026498255,0.000979422,0.0020678765,0.0021786503,0.00028040487],"domain_scores_gemma":[0.992197,0.0013807439,0.0011639174,0.005018185,0.000098738456,0.00014141739],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00989279,0.00031500097,0.0005585805,0.0001590198,0.00009304339,0.0033689062,0.0040076445,0.00020528375,0.0012218527],"category_scores_gemma":[0.011217941,0.00020453367,0.00008691324,0.00029606398,0.00012860942,0.0009327091,0.05069949,0.000770708,0.0017128902],"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":[0.000006270691,0.000040200535,0.0008242495,0.00012647614,0.00011028972,0.000032937864,0.000098432094,0.0000050799654,9.610499e-7,0.052691903,0.89622074,0.049842443],"study_design_scores_gemma":[0.00009142136,0.000008640599,0.0012988102,0.00007074012,0.00008338413,0.000002383014,0.0006704703,0.0011262348,0.000005157995,0.13400663,0.8623864,0.00024972315],"about_ca_topic_score_codex":0.0021402861,"about_ca_topic_score_gemma":0.0022895394,"teacher_disagreement_score":0.28918108,"about_ca_system_score_codex":0.000047778016,"about_ca_system_score_gemma":0.00021257672,"threshold_uncertainty_score":0.9996912},"labels":[],"label_agreement":null},{"id":"W4400015021","doi":"10.14236/ewic/eva2024.44","title":"Your Data Body","year":2024,"lang":"en","type":"article","venue":"Electronic workshops in computing","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.22665943554396764,"score_gpt":0.4733566933482829,"score_spread":0.24669725780431526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400015021","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":[0.13687757,0.020407397,0.76949066,0.018832754,0.0053572385,0.0008250867,0.000060085116,0.00093222864,0.04721701],"genre_scores_gemma":[0.99600667,0.000059160328,0.0008363052,0.00041662992,0.0003545686,0.0000019161835,0.0000604324,0.000014955179,0.0022493617],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99645454,0.00026610275,0.00067108235,0.0010116603,0.0008883056,0.00070830213],"domain_scores_gemma":[0.9957631,0.002401734,0.00007505315,0.0016749649,0.000030381932,0.000054740318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011371601,0.00014495046,0.00022776917,0.0003460283,0.00011831713,0.000991185,0.0028167334,0.000060822462,0.00026360984],"category_scores_gemma":[0.0020026423,0.00012089178,0.00005200557,0.0018489626,0.00004675885,0.000601128,0.0020651803,0.00059521134,0.0006557914],"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":[0.000008752475,0.00005154543,0.00056044594,0.000016148704,0.00003468287,0.000067449684,0.0004916172,0.0016118792,0.00001626263,0.12775914,0.0999071,0.769475],"study_design_scores_gemma":[0.00012347758,0.000021442764,0.0012432793,0.0001080124,0.000008674524,0.000010211963,0.0005552538,0.38286424,0.000010580871,0.049233314,0.56564337,0.00017811492],"about_ca_topic_score_codex":0.00005153448,"about_ca_topic_score_gemma":0.00027086103,"teacher_disagreement_score":0.85912913,"about_ca_system_score_codex":0.00014523447,"about_ca_system_score_gemma":0.00018932974,"threshold_uncertainty_score":0.9558019},"labels":[],"label_agreement":null},{"id":"W4400242142","doi":"10.1145/3643991.3644924","title":"The Impact of Code Ownership of DevOps Artefacts on the Outcome of DevOps CI Builds","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Waterloo","funders":"","keywords":"DevOps; Computer science; Outcome (game theory); Code (set theory); Software engineering; Computer security; Programming language; Software deployment","score_opus":0.38824144749168743,"score_gpt":0.5046893514482588,"score_spread":0.11644790395657134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400242142","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":[0.8499824,0.00035627314,0.010367525,0.024882367,0.00079230266,0.00080200785,0.00076522684,0.00007163546,0.111980304],"genre_scores_gemma":[0.9945758,0.000021378219,0.00011285126,0.00039341708,0.00001856627,0.0000043416785,0.0000036273066,0.000006569666,0.0048634536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969414,0.00035721596,0.0009209651,0.00026642106,0.0013006564,0.00021338358],"domain_scores_gemma":[0.99216634,0.0061803795,0.00026347674,0.0011744893,0.00015817759,0.000057134606],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00807951,0.00012786758,0.00029742415,0.00015529248,0.00008053873,0.00015370756,0.0014216624,0.000045862198,0.0009653756],"category_scores_gemma":[0.003285537,0.000044566095,0.0002891263,0.0007772541,0.0002835816,0.00017114005,0.0002955895,0.00012858112,0.00019758807],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112336464,0.00016823866,0.0060304278,0.000054827142,0.0002635719,0.000004206732,0.0012177754,0.0004216503,0.00061699835,0.63054985,0.32373816,0.036821984],"study_design_scores_gemma":[0.0008536207,0.00143153,0.16256769,0.00028419343,0.00017489136,0.000006631691,0.020126207,0.0076623014,0.02716218,0.37264097,0.40649107,0.000598692],"about_ca_topic_score_codex":0.000698691,"about_ca_topic_score_gemma":0.0005800065,"teacher_disagreement_score":0.25790885,"about_ca_system_score_codex":0.000027444261,"about_ca_system_score_gemma":0.00007489282,"threshold_uncertainty_score":0.9999479},"labels":[],"label_agreement":null},{"id":"W4400321996","doi":"10.22215/rcin/m.24c1","title":"CICP Data Literacy 1.0 - Module 1: Data in the Nonprofit Sector","year":2024,"lang":"en","type":"report","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Carleton University","keywords":"Nonprofit sector; Business; Computer science; Literacy; Data science; Public relations; Psychology; Political science; Pedagogy","score_opus":0.6647299006353016,"score_gpt":0.5554889791904332,"score_spread":0.10924092144486841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400321996","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021910366,0.0046874913,0.007036986,0.016448492,0.008003992,0.0015118239,0.04104387,0.00016456931,0.92088366],"genre_scores_gemma":[0.016998746,0.0039464426,0.0065314583,0.009155134,0.0036387495,0.00012294929,0.10094654,0.00014177768,0.8585182],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9877319,0.00059682387,0.0016909773,0.002781206,0.006767396,0.0004317316],"domain_scores_gemma":[0.9720978,0.002105588,0.00039944163,0.025034538,0.00027727344,0.00008536003],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.04677182,0.00036229583,0.00063961896,0.0005662139,0.000088072884,0.0039214026,0.02761009,0.00020993163,0.0045748902],"category_scores_gemma":[0.009027058,0.00018727325,0.000091525006,0.0015970004,0.00010560943,0.0023904822,0.022746593,0.0008063582,0.0060989163],"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":[0.0000035044443,0.000060052083,0.00006620321,0.00011253782,0.00004623186,0.00019720096,0.0001795248,9.827847e-7,3.296619e-7,0.0026058028,0.8942158,0.10251178],"study_design_scores_gemma":[0.00007149027,0.000012949949,0.0004947451,0.00012229921,0.000069968664,0.000023200933,0.0005887672,0.0023875718,6.9759506e-7,0.012791499,0.9831717,0.00026512487],"about_ca_topic_score_codex":0.0044357614,"about_ca_topic_score_gemma":0.004657397,"teacher_disagreement_score":0.10224666,"about_ca_system_score_codex":0.00008031788,"about_ca_system_score_gemma":0.0008336214,"threshold_uncertainty_score":0.9993203},"labels":[],"label_agreement":null},{"id":"W4400685466","doi":"10.1145/3676961","title":"SimClone: Detecting Tabular Data Clones Using Value Similarity","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Huawei Technologies (Canada); University of Manitoba","funders":"","keywords":"Computer science; Data mining; Header; Software; Visualization; clone (Java method); Similarity (geometry); Margin (machine learning); Artificial intelligence; Image (mathematics); Machine learning","score_opus":0.549696504884526,"score_gpt":0.4849508565192975,"score_spread":0.06474564836522856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400685466","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":[0.019102538,0.0011075753,0.9766895,0.00047750835,0.001892082,0.00012793219,0.0001900513,0.0004058137,0.000007009971],"genre_scores_gemma":[0.120691255,0.00015430944,0.87860125,0.00021182167,0.00012195122,0.00001045791,0.000019974581,0.000032651722,0.00015630123],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973462,0.00057116704,0.0004746813,0.0008655053,0.00042145548,0.00032096653],"domain_scores_gemma":[0.98677385,0.011328391,0.000049390124,0.0016777267,0.000052055544,0.000118587865],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00823037,0.00020710708,0.00035782103,0.00046951816,0.00024308261,0.00026424433,0.0009938305,0.00015274106,0.00008419241],"category_scores_gemma":[0.0116965845,0.00018171356,0.00008206233,0.00070417416,0.00006942535,0.000524469,0.00014674795,0.00046163387,0.000028081171],"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":[0.00004344147,0.00006273903,0.000076519595,0.00022685176,0.00032094464,0.000086981374,0.00085015566,0.19737811,0.0016414718,0.003315311,0.0004023531,0.7955951],"study_design_scores_gemma":[0.0006260757,0.00025050694,0.00081041275,0.00029379642,0.0007064644,0.00028246173,0.0016946119,0.61605173,0.005319016,0.03222547,0.34060052,0.0011389129],"about_ca_topic_score_codex":0.00015104449,"about_ca_topic_score_gemma":0.000025980904,"teacher_disagreement_score":0.7944562,"about_ca_system_score_codex":0.000033954268,"about_ca_system_score_gemma":0.00004291626,"threshold_uncertainty_score":0.99662834},"labels":[],"label_agreement":null},{"id":"W4400875444","doi":"10.3390/computers13070183","title":"Data Lakes: A Survey of Concepts and Architectures","year":2024,"lang":"en","type":"article","venue":"Computers","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Ministry of Higher Education and Scientific Research","keywords":"Data science; Survey data collection; Computer science; Geography; Mathematics; Statistics","score_opus":0.3904131326033246,"score_gpt":0.48886319191730615,"score_spread":0.09845005931398154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400875444","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":[0.41328835,0.0035668397,0.57004344,0.0029191712,0.0028810392,0.00033678737,0.003791872,0.00014171212,0.0030307577],"genre_scores_gemma":[0.99708843,0.000015459233,0.002153528,0.00034713335,0.000029772184,6.0730633e-7,0.000113467766,0.0000033172316,0.00024825786],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987191,0.00022869032,0.00023838076,0.00036095703,0.00037078813,0.00008206982],"domain_scores_gemma":[0.9970598,0.0020569442,0.000037386795,0.0007723561,0.00003263341,0.0000408551],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032031918,0.00005397546,0.00013188344,0.00010951859,0.000024269248,0.00024535548,0.0010002039,0.000014418855,0.00004055122],"category_scores_gemma":[0.00068259606,0.00003759701,0.000015306356,0.0003063233,0.00014389733,0.000121840116,0.0010055911,0.000047592468,0.000040094863],"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":[0.000010834356,0.000017410552,0.0011289384,0.00004532288,0.000044062264,0.000014028924,0.0011501153,0.00013894215,0.000014662419,0.005754022,0.37006652,0.6216151],"study_design_scores_gemma":[0.00023822807,0.00008059528,0.145557,0.00011485449,0.000016099542,0.0000075360135,0.00040758093,0.108062975,0.000028094535,0.013965455,0.73133135,0.0001902458],"about_ca_topic_score_codex":0.00016442694,"about_ca_topic_score_gemma":0.00044646877,"teacher_disagreement_score":0.6214249,"about_ca_system_score_codex":0.0000025672066,"about_ca_system_score_gemma":0.000023337065,"threshold_uncertainty_score":0.23659685},"labels":[],"label_agreement":null},{"id":"W4400884871","doi":"10.2196/54590","title":"Data Lake, Data Warehouse, Datamart, and Feature Store: Their Contributions to the Complete Data Reuse Pipeline","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data warehouse; Metadata; Identifier; Data science; Pipeline (software); Software; USable; Database; Reuse; Data transformation; Feature (linguistics); Adaptation (eye); World Wide Web","score_opus":0.27843646919616866,"score_gpt":0.4669328239810727,"score_spread":0.18849635478490406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400884871","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032068594,0.0009556552,0.2074269,0.28163877,0.0014164497,0.0012463216,0.5053381,0.00027391687,0.0013832215],"genre_scores_gemma":[0.029352468,0.0042574727,0.04839749,0.13643199,0.0051845913,0.00016636497,0.76610804,0.00013425128,0.00996732],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99448943,0.00028065543,0.0012420958,0.00070841226,0.0028352658,0.00044413217],"domain_scores_gemma":[0.9698323,0.0032191563,0.00019682039,0.02601164,0.00017196515,0.0005681091],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.016724644,0.0002419458,0.00040060392,0.00017142305,0.00037148848,0.0017405485,0.031649143,0.00015304521,0.00053361757],"category_scores_gemma":[0.02948405,0.00012562964,0.000026032509,0.0010475366,0.00038393532,0.004083406,0.066817656,0.0007796707,0.0011342346],"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":[0.000011343479,0.00003743469,0.000010426327,0.000056406043,0.000047340138,0.000014437428,0.0010985673,0.000002487715,2.0911378e-7,0.0029312135,0.92908776,0.06670236],"study_design_scores_gemma":[0.00021427772,0.000020163583,0.00009392989,0.000104614475,0.00003662637,0.000021020303,0.0025130727,0.21996665,2.781666e-7,0.001079804,0.775809,0.00014056105],"about_ca_topic_score_codex":0.000030316818,"about_ca_topic_score_gemma":0.003497436,"teacher_disagreement_score":0.26077,"about_ca_system_score_codex":0.000022573853,"about_ca_system_score_gemma":0.00033574973,"threshold_uncertainty_score":0.9996435},"labels":[],"label_agreement":null},{"id":"W4400910536","doi":"10.1109/icde60146.2024.00268","title":"Fairness-Aware Data Preparation for Entity Matching","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Matching (statistics); Mathematics; Statistics","score_opus":0.47250982684582465,"score_gpt":0.5520579657671183,"score_spread":0.07954813892129364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400910536","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":[0.0021990186,0.000053990225,0.9818533,0.0026442583,0.0008658897,0.00027341896,0.00044064905,0.00012855224,0.011540943],"genre_scores_gemma":[0.92753166,0.000011918405,0.008300132,0.00061884563,0.00019945906,0.000030928226,0.0008872386,0.000008084512,0.062411714],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850225,0.00005508559,0.00029758798,0.0005108176,0.00052736764,0.00010689452],"domain_scores_gemma":[0.9982038,0.00059732184,0.000033018117,0.0010825285,0.000051842533,0.00003147333],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00433219,0.000055230725,0.00008706945,0.00008969688,0.0000977859,0.0013360239,0.00105662,0.000022506143,0.00072525686],"category_scores_gemma":[0.0005183835,0.000037867794,0.000036314053,0.00023820785,0.000017058594,0.0019057881,0.00071070454,0.000033523942,0.0009968277],"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":[0.0000088205115,0.000018871291,0.000011907648,0.000038019938,0.000014203974,0.0000019075894,0.00024265143,0.000036911082,0.000020254947,0.217872,0.70461226,0.07712219],"study_design_scores_gemma":[0.000043277614,0.000012351959,0.00008206251,0.000008938531,0.000009493772,5.945389e-7,0.00081213604,0.041473202,0.00004949122,0.20007043,0.7573818,0.00005624044],"about_ca_topic_score_codex":0.000112327354,"about_ca_topic_score_gemma":0.0005747672,"teacher_disagreement_score":0.9735531,"about_ca_system_score_codex":0.0000119366605,"about_ca_system_score_gemma":0.000038635873,"threshold_uncertainty_score":0.999781},"labels":[],"label_agreement":null},{"id":"W4400992667","doi":"10.69554/rpfg8859","title":"Engineering risk-based anonymisation solutions for complex data environments","year":2020,"lang":"en","type":"article","venue":"Journal of data protection & privacy.","topic":"Data Quality and Management","field":"Decision Sciences","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":"Privacy Analytics (Canada)","funders":"","keywords":"Computer science; Data science; Data mining; Risk analysis (engineering); Medicine","score_opus":0.677103680939665,"score_gpt":0.43018124554949594,"score_spread":0.24692243539016906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400992667","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":[0.0009993156,0.000040329785,0.9841751,0.011832832,0.00023997092,0.0005289458,0.0021492487,0.000018825482,0.000015422738],"genre_scores_gemma":[0.6682419,0.00011485264,0.3259581,0.0016908438,0.0013255362,0.00003120461,0.0024995413,0.000041672774,0.00009633721],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971003,0.00022529344,0.00095873384,0.00046319372,0.0010472602,0.0002052317],"domain_scores_gemma":[0.9964172,0.00038005412,0.0010912574,0.0018633708,0.00009497694,0.00015309441],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0072490503,0.00011751328,0.00024241679,0.00017923884,0.0002644245,0.00029144261,0.0036517065,0.00004747958,0.00023254413],"category_scores_gemma":[0.010692049,0.00009846538,0.00006585926,0.00035211223,0.000034970206,0.0028246597,0.0017370312,0.0002491003,0.00008934568],"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":[0.0007499336,0.0005700101,0.00038767367,0.00012439929,0.00035233432,0.000010640484,0.00047954015,0.038648147,0.019474996,0.0005744626,0.5303308,0.40829706],"study_design_scores_gemma":[0.0006306848,0.00012784668,0.0016470603,0.000010392238,0.000051320552,0.000003694335,0.00008860312,0.35308754,0.00012847148,0.00045303343,0.64369124,0.00008012517],"about_ca_topic_score_codex":0.00001991457,"about_ca_topic_score_gemma":0.000005474712,"teacher_disagreement_score":0.6672426,"about_ca_system_score_codex":0.000053222022,"about_ca_system_score_gemma":0.000078467514,"threshold_uncertainty_score":0.9976413},"labels":[],"label_agreement":null},{"id":"W4401043414","doi":"10.18653/v1/2024.naacl-short.11","title":"Unified Examination of Entity Linking in Absence of Candidate Sets","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Simon Fraser University","funders":"","keywords":"Computer science","score_opus":0.13637319101570985,"score_gpt":0.41448734796991704,"score_spread":0.27811415695420716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401043414","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":[0.94064254,0.0000748938,0.018420368,0.0003027134,0.0003583486,0.00011898168,0.000034730507,0.000019055537,0.040028375],"genre_scores_gemma":[0.9972796,0.00002602546,0.000510988,0.00003084144,0.0000042533684,0.0000011543567,0.000008900009,0.0000013236039,0.0021369318],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986819,0.00011539692,0.00040254794,0.00017497447,0.0005599695,0.00006522225],"domain_scores_gemma":[0.9992895,0.00031637345,0.00006958074,0.0002484537,0.000061782506,0.000014325774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004574595,0.00003507806,0.00010469092,0.00029682586,0.000011641886,0.00005935344,0.00029785794,0.00002088465,0.00032149834],"category_scores_gemma":[0.00040008582,0.0000259778,0.000023669902,0.000728669,0.000060328635,0.0003341583,0.00014585097,0.000038930404,0.000045142464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008922512,0.000105551386,0.0038022012,0.00023850467,0.00001786084,0.00001633807,0.0049855155,0.00018127963,0.0026202581,0.47544754,0.0032138366,0.50936216],"study_design_scores_gemma":[0.0005583619,0.00012629761,0.642948,0.00057886547,0.00001999902,0.000001493266,0.010103606,0.045281254,0.02313351,0.22741094,0.049527884,0.00030983536],"about_ca_topic_score_codex":0.00064141385,"about_ca_topic_score_gemma":0.0016160146,"teacher_disagreement_score":0.63914573,"about_ca_system_score_codex":0.000012898514,"about_ca_system_score_gemma":0.000023867979,"threshold_uncertainty_score":0.35201815},"labels":[],"label_agreement":null},{"id":"W4401108396","doi":"10.1007/978-3-031-66431-1_33","title":"DataAssist: A Machine Learning Approach to Data Cleaning and Preparation","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.1569908050652264,"score_gpt":0.3670280918147778,"score_spread":0.2100372867495514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401108396","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":[0.00003099672,0.03540276,0.7853817,0.00039283308,0.0012702013,0.0011651126,0.0003942387,0.000088921384,0.17587326],"genre_scores_gemma":[0.81671196,0.0025769044,0.0024932344,0.00092688575,0.0025657841,0.00006763495,0.0056685656,0.00015974054,0.16882929],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666345,0.00016130239,0.00080706086,0.0014121815,0.0007063927,0.00024963086],"domain_scores_gemma":[0.9973891,0.00092783826,0.000254589,0.0012699048,0.00004370719,0.000114857736],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004855413,0.00032568636,0.00062937086,0.0003146099,0.00015603803,0.0016004768,0.0008145367,0.00031080158,0.000021390118],"category_scores_gemma":[0.00056195346,0.00023877234,0.000035235516,0.00018061209,0.00006187198,0.00026708178,0.0018110384,0.00069513253,0.000027788026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017755371,0.000035815643,0.00030434324,0.0007984965,0.00028127313,0.00007219247,0.0022687623,0.4530181,0.000002218037,0.19166979,0.04027536,0.3110961],"study_design_scores_gemma":[0.00006813752,0.00003750734,0.000010819864,0.00031104113,0.000035564986,0.000016127917,0.000030808565,0.54587036,3.2000113e-8,0.0055325227,0.4478944,0.00019265],"about_ca_topic_score_codex":0.00021570874,"about_ca_topic_score_gemma":0.00081401883,"teacher_disagreement_score":0.81668097,"about_ca_system_score_codex":0.00003271808,"about_ca_system_score_gemma":0.00001697183,"threshold_uncertainty_score":0.99943596},"labels":[],"label_agreement":null},{"id":"W4401334154","doi":"10.33965/celda2023_202306l014","title":"THREE FRAMEWORKS FOR DATA LITERACY","year":2023,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Literacy; Data science; Psychology; Pedagogy","score_opus":0.5491912103233049,"score_gpt":0.5529128637733244,"score_spread":0.003721653450019513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401334154","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":[0.000835912,0.000017988486,0.9726619,0.014787244,0.0006218685,0.00025263077,0.00032934835,0.00015729594,0.010335789],"genre_scores_gemma":[0.20194681,0.00015193755,0.46580562,0.05020787,0.0018571676,0.00027798192,0.006962401,0.00007999269,0.27271023],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983748,0.00002667099,0.000314342,0.00047517716,0.00061947235,0.00018950558],"domain_scores_gemma":[0.995265,0.0022156255,0.00005548996,0.0023217942,0.00008954657,0.00005254525],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005285693,0.000056776094,0.00011035678,0.00013657831,0.00010090863,0.0006140812,0.0024326297,0.000061135055,0.0011113535],"category_scores_gemma":[0.004720361,0.00003763216,0.000036487938,0.0007401475,0.0000279985,0.00087930507,0.0016871134,0.000083171246,0.0046025845],"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":[0.000003910598,0.0000078135445,0.00010990215,0.0000019729823,0.0000042440734,9.03992e-7,0.00004760386,0.0000037902792,8.8575115e-7,0.07055691,0.6197558,0.30950627],"study_design_scores_gemma":[0.000068404464,0.000008821526,0.0012145892,0.0000025905351,0.000002521034,9.178602e-8,0.00015426925,0.04257512,0.0000029371977,0.3290396,0.6268894,0.000041655367],"about_ca_topic_score_codex":0.000041818646,"about_ca_topic_score_gemma":0.00018201949,"teacher_disagreement_score":0.5068563,"about_ca_system_score_codex":0.00000365271,"about_ca_system_score_gemma":0.000013077916,"threshold_uncertainty_score":0.99980175},"labels":[],"label_agreement":null},{"id":"W4401544215","doi":"10.1145/3643991.3644931","title":"On the Executability of R Markdown Files","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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 Manitoba; University of Windsor; Lakehead University","funders":"","keywords":"Computer science; Parallel computing","score_opus":0.21765323021123933,"score_gpt":0.4362016895950086,"score_spread":0.21854845938376927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401544215","genre_codex":"other","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":[0.12155356,0.000099673016,0.011349661,0.030620443,0.0006922738,0.00027264512,0.00015221599,0.00007972305,0.8351798],"genre_scores_gemma":[0.9765538,0.0000048903507,0.00015224164,0.00088326953,0.000013902166,0.0000052893197,0.0000018927856,0.0000016119557,0.022383116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986356,0.00015404064,0.00025740097,0.00021247173,0.00067002483,0.00007044595],"domain_scores_gemma":[0.995191,0.0040709735,0.000024376055,0.0006609994,0.00003405291,0.000018596447],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0049134563,0.000041692896,0.00007766889,0.00005755855,0.000035073244,0.00017217589,0.00054699107,0.000013717105,0.017182913],"category_scores_gemma":[0.0020872715,0.000017294267,0.00006488017,0.00034223447,0.00009138258,0.00011326729,0.00018550016,0.000047079753,0.0014109627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034314614,0.000015068464,0.000016997676,0.0000044551184,0.000004315207,6.263122e-7,0.00009853909,0.0000037417901,0.0000141566825,0.56462026,0.40415394,0.031064488],"study_design_scores_gemma":[0.00001722735,0.00002697692,0.0019765594,0.000010067291,0.0000031988104,1.9618119e-7,0.0011309965,0.0008371919,0.00050174055,0.4946961,0.50076634,0.000033390603],"about_ca_topic_score_codex":0.000054799126,"about_ca_topic_score_gemma":0.000044333243,"teacher_disagreement_score":0.8550002,"about_ca_system_score_codex":0.0000064115584,"about_ca_system_score_gemma":0.000014306593,"threshold_uncertainty_score":0.9993666},"labels":[],"label_agreement":null},{"id":"W4401666276","doi":"10.1007/s10618-024-01054-7","title":"Bayesian network Motifs for reasoning over heterogeneous unlinked datasets","year":2024,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"","keywords":"Computer science; Probabilistic logic; Bayesian network; Python (programming language); Data mining; Aggregate (composite); Real world data; Bayesian probability; Machine learning; Set (abstract data type); Artificial intelligence; Data science","score_opus":0.1674946705782729,"score_gpt":0.43586677779388994,"score_spread":0.26837210721561705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401666276","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":[0.07173932,0.038002245,0.7337181,0.0012870805,0.010564487,0.0015898112,0.13448459,0.00055742793,0.008056971],"genre_scores_gemma":[0.8948025,0.00057772896,0.02130219,0.0009935668,0.0030985833,0.00009195967,0.06366882,0.000114244656,0.015350399],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99704605,0.0001860787,0.0005886095,0.0013072382,0.00042115577,0.00045087424],"domain_scores_gemma":[0.9957396,0.0019828049,0.00010014161,0.001998252,0.00003766196,0.00014157109],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004624117,0.00023140457,0.00033838573,0.00017061859,0.0003175814,0.0026824486,0.0014811197,0.00008105216,0.000069013644],"category_scores_gemma":[0.0015921316,0.00018039165,0.00007776871,0.00049864524,0.000119110315,0.0023165082,0.0021943124,0.00010868802,0.00008928861],"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":[0.00004114622,0.00005423227,0.00032346067,0.00010551724,0.000106018466,0.00003659696,0.00066064514,0.000075718846,0.000007249033,0.0056799673,0.763801,0.2291085],"study_design_scores_gemma":[0.0002618789,0.000059134058,0.00027348136,0.00026895304,0.000089436355,0.00001332386,0.0007255858,0.16961396,0.000009147724,0.0030172335,0.8253931,0.00027477494],"about_ca_topic_score_codex":0.00003748714,"about_ca_topic_score_gemma":0.0004990714,"teacher_disagreement_score":0.8230632,"about_ca_system_score_codex":0.000022459788,"about_ca_system_score_gemma":0.00010740582,"threshold_uncertainty_score":0.9983529},"labels":[],"label_agreement":null},{"id":"W4402078687","doi":"10.47674/9781529238327","title":"Dialogues in Data Power","year":2024,"lang":"en","type":"book","venue":"Bristol University Press eBooks","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Universiteit van Tilburg; Karlstads universitet","keywords":"Power (physics); Computer science; Physics","score_opus":0.3263759557675474,"score_gpt":0.357813835672532,"score_spread":0.03143787990498459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402078687","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000827312,0.00035882968,0.00055336894,0.00016052868,0.0008221212,0.00037408745,0.003719082,0.00010341273,0.9939003],"genre_scores_gemma":[0.00018087085,0.000056777713,0.00012632384,0.00015904826,0.0000797904,4.6503934e-7,0.0007136568,0.000022215912,0.99866086],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963378,0.00029030576,0.0004711931,0.0013672395,0.001243158,0.00029035108],"domain_scores_gemma":[0.9958392,0.00049495156,0.00025132362,0.0031974155,0.000094908944,0.00012220553],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002096653,0.00028215215,0.00052709295,0.0006514185,0.00009407941,0.00041895392,0.0057647335,0.00028164207,0.00010853946],"category_scores_gemma":[0.00027343127,0.00028166958,0.00013068134,0.00007008526,0.00027428294,0.00042884232,0.0073648826,0.00053027895,0.0007186509],"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":[0.000035049743,0.000017496615,0.000001124551,0.000036669055,0.000047073845,0.0008067493,0.00037356614,0.0000015744446,2.6681028e-7,0.16649222,0.82587564,0.006312576],"study_design_scores_gemma":[0.00021931513,0.000015004477,0.000017875274,0.0001273929,0.000080947495,0.0000028191503,0.00026111325,0.00006615283,9.047121e-7,0.013564213,0.9853373,0.00030694145],"about_ca_topic_score_codex":0.00067163684,"about_ca_topic_score_gemma":0.0012481153,"teacher_disagreement_score":0.15946169,"about_ca_system_score_codex":0.00026105577,"about_ca_system_score_gemma":0.00034726373,"threshold_uncertainty_score":0.9999635},"labels":[],"label_agreement":null},{"id":"W4402112538","doi":"10.1007/978-3-031-70626-4_9","title":"GXJoin: Generalized Cell Transformations for Explainable Joinability","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science","score_opus":0.0933103195086047,"score_gpt":0.35450553264650664,"score_spread":0.26119521313790195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402112538","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":[0.000049569393,0.0004302521,0.96263355,0.0036677457,0.0021525435,0.0010946818,0.00018571015,0.000085703075,0.029700216],"genre_scores_gemma":[0.10840646,0.00027845192,0.7690609,0.010717082,0.0020462256,0.00040261395,0.00027156158,0.00016689874,0.1086498],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949111,0.00005356815,0.0010935501,0.0015715971,0.0017954012,0.00057479896],"domain_scores_gemma":[0.9961008,0.0015404536,0.00024044268,0.0015555256,0.00040840518,0.00015441248],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0068505662,0.00039719758,0.0005942408,0.0010387759,0.000386803,0.0013804905,0.0026160225,0.00022126044,0.0003175428],"category_scores_gemma":[0.0004884089,0.00030523562,0.00030493934,0.0007596487,0.00060674525,0.0008075961,0.0007197311,0.00042727467,0.00028799276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040250754,0.000092651564,0.0000052916885,0.00044153773,0.00002086337,0.00002920025,0.003090765,0.038889308,0.000070485505,0.33148172,0.007802029,0.6180359],"study_design_scores_gemma":[0.00019912746,0.00008111127,0.000004183685,0.00006421796,0.00001550414,0.0000034041614,0.0000027331894,0.07103732,0.00047904297,0.6927362,0.235088,0.0002891298],"about_ca_topic_score_codex":0.000030146375,"about_ca_topic_score_gemma":0.0001984649,"teacher_disagreement_score":0.6177468,"about_ca_system_score_codex":0.0002638089,"about_ca_system_score_gemma":0.00037869692,"threshold_uncertainty_score":0.99994},"labels":[],"label_agreement":null},{"id":"W4402118981","doi":"10.1007/978-3-031-68034-2_4","title":"Data and Information Security","year":2024,"lang":"en","type":"book-chapter","venue":"Progress in IS","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; York University; University of Toronto","funders":"","keywords":"Information security; Computer science; Computer security","score_opus":0.19680858132879125,"score_gpt":0.43660748731482996,"score_spread":0.2397989059860387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402118981","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024221574,0.006275441,0.0000962718,0.005287462,0.0006478391,0.0003982313,0.004677953,0.00005082461,0.98254174],"genre_scores_gemma":[0.022476144,0.006298287,0.0022703689,0.005626031,0.00054350897,0.00008016626,0.005178609,0.00006643661,0.95746046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99798256,0.000015856152,0.00055620726,0.00042552993,0.00090717006,0.000112661386],"domain_scores_gemma":[0.9983168,0.0001376236,0.00017450155,0.0012722586,0.000056188666,0.000042622425],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025323776,0.00013448599,0.00021222969,0.00035004123,0.000031847467,0.00080075813,0.0011929875,0.0001257146,0.0005801005],"category_scores_gemma":[0.0001606717,0.00010447423,0.000025138714,0.00007772428,0.00014671494,0.0017142264,0.0028394535,0.0002351275,0.0016669197],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044750414,0.000004085551,0.00006078588,0.000083226754,0.000013529104,0.000008213136,0.00062226737,2.573888e-8,8.017406e-10,0.5138197,0.12615874,0.35922495],"study_design_scores_gemma":[0.00004186981,0.000007122175,0.000037326765,0.00007714602,0.000010338987,0.0000010709122,0.00006494803,0.0004526949,1.6362755e-7,0.35096174,0.64826614,0.00007946219],"about_ca_topic_score_codex":0.000006901802,"about_ca_topic_score_gemma":0.000064492655,"teacher_disagreement_score":0.52210736,"about_ca_system_score_codex":0.000017759921,"about_ca_system_score_gemma":0.00002262926,"threshold_uncertainty_score":0.9991104},"labels":[],"label_agreement":null},{"id":"W4402390590","doi":"10.23889/ijpds.v9i5.2514","title":"Improving Cardiac Insights: Harnessing Privacy-Preserving Record Linkage (PPRL) to Obtain, Link, and Enhance Data for a Healthier Australia","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"Victoria Park","funders":"","keywords":"Record linkage; Link (geometry); Linkage (software); Computer science; Data mining; Computer network; Medicine; Environmental health; Genetics; Biology; Gene","score_opus":0.35526995340542455,"score_gpt":0.5394998433459082,"score_spread":0.18422988994048362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402390590","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":[0.06417964,0.00046615585,0.89300764,0.022269603,0.014528742,0.0009837556,0.004439086,0.00006538955,0.000059996706],"genre_scores_gemma":[0.76680976,0.00020695962,0.2223817,0.0015656053,0.003421169,0.000050532828,0.0024423092,0.000036258687,0.0030857187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949117,0.00011686367,0.0010994343,0.0013802277,0.0020994332,0.0003923971],"domain_scores_gemma":[0.99533534,0.0011233761,0.00042138898,0.0019277879,0.00089331093,0.00029877544],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.014527803,0.00016891168,0.0002455044,0.00083134556,0.0008053692,0.006721777,0.0087034255,0.000057635723,0.000041456096],"category_scores_gemma":[0.019698167,0.00013616067,0.000060308204,0.0008471148,0.00012606011,0.012206679,0.0054492173,0.00024527093,0.000029214436],"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":[0.00010583107,0.000033665747,0.0015281097,0.00009194818,0.000061461535,0.000010519184,0.00075568265,0.00020731206,0.001856756,0.0147260055,0.086471744,0.894151],"study_design_scores_gemma":[0.00018850491,0.00006371229,0.0049935346,0.0002715778,0.000027207287,0.000014305436,0.00035835162,0.23435855,0.000093529554,0.025393838,0.7340053,0.00023160432],"about_ca_topic_score_codex":0.00049560476,"about_ca_topic_score_gemma":0.00024808178,"teacher_disagreement_score":0.89391935,"about_ca_system_score_codex":0.00018742302,"about_ca_system_score_gemma":0.00026375699,"threshold_uncertainty_score":0.99665993},"labels":[],"label_agreement":null},{"id":"W4402391115","doi":"10.23889/ijpds.v9i5.2502","title":"Development of a dictionary of information items inspired by common data models to support health research data access requests","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; Canadian Institute for Health Information","funders":"","keywords":"Computer science; Data access; Data science; Data mining; Information retrieval; Database","score_opus":0.8228812729718443,"score_gpt":0.6533858271484233,"score_spread":0.16949544582342102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402391115","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":[0.030685231,0.00016879763,0.9033162,0.012239527,0.00492567,0.0010450883,0.046997774,0.000043877026,0.0005778159],"genre_scores_gemma":[0.9092532,0.00012264522,0.049879048,0.00054868055,0.0001602007,0.000011163397,0.039861135,0.000009454456,0.00015451778],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9904437,0.00017634165,0.0021320616,0.0007243376,0.006231599,0.00029197862],"domain_scores_gemma":[0.9942442,0.0005998697,0.0007220942,0.0026757321,0.0015377282,0.00022035433],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.045107204,0.00010497393,0.00022407569,0.0017129019,0.0004478292,0.002046943,0.020691669,0.00003391594,0.000053190543],"category_scores_gemma":[0.004072517,0.00008639069,0.000022338545,0.0017687244,0.00018621505,0.037062112,0.011512933,0.00019637724,0.00002805925],"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":[0.00009869539,0.00011479223,0.0007033988,0.00004784731,0.00004573679,0.0000015711139,0.0012019769,0.0013041905,0.0001621474,0.019060122,0.41191626,0.56534326],"study_design_scores_gemma":[0.00022893054,0.000086923064,0.0046581617,0.00022590796,0.000006021518,0.000018958335,0.0006804635,0.36384434,0.00008443063,0.015297875,0.61474353,0.00012442686],"about_ca_topic_score_codex":0.0008483648,"about_ca_topic_score_gemma":0.00064554205,"teacher_disagreement_score":0.87856793,"about_ca_system_score_codex":0.00025242154,"about_ca_system_score_gemma":0.0015090227,"threshold_uncertainty_score":0.99898905},"labels":[],"label_agreement":null},{"id":"W4402391230","doi":"10.23889/ijpds.v9i5.2890","title":"Providing data analytic services for national knowledge users in a federated system: learnings from two Canadian use cases","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Nova Scotia Health Authority; Dalhousie University; Government of Newfoundland and Labrador; University of New Brunswick; Alberta Health; Manitoba Health; Canadian Institute for Health Information; Newfoundland and Labrador Centre for Applied Health Research; Alberta Health Services","funders":"","keywords":"Knowledge management; Computer science; Data science","score_opus":0.4809236346985375,"score_gpt":0.5410040609025777,"score_spread":0.060080426204040194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402391230","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":[0.7268765,0.00066952035,0.13208228,0.01322738,0.025209596,0.002746198,0.09807085,0.0002420387,0.0008756292],"genre_scores_gemma":[0.9858396,0.000008626617,0.0051697777,0.00025807164,0.0005295594,0.000012742494,0.0075594364,0.000012603837,0.0006095769],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953856,0.00012215406,0.00096235244,0.001078403,0.0021059206,0.00034558587],"domain_scores_gemma":[0.99476504,0.0025464757,0.0003353125,0.00071528944,0.0013959947,0.00024188327],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.011763232,0.00014917663,0.00019427392,0.0018383664,0.0007012323,0.009488595,0.005964127,0.000041019037,0.000080789396],"category_scores_gemma":[0.010558178,0.00012594374,0.00005254642,0.001218209,0.000090726964,0.0150584,0.0010420461,0.00016965663,0.000054496326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093173055,0.00034963002,0.1652997,0.0004317323,0.00086495944,0.00054297084,0.004277897,0.022208283,0.00091361644,0.2742108,0.24876885,0.2811998],"study_design_scores_gemma":[0.00034535493,0.00001671147,0.011215242,0.00024973185,0.000020309015,0.000048316237,0.0011067821,0.73665583,0.000007192781,0.002393683,0.24779417,0.00014664761],"about_ca_topic_score_codex":0.09150772,"about_ca_topic_score_gemma":0.5188786,"teacher_disagreement_score":0.71444756,"about_ca_system_score_codex":0.0008889749,"about_ca_system_score_gemma":0.001349568,"threshold_uncertainty_score":0.9994141},"labels":[],"label_agreement":null},{"id":"W4402404963","doi":"10.23889/ijpds.v9i5.2624","title":"From Probabilistic to Fuzzy Matching Record Linkage: A promising Transition","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Probabilistic logic; Matching (statistics); Transition (genetics); Linkage (software); Computer science; Record linkage; Fuzzy logic; Data mining; Artificial intelligence; Mathematics; Biology; Genetics; Statistics; Sociology","score_opus":0.24547470867080023,"score_gpt":0.5016516879164926,"score_spread":0.2561769792456924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402404963","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":[0.19466418,0.00003790429,0.77294815,0.018404268,0.011138708,0.0004731304,0.0019156949,0.00007536018,0.0003425917],"genre_scores_gemma":[0.940707,0.000009808396,0.05571961,0.0008955071,0.0015107207,0.000013972758,0.0007179431,0.000012356561,0.00041302617],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99531275,0.000090420486,0.0008622272,0.0008333096,0.0026665777,0.00023470377],"domain_scores_gemma":[0.9977128,0.0006455926,0.00019582434,0.0006659527,0.0005966003,0.00018325522],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008973889,0.000115856776,0.00014322823,0.00078029756,0.00046332073,0.005798174,0.0038793266,0.00003221971,0.00017217478],"category_scores_gemma":[0.0045906766,0.000091662325,0.00007003001,0.0008644378,0.00008288154,0.006713409,0.0006014244,0.00017572743,0.000190028],"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":[0.00015736445,0.00009672051,0.00022385089,0.00002005972,0.00006496019,0.000047754336,0.0037561767,0.008350462,0.002697369,0.04998855,0.0342724,0.90032434],"study_design_scores_gemma":[0.00027359207,0.00006323039,0.0057203015,0.0003412433,0.000030230958,0.000047037127,0.000943079,0.14849105,0.000053570813,0.691453,0.15233374,0.0002499561],"about_ca_topic_score_codex":0.0005538721,"about_ca_topic_score_gemma":0.00023000468,"teacher_disagreement_score":0.90007436,"about_ca_system_score_codex":0.00022475798,"about_ca_system_score_gemma":0.00018322188,"threshold_uncertainty_score":0.9952339},"labels":[],"label_agreement":null},{"id":"W4402405604","doi":"10.23889/ijpds.v9i5.2820","title":"Expanding data resources beyond “health care”: exploring options and implications","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health care; Data science; Business; Computer science; Risk analysis (engineering); Economics; Economic growth","score_opus":0.5693426971422808,"score_gpt":0.5715981845222683,"score_spread":0.0022554873799874864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402405604","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":[0.120019905,0.0068745622,0.7119804,0.1108698,0.02315352,0.0011832508,0.023595365,0.000286001,0.0020371622],"genre_scores_gemma":[0.96166706,0.0009887329,0.031964637,0.00076078874,0.0010432545,0.000025212317,0.0030938778,0.000015558719,0.00044086637],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962222,0.00007864156,0.00077036116,0.00091328187,0.0017645194,0.00025102214],"domain_scores_gemma":[0.9970414,0.0006111776,0.00027010002,0.0014429451,0.00043618988,0.00019815873],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.009484196,0.000102402235,0.0001313745,0.0009274553,0.001157893,0.005158786,0.006217192,0.000019112063,0.000049084578],"category_scores_gemma":[0.0032109998,0.000082959225,0.000031654654,0.00078339735,0.00018448487,0.0124253845,0.0029153503,0.00014978666,0.000026226196],"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":[0.000016082775,0.00003026588,0.0024228173,0.000015855292,0.000042658146,0.0000041442686,0.0024543735,0.00029597152,0.0001396362,0.1809204,0.051819444,0.7618383],"study_design_scores_gemma":[0.00021470568,0.000039199866,0.039782528,0.000109322325,0.000020506483,0.000107986416,0.004902321,0.027303975,0.000009997244,0.045606297,0.8817113,0.0001918554],"about_ca_topic_score_codex":0.00016754871,"about_ca_topic_score_gemma":0.000252006,"teacher_disagreement_score":0.84164715,"about_ca_system_score_codex":0.00017460997,"about_ca_system_score_gemma":0.00022287772,"threshold_uncertainty_score":0.99915963},"labels":[],"label_agreement":null},{"id":"W4402405672","doi":"10.23889/ijpds.v9i5.2758","title":"Data Quality Implications in Research when Transitioning to a New Electronic Medical Record","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Alberta Health","funders":"","keywords":"Quality (philosophy); Electronic medical record; Data quality; Computer science; Data science; Business; Internet privacy; Marketing","score_opus":0.7950921562511286,"score_gpt":0.6891429991574641,"score_spread":0.10594915709366448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402405672","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":[0.017567823,0.0001081076,0.8088138,0.16696188,0.0030546277,0.00046998,0.002317967,0.00004445776,0.00066136423],"genre_scores_gemma":[0.943832,0.00019144677,0.045409992,0.00250774,0.0017908945,0.000033501165,0.0035052288,0.000022340779,0.002706873],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9910117,0.00034229143,0.0012462434,0.0011812999,0.005722623,0.00049588224],"domain_scores_gemma":[0.99459374,0.001962543,0.00015767278,0.002007676,0.0008642442,0.00041411398],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06448714,0.00009622802,0.00015803988,0.0016979122,0.00044802186,0.0034728807,0.013950976,0.00004952095,0.00061116554],"category_scores_gemma":[0.027433882,0.00008042308,0.00004078944,0.0021567035,0.00014961608,0.0074740513,0.002569062,0.00049635005,0.00018541403],"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":[0.00005465957,0.00005570337,0.0015589201,0.000003961621,0.000017769959,0.000007878547,0.00040074508,0.00013956007,0.00014158581,0.29131266,0.15313664,0.5531699],"study_design_scores_gemma":[0.00021375877,0.00003498851,0.019567078,0.000100856174,0.0000041217013,0.00003869272,0.00030395892,0.031593006,0.000004994936,0.31638128,0.63164645,0.0001108149],"about_ca_topic_score_codex":0.0021693576,"about_ca_topic_score_gemma":0.012139637,"teacher_disagreement_score":0.92626417,"about_ca_system_score_codex":0.00043968394,"about_ca_system_score_gemma":0.0017965533,"threshold_uncertainty_score":0.99756163},"labels":[],"label_agreement":null},{"id":"W4402405684","doi":"10.23889/ijpds.v9i5.2760","title":"Reporting on the establishment of a Privacy Preserving Record Linkage to Facilitate an Ongoing Crosswalk Between Research and Health Administrative Databases","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Indoc Research; Ontario Brain Institute","funders":"","keywords":"Schema crosswalk; Record linkage; Linkage (software); Database; Data science; Computer science; Internet privacy; Data mining; Business; Medicine; Engineering; Environmental health; Transport engineering","score_opus":0.9109178340257105,"score_gpt":0.6727323830946649,"score_spread":0.2381854509310456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402405684","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":[0.8729688,0.00006272398,0.0783184,0.042497046,0.0015587402,0.00085150276,0.0033514863,0.000026322057,0.0003650106],"genre_scores_gemma":[0.9868198,0.000026771106,0.01188766,0.00026076933,0.0002495353,0.000011489989,0.00028907892,0.000005856443,0.0004490145],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9932593,0.0002801639,0.001757249,0.00078377395,0.0036200576,0.00029945164],"domain_scores_gemma":[0.993659,0.0028497535,0.00097388297,0.0011531757,0.0011277501,0.000236404],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06985871,0.000094416304,0.00018307875,0.0007846038,0.0008914953,0.0035875791,0.0038884936,0.000014552462,0.000047748363],"category_scores_gemma":[0.035505973,0.0000609864,0.000032080814,0.0010235145,0.00023822098,0.005406113,0.0022401514,0.0002666804,0.000008307293],"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":[0.00019161639,0.00021381005,0.066111736,0.00008625077,0.00009549926,0.000036885376,0.009235814,0.0005274934,0.00054585614,0.14943387,0.058815822,0.71470535],"study_design_scores_gemma":[0.0003920547,0.0015037633,0.4259354,0.0016207147,0.000014649196,0.000055362303,0.010629838,0.041163288,0.0006195438,0.112357154,0.40534508,0.00036316054],"about_ca_topic_score_codex":0.001388872,"about_ca_topic_score_gemma":0.0006335622,"teacher_disagreement_score":0.7143422,"about_ca_system_score_codex":0.00016780841,"about_ca_system_score_gemma":0.0004475631,"threshold_uncertainty_score":0.9974468},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4402406136","doi":"10.23889/ijpds.v9i5.2657","title":"Navigating Data Acquisition and Data Quality Validation of Large Databases: Practical Lessons","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Saskatchewan Health Quality Council","funders":"","keywords":"Database; Computer science; Data quality; Quality (philosophy); Data mining; Data science; Engineering; Operations management","score_opus":0.6281295486631037,"score_gpt":0.6648589747416125,"score_spread":0.03672942607850882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406136","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":[0.06595144,0.00020447468,0.8357032,0.026695363,0.0046011815,0.00034389028,0.066365734,0.000045778826,0.000088934175],"genre_scores_gemma":[0.9157238,0.00012906549,0.046847533,0.00032763023,0.00050738733,0.0000025396942,0.036396317,0.000009690515,0.00005601757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99327433,0.00027861583,0.0013223359,0.0013267556,0.0035490047,0.00024896918],"domain_scores_gemma":[0.9926621,0.0021004286,0.00074926333,0.003532158,0.00080841803,0.00014765745],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.042797815,0.00012406052,0.00020190568,0.00028150933,0.00046708243,0.0026661928,0.008188024,0.00003369242,0.00014056846],"category_scores_gemma":[0.0253353,0.00010044949,0.000028326984,0.00072410493,0.00024186455,0.0271492,0.009238501,0.0002703435,0.000023142711],"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":[0.00018760686,0.0003826917,0.010370395,0.0001014918,0.00018126826,0.000034779747,0.00058945373,0.00021222522,0.002072671,0.57250696,0.08859328,0.3247672],"study_design_scores_gemma":[0.00075492397,0.00005223366,0.02958228,0.0004835178,0.00011345001,0.0002233075,0.0021858478,0.63481325,0.0003244031,0.04551482,0.2855817,0.00037029432],"about_ca_topic_score_codex":0.0002974666,"about_ca_topic_score_gemma":0.00016895811,"teacher_disagreement_score":0.8497724,"about_ca_system_score_codex":0.00006888637,"about_ca_system_score_gemma":0.0002979884,"threshold_uncertainty_score":0.9987746},"labels":[],"label_agreement":null},{"id":"W4402406137","doi":"10.23889/ijpds.v9i5.2666","title":"Conceptualizing community data governance for race-related, population data: a scoping review and key informant interviews","year":2024,"lang":"en","type":"review","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","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":"McMaster University; Sunnybrook Health Science Centre; SickKids Foundation","funders":"","keywords":"Race (biology); Key (lock); Population; Corporate governance; Psychology; Business; Computer science; Sociology; Demography; Computer security; Finance; Gender studies","score_opus":0.6948268504810855,"score_gpt":0.6210748162597212,"score_spread":0.07375203422136434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406137","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003482291,0.94066906,0.019812629,0.0011673731,0.0057906792,0.002736569,0.029702222,0.000042718137,0.00007528925],"genre_scores_gemma":[0.000048112917,0.9463527,0.0058294083,0.0006347199,0.00040862482,0.000054098884,0.046274595,0.00003394962,0.00036375367],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99015117,0.00064416864,0.0041891383,0.0016873744,0.002865253,0.00046288437],"domain_scores_gemma":[0.9865565,0.0020552923,0.0040274765,0.00625238,0.00086643186,0.00024192271],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["metaresearch","scholarly_communication","open_science"],"category_scores_codex":[0.045808423,0.00048478998,0.0015868772,0.0006573362,0.0011340831,0.004514263,0.027089179,0.00014664467,0.000083906525],"category_scores_gemma":[0.025646726,0.00035195638,0.00020933371,0.001161882,0.00033950096,0.018755615,0.019898457,0.0008691522,0.00006495248],"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":[0.000009488855,0.000035734487,0.000011821238,0.009915493,0.00014964918,0.0000028372654,0.00012362603,0.000008519429,5.250445e-8,0.010117696,0.061113525,0.91851157],"study_design_scores_gemma":[0.00025134574,0.000033301654,0.00003702739,0.093192734,0.0008997636,0.00015349727,0.00013339576,0.01245612,2.0955271e-8,0.0033869324,0.8890781,0.00037776656],"about_ca_topic_score_codex":0.00052288536,"about_ca_topic_score_gemma":0.0010836427,"teacher_disagreement_score":0.9181338,"about_ca_system_score_codex":0.00034650546,"about_ca_system_score_gemma":0.0006487189,"threshold_uncertainty_score":0.99989325},"labels":[],"label_agreement":null},{"id":"W4402406476","doi":"10.23889/ijpds.v9i5.2872","title":"Addressing data gaps on long-term care in Canada through data linkage","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Term (time); Linkage (software); Record linkage; Computer science; Data science; Business; Medicine; Environmental health; Biology; Genetics","score_opus":0.5619007749469208,"score_gpt":0.5650601188922989,"score_spread":0.0031593439453780903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406476","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":[0.31727976,0.0063861446,0.31795397,0.04661607,0.10431838,0.0025263154,0.19857016,0.00021493259,0.0061342735],"genre_scores_gemma":[0.97438085,0.00017197315,0.0042544752,0.000988282,0.00072143885,0.0000028332552,0.019235743,0.000012713461,0.00023171127],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928875,0.000116963914,0.0009840365,0.0014027874,0.0042764726,0.0003322556],"domain_scores_gemma":[0.9946123,0.0007785897,0.00031351246,0.0037551,0.00041172412,0.00012878327],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.007643748,0.00014997055,0.00018051591,0.00053581403,0.00038612942,0.003969571,0.021719158,0.00003135393,0.00019140517],"category_scores_gemma":[0.00577839,0.000117880285,0.00002487575,0.0008914254,0.00011871433,0.015062886,0.0065731937,0.00030619878,0.000046940087],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011867532,0.000086969754,0.03872764,0.000060798757,0.000067810266,0.00045494956,0.0005733267,0.002581241,0.00005047676,0.015561203,0.20476794,0.73694897],"study_design_scores_gemma":[0.0007501902,0.000053457792,0.19660865,0.0010975983,0.000037753052,0.00013111878,0.0018590741,0.26192424,0.00004262862,0.008945253,0.5280487,0.0005013468],"about_ca_topic_score_codex":0.13719052,"about_ca_topic_score_gemma":0.68050826,"teacher_disagreement_score":0.73644763,"about_ca_system_score_codex":0.00072396797,"about_ca_system_score_gemma":0.0019889413,"threshold_uncertainty_score":0.9987129},"labels":[],"label_agreement":null},{"id":"W4402406479","doi":"10.23889/ijpds.v9i5.2865","title":"Efficiency gains from the implementation of Research IDs for data linkage: A case study from Population Data BC and the Data Innovation Program in British Columbia, Canada","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linkage (software); Record linkage; Linked data; Population; Computer science; Data science; Research data; World Wide Web; Demography; Biology; Sociology; Genetics; Data curation","score_opus":0.4921450913277475,"score_gpt":0.6045446402558524,"score_spread":0.11239954892810494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406479","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":[0.90049005,0.00018364341,0.021743303,0.0052850856,0.002354611,0.0026317788,0.06728862,0.000016862525,0.0000060587113],"genre_scores_gemma":[0.9493558,0.00003834852,0.0040356074,0.00014844105,0.0003897671,0.00004251696,0.045942806,0.000009955093,0.00003680508],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99197733,0.0005668273,0.0016822978,0.0014664421,0.004002493,0.00030463043],"domain_scores_gemma":[0.98948175,0.0045466796,0.0006070544,0.0040706955,0.0012275538,0.00006625866],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.043939915,0.000107991495,0.00022163712,0.00036601728,0.0010184221,0.00774277,0.014782037,0.00003554312,0.00006461908],"category_scores_gemma":[0.014803424,0.00009015787,0.000016946538,0.0022678475,0.00036932318,0.008259815,0.008567214,0.00031121858,9.868891e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076963246,0.00023551534,0.23483013,0.000014085735,0.000109244895,0.00009413893,0.00089431123,0.00009522119,0.000009856028,0.0023319442,0.07071202,0.6905966],"study_design_scores_gemma":[0.0017624174,0.00007547489,0.350284,0.00010801156,0.00006503086,0.00006599552,0.021288028,0.5814206,8.009869e-7,0.015291888,0.02948316,0.00015456663],"about_ca_topic_score_codex":0.97160274,"about_ca_topic_score_gemma":0.99270624,"teacher_disagreement_score":0.690442,"about_ca_system_score_codex":0.00020205289,"about_ca_system_score_gemma":0.0010170622,"threshold_uncertainty_score":0.9994513},"labels":[],"label_agreement":null},{"id":"W4402406486","doi":"10.23889/ijpds.v9i5.2867","title":"Creating a Data Cleaning and Pre-Processing Module for Generalisable Data Linkage","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; University of Calgary; Alberta Health; Alberta Health Services","funders":"","keywords":"Linkage (software); Database; Data processing; Computer science; Process engineering; Engineering; Chemistry","score_opus":0.4833771817173695,"score_gpt":0.5563532414405485,"score_spread":0.07297605972317905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402406486","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":[0.015870199,0.0005829029,0.96248245,0.0044142157,0.0039001973,0.00038318522,0.012040771,0.000058075944,0.00026803112],"genre_scores_gemma":[0.7222004,0.00016369503,0.25846788,0.00075796404,0.002233456,0.000011655722,0.014250579,0.00002810961,0.0018862599],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99541,0.000058511396,0.0008503473,0.0013455065,0.0020464403,0.00028917144],"domain_scores_gemma":[0.9959332,0.0008187246,0.0003673956,0.0021786133,0.0005591608,0.00014295796],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.018859012,0.0001269114,0.00016317275,0.00048018587,0.0009448366,0.008934693,0.011833168,0.000034922672,0.00004662177],"category_scores_gemma":[0.01163909,0.00010027364,0.000026460406,0.0005364728,0.00016251537,0.021402681,0.0066036363,0.00014780984,0.000009650163],"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":[0.00007189693,0.00005082734,0.0016968935,0.000056834608,0.00006035331,0.000010089593,0.00039490085,0.0019042271,0.00047429008,0.035263043,0.08484333,0.87517333],"study_design_scores_gemma":[0.00018753968,0.000017735525,0.0018361699,0.00011324606,0.000023062408,0.00004353309,0.00022446983,0.7818284,0.0000145736085,0.018244782,0.19735579,0.000110692104],"about_ca_topic_score_codex":0.00021343428,"about_ca_topic_score_gemma":0.00019232526,"teacher_disagreement_score":0.87506264,"about_ca_system_score_codex":0.00007241251,"about_ca_system_score_gemma":0.00023066564,"threshold_uncertainty_score":0.9966863},"labels":[],"label_agreement":null},{"id":"W4402453836","doi":"10.29173/cais1844","title":"Measuring Data Re-Use In OpenAlex by Researchers, Institutions, and Countries","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Political science; Regional science; Geography","score_opus":0.42138363346943747,"score_gpt":0.4117599338071687,"score_spread":0.009623699662268781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402453836","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":[0.9752687,0.001734034,0.00011574425,0.0122787515,0.00019576987,0.00050778274,0.0022526789,0.000042305503,0.007604211],"genre_scores_gemma":[0.9968912,0.00084087846,0.00030802854,0.00022783475,0.000029164095,0.0000136226345,0.000020736952,0.000010108177,0.0016584074],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99686414,0.00008086175,0.0007212292,0.0006208977,0.0013729263,0.00033994042],"domain_scores_gemma":[0.9773294,0.0013583156,0.00046588125,0.0009110797,0.019745883,0.00018947003],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.007695467,0.00017788984,0.0003777944,0.00035652396,0.00014356416,0.012193516,0.0041275034,0.00009344355,0.000046336143],"category_scores_gemma":[0.08955652,0.00012416969,0.00005205958,0.0009087922,0.0008165713,0.028911257,0.0036592113,0.0003188156,0.000010622663],"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":[0.00042300363,0.00026227243,0.17459057,0.001179745,0.00022685502,0.000015595731,0.043355357,0.000008186658,0.004046102,0.26520577,0.47391397,0.036772575],"study_design_scores_gemma":[0.00030379256,0.00007372153,0.026121663,0.0006246316,0.000035599838,0.000008322059,0.006738021,0.0007843661,0.001899051,0.010840337,0.9523648,0.000205695],"about_ca_topic_score_codex":0.0011360692,"about_ca_topic_score_gemma":0.00039444614,"teacher_disagreement_score":0.47845083,"about_ca_system_score_codex":0.000054513042,"about_ca_system_score_gemma":0.00038192028,"threshold_uncertainty_score":0.98883194},"labels":[],"label_agreement":null},{"id":"W4402554712","doi":"10.1177/18333583241277952","title":"System interoperability and data linkage in the era of health information management: A bibliometric analysis","year":2024,"lang":"en","type":"article","venue":"Health Information Management Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Universidade de Lisboa; Universidade dos Açores","keywords":"Interoperability; Health informatics; Computer science; Linkage (software); Data science; Sample (material); Stakeholder; Knowledge management; World Wide Web; Medicine; Public health; Political science","score_opus":0.17824280409310886,"score_gpt":0.45076212203237365,"score_spread":0.27251931793926476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402554712","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":[0.007852998,0.002614916,0.9369289,0.032045133,0.0012497416,0.002627329,0.00052157464,0.0001208028,0.016038587],"genre_scores_gemma":[0.97903246,0.006229939,0.0069609,0.0069756825,0.000046480884,0.000037574096,0.00062949007,0.0000064717537,0.00008099456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9912491,0.0012589734,0.004112505,0.0003016686,0.0026346787,0.00044311257],"domain_scores_gemma":[0.99643826,0.0003530533,0.0014105513,0.0014517913,0.000194149,0.00015217141],"candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.06137361,0.00018959054,0.0005149147,0.049531363,0.0004205909,0.0030158458,0.0020638902,0.000042269476,0.00008130522],"category_scores_gemma":[0.00028030822,0.0001225551,0.000112289854,0.07916752,0.00006688046,0.01027011,0.0010616701,0.00048015235,0.00017591551],"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":[0.000019567547,0.00003837475,0.0008295657,0.0029095246,0.00025741302,0.0000045464085,0.005060428,0.00046109676,3.5653707e-9,0.037748933,0.028140627,0.9245299],"study_design_scores_gemma":[0.00091140845,0.00018510653,0.2106425,0.000711401,0.00017766163,0.0000354329,0.06675139,0.09575997,8.9525486e-8,0.0032274344,0.62138015,0.00021744861],"about_ca_topic_score_codex":0.00024457678,"about_ca_topic_score_gemma":0.00006219722,"teacher_disagreement_score":0.9711795,"about_ca_system_score_codex":0.00030184854,"about_ca_system_score_gemma":0.000100225254,"threshold_uncertainty_score":0.9980191},"labels":[],"label_agreement":null},{"id":"W4402594319","doi":"10.1109/sse62657.2024.00025","title":"Efficient Incident Summarization in ITOps: Leveraging Entity-Based Grouping","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"IBM (Canada)","funders":"","keywords":"Automatic summarization; Computer science; Information retrieval; Artificial intelligence","score_opus":0.14597231352848483,"score_gpt":0.4072017318811585,"score_spread":0.26122941835267366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402594319","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":[0.21523996,0.00012225029,0.7663971,0.0029425402,0.0012269766,0.00024469543,0.0000082642755,0.00015096701,0.013667234],"genre_scores_gemma":[0.9960365,0.0000031017994,0.0012121133,0.00095212006,0.000043015312,0.0000107333735,0.000022503546,0.000006030159,0.0017138725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975297,0.00018492497,0.0005250725,0.00048052156,0.0010805009,0.0001993221],"domain_scores_gemma":[0.9989063,0.00056373375,0.00004839932,0.00038212002,0.000051171326,0.000048245965],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052559027,0.00008994018,0.00012964333,0.00065592804,0.000076397366,0.0009817993,0.00042993328,0.000031142532,0.00068713765],"category_scores_gemma":[0.0007334911,0.000070024274,0.00006071596,0.0013130723,0.0000289276,0.00024736422,0.00025054472,0.00009932422,0.00078990875],"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":[0.00003393639,0.00043715394,0.021376792,0.00021742813,0.00003303293,0.00023399323,0.0040884805,0.25113598,0.0008199341,0.45308158,0.037350707,0.231191],"study_design_scores_gemma":[0.0002662243,0.000018262763,0.014642949,0.00013160857,0.000008440313,8.194968e-7,0.0015756648,0.8684668,0.0003944309,0.013038359,0.101252824,0.00020361147],"about_ca_topic_score_codex":0.0004161775,"about_ca_topic_score_gemma":0.00048453177,"teacher_disagreement_score":0.7807965,"about_ca_system_score_codex":0.00011508252,"about_ca_system_score_gemma":0.00005573328,"threshold_uncertainty_score":0.9999881},"labels":[],"label_agreement":null},{"id":"W4402647595","doi":"10.54501/jots.v2i4.215","title":"A Multi-Stakeholder Approach for Leveraging Data Portability to Support Research on the Digital Information Environment","year":2024,"lang":"en","type":"article","venue":"Journal of Online Trust and Safety","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Charles Koch Foundation; Craig Newmark Philanthropies; York University; John S. and James L. Knight Foundation; Bill and Melinda Gates Foundation","keywords":"Software portability; Computer science; Stakeholder; Data science; Human–computer interaction; Knowledge management; World Wide Web; Political science; Operating system; Public relations","score_opus":0.6331715962950767,"score_gpt":0.4901302457559833,"score_spread":0.1430413505390934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402647595","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":[0.17697269,0.00018098351,0.7429106,0.067071,0.00069349725,0.0018171491,0.0066974927,0.000024625659,0.0036319462],"genre_scores_gemma":[0.9791512,0.00008731059,0.017940463,0.0009377653,0.00023632283,0.000006790464,0.0004558904,0.000007922274,0.0011763477],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973396,0.000117598,0.0008506819,0.00022933945,0.0012848863,0.0001778625],"domain_scores_gemma":[0.9979472,0.0010506226,0.00013624893,0.0006319842,0.00012306328,0.00011089424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01697394,0.00008410208,0.00017486967,0.00024674647,0.00017756931,0.0008252242,0.000880496,0.000028817358,0.000100442136],"category_scores_gemma":[0.0017873171,0.000043831402,0.00006188677,0.0002557378,0.00007559277,0.00154734,0.00052791927,0.0002796771,0.000028559825],"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":[0.0004989018,0.00047633678,0.0007698064,0.00007265179,0.00008518179,0.000010151751,0.0025709905,0.0011750103,0.000008986484,0.0035403608,0.11276987,0.8780218],"study_design_scores_gemma":[0.00037891424,0.00026177126,0.014125583,0.00002387682,0.0000141579385,0.000014312685,0.009159132,0.03106519,0.0000036609717,0.001127548,0.9437491,0.00007673165],"about_ca_topic_score_codex":0.00000394884,"about_ca_topic_score_gemma":0.00000332639,"teacher_disagreement_score":0.877945,"about_ca_system_score_codex":0.000052905605,"about_ca_system_score_gemma":0.00010498716,"threshold_uncertainty_score":0.7957656},"labels":[],"label_agreement":null},{"id":"W4402898151","doi":"10.1016/j.is.2024.102460","title":"Data Lakehouse: A survey and experimental study","year":2024,"lang":"en","type":"article","venue":"Information Systems","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Computer science; Survey research; Data science; Psychology","score_opus":0.4319128260972868,"score_gpt":0.47713784578125534,"score_spread":0.045225019683968526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402898151","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":[0.88636225,0.003334749,0.046899572,0.0005554418,0.009997536,0.0037933434,0.008423107,0.0007818808,0.039852105],"genre_scores_gemma":[0.99886745,0.0000030247875,0.000015526839,0.00007908206,0.000038154292,0.000020905247,0.00029121723,0.0000028302982,0.0006818258],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977377,0.0003096543,0.0006779349,0.0002066723,0.0009724983,0.00009554423],"domain_scores_gemma":[0.9984728,0.00043092002,0.00009256496,0.0008833306,0.00006949369,0.00005085908],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010299285,0.00007268968,0.00013353673,0.00021265581,0.00008388504,0.0030339882,0.0007045482,0.00002174519,0.000047580565],"category_scores_gemma":[0.00050336454,0.00005103362,0.000010453565,0.00039296955,0.000024462883,0.0050950996,0.0006615904,0.000048494454,0.001781812],"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":[0.000046832527,0.00022516707,0.010690324,0.00012809614,0.00013313226,0.000015352834,0.027606232,0.00019881518,0.000006657941,0.016399203,0.9057835,0.038766727],"study_design_scores_gemma":[0.00020673097,0.000071118666,0.008069685,0.000015660773,0.000003842513,0.000007753752,0.037201148,0.018985482,0.0000028711277,0.000028669414,0.935314,0.00009305626],"about_ca_topic_score_codex":0.00061143516,"about_ca_topic_score_gemma":0.00020618402,"teacher_disagreement_score":0.11250517,"about_ca_system_score_codex":0.00001766996,"about_ca_system_score_gemma":0.000025873413,"threshold_uncertainty_score":0.9989954},"labels":[],"label_agreement":null},{"id":"W4403054350","doi":"10.2196/64726","title":"Strengthening the Backbone: Government-Academic Data Collaborations for Crisis Response","year":2024,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Government (linguistics); Political science; Computer science; World Wide Web","score_opus":0.30457572968655755,"score_gpt":0.47526680444772557,"score_spread":0.17069107476116802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403054350","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":[0.03812005,0.00731356,0.04912936,0.8914538,0.0013619261,0.001976622,0.009494161,0.00020409346,0.0009464345],"genre_scores_gemma":[0.97654724,0.0011435996,0.0011906704,0.015351842,0.00031695023,0.00031524498,0.00041070773,0.000022898777,0.004700831],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957561,0.0011667986,0.0007888936,0.0007240177,0.0011058716,0.00045833903],"domain_scores_gemma":[0.9918275,0.0062363353,0.00017599556,0.0013243181,0.0001203268,0.00031552964],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03131606,0.00012439075,0.00023274093,0.000091427864,0.0005577939,0.0012458062,0.0012234095,0.00005784847,0.000066519475],"category_scores_gemma":[0.009139617,0.00007867993,0.00003370768,0.0011037532,0.00009124949,0.00082182756,0.0005476792,0.00020393118,0.000046892652],"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":[0.00008973952,0.000015357982,0.00096381106,0.000048526184,0.000015786534,8.293739e-7,0.0012374702,0.0000019616452,0.000003335214,0.016453214,0.8628381,0.11833189],"study_design_scores_gemma":[0.00016257733,0.00006609841,0.0034617241,0.0000069475623,5.6003944e-7,0.0000020599125,0.008792205,0.007402232,2.140725e-7,0.0011645735,0.97884804,0.000092779956],"about_ca_topic_score_codex":0.000029749082,"about_ca_topic_score_gemma":0.00029135327,"teacher_disagreement_score":0.9384272,"about_ca_system_score_codex":0.00008060463,"about_ca_system_score_gemma":0.0007605523,"threshold_uncertainty_score":0.99979097},"labels":[],"label_agreement":null},{"id":"W4403509127","doi":"10.2196/67286","title":"Correction: Data Integrity Issues With Web-Based Studies: An Institutional Example of a Widespread Challenge","year":2024,"lang":"en","type":"erratum","venue":"JMIR Mental Health","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Economic and Social Research Council","keywords":"Research integrity; Computer science; Data science; World Wide Web; Engineering ethics; Engineering","score_opus":0.4180722274788815,"score_gpt":0.5205633684969673,"score_spread":0.10249114101808576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403509127","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002383698,0.14090493,0.0034664043,0.14545394,0.5037949,0.015147378,0.07954226,0.0015597783,0.10774668],"genre_scores_gemma":[0.027471032,0.031775914,0.009264349,0.011923403,0.0083144065,0.001141661,0.0968946,0.00027321986,0.81294143],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99305135,0.0007124874,0.0012908189,0.0016701143,0.0028593543,0.00041586286],"domain_scores_gemma":[0.99547035,0.00047072172,0.0007394529,0.0027856955,0.00027690962,0.0002568728],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0066752024,0.0004211958,0.0010410065,0.00051669823,0.00041355452,0.00022907407,0.0023067256,0.00020961615,0.00033943294],"category_scores_gemma":[0.00040207565,0.00029137896,0.0000933543,0.00084968016,0.0005783505,0.0008899062,0.0013445035,0.0011397989,0.00024532515],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015887358,0.000608416,0.000017716995,0.001116463,0.00011357501,0.000014334325,0.0022151556,0.0000032165865,2.0737629e-7,0.0025974002,0.9644506,0.02870407],"study_design_scores_gemma":[0.00049232517,0.0013199,0.00015471499,0.0024834285,0.000027277314,0.000008783368,0.0097975265,0.0022672932,0.000001920239,0.0010550361,0.98211664,0.00027513775],"about_ca_topic_score_codex":0.0051358184,"about_ca_topic_score_gemma":0.034535788,"teacher_disagreement_score":0.7051947,"about_ca_system_score_codex":0.0005622047,"about_ca_system_score_gemma":0.0027411329,"threshold_uncertainty_score":0.9999538},"labels":[],"label_agreement":null},{"id":"W4403536522","doi":"10.1145/3691620.3695061","title":"What Makes a High-Quality Training Dataset for Large Language Models: A Practitioners' Perspective","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"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 Ottawa","funders":"Natural Science Foundation of Chongqing","keywords":"Perspective (graphical); Computer science; Training (meteorology); Quality (philosophy); Language model; Artificial intelligence; Natural language processing; Data science; Machine learning","score_opus":0.33202770851424385,"score_gpt":0.5121126675199051,"score_spread":0.1800849590056613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403536522","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":[0.0031963675,0.0014500243,0.89991915,0.037481092,0.0019302422,0.0010064313,0.040870428,0.00031224405,0.013834018],"genre_scores_gemma":[0.93514174,0.00018198065,0.018750394,0.009159809,0.00047168418,0.00027876897,0.008988736,0.00003573791,0.026991135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99727225,0.00026252915,0.00047451525,0.0007760278,0.0009011271,0.00031357235],"domain_scores_gemma":[0.9968282,0.0020976923,0.00009367001,0.0007434677,0.00014490339,0.000092060334],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007759336,0.00014120898,0.00024776495,0.00022927753,0.00017337894,0.0024509127,0.00054813235,0.000053963115,0.0012512248],"category_scores_gemma":[0.0017317329,0.000101443366,0.000118117,0.0004377294,0.00004646418,0.0051189675,0.0002529614,0.000120052646,0.00045044883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028735634,0.0000630061,1.7944157e-7,0.000021694708,0.000048818743,0.000013777627,0.014474533,0.00004149413,0.00003300914,0.74285656,0.23321171,0.009206475],"study_design_scores_gemma":[0.00024528624,0.000033546028,0.000008453453,0.000027473183,0.000023679448,0.0000023589223,0.35270083,0.008376753,0.000041632164,0.28385374,0.35454947,0.00013677086],"about_ca_topic_score_codex":0.00043434894,"about_ca_topic_score_gemma":0.0010569642,"teacher_disagreement_score":0.9319454,"about_ca_system_score_codex":0.00007474463,"about_ca_system_score_gemma":0.0000813992,"threshold_uncertainty_score":0.99966174},"labels":[],"label_agreement":null},{"id":"W4403557110","doi":"10.1007/978-3-031-68146-2_7","title":"Improving Information Interoperability for Safety and Security Organizations Using Information Mesh","year":2024,"lang":"en","type":"book-chapter","venue":"Advanced sciences and technologies for security applications","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Interoperability; Computer security; Information security; Business; Computer science; Knowledge management; World Wide Web","score_opus":0.03880117234383387,"score_gpt":0.34338798377593094,"score_spread":0.3045868114320971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403557110","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":[0.00035516627,0.0010092958,0.96499604,0.00430025,0.00036707614,0.0057785125,0.005539491,0.0007501968,0.016903965],"genre_scores_gemma":[0.5957168,0.0153058395,0.35129535,0.0029737812,0.0004316787,0.0070971176,0.007028426,0.000216315,0.019934705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975732,0.000010239621,0.0010339263,0.00063127617,0.00047466328,0.0002766989],"domain_scores_gemma":[0.9973223,0.00061918126,0.0006149544,0.00065751554,0.00072816724,0.000057861063],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019252213,0.00028380254,0.0003844715,0.00060037983,0.001200006,0.0010481396,0.0008594864,0.00029436708,0.000012312744],"category_scores_gemma":[0.0015416663,0.0002348273,0.0000862628,0.0005720762,0.001038528,0.0034825213,0.00095548364,0.0002481797,0.0000175366],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011777619,0.0000067296446,0.00000299205,0.00019891866,0.000012998914,2.086011e-8,0.00043881437,0.00003498129,0.0000069776397,0.8357895,0.00023721247,0.16325909],"study_design_scores_gemma":[0.00012242622,0.00006437303,0.0000015465597,0.000030486617,0.000037812904,0.0000022396175,0.0027432058,0.013009671,0.000035408495,0.5274419,0.45633766,0.00017324931],"about_ca_topic_score_codex":0.000026834634,"about_ca_topic_score_gemma":0.00011518053,"teacher_disagreement_score":0.6137007,"about_ca_system_score_codex":0.00010583606,"about_ca_system_score_gemma":0.00010939913,"threshold_uncertainty_score":0.99998885},"labels":[],"label_agreement":null},{"id":"W4403557122","doi":"10.1007/978-3-031-68146-2_4","title":"Information Management Standards in Canadian Public Safety and Security: Enhancing Interoperability, Collaboration and Resilience","year":2024,"lang":"en","type":"book-chapter","venue":"Advanced sciences and technologies for security applications","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Interoperability; Resilience (materials science); Business; Computer security; Standard of Good Practice; Information security; Knowledge management; Computer science; World Wide Web; Security service","score_opus":0.026241686489295955,"score_gpt":0.34927696369378647,"score_spread":0.3230352772044905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403557122","genre_codex":"other","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":[0.008290739,0.026735611,0.11728261,0.14291312,0.0010687163,0.024077818,0.018257242,0.0017237158,0.65965044],"genre_scores_gemma":[0.9652253,0.020651113,0.006235673,0.0004216908,0.000023135186,0.0010590794,0.00021190703,0.000023223149,0.0061489134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973313,0.000018129176,0.00078128587,0.0007993659,0.000690939,0.00037897576],"domain_scores_gemma":[0.9984496,0.00030780892,0.00024411076,0.00056570594,0.00031341347,0.00011934597],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0038216421,0.00024658366,0.00034133877,0.0012377922,0.00078110385,0.0012309314,0.0007283291,0.00021880753,0.000011275833],"category_scores_gemma":[0.0005832913,0.00021195922,0.000032813587,0.00076933316,0.0012504328,0.0017113223,0.00087355566,0.00026420766,0.0000076257334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070978963,0.000004432319,0.000019881996,0.00012489625,0.00000726981,4.868023e-7,0.00047675724,0.0000048604143,0.0000011125896,0.8119295,0.00018056341,0.18724315],"study_design_scores_gemma":[0.00008842232,0.00005017303,0.0000135948985,0.00006059846,0.0000093502695,0.0000017046191,0.007303825,0.0005012644,0.000006908997,0.48845533,0.5033747,0.00013411263],"about_ca_topic_score_codex":0.00091533404,"about_ca_topic_score_gemma":0.25299358,"teacher_disagreement_score":0.9569345,"about_ca_system_score_codex":0.0002923554,"about_ca_system_score_gemma":0.00022858575,"threshold_uncertainty_score":0.99980587},"labels":[],"label_agreement":null},{"id":"W4403659932","doi":"10.2196/59844","title":"The University of California Study of Outcomes in Mothers and Infants (a Population-Based Research Resource): Retrospective Cohort Study","year":2024,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute on Drug Abuse","keywords":"Preprint; Retrospective cohort study; Cohort study; Medicine; Resource (disambiguation); Population; Environmental health; Computer science; World Wide Web","score_opus":0.153319479851705,"score_gpt":0.44182126216866263,"score_spread":0.28850178231695767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403659932","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":[0.99393487,0.0001519711,0.00003111349,0.0040800343,0.00004123612,0.0013585436,0.00009029007,0.000012492136,0.00029942428],"genre_scores_gemma":[0.9996166,0.00003396816,0.0000075621747,0.00005835367,0.000004778105,0.000008040373,0.0000060031966,0.0000036802703,0.0002610071],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99548084,0.002131107,0.0005006154,0.00041269048,0.0012161708,0.0002585551],"domain_scores_gemma":[0.9967195,0.002380839,0.00012912274,0.00046778665,0.00016857119,0.00013421367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026326764,0.00007176566,0.00034449075,0.00035238572,0.00029036473,0.00014149073,0.00033176242,0.000026778125,0.00001701137],"category_scores_gemma":[0.0019523961,0.00004752003,0.000019177915,0.0011782174,0.00014870596,0.000120321056,0.00018789966,0.00016852788,0.0000021845983],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048449067,0.00023412381,0.98223436,0.000023429184,0.000019357274,0.0000031673485,0.004751895,0.0000051383463,4.7062976e-8,0.0002926381,0.0015054615,0.010881958],"study_design_scores_gemma":[0.00044368443,0.00033959758,0.9411237,0.000005693986,3.182735e-7,1.00443266e-7,0.04142931,0.00072590186,8.360005e-9,0.00025230265,0.015639612,0.00003974844],"about_ca_topic_score_codex":0.0073806597,"about_ca_topic_score_gemma":0.027875237,"teacher_disagreement_score":0.041110616,"about_ca_system_score_codex":0.00009151299,"about_ca_system_score_gemma":0.00019887545,"threshold_uncertainty_score":0.99922925},"labels":[],"label_agreement":null},{"id":"W4403950719","doi":"10.23889/ijpds.v9i5.2932","title":"Leveraging Full Count Census Data through Record Linkage","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadiana.org","funders":"","keywords":"Census; Record linkage; Computer science; Linkage (software); Count data; Data science; Statistics; Medicine; Population; Biology; Environmental health; Mathematics; Genetics","score_opus":0.5370824940918127,"score_gpt":0.5509539962253384,"score_spread":0.013871502133525615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403950719","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":[0.021364896,0.00043702207,0.9031435,0.024013445,0.03888318,0.00041520124,0.009441078,0.00013390621,0.002167734],"genre_scores_gemma":[0.8923285,0.00046338825,0.0896165,0.00245971,0.0033795638,0.000008620402,0.008766144,0.00003182752,0.0029457211],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99347734,0.0000912814,0.0010280062,0.0011620484,0.0039183185,0.00032301486],"domain_scores_gemma":[0.9957987,0.00080561236,0.0003590944,0.0021233286,0.00078048575,0.00013280002],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.015322757,0.00014118584,0.00016592885,0.0005475529,0.0005890452,0.006394272,0.013292665,0.000037351587,0.00028978518],"category_scores_gemma":[0.007141498,0.000108392305,0.000059133705,0.0009020839,0.00018437089,0.015421571,0.0038159594,0.00024934113,0.00021253298],"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":[0.00007716733,0.00007376689,0.0012414326,0.00001458058,0.00008035225,0.00007914997,0.00042342918,0.0006158901,0.00025945416,0.08077075,0.4325919,0.48377213],"study_design_scores_gemma":[0.00015505418,0.000020276433,0.0020466885,0.00007015387,0.000014367585,0.00009137753,0.00030670647,0.1741634,0.000009177234,0.055332158,0.76766115,0.0001294928],"about_ca_topic_score_codex":0.00036850246,"about_ca_topic_score_gemma":0.0001689752,"teacher_disagreement_score":0.87096363,"about_ca_system_score_codex":0.00020764838,"about_ca_system_score_gemma":0.00025974284,"threshold_uncertainty_score":0.99834925},"labels":[],"label_agreement":null},{"id":"W4404049985","doi":"10.2196/60244","title":"Building a Foundation for High-Quality Health Data: Multihospital Case Study in Belgium","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Medicine; Quality (philosophy); Foundation (evidence); Computer science; Data science; World Wide Web; Geography","score_opus":0.2941413349360141,"score_gpt":0.5625659524406184,"score_spread":0.2684246175046043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404049985","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":[0.6425593,0.000044958655,0.34685865,0.0056460584,0.0017267726,0.002507596,0.00032697135,0.00013763951,0.00019206517],"genre_scores_gemma":[0.9803022,0.00001382645,0.017001335,0.0018674217,0.00020373633,0.00017817465,0.00029640482,0.000010162992,0.00012670715],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994443,0.0002695167,0.0022924056,0.000340914,0.0023039267,0.00035024376],"domain_scores_gemma":[0.9961547,0.0021414997,0.00028440476,0.0010755406,0.00009004545,0.00025379247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023583386,0.00014428742,0.00038180128,0.0003414754,0.00016538247,0.00074743223,0.0011912669,0.000084453546,0.00012647444],"category_scores_gemma":[0.0042510787,0.00010561873,0.000047487694,0.0008092899,0.00009136468,0.002253369,0.0010662094,0.00029580505,0.00015485552],"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":[0.000022864162,0.0005749775,0.00037229504,0.0005253799,0.000044165903,0.00025244695,0.025320714,0.000015282338,1.8902978e-7,0.0422483,0.045321226,0.8853022],"study_design_scores_gemma":[0.0038088807,0.0009778244,0.0036672733,0.00038387917,0.000035303758,0.00018323991,0.23899774,0.31380144,0.0000025760335,0.025905266,0.41162497,0.0006115913],"about_ca_topic_score_codex":0.0011334874,"about_ca_topic_score_gemma":0.0024138065,"teacher_disagreement_score":0.8846906,"about_ca_system_score_codex":0.00013070733,"about_ca_system_score_gemma":0.00035448087,"threshold_uncertainty_score":0.81735784},"labels":[],"label_agreement":null},{"id":"W4404818404","doi":"10.1007/978-981-96-0579-8_16","title":"RePair My Queries: Personalized Query Reformulation via Conditional Transformers","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Query optimization; Information retrieval; Transformer; Sargable; Web search query; Database; Search engine","score_opus":0.06617546119587851,"score_gpt":0.35038473437706585,"score_spread":0.2842092731811873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404818404","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":[0.00005427585,0.00033383735,0.9708861,0.0023396458,0.0018920668,0.0004437142,0.00014496905,0.00018225552,0.023723146],"genre_scores_gemma":[0.4587648,0.00051817973,0.36315045,0.031274445,0.0048836344,0.00016714525,0.0016565998,0.000325571,0.13925919],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99346095,0.000059821006,0.0010431131,0.0017009886,0.0032632088,0.0004719393],"domain_scores_gemma":[0.9972819,0.0010564296,0.0002793129,0.0009093737,0.0003145673,0.0001584185],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0046072397,0.00043740452,0.0005593387,0.001278752,0.00030662445,0.00063386693,0.0014370187,0.0002805914,0.00086846325],"category_scores_gemma":[0.00032509086,0.00033237395,0.0003634065,0.0008150546,0.0014730146,0.0010494161,0.0005076557,0.00062119256,0.0005753715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066593355,0.000039704697,0.000022683287,0.00012635079,0.0000673556,0.00013403741,0.0028163788,0.010038618,0.000054346132,0.47989398,0.001720032,0.5050199],"study_design_scores_gemma":[0.000193994,0.00009427353,0.00006664997,0.00019111329,0.00002182262,0.000026284273,0.00000575044,0.088416345,0.000055641416,0.7028222,0.20768617,0.0004197496],"about_ca_topic_score_codex":0.000059911865,"about_ca_topic_score_gemma":0.0003324005,"teacher_disagreement_score":0.60773563,"about_ca_system_score_codex":0.0004093812,"about_ca_system_score_gemma":0.00039892748,"threshold_uncertainty_score":0.99991286},"labels":[],"label_agreement":null},{"id":"W4405035632","doi":"10.48550/arxiv.2412.01953","title":"The Landscape of Causal Discovery Data: Grounding Causal Discovery in Real-World Applications","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health; Bundesministerium für Bildung und Forschung; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Data science; Data discovery; Computer science; Geography; World Wide Web","score_opus":0.281484289759273,"score_gpt":0.3330710474130075,"score_spread":0.05158675765373455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405035632","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":[0.63710594,0.0008436034,0.25321496,0.002387882,0.005098517,0.0032365622,0.007983371,0.0002822526,0.08984692],"genre_scores_gemma":[0.9639369,0.001048167,0.000047773818,0.000040085866,0.00016304327,0.000006599835,0.00045791946,0.00001954834,0.034279935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962901,0.00041141943,0.0007591414,0.0016645197,0.00049551844,0.00037928927],"domain_scores_gemma":[0.9933464,0.0019191556,0.00050425384,0.0040422017,0.000096418575,0.00009160405],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.004061518,0.00029513883,0.0004972107,0.00074746646,0.00023418198,0.0011888158,0.004639508,0.0001404304,0.00003134374],"category_scores_gemma":[0.00031200715,0.00022759847,0.00017780291,0.0021013243,0.0003501082,0.0014176856,0.012569459,0.0007157535,0.00015641164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009046879,0.00013649046,0.009453174,0.00013818234,0.0001616605,0.00012626902,0.00017295286,0.012137986,0.000007921814,0.9613453,0.014457149,0.0017724056],"study_design_scores_gemma":[0.000635302,0.00005249463,0.021760944,0.00037230543,0.00043905948,0.0000021589553,0.006760708,0.034189567,0.000020234462,0.8448451,0.090073004,0.0008491112],"about_ca_topic_score_codex":0.003081363,"about_ca_topic_score_gemma":0.026861524,"teacher_disagreement_score":0.32683098,"about_ca_system_score_codex":0.00019542035,"about_ca_system_score_gemma":0.00031622103,"threshold_uncertainty_score":0.99984807},"labels":[],"label_agreement":null},{"id":"W4405688611","doi":"10.1017/s1049096524000945","title":"Data Sovereignty and Development: How do Native Americans View Data Sharing by Tribal Governments?","year":2024,"lang":"en","type":"article","venue":"PS Political Science & Politics","topic":"Data Quality and Management","field":"Decision Sciences","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 Victoria","funders":"","keywords":"Indigenous; Sovereignty; Political science; Data sharing; Survey data collection; Native american; Data collection; Economic growth; Public relations; Public administration; Sociology; Law; Ethnology; Economics; Medicine; Social science; Politics","score_opus":0.3863989094866279,"score_gpt":0.4780098752387215,"score_spread":0.0916109657520936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405688611","genre_codex":"other","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":[0.06218949,0.0060383556,0.2559633,0.11067321,0.005764329,0.0030292303,0.121772796,0.0010973202,0.43347198],"genre_scores_gemma":[0.9882845,0.00007170595,0.004810383,0.0034202915,0.00019908894,0.00000870187,0.0003833705,0.000019276642,0.0028026737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99093646,0.00014637993,0.0007177612,0.002491904,0.0038748973,0.0018325717],"domain_scores_gemma":[0.9934185,0.0014401266,0.000121996476,0.0036263396,0.00015444007,0.0012385979],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00919108,0.0002936361,0.00039259862,0.00021926968,0.00062433025,0.0046795863,0.0090988865,0.00006333356,0.00042553758],"category_scores_gemma":[0.00874372,0.00022384523,0.000031103915,0.0011450305,0.0026142027,0.0040518027,0.013529388,0.0003019602,0.00027325584],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019175754,0.000062048886,0.00032743727,0.000031953557,0.000022533806,0.000013228006,0.00022095104,1.6206664e-7,0.00001928239,0.9490635,0.024004554,0.02623248],"study_design_scores_gemma":[0.00017498748,0.00004256872,0.0015336764,0.00007794853,0.000040563926,0.000016988295,0.004485026,0.008619109,0.00023066779,0.19545387,0.7889028,0.00042178304],"about_ca_topic_score_codex":0.00030073788,"about_ca_topic_score_gemma":0.000027940912,"teacher_disagreement_score":0.926095,"about_ca_system_score_codex":0.00057050487,"about_ca_system_score_gemma":0.0009132468,"threshold_uncertainty_score":0.9996061},"labels":[],"label_agreement":null},{"id":"W4406143719","doi":"10.2139/ssrn.5075185","title":"An Observation-Driven State-Space Model for Claims Size Modeling","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"State space; Space (punctuation); State (computer science); State-space representation; Econometrics; Computer science; Statistical physics; Mathematics; Physics; Statistics; Algorithm","score_opus":0.17088413144311337,"score_gpt":0.42279479117673335,"score_spread":0.25191065973362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406143719","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":[0.026859516,0.00047186832,0.9654588,0.0050827046,0.0007359713,0.00070098956,0.00034385314,0.00006651278,0.00027975795],"genre_scores_gemma":[0.848713,0.007845883,0.073337026,0.0020047533,0.0007585459,0.00020858648,0.00031416808,0.000084233325,0.06673382],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931142,0.00040433975,0.001430709,0.0010626398,0.0016482931,0.0023398418],"domain_scores_gemma":[0.99578476,0.0007775511,0.0008243082,0.0014371951,0.0009875263,0.00018865969],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01618976,0.00040834665,0.0006685731,0.00039741077,0.00053869735,0.0012209195,0.0034372308,0.00026924894,0.000028226697],"category_scores_gemma":[0.0015852887,0.00034817387,0.0004446977,0.00036054634,0.00004757881,0.0008864287,0.00088280713,0.003141288,0.000021285556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010230506,0.00008203262,0.000037703783,0.000023844632,0.00016329499,6.3630205e-7,0.0005350419,0.79069173,0.00001132811,0.18651855,0.0016121219,0.020221412],"study_design_scores_gemma":[0.000285401,0.000059220205,0.0000046058653,0.00003322758,0.000047260044,0.0000019724139,0.0011645566,0.5001018,0.0000025020306,0.49667776,0.0014321358,0.00018955485],"about_ca_topic_score_codex":0.00015749072,"about_ca_topic_score_gemma":0.0038589842,"teacher_disagreement_score":0.8921218,"about_ca_system_score_codex":0.0012406935,"about_ca_system_score_gemma":0.0076872944,"threshold_uncertainty_score":0.999897},"labels":[],"label_agreement":null},{"id":"W4406235423","doi":"10.51594/gjabr.v3i1.66","title":"A collaborative model for data governance: enhancing integration across multi-line businesses","year":2025,"lang":"en","type":"article","venue":"Gulf Journal of Advance Business Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TD Bank Group","funders":"Cisco Systems","keywords":"Corporate governance; Business; Line (geometry); Collaborative governance; Process management; Knowledge management; Computer science; Finance","score_opus":0.417733298033663,"score_gpt":0.5943428410539254,"score_spread":0.17660954302026244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406235423","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":[0.0022786474,0.0020464119,0.9853763,0.0083449595,0.00068049337,0.00040804737,0.0007074704,0.000009299661,0.00014837438],"genre_scores_gemma":[0.4265559,0.008899268,0.5331535,0.0011252871,0.0008228052,0.00011952587,0.00025826858,0.0000583784,0.029007101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99452424,0.00034237304,0.0014555354,0.0006141651,0.0025299583,0.0005337356],"domain_scores_gemma":[0.9770382,0.0028217973,0.00083201687,0.0014131165,0.01779677,0.000098115044],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016521309,0.00018410922,0.00055856496,0.00045540335,0.0005443203,0.0008716095,0.0033637565,0.00008328038,0.000026945903],"category_scores_gemma":[0.04867895,0.0001327807,0.00006728159,0.0053873984,0.00032604573,0.0041787387,0.0014759327,0.0003705537,0.000012417373],"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":[0.0028628036,0.00090463203,0.00015516032,0.00027749236,0.00013330142,0.00004469512,0.0016338073,0.06255849,0.0075767497,0.030275717,0.12663718,0.76694],"study_design_scores_gemma":[0.003958083,0.00014142343,0.0025870653,0.0011425465,0.000035669884,0.000012267167,0.009071934,0.5594607,0.0049448437,0.10851952,0.3097689,0.00035704154],"about_ca_topic_score_codex":0.00005538145,"about_ca_topic_score_gemma":0.0018759061,"teacher_disagreement_score":0.7665829,"about_ca_system_score_codex":0.00019762877,"about_ca_system_score_gemma":0.0012976754,"threshold_uncertainty_score":0.95933443},"labels":[],"label_agreement":null},{"id":"W4406435392","doi":"10.1162/99608f92.6f5dfc6f","title":"Data Literacy in Industry: High Time to Focus on Operationalization Through Middle Managers","year":2025,"lang":"en","type":"article","venue":"Harvard Data Science Review","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Dalhousie University","keywords":"Operationalization; Focus (optics); Middle management; Business; Literacy; Psychology; Marketing; Pedagogy","score_opus":0.33414786909287836,"score_gpt":0.49253170853835254,"score_spread":0.15838383944547418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406435392","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001857673,0.016457664,0.21028414,0.41643775,0.004368391,0.015129707,0.03695855,0.0004718614,0.29803428],"genre_scores_gemma":[0.034918036,0.10081,0.15972184,0.5483087,0.00079568656,0.00068925106,0.047949623,0.00012144052,0.106685475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994378,0.00039793574,0.0010023107,0.0018352235,0.0020126705,0.0003738707],"domain_scores_gemma":[0.9913082,0.0004960886,0.00019579894,0.0076333047,0.00024116503,0.00012545682],"candidate_categories":["metaresearch","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.015204515,0.00018067964,0.0004279747,0.0004731114,0.00026429398,0.0013613942,0.011712191,0.000057303325,0.0037626894],"category_scores_gemma":[0.013914847,0.00013756812,0.000024729077,0.007387759,0.00020849891,0.009244401,0.007072378,0.00021285507,0.0151168015],"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":[0.000006683358,0.00010180463,0.00006921301,0.00015545244,0.000006479927,0.000007522959,0.00004072033,0.00006766745,0.000011018866,0.098153025,0.6566022,0.24477823],"study_design_scores_gemma":[0.00012135406,0.000017654502,0.00089214137,0.002360533,0.000019450938,8.180194e-7,0.000042647753,0.002341711,0.000012228538,0.0055055707,0.98852944,0.00015641772],"about_ca_topic_score_codex":0.0001754103,"about_ca_topic_score_gemma":0.00008713342,"teacher_disagreement_score":0.3319273,"about_ca_system_score_codex":0.00010733308,"about_ca_system_score_gemma":0.0003832127,"threshold_uncertainty_score":0.9996753},"labels":[],"label_agreement":null},{"id":"W4406458491","doi":"10.1109/bigdata62323.2024.10825531","title":"Evaluating Blocking Biases in Entity Matching","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Blocking (statistics); Computer science; Matching (statistics); Computer network; Statistics; Mathematics","score_opus":0.6492312296609014,"score_gpt":0.5953427079241184,"score_spread":0.053888521736783046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406458491","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":[0.93461835,0.0002325396,0.020309202,0.0017748687,0.00076638494,0.00013220185,0.00000839493,0.00012964205,0.04202842],"genre_scores_gemma":[0.9903486,0.0000068240925,0.0033172516,0.0004088325,0.000048352915,0.0000052548635,0.0000032751534,0.0000037913144,0.0058578146],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979011,0.00019841951,0.00041180142,0.0003580917,0.0009576734,0.00017290561],"domain_scores_gemma":[0.99777687,0.0018179007,0.000031276562,0.0003128286,0.000028138125,0.00003297003],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.011493436,0.000059179638,0.00010503353,0.00030893,0.00006302329,0.0010021469,0.00039785635,0.000018263288,0.0018872285],"category_scores_gemma":[0.0030378466,0.00004182712,0.000046487952,0.0007405827,0.000018292314,0.00059759244,0.00035731948,0.00008787863,0.0011146942],"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":[0.0000055228793,0.00008699322,0.0013968755,0.000037465612,0.00001582578,0.00007018458,0.0024046127,0.0040764124,0.0007341018,0.135069,0.02039029,0.83571273],"study_design_scores_gemma":[0.00037914616,0.000059708218,0.008699613,0.00046052056,0.000020907315,0.0000065960267,0.01073867,0.28689712,0.00086852594,0.5688907,0.12260345,0.0003750416],"about_ca_topic_score_codex":0.00058710645,"about_ca_topic_score_gemma":0.0011872663,"teacher_disagreement_score":0.8353377,"about_ca_system_score_codex":0.000030861644,"about_ca_system_score_gemma":0.000031249474,"threshold_uncertainty_score":0.99966305},"labels":[],"label_agreement":null},{"id":"W4406521103","doi":"10.1016/s0029-7437(06)71612-3","title":"10.1016/s0029-7437(06)71612-3","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Health records; Psychology; Medicine; Health care; Political science","score_opus":0.06377578750155208,"score_gpt":0.3041293908618411,"score_spread":0.24035360336028902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406521103","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016479442,0.000025642652,0.00004013639,0.0017020537,5.130707e-7,0.00020104133,0.000067532994,0.00011609511,0.9976822],"genre_scores_gemma":[0.00007415473,3.0009264e-7,0.00033893704,0.00037564503,0.00011202828,0.000014655942,0.000026139178,0.000011066802,0.9990471],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975099,0.00016426446,0.0004562801,0.0004947526,0.0010565172,0.00031826162],"domain_scores_gemma":[0.9983019,0.00031774395,0.000063867345,0.0010312032,0.00008081978,0.00020445802],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021917587,0.00013863777,0.00022921241,0.00017453835,0.0001346702,0.00034797506,0.0012022766,0.00004821441,0.9994245],"category_scores_gemma":[0.0005439765,0.00011160248,0.000089031884,0.0006559132,0.000056123677,0.00037531275,0.0002607082,0.00008777581,0.9997176],"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":[0.00002063746,0.00003499388,5.920417e-8,9.824105e-7,0.0000060626135,0.000002728163,0.000021411284,0.000036304627,0.000002245158,0.000023875038,0.64246005,0.35739064],"study_design_scores_gemma":[0.0001658935,0.00007612913,0.00006086972,0.000006474017,0.00000921006,0.0000020477635,0.000012362589,0.00017913622,0.000017714914,0.0006467692,0.998659,0.0001643502],"about_ca_topic_score_codex":0.00003813403,"about_ca_topic_score_gemma":0.0000012392557,"teacher_disagreement_score":0.35722628,"about_ca_system_score_codex":0.000025372929,"about_ca_system_score_gemma":0.000022576081,"threshold_uncertainty_score":0.4551017},"labels":[],"label_agreement":null},{"id":"W4406547244","doi":"10.1016/s1541-9800(06)70944-9","title":"10.1016/s1541-9800(06)70944-9","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Key (lock); Sense of control; Sense (electronics); Control (management); Computer science; Psychology; Engineering; Computer security; Electrical engineering; Artificial intelligence; Social psychology","score_opus":0.06211475748195413,"score_gpt":0.3016894417369277,"score_spread":0.23957468425497355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406547244","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001693011,0.000025948064,0.000035910438,0.0020239837,0.000003457553,0.00020089753,0.000066587585,0.00009952888,0.99737436],"genre_scores_gemma":[0.0000983528,3.0465824e-7,0.00028461582,0.0004286674,0.00010264024,0.000014571827,0.00002772491,0.000011065237,0.9990321],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974823,0.00016917914,0.00045762732,0.00049503986,0.001073556,0.00032231098],"domain_scores_gemma":[0.9982896,0.00032506094,0.000062538915,0.001031541,0.00008149916,0.00020975678],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0022240987,0.0001392459,0.00023075228,0.00017528508,0.00013329324,0.0003483546,0.001203863,0.000049196686,0.9992837],"category_scores_gemma":[0.0005794754,0.00011166848,0.00008945374,0.0006569762,0.000057260444,0.00037544037,0.00026187094,0.00008819856,0.9996963],"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":[0.00001868861,0.000030557036,5.035329e-8,8.8098926e-7,0.000005287743,0.0000033646982,0.000019383839,0.00003800034,0.0000021541682,0.000019556393,0.5482641,0.451598],"study_design_scores_gemma":[0.00016997568,0.000074817915,0.000064593594,0.000006543693,0.00000924532,0.000002026224,0.000012025612,0.00019549548,0.000018845376,0.00066708215,0.998615,0.0001643273],"about_ca_topic_score_codex":0.000038675174,"about_ca_topic_score_gemma":0.0000012735612,"teacher_disagreement_score":0.45143366,"about_ca_system_score_codex":0.000025682282,"about_ca_system_score_gemma":0.000024240198,"threshold_uncertainty_score":0.45537084},"labels":[],"label_agreement":null},{"id":"W4406764237","doi":"10.9734/jerr/2025/v27i21391","title":"Continuous Data Quality Improvement in Enterprise Data Governance: A Model for Best Practices and Implementation","year":2025,"lang":"en","type":"article","venue":"Journal of Engineering Research and Reports","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TD Bank Group","funders":"","keywords":"Data governance; Data quality; Process management; Computer science; Enterprise data management; Best practice; Quality (philosophy); Corporate governance; Quality management; Knowledge management; Business; Enterprise information system; Engineering; Management system; Operations management","score_opus":0.44797708373746586,"score_gpt":0.5894965732693396,"score_spread":0.1415194895318737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406764237","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":[0.81443584,0.0045014448,0.17005372,0.008250694,0.0006820289,0.0012161048,0.0005953143,0.000009124031,0.00025570026],"genre_scores_gemma":[0.99093944,0.0014244174,0.006490964,0.000048251168,0.00006416621,0.000010472574,0.000050054925,0.000005244343,0.0009670107],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972165,0.00007236599,0.0010938055,0.00039338152,0.0010059999,0.00021790153],"domain_scores_gemma":[0.9965397,0.0011903305,0.0008256293,0.0009961961,0.00035797703,0.00009013947],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.029136019,0.00007157294,0.000240039,0.0002662489,0.00006916882,0.00041006092,0.00070415455,0.000029550762,0.0000051941943],"category_scores_gemma":[0.013222581,0.00005313227,0.000016560743,0.00025405493,0.000040865172,0.0014323264,0.0014771684,0.00021141792,1.6165568e-7],"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":[0.00068767,0.00091861683,0.03725081,0.000999446,0.0003731793,0.0005761275,0.0012685289,0.0023846976,0.0064618853,0.0065079173,0.13854355,0.80402756],"study_design_scores_gemma":[0.0043319413,0.0012113327,0.05739044,0.0008595024,0.00011288359,0.0001959172,0.013056424,0.48721084,0.00064015144,0.032301538,0.40220705,0.00048197497],"about_ca_topic_score_codex":0.00036714657,"about_ca_topic_score_gemma":0.0004915923,"teacher_disagreement_score":0.8035456,"about_ca_system_score_codex":0.00004369677,"about_ca_system_score_gemma":0.00018497906,"threshold_uncertainty_score":0.9997088},"labels":[],"label_agreement":null},{"id":"W4407186971","doi":"10.48550/arxiv.2502.02495","title":"The Causal-Effect Score in Data Management","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Econometrics; Psychology; Business; Computer science; Economics","score_opus":0.4129349039886431,"score_gpt":0.4731542193109673,"score_spread":0.06021931532232422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407186971","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":[0.6333372,0.0045363363,0.014795522,0.04750998,0.020799048,0.009726464,0.0031250305,0.00050009735,0.26567033],"genre_scores_gemma":[0.8156287,0.0038048949,0.0008722424,0.004450418,0.000513702,0.00069238775,0.0019518556,0.000050548177,0.17203525],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99406147,0.001005192,0.0011172575,0.001787754,0.0015371756,0.00049113703],"domain_scores_gemma":[0.98835367,0.0022515045,0.0003802265,0.008851401,0.00008045773,0.0000827229],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.015896633,0.000351888,0.0005342422,0.00039717264,0.00027778072,0.0007790458,0.010212475,0.00016797741,0.00014062261],"category_scores_gemma":[0.0024147488,0.00022017393,0.00013104739,0.00082622643,0.0001800306,0.00031975095,0.03036569,0.00071605475,0.0012672272],"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":[0.00010180991,0.00015597034,0.20280969,0.00035497526,0.00031071788,0.00019212264,0.0002573166,0.00042851202,0.0000016074099,0.018399332,0.54188204,0.23510595],"study_design_scores_gemma":[0.00035911254,0.000020118023,0.22780351,0.00028859972,0.00008193598,4.53836e-7,0.00043604855,0.00068405585,0.000016039681,0.015866319,0.7541539,0.0002899111],"about_ca_topic_score_codex":0.00046268926,"about_ca_topic_score_gemma":0.0026011781,"teacher_disagreement_score":0.23481603,"about_ca_system_score_codex":0.00010527765,"about_ca_system_score_gemma":0.000096710864,"threshold_uncertainty_score":0.9995104},"labels":[],"label_agreement":null},{"id":"W4407189694","doi":"10.23977/jeis.2024.090325","title":"Full-Link Metadata Capability Construction and Practice in Data Governance Platforms","year":2024,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Metadata; Link (geometry); Corporate governance; Computer science; World Wide Web; Database; Business; Data science; Computer network; Finance","score_opus":0.08966162636159357,"score_gpt":0.40991070344795144,"score_spread":0.32024907708635786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407189694","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":[0.5266454,0.022966485,0.34276494,0.08627388,0.0035823665,0.0008586932,0.0004539519,0.000047206628,0.016407039],"genre_scores_gemma":[0.9652729,0.017444357,0.015947087,0.0011581051,0.00008731207,0.0000013525882,0.000014495119,0.0000031466607,0.000071216804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99728906,0.000044211247,0.00090612523,0.0001994956,0.0013768948,0.00018420961],"domain_scores_gemma":[0.99769104,0.000873851,0.0005396618,0.00044204082,0.00037012075,0.000083269755],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.026031267,0.00006843273,0.00015264303,0.00034027116,0.0001260439,0.0020964711,0.0009186904,0.000027110878,0.000014211262],"category_scores_gemma":[0.012382384,0.000045096527,0.000016194783,0.0012520904,0.00033972412,0.07401468,0.00045311803,0.0002535101,0.000007668191],"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":[0.00008310064,0.000011778093,0.00004835616,0.000020336234,0.000008472682,0.0000025005447,0.0007808708,0.00007015079,0.00014625269,0.44641757,0.0017093375,0.55070126],"study_design_scores_gemma":[0.00023804451,0.00016419445,0.0018750057,0.00003618227,0.000016259866,0.0004789544,0.0020796289,0.029772853,0.00007061582,0.031706307,0.9334715,0.00009047245],"about_ca_topic_score_codex":0.0000132498735,"about_ca_topic_score_gemma":0.000042773583,"teacher_disagreement_score":0.93176216,"about_ca_system_score_codex":0.00008768448,"about_ca_system_score_gemma":0.0005537979,"threshold_uncertainty_score":0.99893945},"labels":[],"label_agreement":null},{"id":"W4407328480","doi":"10.2139/ssrn.5129284","title":"Data Portability in financial services: A research note on the progress &amp;amp; debates around Canadian open banking regulation","year":2025,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Software portability; Business; Financial services; Financial system; Economics; Finance; Computer science; Operating system","score_opus":0.24610564274127691,"score_gpt":0.4883171585682954,"score_spread":0.24221151582701847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407328480","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":[0.8414767,0.0017525308,0.013073443,0.11486203,0.0010411771,0.0032960908,0.0002983351,0.000034466128,0.024165228],"genre_scores_gemma":[0.9953854,0.00016157111,0.00019228648,0.00081331166,0.00011771447,0.000025398402,0.000115519775,0.000007822465,0.0031809823],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99382776,0.001465704,0.0007378425,0.00065902655,0.001398145,0.0019115087],"domain_scores_gemma":[0.9961338,0.0011899632,0.0002183878,0.0020232236,0.00032930283,0.00010532397],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0770772,0.00013569945,0.00022801835,0.0006356054,0.0010183553,0.0019236945,0.0064224973,0.000088147266,0.00023095714],"category_scores_gemma":[0.0029321322,0.00008950049,0.00004315361,0.0019466932,0.00015362799,0.0011452005,0.0013503872,0.0019114701,0.00015962339],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027409516,0.00016061662,0.020389963,0.000014450454,0.00004702516,0.000005755844,0.0009235253,0.00010510516,0.000005723654,0.72949374,0.010093615,0.2384864],"study_design_scores_gemma":[0.00022616478,0.00003265763,0.02318224,0.00007838087,0.0000065448044,0.0000053936355,0.002028652,0.0004797319,0.0000026914165,0.7459482,0.22792567,0.00008370397],"about_ca_topic_score_codex":0.08210646,"about_ca_topic_score_gemma":0.9807238,"teacher_disagreement_score":0.8986173,"about_ca_system_score_codex":0.00158528,"about_ca_system_score_gemma":0.008206584,"threshold_uncertainty_score":0.9991124},"labels":[],"label_agreement":null},{"id":"W4407873161","doi":"10.2139/ssrn.5152241","title":"Context-Aware Entity-Relation Extraction Pipeline for Threat Intelligence Knowledge Graphs","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Pipeline (software); Context (archaeology); Computer science; Relation (database); Knowledge graph; Relationship extraction; Extraction (chemistry); Entity linking; Artificial intelligence; Data science; Knowledge management; Data mining; Knowledge base; Programming language; Geography; Chemistry; Chromatography","score_opus":0.12341697991583002,"score_gpt":0.4437445261267874,"score_spread":0.3203275462109574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407873161","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":[0.001079395,0.009121856,0.9804411,0.0020376889,0.003705349,0.00088651874,0.00016637157,0.000063883796,0.0024978537],"genre_scores_gemma":[0.9071631,0.021516986,0.00062898063,0.00029830282,0.0007735472,0.00012153962,0.00031517012,0.000031760464,0.06915064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942973,0.0005526175,0.0015793303,0.0009228458,0.0010396625,0.0016082294],"domain_scores_gemma":[0.99555194,0.0012452558,0.0011286167,0.0008984431,0.0010582668,0.00011749488],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.018248295,0.0003823036,0.0005981081,0.0009590777,0.00056262827,0.000747582,0.0019270123,0.00037556482,0.00016181344],"category_scores_gemma":[0.0020034274,0.0003239696,0.0006312668,0.00059253233,0.00009928931,0.00066270534,0.00075835735,0.0035727026,0.00017961064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010648888,0.0001446864,0.00010294749,0.000040162235,0.00015891189,8.2205474e-7,0.00022710525,0.000524519,0.0000035010264,0.52631855,0.0072372276,0.4651351],"study_design_scores_gemma":[0.00031743618,0.00010247598,0.000104058985,0.00015947578,0.00016430403,0.000021988733,0.0038746041,0.0078079067,0.00006781075,0.91745687,0.06963392,0.0002891305],"about_ca_topic_score_codex":0.00017799437,"about_ca_topic_score_gemma":0.009585654,"teacher_disagreement_score":0.9798121,"about_ca_system_score_codex":0.00123808,"about_ca_system_score_gemma":0.0030766493,"threshold_uncertainty_score":0.99992126},"labels":[],"label_agreement":null},{"id":"W4408326934","doi":"10.1007/s42822-025-00200-0","title":"The Data Resistance: Preserving Data Set Integrity During Federal Purges","year":2025,"lang":"en","type":"article","venue":"Behavior and Social Issues","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Research integrity; Resistance (ecology); Set (abstract data type); Data integrity; Data set; Psychology; Computer science; Computer security; Political science; Public relations; Artificial intelligence; Programming language","score_opus":0.41652782713431913,"score_gpt":0.5290144536975795,"score_spread":0.11248662656326036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408326934","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":[0.9258716,0.005492972,0.00038066777,0.05208191,0.00154053,0.0008406752,0.004740418,0.00016648615,0.008884756],"genre_scores_gemma":[0.9369826,0.0006226004,0.0003672414,0.00024673497,0.00025671857,0.000027428803,0.0007825207,0.000008420755,0.06070574],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99774635,0.00032447782,0.0004021096,0.0006199499,0.0006753909,0.00023172096],"domain_scores_gemma":[0.9972899,0.00043380065,0.00009887372,0.0020537819,0.00008866632,0.000034980007],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0042409324,0.00010931474,0.00020856163,0.000052647734,0.0018125856,0.0018469439,0.0038687622,0.00006705381,0.00006707381],"category_scores_gemma":[0.0012872334,0.000072988034,0.00002710419,0.00023761441,0.00021956245,0.0009940647,0.006437748,0.00019950645,0.000012047342],"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":[0.00007996171,0.00010258664,0.03453775,0.000052858803,0.00004467754,0.000017706685,0.0029329387,6.132504e-8,0.00007044579,0.026121292,0.88853025,0.047509477],"study_design_scores_gemma":[0.00018085146,0.0000037049304,0.19302428,0.00002054448,0.000047765938,2.2091741e-7,0.015034627,0.000027163751,0.00003767225,0.008397358,0.7831076,0.000118243384],"about_ca_topic_score_codex":0.0012278686,"about_ca_topic_score_gemma":0.008423582,"teacher_disagreement_score":0.15848652,"about_ca_system_score_codex":0.000016414824,"about_ca_system_score_gemma":0.00004028553,"threshold_uncertainty_score":0.9994869},"labels":[],"label_agreement":null},{"id":"W4408440538","doi":"10.5194/egusphere-egu25-4596","title":"ContrailBench: evaluating the performance of contrail models","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Environmental science","score_opus":0.5004050430154415,"score_gpt":0.5058007409941256,"score_spread":0.005395697978684111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408440538","genre_codex":"other","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":[0.22057688,0.0008807807,0.1506733,0.008584431,0.002839778,0.0025453486,0.00080749224,0.00011089414,0.6129811],"genre_scores_gemma":[0.95303947,0.00014062054,0.0028543137,0.0016588286,0.00005911552,0.00007882763,0.000028071365,0.000004907962,0.04213584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99493825,0.00057513634,0.0013582163,0.00066001463,0.0022193985,0.00024896362],"domain_scores_gemma":[0.993834,0.0026831545,0.0006655997,0.0021275354,0.00064470666,0.000044965724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016420128,0.00021182127,0.0005703537,0.00018401547,0.00015340878,0.00031176675,0.0031606287,0.00013911794,0.00082344824],"category_scores_gemma":[0.0020834864,0.00011472414,0.00022378216,0.00032757656,0.00021277767,0.00026069925,0.0031355207,0.0003978456,0.000057334724],"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":[0.00010511749,0.00010557221,0.00014204507,0.00023748128,0.00020700725,7.5353984e-7,0.0019135909,0.17222592,0.0000463908,0.43930194,0.044935074,0.3407791],"study_design_scores_gemma":[0.0003142451,0.00007917736,0.00046793564,0.0001488541,0.0000732039,2.951633e-7,0.0011219735,0.79682297,0.00020061035,0.19318214,0.0074123917,0.0001761882],"about_ca_topic_score_codex":0.0003262052,"about_ca_topic_score_gemma":0.00012835719,"teacher_disagreement_score":0.7324626,"about_ca_system_score_codex":0.000027731876,"about_ca_system_score_gemma":0.00034768874,"threshold_uncertainty_score":0.90161806},"labels":[],"label_agreement":null},{"id":"W4408609818","doi":"10.63485/9qejk-7xc91","title":"Data management in Canada: new toolkit","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Data science","score_opus":0.4513939880500616,"score_gpt":0.4526671682149107,"score_spread":0.0012731801648491192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408609818","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007866744,0.0002893943,0.07761506,0.045162097,0.012933396,0.0025254034,0.0036059103,0.00012524509,0.84987676],"genre_scores_gemma":[0.15888703,0.0010146555,0.1475067,0.028679335,0.0012734152,0.00013045485,0.007207559,0.00010298104,0.65519786],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942615,0.00015190683,0.0011216196,0.0016474423,0.002434086,0.00038341506],"domain_scores_gemma":[0.9910815,0.00035279934,0.00028859542,0.008012592,0.000053137937,0.00021141714],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0051682643,0.00025746203,0.00046235765,0.0003357957,0.00004312121,0.0006580745,0.010951347,0.00013301361,0.005382584],"category_scores_gemma":[0.0007305069,0.00020184647,0.000046963305,0.00039012547,0.000031044514,0.00036044442,0.029576266,0.0007544063,0.0006559733],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004950518,0.000020026488,0.00024645633,0.000016994725,0.000028667206,0.00006558138,0.000020447882,0.00016912956,1.5117601e-7,0.0189882,0.7420899,0.2383495],"study_design_scores_gemma":[0.00018537819,0.0000022035822,0.010457018,0.000021597074,0.000018483857,5.179079e-7,0.00071803684,0.002264743,0.000002215119,0.06519048,0.92087996,0.00025936923],"about_ca_topic_score_codex":0.9828772,"about_ca_topic_score_gemma":0.9994447,"teacher_disagreement_score":0.23809013,"about_ca_system_score_codex":0.00029211765,"about_ca_system_score_gemma":0.0022549767,"threshold_uncertainty_score":0.9955266},"labels":[],"label_agreement":null},{"id":"W4408662976","doi":"10.31581/jbs-35.1-2.588(2025)","title":"Identity Trap","year":2025,"lang":"en","type":"article","venue":"The Journal of Bahá’í Studies","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Trap (plumbing); Identity (music); Art; Physics; Aesthetics","score_opus":0.4131826001841808,"score_gpt":0.5609315567244447,"score_spread":0.14774895654026393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408662976","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":[0.6308249,0.04878626,0.09961041,0.1526445,0.009494154,0.00044369564,0.000027410457,0.000038700186,0.058129944],"genre_scores_gemma":[0.98458976,0.0039855707,0.00038221752,0.0026028939,0.00014959558,0.0000010335319,1.0493295e-7,0.000002616489,0.008286207],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99786097,0.00031508855,0.0006836503,0.00008015504,0.0009463092,0.0001138407],"domain_scores_gemma":[0.99699694,0.0017832258,0.0003854465,0.0003504645,0.00046007344,0.00002384409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0124793155,0.00006829889,0.00028364552,0.00019109686,0.00025830063,0.00012378766,0.0012023333,0.000013822984,0.000060239436],"category_scores_gemma":[0.003831536,0.0000320013,0.00011692962,0.00056420965,0.00019216414,0.000575602,0.00047125737,0.00013332376,0.00007506495],"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":[0.000100235906,0.00008728457,0.00086688384,0.00001993933,0.0006518667,0.000012809106,0.0043624123,0.00009014009,0.000094808194,0.07365269,0.8703503,0.0497106],"study_design_scores_gemma":[0.00046116218,0.000106805295,0.033164963,0.000082363156,0.00021419903,0.0000111677355,0.050526872,0.000015511043,0.00025804894,0.5963883,0.31869018,0.00008047698],"about_ca_topic_score_codex":0.0000113694405,"about_ca_topic_score_gemma":0.00011238392,"teacher_disagreement_score":0.5516602,"about_ca_system_score_codex":0.000028222752,"about_ca_system_score_gemma":0.000032337095,"threshold_uncertainty_score":0.45869833},"labels":[],"label_agreement":null},{"id":"W4408721644","doi":"10.63485/damx6-p4264","title":"Update on Canada&amp;#39;s Data Liberation Initiative","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Liberation; Political science; Public administration; Chemistry; Biochemistry","score_opus":0.5931167707934143,"score_gpt":0.48504576277155675,"score_spread":0.10807100802185754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408721644","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027556831,0.0001342128,0.27023536,0.1072314,0.0049009053,0.00155756,0.010846441,0.00022587061,0.6021126],"genre_scores_gemma":[0.30073747,0.0011891917,0.0847031,0.3558728,0.0026518,0.00012641218,0.098525696,0.00011598095,0.15607752],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9943848,0.00055478956,0.0008885463,0.00142153,0.0024865363,0.00026377634],"domain_scores_gemma":[0.993414,0.0006724549,0.00045213796,0.005088537,0.00023525443,0.00013761094],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004686904,0.00027369117,0.00041097114,0.00022486669,0.00015047444,0.0010369163,0.004356002,0.00013896782,0.002253946],"category_scores_gemma":[0.0024358046,0.00020494856,0.000051223633,0.00028156018,0.000042729087,0.00054976123,0.005089448,0.00046503468,0.0012918818],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001537858,0.00004723049,0.000007061877,0.00000566005,0.000028308166,0.000008335116,0.0000719315,0.0004804417,4.3506728e-7,0.026784943,0.9112922,0.061258055],"study_design_scores_gemma":[0.00010245552,0.000016215146,0.0012296971,0.000028266053,0.000017932776,3.9235232e-7,0.00016840894,0.0010556378,0.000019186044,0.11094851,0.88615865,0.00025465342],"about_ca_topic_score_codex":0.17604671,"about_ca_topic_score_gemma":0.8747024,"teacher_disagreement_score":0.6986557,"about_ca_system_score_codex":0.00016162379,"about_ca_system_score_gemma":0.0010407111,"threshold_uncertainty_score":0.9999008},"labels":[],"label_agreement":null},{"id":"W4408795074","doi":"10.1109/swc62898.2024.00311","title":"Overcoming the Data Availability Paradox with Managed Digital Twin Instances","year":2024,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Saskatchewan","funders":"","keywords":"Computer science","score_opus":0.22848979999639593,"score_gpt":0.40554132399452325,"score_spread":0.17705152399812732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408795074","genre_codex":"other","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":[0.12091327,0.0011759681,0.17294629,0.03338276,0.0014070391,0.0011379854,0.0012503074,0.000624196,0.6671622],"genre_scores_gemma":[0.9747534,0.000017679678,0.0008058273,0.00088681735,0.00006183213,0.0000072345742,0.000054963723,0.000007008581,0.023405239],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971853,0.00014010232,0.00041170928,0.0008004348,0.0012555143,0.00020696029],"domain_scores_gemma":[0.99530387,0.0018134989,0.000053933563,0.0027372679,0.000037359787,0.000054070137],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0055060247,0.000121286,0.00015732784,0.00007921179,0.00017589219,0.0035673038,0.0027766705,0.000021511592,0.00094955554],"category_scores_gemma":[0.0009711943,0.000052375544,0.00003916125,0.00078165665,0.00024314382,0.0030181548,0.0014849335,0.00014105356,0.0015124971],"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":[0.00005206763,0.0000727267,0.00285245,0.000035197932,0.00008913088,0.000052124244,0.00059967546,0.000025489844,0.0000032551868,0.14500825,0.4825644,0.36864522],"study_design_scores_gemma":[0.000086899854,0.000023334776,0.00204386,0.000020922498,0.000014646785,0.0000033594426,0.0034013588,0.0048699584,0.000007025916,0.03097162,0.9584416,0.00011540482],"about_ca_topic_score_codex":0.00007605762,"about_ca_topic_score_gemma":0.0006863723,"teacher_disagreement_score":0.8538401,"about_ca_system_score_codex":0.000020332083,"about_ca_system_score_gemma":0.000045433895,"threshold_uncertainty_score":0.9999637},"labels":[],"label_agreement":null},{"id":"W4409166166","doi":"10.1007/978-3-031-88720-8_38","title":"Advancing Query Performance Prediction: Challenges and Adaptive Solutions","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Query optimization; Information retrieval; Artificial intelligence","score_opus":0.10141723586476338,"score_gpt":0.3252785790447352,"score_spread":0.22386134317997186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409166166","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":[0.00003848532,0.004606972,0.95754987,0.0025345073,0.0016637396,0.00031057824,0.0000438223,0.00006471702,0.03318733],"genre_scores_gemma":[0.4889973,0.03407869,0.42959827,0.010866387,0.0032294854,0.00011584866,0.00006104847,0.00010327662,0.03294967],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960993,0.00006297185,0.00059853203,0.0013582611,0.0014235051,0.0004574076],"domain_scores_gemma":[0.9969599,0.0013787649,0.0002353573,0.0010305641,0.0002802855,0.00011507558],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0042208917,0.00029984186,0.00042200173,0.00096897676,0.0004466028,0.00034687907,0.001439029,0.0001759884,0.000042553907],"category_scores_gemma":[0.000585557,0.00024745014,0.00006752128,0.0003976388,0.00087224034,0.00093819835,0.0019006613,0.00049125496,0.000035281926],"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":[0.0000076624165,0.000011298464,0.00001548004,0.000028032313,0.000008041846,0.000006947248,0.0005490949,0.005216054,0.0000016483613,0.040074628,0.00033062705,0.9537505],"study_design_scores_gemma":[0.00032885055,0.0003746541,0.0023249255,0.0012145367,0.00003139963,0.0000309499,0.000020567893,0.346992,0.00005002898,0.5406549,0.10730065,0.0006765569],"about_ca_topic_score_codex":0.000010780862,"about_ca_topic_score_gemma":0.0003148217,"teacher_disagreement_score":0.9530739,"about_ca_system_score_codex":0.00016516514,"about_ca_system_score_gemma":0.00030595547,"threshold_uncertainty_score":0.9999978},"labels":[],"label_agreement":null},{"id":"W4409203171","doi":"10.1002/cem.70025","title":"Data Quality: Importance of the ‘before analysis’ domain (Theory of Sampling, TOS)","year":2025,"lang":"en","type":"article","venue":"Journal of Chemometrics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sampling (signal processing); Quality (philosophy); Domain (mathematical analysis); Statistics; Mathematics; Computer science; Philosophy; Mathematical analysis; Epistemology","score_opus":0.3448048197220179,"score_gpt":0.4975400213069517,"score_spread":0.1527352015849338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409203171","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":[0.6640515,0.0013991059,0.32343376,0.0041370806,0.0007933537,0.00015676253,0.00050229684,0.0000050942585,0.005521087],"genre_scores_gemma":[0.98919135,0.00010709843,0.008032216,0.00068097527,0.00005886844,4.077611e-7,0.000013368761,0.000004886032,0.0019108024],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9943826,0.0004283801,0.0024126056,0.00025593617,0.0023677263,0.00015272654],"domain_scores_gemma":[0.9908751,0.0025718384,0.0033311304,0.0023336615,0.00082641625,0.00006184192],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031389177,0.00010509898,0.00074933097,0.0022978194,0.000058568905,0.00008135187,0.0044301716,0.00006663733,0.00015582968],"category_scores_gemma":[0.026335066,0.000060935145,0.00042086653,0.016579792,0.00018419222,0.00042028568,0.0012614684,0.00022349303,0.00000169939],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028422635,0.0008785534,0.52851796,0.00023042891,0.0033423183,0.0000084140165,0.0011431072,0.00046962083,0.000555409,0.24763392,0.051261168,0.16567485],"study_design_scores_gemma":[0.00079332775,0.0000851672,0.36625642,0.00007501168,0.0009575737,0.000003221274,0.005135356,0.00012138629,0.0012374569,0.43730456,0.18789111,0.00013943086],"about_ca_topic_score_codex":0.000007938154,"about_ca_topic_score_gemma":0.0000640793,"teacher_disagreement_score":0.3251399,"about_ca_system_score_codex":0.000045349636,"about_ca_system_score_gemma":0.0001864507,"threshold_uncertainty_score":0.99738866},"labels":[],"label_agreement":null},{"id":"W4409229080","doi":"10.1007/s12599-025-00939-1","title":"Mapping Uncharted Territory","year":2025,"lang":"en","type":"article","venue":"Business & Information Systems Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Geography; Computer science","score_opus":0.046976017032913334,"score_gpt":0.2987515658446621,"score_spread":0.2517755488117488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409229080","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":[0.006801622,0.000116659285,0.97083557,0.000507003,0.0043761297,0.0003565588,0.000026862122,0.00027668694,0.016702907],"genre_scores_gemma":[0.9971648,0.0000075663656,0.0005253784,0.00033367926,0.0001226593,0.00007263612,0.0000744158,0.0000056223907,0.001693271],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99799955,0.00003549178,0.00095276436,0.00013914995,0.00068233605,0.0001906826],"domain_scores_gemma":[0.9986711,0.00017562258,0.0001884283,0.0005070189,0.00041610494,0.000041735893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019908457,0.000126057,0.00022126365,0.0010025143,0.000100815,0.00081810134,0.0005088256,0.00006079779,0.000021879683],"category_scores_gemma":[0.0009775275,0.00010925979,0.000041283492,0.0016525582,0.00001313555,0.0026445864,0.00017643957,0.00007461465,0.00048403675],"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":[0.000020197076,0.000042945667,0.0013039379,0.0017493492,0.0001587622,0.0000055732,0.0034418765,0.47490758,0.00041877644,0.22728369,0.18306105,0.10760628],"study_design_scores_gemma":[0.00020561754,0.000001433716,0.012667191,0.00016434328,0.0000032828232,0.0000014989658,0.0021629017,0.0694261,0.000016976031,0.000056172772,0.91517496,0.000119494114],"about_ca_topic_score_codex":0.000104475395,"about_ca_topic_score_gemma":0.00000260125,"teacher_disagreement_score":0.9903631,"about_ca_system_score_codex":0.00007405605,"about_ca_system_score_gemma":0.000046750665,"threshold_uncertainty_score":0.788897},"labels":[],"label_agreement":null},{"id":"W4409568128","doi":"10.63485/s8mt9-9h186","title":"Praise for Manitoba&amp;#39;s open data policy","year":2006,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Praise; Economics; Political science; Psychology; Social psychology","score_opus":0.767664678275732,"score_gpt":0.5955268116328487,"score_spread":0.17213786664288333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409568128","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035468186,0.00007980723,0.47791058,0.029426672,0.0017502427,0.0042019477,0.014848124,0.00014458767,0.47128338],"genre_scores_gemma":[0.0044320095,0.00008526388,0.3349478,0.0151308635,0.002955124,0.00072076527,0.031104166,0.00009221405,0.6105318],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942912,0.00029219178,0.0012832847,0.0021601277,0.0015137959,0.0004594109],"domain_scores_gemma":[0.9876386,0.0012439751,0.0006311111,0.010020892,0.00031047978,0.00015492298],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.011508113,0.00033823834,0.0006673252,0.00047547594,0.00021933934,0.0052736807,0.025332075,0.00022853902,0.0008686719],"category_scores_gemma":[0.006598575,0.0002523503,0.00015043197,0.0004250057,0.00010884602,0.0011548359,0.08186608,0.00027114968,0.0018967083],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023937573,0.00011736766,0.00004535907,0.000040274248,0.00003757741,0.0000014937148,0.000038428512,0.00005989606,0.0000010304537,0.07534781,0.83758736,0.086699456],"study_design_scores_gemma":[0.00027314943,0.000012224791,0.0006754445,0.000021805949,0.000028215805,7.786955e-7,0.00023867349,0.0004560202,0.0000033251092,0.25010106,0.7479217,0.00026758108],"about_ca_topic_score_codex":0.049724907,"about_ca_topic_score_gemma":0.057881314,"teacher_disagreement_score":0.17475325,"about_ca_system_score_codex":0.00009300032,"about_ca_system_score_gemma":0.0005789247,"threshold_uncertainty_score":0.99999285},"labels":[],"label_agreement":null},{"id":"W4409625226","doi":"10.1007/978-3-031-85908-3_42","title":"A Health Records Kiosk, Using an Ontology-Based Information Architecture","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Interactive kiosk; Ontology; Computer science; Information retrieval; Architecture; World Wide Web; Geography; Archaeology; Philosophy","score_opus":0.20991404066395322,"score_gpt":0.44267862084468507,"score_spread":0.23276458018073184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409625226","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":[0.000045024997,0.00011694564,0.82333624,0.007127773,0.00048739434,0.0006573702,0.0001683913,0.00006538668,0.16799547],"genre_scores_gemma":[0.02510276,0.0017123221,0.89576185,0.069308035,0.00012189359,0.00008253146,0.0024113138,0.000020767015,0.0054785097],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996582,0.00018625139,0.0016172483,0.0002942034,0.0010554834,0.00026484954],"domain_scores_gemma":[0.99466884,0.0005509837,0.00094348495,0.0030431582,0.00064718595,0.00014636396],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007096228,0.0002205254,0.0004006984,0.002934378,0.0008171302,0.001328859,0.0037888412,0.00013534086,0.000031142397],"category_scores_gemma":[0.00045678075,0.00019829544,0.000058408983,0.00086640706,0.00091755646,0.010884624,0.001897122,0.00048147197,0.00006312657],"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":[0.0000065380273,0.000016750615,0.000023344717,0.000033767672,0.0000030331157,6.172881e-8,0.001543832,0.0023145063,7.6425664e-8,0.25482407,0.0019453426,0.7392887],"study_design_scores_gemma":[0.00023940497,0.00006745365,0.000538086,0.00017828569,0.0000044685544,0.0000042612414,0.00013426365,0.31658638,4.985969e-7,0.025026845,0.6570288,0.0001912665],"about_ca_topic_score_codex":0.00019054828,"about_ca_topic_score_gemma":0.00040873655,"teacher_disagreement_score":0.7390974,"about_ca_system_score_codex":0.00025453037,"about_ca_system_score_gemma":0.0011589965,"threshold_uncertainty_score":0.9997079},"labels":[],"label_agreement":null},{"id":"W4409671330","doi":"10.1145/3696410.3714701","title":"MixedSAND: Semantic Annotation of Mixed-unit Numeric Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Annotation; Natural language processing; Unit (ring theory); Information retrieval; Semantic annotation; Artificial intelligence; Mathematics","score_opus":0.3282300458693544,"score_gpt":0.491568531296563,"score_spread":0.16333848542720864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409671330","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":[0.06789463,0.00020771897,0.716452,0.0075054234,0.0013691952,0.0003911501,0.00027816038,0.00008201728,0.20581967],"genre_scores_gemma":[0.96730804,0.000027581114,0.0035272052,0.0008229215,0.000015199442,0.0000031246998,0.00017779521,0.000002829438,0.028115295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815,0.00017935676,0.00053481304,0.00037269582,0.00064586016,0.00011727958],"domain_scores_gemma":[0.99725026,0.0007076544,0.00013688172,0.001740911,0.00013532376,0.00002898251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031750496,0.00006817146,0.00018405693,0.00028496026,0.000062030704,0.0001244924,0.0016769216,0.000025816136,0.0007142498],"category_scores_gemma":[0.001768855,0.000049600014,0.00003147335,0.0011520243,0.00006592667,0.00057069294,0.00096729374,0.00004167155,0.0003903929],"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":[0.000017503991,0.000116551055,0.0033256642,0.000035291945,0.000039812545,0.0000016946989,0.00008970637,0.000034452944,0.00014441437,0.13766411,0.54519475,0.31333607],"study_design_scores_gemma":[0.00039501642,0.00003138147,0.044685457,0.0000300684,0.000044186418,4.8089976e-7,0.0031064514,0.008120248,0.00090351905,0.06693112,0.87562543,0.00012666138],"about_ca_topic_score_codex":0.00030818506,"about_ca_topic_score_gemma":0.0003079298,"teacher_disagreement_score":0.8994134,"about_ca_system_score_codex":0.000004655367,"about_ca_system_score_gemma":0.000055081888,"threshold_uncertainty_score":0.7820534},"labels":[],"label_agreement":null},{"id":"W4410049805","doi":"10.1177/0282423x251329407","title":"Linking Trade Data from Different National Statistical Offices Through a Private Set Intersection","year":2025,"lang":"en","type":"article","venue":"Journal of Official Statistics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Intersection (aeronautics); Set (abstract data type); Data set; Statistics; Probability and statistics; Geography; Computer science; Business; Mathematics; Cartography","score_opus":0.31712642016439646,"score_gpt":0.4808368688614867,"score_spread":0.16371044869709023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410049805","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":[0.0117763905,0.00006378878,0.9744309,0.001290301,0.0021935874,0.000100878606,0.009290415,0.00001065127,0.0008430612],"genre_scores_gemma":[0.8999696,0.00010774628,0.095826976,0.001536779,0.0009640514,0.00000138649,0.0013803384,0.000014306351,0.00019885153],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99554324,0.00037311603,0.0014832403,0.00033559612,0.002074997,0.00018982563],"domain_scores_gemma":[0.9944495,0.003903771,0.00085994985,0.00041593224,0.00029560953,0.0000752412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024614716,0.00015273133,0.00042041633,0.0002317943,0.00016994798,0.00050586567,0.0014730683,0.00007009008,0.00037331006],"category_scores_gemma":[0.0061255195,0.00011474424,0.000056842804,0.0003102681,0.00012644373,0.0005816017,0.000530984,0.00034790835,0.000033956676],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004938663,0.00046483078,0.0010189252,0.000031926356,0.00028909213,0.00007270389,0.0008045369,0.0005606453,0.00007999237,0.42347977,0.49572772,0.076976],"study_design_scores_gemma":[0.0008781415,0.00019298187,0.03239788,0.00014467422,0.00017045697,0.0000067412684,0.001230931,0.02037464,0.00006688205,0.6102806,0.3340668,0.00018929092],"about_ca_topic_score_codex":0.00007138902,"about_ca_topic_score_gemma":0.0006302715,"teacher_disagreement_score":0.8881932,"about_ca_system_score_codex":0.00013817886,"about_ca_system_score_gemma":0.00024821918,"threshold_uncertainty_score":0.73332614},"labels":[],"label_agreement":null},{"id":"W4410115952","doi":"10.1109/emr.2025.3567192","title":"Understanding and Deobfuscating Textual Data: Managerial Insights and Computational Challenges","year":2025,"lang":"en","type":"article","venue":"IEEE Engineering Management Review","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Lethbridge","funders":"","keywords":"Business; Data science; Computer science; Industrial organization; Knowledge management; Management science; Process management; Econometrics; Economics","score_opus":0.35076183764403557,"score_gpt":0.3984480790666918,"score_spread":0.047686241422656206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410115952","genre_codex":"methods","genre_gemma":"review","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":[0.00046856963,0.13799144,0.83183104,0.0057820654,0.0009707003,0.0011572372,0.000028555827,0.00017368769,0.021596694],"genre_scores_gemma":[0.38646024,0.56558913,0.04060252,0.00397887,0.00028370842,0.00013192062,0.000202367,0.000050133767,0.0027011298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99792,0.000097008044,0.00056029303,0.0006797867,0.0005478547,0.00019509612],"domain_scores_gemma":[0.9985025,0.0005436024,0.00011296889,0.0007487856,0.000029108227,0.00006304218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002665402,0.00018490464,0.00035654675,0.00032955114,0.00013771658,0.00028394785,0.0006870172,0.000029589042,0.000013507033],"category_scores_gemma":[0.00030510002,0.00015828341,0.000030564373,0.00046769774,0.000062904226,0.00050810975,0.0010246562,0.00009323433,0.000018733317],"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":[0.0000035202208,0.000024822379,0.000012537771,0.0047275145,0.00016560045,0.000018152463,0.00010149834,0.0016898081,0.0000013876493,0.77284557,0.026629614,0.19377999],"study_design_scores_gemma":[0.000613925,0.000023576902,0.0022502402,0.0043819663,0.0002578328,0.0000048753695,0.0009657314,0.04153285,0.0000010833372,0.03901654,0.9105354,0.0004159702],"about_ca_topic_score_codex":0.000004844023,"about_ca_topic_score_gemma":0.000011738891,"teacher_disagreement_score":0.88390577,"about_ca_system_score_codex":0.00004356113,"about_ca_system_score_gemma":0.000007768327,"threshold_uncertainty_score":0.64546096},"labels":[],"label_agreement":null},{"id":"W4410337211","doi":"10.64000/86zpj-dma63","title":"Event Data as Underlying Altmetrics Infrastructure at the 4:AM Altmetrics Conference","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Altmetrics; Event (particle physics); Data science; Event data; Computer science; Social media; World Wide Web; Physics","score_opus":0.6714085820491087,"score_gpt":0.5432828328911826,"score_spread":0.12812574915792607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410337211","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":[0.007136078,0.0024534443,0.6819907,0.029866159,0.012279458,0.0030064299,0.005458085,0.00026748143,0.25754216],"genre_scores_gemma":[0.7601281,0.005042003,0.014961089,0.008282814,0.0006622166,0.00008881285,0.004769446,0.00009069771,0.20597482],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9895081,0.0007081124,0.0014583402,0.0024337552,0.0052740513,0.0006176397],"domain_scores_gemma":[0.9756539,0.003659253,0.0019367485,0.017724292,0.0007391002,0.00028671566],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.015959136,0.0005529301,0.0008145644,0.00095374306,0.0012523846,0.0056012706,0.023122247,0.00047530435,0.0052987896],"category_scores_gemma":[0.031604934,0.00031852978,0.00023524817,0.0012084425,0.00047353288,0.0011035517,0.064318895,0.0012428471,0.0024538834],"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":[0.000016991595,0.000048583395,0.00042182425,0.000048288806,0.00013115532,0.000019911748,0.00024121253,0.00089022145,0.0000015636779,0.041732866,0.5602375,0.39620984],"study_design_scores_gemma":[0.00020125281,0.000030287583,0.0046238415,0.000043849366,0.00009203303,0.000007951055,0.00087599724,0.008060496,0.0000126957975,0.26251546,0.7231285,0.000407655],"about_ca_topic_score_codex":0.0016499785,"about_ca_topic_score_gemma":0.0019451719,"teacher_disagreement_score":0.75299203,"about_ca_system_score_codex":0.0002680338,"about_ca_system_score_gemma":0.0007513132,"threshold_uncertainty_score":0.9999267},"labels":[],"label_agreement":null},{"id":"W4410414373","doi":"10.1038/s41597-025-05052-2","title":"A collection of FAIR Dutch Freedom of Information Act documents","year":2025,"lang":"en","type":"article","venue":"Scientific Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Metadata; Computer science; World Wide Web; Standardization; Information retrieval; Publishing; Quality (philosophy); Process (computing); Metadata repository; Political science","score_opus":0.1328692685136867,"score_gpt":0.42210031862309055,"score_spread":0.28923105010940386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410414373","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":[0.15377128,0.00022500292,0.4645215,0.006626419,0.03169719,0.0032167947,0.037307378,0.00018510445,0.30244932],"genre_scores_gemma":[0.95077693,0.000010910801,0.0055714003,0.00016384994,0.000017703192,0.000009711443,0.0045501706,0.0000030661217,0.038896244],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972411,0.000120500794,0.00082240533,0.0003741871,0.0013125612,0.000129273],"domain_scores_gemma":[0.9962247,0.00024151983,0.00039446604,0.0027521625,0.00035504444,0.000032085747],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009052688,0.00006455895,0.0001777234,0.0007412124,0.00016404934,0.00047444724,0.0028737755,0.000031972588,0.0003829104],"category_scores_gemma":[0.003559891,0.00005128905,0.00003777591,0.0028446624,0.00026664758,0.0031639002,0.0020229127,0.000046136876,0.00020217836],"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":[0.000025726005,0.00006933449,0.0007010252,0.000037580474,0.000020682137,1.0480466e-7,0.00036145322,0.00003833878,0.00021182813,0.009029287,0.9336239,0.055880755],"study_design_scores_gemma":[0.00043304966,0.000023451794,0.008052328,0.0000462414,0.000023774082,2.0222586e-7,0.0019263768,0.0050157756,0.0022720713,0.01810139,0.96403486,0.00007045928],"about_ca_topic_score_codex":0.0002892763,"about_ca_topic_score_gemma":0.00029887582,"teacher_disagreement_score":0.79700565,"about_ca_system_score_codex":0.000022762588,"about_ca_system_score_gemma":0.00017036144,"threshold_uncertainty_score":0.53402376},"labels":[],"label_agreement":null},{"id":"W4410447735","doi":"10.3233/shti250479","title":"Applying AI to Support Categorization of Heterogeneous Epidemiological Datasets","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Data Quality and Management","field":"Decision Sciences","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":"McGill University Health Centre","funders":"Deutsche Forschungsgemeinschaft","keywords":"Computer science; Metadata; Annotation; Interoperability; World Wide Web; Information retrieval; Controlled vocabulary; Categorization; Data curation; Context (archaeology); Data science; Artificial intelligence","score_opus":0.24803698980544267,"score_gpt":0.5283460737041448,"score_spread":0.2803090838987021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410447735","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":[0.1931841,0.008638027,0.6205641,0.15683039,0.0035455711,0.00886306,0.0012561382,0.0004994714,0.0066191237],"genre_scores_gemma":[0.9677377,0.0023529844,0.009479021,0.020054393,0.0000064854917,0.00021086776,0.00006881823,0.000002314654,0.00008743507],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977895,0.000096147814,0.0015462751,0.00014918494,0.00018882935,0.00023005431],"domain_scores_gemma":[0.9985619,0.00058693654,0.0003024694,0.00042732764,0.0000897099,0.00003162566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0049517895,0.00008829195,0.0004648936,0.0008926299,0.00015152604,0.000012127028,0.00041402073,0.00009403489,0.0000060599073],"category_scores_gemma":[0.006259824,0.00006336493,0.000015805404,0.001358029,0.00030876783,0.0001713472,0.0010096873,0.0001474424,0.000014352439],"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":[0.000028844004,0.000054547836,0.020220548,0.00073238905,0.000046120265,0.0000024441395,0.0021391953,0.0007273177,9.0496223e-7,0.40827754,0.0792206,0.48854953],"study_design_scores_gemma":[0.00044916055,0.00059878157,0.0020224426,0.00017456437,0.000008711968,0.0000075630055,0.027141066,0.002174553,0.00009794726,0.3109235,0.656243,0.00015870376],"about_ca_topic_score_codex":0.000014179255,"about_ca_topic_score_gemma":0.000061438885,"teacher_disagreement_score":0.7745536,"about_ca_system_score_codex":0.0000417553,"about_ca_system_score_gemma":0.000047816928,"threshold_uncertainty_score":0.7494046},"labels":[],"label_agreement":null},{"id":"W4410491654","doi":"10.2139/ssrn.5260351","title":"Toward Sustainable Data Governance in Refugee and Immigrant Serving Sector in Canada","year":2025,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Refugee; Immigration; Corporate governance; Political science; Economic growth; Public administration; Business; Economics; Law; Finance","score_opus":0.04917905298851862,"score_gpt":0.3308357864920949,"score_spread":0.2816567335035763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410491654","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":[0.9616386,0.011398208,0.003971636,0.01977867,0.00041349052,0.00032523074,0.00006705209,0.000008507325,0.0023985798],"genre_scores_gemma":[0.99138635,0.0025513188,0.000045678,0.0005636261,0.000026033733,0.0000025612212,0.0000063768302,0.000004606266,0.0054134633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964984,0.00023144511,0.000593534,0.0004235774,0.00067807076,0.0015749749],"domain_scores_gemma":[0.99878865,0.00027543172,0.00017391054,0.0006447137,0.00006525534,0.00005204599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01075728,0.00011206264,0.00024710814,0.00019658855,0.00010365622,0.00022512833,0.0017193604,0.000030143014,0.000043031538],"category_scores_gemma":[0.0013904871,0.00009223088,0.000018555716,0.0009253088,0.000023065784,0.00080441666,0.00089804555,0.00094204105,0.0000033141655],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017217448,0.00007923464,0.06359158,0.0000697236,0.00007660214,0.00026984976,0.00047632033,0.0002870606,0.00001703686,0.7833762,0.015432042,0.13615215],"study_design_scores_gemma":[0.0013909087,0.000051409337,0.07045467,0.000108185486,0.000013206286,0.00005345352,0.061120894,0.0022753805,0.000013218477,0.6652082,0.1990579,0.00025251895],"about_ca_topic_score_codex":0.8785224,"about_ca_topic_score_gemma":0.99737936,"teacher_disagreement_score":0.18362588,"about_ca_system_score_codex":0.002993002,"about_ca_system_score_gemma":0.009317056,"threshold_uncertainty_score":0.9962992},"labels":[],"label_agreement":null},{"id":"W4410636879","doi":"10.1145/3701716.3715600","title":"WebTableX: Efficiently Discovering Web Table Transformations Through Sampling","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Universitas Brawijaya","keywords":"Computer science; Table (database); Information retrieval; Sampling (signal processing); Data mining; World Wide Web; Data science","score_opus":0.17787192899621215,"score_gpt":0.4464159695996306,"score_spread":0.2685440406034184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410636879","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":[0.005411648,0.000065113134,0.6145096,0.002424521,0.00039611146,0.0001599577,0.000058306505,0.0000690158,0.37690574],"genre_scores_gemma":[0.89260256,0.00010602695,0.01670698,0.0040361295,0.00004108319,0.00003801196,0.00004745225,0.000008195582,0.08641353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980252,0.00006636091,0.0005925387,0.00034682962,0.00068641925,0.00028265925],"domain_scores_gemma":[0.99864495,0.00054406025,0.000064490705,0.0006235166,0.000084048894,0.00003891533],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020091548,0.00010622616,0.00018911647,0.0001970521,0.00037769525,0.00076627557,0.00076677714,0.000034628414,0.0011752673],"category_scores_gemma":[0.00050633796,0.0000774933,0.00007694197,0.0015008393,0.000053714404,0.001483166,0.00024871307,0.00008698896,0.00057079026],"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":[0.000011411856,0.000102379,0.0001548702,0.00002725766,0.000027296657,6.7078287e-7,0.0007873287,0.009342011,0.00035898862,0.8697158,0.09821982,0.021252144],"study_design_scores_gemma":[0.00029770078,0.000010029954,0.0002628995,0.00002988274,0.000014074835,3.4165492e-7,0.0045247627,0.008319943,0.0006766559,0.046534188,0.9392161,0.000113439535],"about_ca_topic_score_codex":0.0001942397,"about_ca_topic_score_gemma":0.00043990195,"teacher_disagreement_score":0.88719094,"about_ca_system_score_codex":0.000037193193,"about_ca_system_score_gemma":0.00008808673,"threshold_uncertainty_score":0.9997378},"labels":[],"label_agreement":null},{"id":"W4411089189","doi":"10.1067/j.cpradiol.2025.06.004","title":"Data governance in radiology Part I: Overview of data management approaches to radiology","year":2025,"lang":"en","type":"review","venue":"Current Problems in Diagnostic Radiology","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Medicine; Radiology; Interventional radiology; Medical physics; Corporate governance; Management","score_opus":0.7829499519654881,"score_gpt":0.5159219243327299,"score_spread":0.26702802763275824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411089189","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002186777,0.9751556,0.0036115968,0.0006647488,0.0043625226,0.005303725,0.008964863,0.00003576849,0.0018990235],"genre_scores_gemma":[0.000016171529,0.98605126,0.0016466998,0.00020399415,0.00025268306,0.0012770982,0.010168712,0.000042238884,0.00034113706],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9798804,0.006017716,0.0066587674,0.005082751,0.00096650247,0.0013938565],"domain_scores_gemma":[0.95372,0.030719742,0.002376663,0.012882831,0.00006947938,0.00023130159],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.021219661,0.0010406702,0.006441292,0.0017805543,0.00007291642,0.0001005338,0.02246003,0.00067202107,0.0002391434],"category_scores_gemma":[0.033427123,0.000840447,0.00029237274,0.0037294717,0.000673403,0.0007182218,0.018433569,0.0012149788,0.00030750394],"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":[0.000010985732,0.00042199183,0.00028242264,0.016730228,0.00017350713,0.000061426006,0.000055314442,0.00025626464,3.75196e-9,0.052494198,0.15166998,0.77784365],"study_design_scores_gemma":[0.0006767647,0.00010727853,0.00036111887,0.020214465,0.00042236436,0.00006590078,0.00004508123,0.00016340848,1.4570693e-8,0.009960283,0.96731097,0.0006723323],"about_ca_topic_score_codex":0.000086519845,"about_ca_topic_score_gemma":0.0009487495,"teacher_disagreement_score":0.815641,"about_ca_system_score_codex":0.00035358686,"about_ca_system_score_gemma":0.00059311726,"threshold_uncertainty_score":0.9994046},"labels":[],"label_agreement":null},{"id":"W4411112895","doi":"10.18653/v1/2025.findings-naacl.104","title":"Can’t Hide Behind the API: Stealing Black-Box Commercial Embedding Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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; Compute Canada","keywords":"Computer science; Embedding; Black box; Computer security; Artificial intelligence","score_opus":0.21380671454932942,"score_gpt":0.4509011484647079,"score_spread":0.2370944339153785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411112895","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":[0.04638164,0.00010221354,0.54930943,0.08114671,0.0011813783,0.0005781608,0.00008247928,0.00012535219,0.3210926],"genre_scores_gemma":[0.9514278,0.000019325349,0.001493559,0.012291305,0.00008318566,0.000011683872,0.000010574993,0.000005913508,0.03465661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975027,0.00029280735,0.0005861986,0.00040738602,0.0009264248,0.0002844816],"domain_scores_gemma":[0.9974468,0.0013048403,0.000113418624,0.0009701112,0.000105183375,0.00005969495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046250056,0.00012449165,0.00021504157,0.00017615549,0.00041867737,0.00067709293,0.0015214243,0.0000494797,0.00049185514],"category_scores_gemma":[0.00063678273,0.00007263454,0.00009863804,0.00041971164,0.00014748314,0.00041683187,0.0009093435,0.00016281154,0.00022236665],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016037222,0.00004090603,0.00019531872,0.000008319496,0.000037018737,0.0000032051341,0.0020909873,0.008855029,0.00001333193,0.55282086,0.38106653,0.054852456],"study_design_scores_gemma":[0.0004768663,0.000019451614,0.00097404333,0.000040675608,0.000048952414,6.6463815e-7,0.01546437,0.15302882,0.00029447224,0.49308178,0.33632585,0.00024406808],"about_ca_topic_score_codex":0.0015170224,"about_ca_topic_score_gemma":0.0045395233,"teacher_disagreement_score":0.9050462,"about_ca_system_score_codex":0.000046239955,"about_ca_system_score_gemma":0.00007157157,"threshold_uncertainty_score":0.6529223},"labels":[],"label_agreement":null},{"id":"W4411141791","doi":"10.1145/3725253","title":"Towards Practical FPRAS for #NFA: Exploiting the Power of Dependence","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"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","keywords":"Computer science; Power (physics); Physics; Thermodynamics","score_opus":0.3512875317024356,"score_gpt":0.4853916397535502,"score_spread":0.1341041080511146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411141791","genre_codex":"other","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":[0.16193967,0.00042803897,0.04646963,0.37070012,0.0025785083,0.009395396,0.0026101267,0.00014082917,0.4057377],"genre_scores_gemma":[0.9390636,0.00012404908,0.056339905,0.0012260502,0.0000311521,0.00006338455,0.000020771708,0.000013042477,0.003118062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99662274,0.000036736452,0.0008861673,0.0005740526,0.0016592909,0.00022101335],"domain_scores_gemma":[0.99388444,0.0013351043,0.00096621463,0.0033381649,0.00044775227,0.000028320248],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0099159945,0.00014000782,0.00030806998,0.00016820767,0.00014106078,0.00014316633,0.013026213,0.000038482372,0.000050767292],"category_scores_gemma":[0.01685998,0.00007696724,0.00011556368,0.00085259747,0.0002342756,0.0010248135,0.01601715,0.00012584077,0.000007758214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020518246,0.0002606869,0.00068431103,0.00047227863,0.0002531939,3.197928e-7,0.00022443001,0.0000052381074,0.0002669767,0.6632769,0.29642883,0.03792165],"study_design_scores_gemma":[0.0013810998,0.00030970157,0.012049801,0.0010430168,0.0006123891,0.0000012796462,0.04163684,0.0008499566,0.015342247,0.58777887,0.33870068,0.00029413385],"about_ca_topic_score_codex":0.000020225616,"about_ca_topic_score_gemma":0.0000034683087,"teacher_disagreement_score":0.7771239,"about_ca_system_score_codex":0.000017675475,"about_ca_system_score_gemma":0.00003292517,"threshold_uncertainty_score":0.9923138},"labels":[],"label_agreement":null},{"id":"W4411293798","doi":"10.12927/cjnl.2025.27614","title":"Data, Advocacy and Policy: A Powerful Trio for Change","year":2025,"lang":"en","type":"article","venue":"Nursing leadership","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Nova Scotia Health Authority","funders":"","keywords":"Nursing; Political science; Psychology; Politics; Public relations; Sociology; Medicine; Law","score_opus":0.7680123390100543,"score_gpt":0.5207524097233138,"score_spread":0.24725992928674045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411293798","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":[0.004787327,0.0038181932,0.10464267,0.8298423,0.002845274,0.0020812312,0.00068633613,0.00021406841,0.0510826],"genre_scores_gemma":[0.9188392,0.00004142178,0.0052124313,0.03443084,0.0009453052,0.00005190699,0.00027397467,0.000024342495,0.04018057],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981672,0.00014347535,0.00031865734,0.0005969674,0.00042650505,0.0003471732],"domain_scores_gemma":[0.9976052,0.0010308045,0.00009009751,0.0011248869,0.000069330024,0.000079701844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031595395,0.00011440948,0.00021375404,0.00045791085,0.00016417785,0.00038560928,0.0010675769,0.00006824038,0.000029967741],"category_scores_gemma":[0.0035696935,0.000097817494,0.00004170827,0.00066980295,0.0002181068,0.0005952645,0.00016417903,0.00009153315,0.000067343106],"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":[0.0000869454,0.0000755277,0.00009833481,0.000044104338,0.000014600689,9.865203e-7,0.0037696888,3.2162447e-7,0.000012399221,0.057950735,0.31773373,0.6202126],"study_design_scores_gemma":[0.00081217475,0.00006742481,0.0050753844,0.00021478308,0.000040135426,0.0000015973997,0.02309701,0.00075830024,0.00003706702,0.0925449,0.8772012,0.00015001069],"about_ca_topic_score_codex":0.000107105356,"about_ca_topic_score_gemma":0.0000970452,"teacher_disagreement_score":0.9140519,"about_ca_system_score_codex":0.000054700347,"about_ca_system_score_gemma":0.00014011098,"threshold_uncertainty_score":0.42735144},"labels":[],"label_agreement":null},{"id":"W4411374296","doi":"10.1145/3722212.3724424","title":"The Case for Collaboration","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.18128650685032327,"score_gpt":0.5089256116388177,"score_spread":0.3276391047884944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411374296","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":[0.0039799516,0.000070608214,0.67960453,0.09596537,0.0011123818,0.0005984122,0.000043194817,0.0000334196,0.2185921],"genre_scores_gemma":[0.5522685,0.000011085836,0.0032608937,0.005540785,0.000036668454,0.00008867819,0.000006182535,0.0000015281433,0.43878564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995112,0.000048882164,0.00015924293,0.00010127554,0.00012647844,0.000052956482],"domain_scores_gemma":[0.9979163,0.0016013731,0.00002640686,0.0002981983,0.00014824631,0.000009486481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028603582,0.000019561325,0.00003259531,0.00003264167,0.00030118346,0.00048680755,0.00022630006,0.000008884859,0.000048518785],"category_scores_gemma":[0.0022929432,0.000009452717,0.000016445483,0.00037318232,0.000022073755,0.00012157151,0.000072291485,0.000009312705,0.00006760357],"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":[0.0000036714607,0.0000025654683,0.0000030379456,4.3077148e-7,0.0000017383736,0.0000013152578,0.00001759897,0.0000027876217,0.0000015324841,0.4813045,0.4374453,0.0812155],"study_design_scores_gemma":[0.00006704852,0.000005746926,0.000023763307,3.6972136e-7,0.0000020868613,6.2603374e-7,0.0049002236,0.0013063848,0.000079305166,0.18367498,0.80992794,0.00001152507],"about_ca_topic_score_codex":0.000029324634,"about_ca_topic_score_gemma":0.002783176,"teacher_disagreement_score":0.6763437,"about_ca_system_score_codex":0.0000070155697,"about_ca_system_score_gemma":0.000025443318,"threshold_uncertainty_score":0.46942964},"labels":[],"label_agreement":null},{"id":"W4411382438","doi":"10.33424/futurum590","title":"What are the effects of data portability?","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Software portability; Computer science; Programming language","score_opus":0.21319316130303845,"score_gpt":0.47206465608300674,"score_spread":0.2588714947799683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411382438","genre_codex":"other","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":[0.24768515,0.006828925,0.18614653,0.24685036,0.017962182,0.0042780563,0.00037254693,0.00025661296,0.28961962],"genre_scores_gemma":[0.9480245,0.00020807137,0.00054418953,0.0069363373,0.000024055034,0.000009489996,0.000029458477,0.0000023020339,0.044221573],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848616,0.00020466332,0.00033311316,0.000321967,0.00057066034,0.000083421786],"domain_scores_gemma":[0.9931137,0.003513857,0.00010657335,0.0031734998,0.00007451384,0.000017876067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047786804,0.000046756657,0.00013395604,0.000060353974,0.000056898516,0.00029078513,0.0026015101,0.00001743687,0.00024977684],"category_scores_gemma":[0.005633849,0.000022209546,0.00003129574,0.00049484667,0.000106253174,0.0012078094,0.0017956117,0.000040933082,0.00009420282],"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":[0.000008184041,0.000094565294,0.0040886877,0.00007151795,0.000030211882,0.0000019727277,0.00014151288,0.0000015066344,0.000021952581,0.11720635,0.5863263,0.29200724],"study_design_scores_gemma":[0.00018769804,0.000018462828,0.047516048,0.00007090364,0.00002819321,1.2898803e-7,0.013534081,0.00028872516,0.0007188616,0.12645583,0.8111199,0.00006117684],"about_ca_topic_score_codex":0.00007721652,"about_ca_topic_score_gemma":0.00044815263,"teacher_disagreement_score":0.7003394,"about_ca_system_score_codex":0.000004114806,"about_ca_system_score_gemma":0.000023701556,"threshold_uncertainty_score":0.6744651},"labels":[],"label_agreement":null},{"id":"W4411404655","doi":"10.1017/9781009403092.005","title":"Data Handling","year":2025,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Computer science; Business","score_opus":0.24372387040875457,"score_gpt":0.34079947961563667,"score_spread":0.0970756092068821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411404655","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019995464,0.00014255526,0.012562732,0.00011215731,0.0006435885,0.00033075974,0.0065656207,0.00010357338,0.979537],"genre_scores_gemma":[0.000038213024,0.000109821995,0.00035054213,0.00031727806,0.00011143784,2.0139706e-7,0.00064319547,0.00001494674,0.99841434],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967824,0.00010852211,0.0004431604,0.0012880943,0.0011104771,0.00026729962],"domain_scores_gemma":[0.9943421,0.00065002445,0.00037869808,0.004223728,0.0002555161,0.00014994254],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016096329,0.0003148389,0.00052744575,0.0004585672,0.00029844153,0.00035106577,0.0058304346,0.00026678346,0.000038385366],"category_scores_gemma":[0.00035486193,0.000322159,0.00016960614,0.000024696754,0.0002523328,0.00036353053,0.007839184,0.00040916746,0.00017865647],"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":[0.000022780136,0.0000037631928,2.537238e-7,0.000019022162,0.000064907064,0.00008899442,0.0000071876893,8.987612e-7,5.7280573e-7,0.52571213,0.4617589,0.012320612],"study_design_scores_gemma":[0.00029532885,0.000013132641,0.0000035973007,0.0001329131,0.00019754759,0.0000017004586,0.00008413267,0.00028167444,0.000010652245,0.00026755084,0.99839437,0.0003173863],"about_ca_topic_score_codex":0.00015140198,"about_ca_topic_score_gemma":0.000024037892,"teacher_disagreement_score":0.53663546,"about_ca_system_score_codex":0.0000969777,"about_ca_system_score_gemma":0.00018819222,"threshold_uncertainty_score":0.99992305},"labels":[],"label_agreement":null},{"id":"W4411992116","doi":"10.1016/j.socscimed.2025.118370","title":"Challenges in data documentation and retrieval in the ASHA diary from a usability perspective","year":2025,"lang":"en","type":"article","venue":"Social Science & Medicine","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Providence Health Care","keywords":"Usability; Asha; Documentation; Perspective (graphical); Computer science; World Wide Web; Library science; Linguistics; Human–computer interaction; Artificial intelligence","score_opus":0.30746827408695215,"score_gpt":0.5199861204509014,"score_spread":0.21251784636394927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411992116","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":[0.6468387,0.002244433,0.00053006463,0.2838513,0.00081130967,0.00066802435,0.000059994516,0.000016419843,0.06497972],"genre_scores_gemma":[0.9981655,0.00027893423,0.000020745252,0.0013657806,0.000095583055,0.0000045997967,0.000010138683,8.746495e-7,0.000057857782],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966222,0.00062925374,0.00035957483,0.0007245613,0.0014741091,0.00019030536],"domain_scores_gemma":[0.9972974,0.0018563345,0.00008602654,0.00063470064,0.00009230445,0.00003320238],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030623013,0.00006997776,0.00018638434,0.00024065879,0.00022806361,0.00013690304,0.0017936819,0.000031346353,0.000077627796],"category_scores_gemma":[0.015016588,0.000041350053,0.000010569861,0.0022130047,0.0016349562,0.0010307598,0.00055622595,0.0001503301,0.000005400357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109372166,0.00018438094,0.02687242,0.0000100878415,0.0000076170013,0.00001139731,0.28493413,7.268731e-7,0.00020920884,0.2646596,0.009000181,0.41400084],"study_design_scores_gemma":[0.00035182733,0.000016036436,0.48043305,0.000021408,0.000005979584,1.0982989e-7,0.22338018,0.00013056326,0.0000036618417,0.29153267,0.004085344,0.000039176906],"about_ca_topic_score_codex":0.0035368593,"about_ca_topic_score_gemma":0.0063637025,"teacher_disagreement_score":0.45356062,"about_ca_system_score_codex":0.00014629883,"about_ca_system_score_gemma":0.00012450278,"threshold_uncertainty_score":0.9981776},"labels":[],"label_agreement":null},{"id":"W4412017881","doi":"10.1177/23328584251352814","title":"Data Deidentification for Data Sharing in Education and Psychological Research: Importance, Barriers, and Techniques","year":2025,"lang":"en","type":"article","venue":"AERA Open","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"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":"Canada Excellence Research Chairs, Government of Canada; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Office of Special Education Programs, Office of Special Education and Rehabilitative Services","keywords":"Psychology; Data sharing; Applied psychology; Medicine","score_opus":0.8329394390274139,"score_gpt":0.6719423566313527,"score_spread":0.16099708239606114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412017881","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":[0.63367724,0.0062622703,0.063676834,0.12658659,0.0018845416,0.01966873,0.004743806,0.0001947793,0.1433052],"genre_scores_gemma":[0.8806764,0.0018752854,0.09223961,0.0042446717,0.00011239655,0.000810119,0.0050154272,0.000015964506,0.015010116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980321,0.00016054256,0.0003707371,0.0010352031,0.00027079196,0.00013066104],"domain_scores_gemma":[0.99639106,0.00048464496,0.00007072206,0.002908897,0.00009512007,0.000049535145],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01977534,0.00005080527,0.0001207679,0.0002185845,0.00019018301,0.0015266099,0.004984203,0.000040143303,0.00004803386],"category_scores_gemma":[0.0062615424,0.00004132068,0.000004089683,0.0005244267,0.000101565165,0.0019412742,0.00859369,0.00009227095,0.0000054519546],"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":[0.00003055605,0.00006543661,0.016241722,0.000012183192,0.0000041758817,4.1187357e-7,0.00007054937,2.3074447e-8,0.000052078954,0.055386648,0.49608427,0.43205193],"study_design_scores_gemma":[0.00017124954,0.00002076565,0.0387345,0.000047265206,0.0000048673187,7.288809e-7,0.0017429399,0.0005910123,0.00003766527,0.23315112,0.7254343,0.00006360279],"about_ca_topic_score_codex":0.00035030078,"about_ca_topic_score_gemma":0.0019570014,"teacher_disagreement_score":0.43198833,"about_ca_system_score_codex":0.000016276541,"about_ca_system_score_gemma":0.000072422976,"threshold_uncertainty_score":0.99950993},"labels":[],"label_agreement":null},{"id":"W4412402624","doi":"10.1145/3749116.3749124","title":"Reminiscences on Influential Papers","year":2025,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Library science; Computer science","score_opus":0.12901287901589728,"score_gpt":0.439895915516474,"score_spread":0.3108830365005767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412402624","genre_codex":"other","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":[0.24283487,0.00007482253,0.0017896678,0.021829331,0.0053904704,0.00043259253,0.00003403587,0.00016217402,0.72745204],"genre_scores_gemma":[0.9280356,0.000066828565,0.0018082674,0.0084297815,0.0001349199,0.000024955418,0.000010085684,0.0000068394456,0.06148271],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997725,0.00019011926,0.00049452035,0.000548426,0.00081099215,0.00023093565],"domain_scores_gemma":[0.9966261,0.0015995047,0.00012921817,0.0015149162,0.00006819359,0.000062084844],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002015107,0.00012231969,0.0002102655,0.00027065998,0.0001767163,0.00028702285,0.001995449,0.00006506922,0.0012025423],"category_scores_gemma":[0.0066224723,0.000088091896,0.00010538728,0.0007021045,0.00009986593,0.00022478116,0.00068176404,0.00012896112,0.0010909939],"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":[0.00006393772,0.00005433889,0.0021864928,0.0000045466027,0.000022590431,0.000005180948,0.00010500213,0.0000113057295,0.00012555221,0.027618982,0.22292525,0.74687684],"study_design_scores_gemma":[0.00023060868,0.000085151914,0.007787824,0.000029612995,0.000011737365,2.2254265e-7,0.00067291316,0.00003857572,0.00041346956,0.071809165,0.91880786,0.00011284459],"about_ca_topic_score_codex":0.00009086941,"about_ca_topic_score_gemma":0.0001698397,"teacher_disagreement_score":0.746764,"about_ca_system_score_codex":0.000023305314,"about_ca_system_score_gemma":0.000050672686,"threshold_uncertainty_score":0.9997105},"labels":[],"label_agreement":null},{"id":"W4412805152","doi":"10.1016/j.ijmedinf.2025.106045","title":"Privacy-by-design: Case studies in interactive record linkage using a hybrid human-computer system","year":2025,"lang":"en","type":"article","venue":"International Journal of Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","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":"Alberta Health Services","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institutes of Health; Patient-Centered Outcomes Research Institute","keywords":"Computer science; Record linkage; Linkage (software); Human–computer interaction; Gene; Medicine; Genetics; Biology","score_opus":0.24725292966649737,"score_gpt":0.5161682721501035,"score_spread":0.26891534248360616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412805152","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":[0.17460169,0.00010233599,0.8182509,0.0020537528,0.0042661726,0.00013557613,0.000024000386,0.000011003387,0.000554597],"genre_scores_gemma":[0.9703865,0.00012215012,0.026271572,0.002636965,0.00038085814,0.0000034297316,0.0000055585383,0.000005752385,0.00018720569],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938621,0.0003218091,0.0026194218,0.000104525265,0.0029370645,0.0001551048],"domain_scores_gemma":[0.99553365,0.002006812,0.0011638217,0.00021953735,0.0009617823,0.00011442498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00949777,0.00012793524,0.00042390646,0.0008549123,0.00006813047,0.0003457624,0.0018564552,0.00006616079,0.000083061015],"category_scores_gemma":[0.0037475186,0.00009005195,0.00011999792,0.0002883934,0.00013225556,0.001166245,0.00092284713,0.00047455015,0.000025423962],"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":[0.00035777767,0.00067200174,0.00053284183,0.00037254128,0.0020522815,0.021544585,0.020856252,0.0026982652,0.000023298679,0.014183819,0.51282334,0.423883],"study_design_scores_gemma":[0.0057426966,0.00041687008,0.000066353525,0.0074965237,0.00012604293,0.013556903,0.084590614,0.75989246,0.0004724531,0.017964786,0.10919745,0.00047684362],"about_ca_topic_score_codex":0.000041357907,"about_ca_topic_score_gemma":0.000011546636,"teacher_disagreement_score":0.79578483,"about_ca_system_score_codex":0.00042970662,"about_ca_system_score_gemma":0.00019362402,"threshold_uncertainty_score":0.44864005},"labels":[],"label_agreement":null},{"id":"W4412984254","doi":"10.1016/j.jss.2025.112584","title":"Data catalog tools: A systematic multivocal literature review","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Technische Universiteit Eindhoven; Government of Canada; NXP Semiconductors","keywords":"Computer science; Library science; Information retrieval; Data science","score_opus":0.19432335379260254,"score_gpt":0.42949110579059563,"score_spread":0.23516775199799309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412984254","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007948774,0.88989997,0.10123741,0.0028248606,0.0026559504,0.0011408096,0.0010071386,0.000027659802,0.00041135465],"genre_scores_gemma":[0.4486419,0.4078963,0.030874785,0.030578505,0.0031294103,0.00019483194,0.0012244898,0.00013182011,0.07732795],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962991,0.00057760865,0.0017249392,0.00027878024,0.0009826865,0.00013687224],"domain_scores_gemma":[0.9956036,0.0015639818,0.0009261136,0.0012172796,0.00058880344,0.00010022812],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0116908625,0.00012968463,0.0008849504,0.0002466353,0.000107322514,0.0010141529,0.0015070548,0.00006680112,0.000009036255],"category_scores_gemma":[0.014951352,0.000072400515,0.00009950227,0.00059254176,0.000041384577,0.001280177,0.00054461975,0.00020574998,0.000021399686],"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":[0.000032222724,0.00011464177,0.0007472651,0.17324154,0.0003345937,0.00035500916,0.0005832216,0.000013559429,0.0000033042486,0.0083585065,0.7920585,0.02415758],"study_design_scores_gemma":[0.00080046634,0.00011319652,0.0011554839,0.38742527,0.0004335333,0.0007413869,0.0033554262,0.00034053615,9.0844463e-7,0.0022296465,0.6031467,0.0002574779],"about_ca_topic_score_codex":0.000013450831,"about_ca_topic_score_gemma":0.000014094565,"teacher_disagreement_score":0.48200363,"about_ca_system_score_codex":0.000026740217,"about_ca_system_score_gemma":0.00008249794,"threshold_uncertainty_score":0.99334615},"labels":[],"label_agreement":null},{"id":"W4413392074","doi":"10.2196/63544","title":"Medical Science Data Value Evaluation Model: Mixed Methods Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Weighting; Computer science; Data mining; Entropy (arrow of time); Data set; Data science; Information retrieval; Medicine; Artificial intelligence","score_opus":0.3897749305494763,"score_gpt":0.6237581904605167,"score_spread":0.2339832599110404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413392074","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":[0.03208911,0.000036103596,0.9206663,0.0052865944,0.001597698,0.0014246383,0.000037934336,0.00010821117,0.038753442],"genre_scores_gemma":[0.7662481,0.000064799424,0.20523418,0.025450116,0.00022858524,0.0004083367,0.00030218018,0.000019734087,0.0020439294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9739087,0.0013507678,0.0025844818,0.00058694434,0.021044185,0.00052491017],"domain_scores_gemma":[0.99233013,0.0024465213,0.0003782235,0.0035632844,0.0006766744,0.000605178],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15816848,0.00017837442,0.0004230941,0.00067808235,0.00039109364,0.00061643956,0.009235006,0.00017145516,0.0011206638],"category_scores_gemma":[0.076586306,0.000120978584,0.00005292562,0.0028940316,0.0008834166,0.0023720367,0.0076024854,0.00048110855,0.00029278293],"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":[0.000010413718,0.00040461973,0.000080296944,0.000027196726,0.000029787692,0.0000025526908,0.0033850055,0.00026552708,8.2557864e-7,0.028579919,0.11276112,0.8544527],"study_design_scores_gemma":[0.00078692246,0.000045946632,0.00069894304,0.000051732943,0.000045252284,0.0000019529305,0.01666261,0.9175066,0.0000112342705,0.024447232,0.03961809,0.00012349388],"about_ca_topic_score_codex":0.00002430427,"about_ca_topic_score_gemma":0.00006081917,"teacher_disagreement_score":0.91724104,"about_ca_system_score_codex":0.000115714734,"about_ca_system_score_gemma":0.0032177109,"threshold_uncertainty_score":0.99979246},"labels":[],"label_agreement":null},{"id":"W4413443076","doi":"10.1109/mitp.2025.3561079","title":"Data-as-an-Asset: Challenges and Future Directions","year":2025,"lang":"en","type":"article","venue":"IT Professional","topic":"Data Quality and Management","field":"Decision Sciences","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":"Université TÉLUQ","funders":"","keywords":"Computer science; Asset (computer security); Asset management; Business; Knowledge management; Data science; Risk analysis (engineering); Computer security; Finance","score_opus":0.3049530404859407,"score_gpt":0.5156489578308201,"score_spread":0.2106959173448794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413443076","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037442364,0.016823487,0.0007098337,0.6475796,0.013587739,0.0008145768,0.0012239376,0.00022982378,0.28158864],"genre_scores_gemma":[0.3561739,0.028232189,0.008440327,0.056805428,0.0042889244,0.00031363955,0.0020062497,0.00005459955,0.5436847],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99782586,0.00034493985,0.00032325566,0.0006243838,0.00072564126,0.00015591874],"domain_scores_gemma":[0.9979479,0.0006021898,0.000082146835,0.0011823659,0.000102845894,0.00008258497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031129972,0.000098774384,0.00016317102,0.00017811982,0.00034717965,0.00013725093,0.0010696878,0.00008471634,0.00085360184],"category_scores_gemma":[0.0006047372,0.00006650091,0.00002405239,0.00025704192,0.00007803796,0.0008683891,0.0012452152,0.0001700974,0.00026189332],"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":[0.000021178106,0.00013653838,0.00006483664,0.000010953747,0.000020770254,0.0000030008796,0.00063873647,1.1922704e-7,0.000009850467,0.25524458,0.25596902,0.4878804],"study_design_scores_gemma":[0.00015371562,0.000016540083,0.01712557,0.000023409078,0.000011304799,0.0000016018843,0.010141638,0.00006867497,0.000006116748,0.093541905,0.87883806,0.00007147254],"about_ca_topic_score_codex":0.000017392296,"about_ca_topic_score_gemma":0.00052758027,"teacher_disagreement_score":0.622869,"about_ca_system_score_codex":0.00001125165,"about_ca_system_score_gemma":0.00011470833,"threshold_uncertainty_score":0.93463415},"labels":[],"label_agreement":null},{"id":"W4414004064","doi":"10.14778/3749646.3749702","title":"ThriftLLM: On Cost-Effective Selection of Large Language Models for Classification Queries","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Selection (genetic algorithm); Computer science; Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.09834815259862227,"score_gpt":0.4145340017749151,"score_spread":0.31618584917629283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414004064","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":[0.5803645,0.0003804481,0.15552944,0.019755337,0.002064,0.025336618,0.00093051937,0.0002262028,0.21541293],"genre_scores_gemma":[0.9961619,0.000015132986,0.0006128923,0.00032023204,0.000019580777,0.0006632246,0.0000044916083,0.0000049164305,0.0021976524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99850607,0.000026503025,0.00043044638,0.00029698684,0.00058439095,0.00015559634],"domain_scores_gemma":[0.99859476,0.00036713108,0.0004082665,0.00018823045,0.00042113476,0.00002045828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023218372,0.000100669124,0.00021614583,0.00019056893,0.00012981067,0.00006280022,0.00056791486,0.000043113134,0.000015836597],"category_scores_gemma":[0.0010895476,0.00006373677,0.000121068355,0.00055930106,0.00006504696,0.00030057595,0.0002024984,0.00006840115,0.0000036606534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024352982,0.00027290577,0.0005469158,0.00012654062,0.00006211047,1.3252652e-8,0.0016728443,0.000094482755,0.022499759,0.9178571,0.021165498,0.035458308],"study_design_scores_gemma":[0.0017091456,0.00041660317,0.008408657,0.0002607367,0.000114170325,4.0421176e-7,0.017176539,0.01797265,0.63215995,0.25082785,0.07076044,0.00019287037],"about_ca_topic_score_codex":0.000037848666,"about_ca_topic_score_gemma":0.000027975462,"teacher_disagreement_score":0.66702926,"about_ca_system_score_codex":0.00007445316,"about_ca_system_score_gemma":0.00002401068,"threshold_uncertainty_score":0.259911},"labels":[],"label_agreement":null},{"id":"W4414227274","doi":"10.18438/eblip30802","title":"Why Are Data so Important to Library Development Today? Implications for Practice","year":2025,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Collection development; Development (topology); Information system; Academic library","score_opus":0.13139444587271806,"score_gpt":0.41559967024133077,"score_spread":0.28420522436861273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414227274","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000074908035,0.00063182035,0.2483643,0.7413544,0.00025713566,0.0010490394,0.00041870438,0.0001407566,0.007708918],"genre_scores_gemma":[0.0016522964,0.0007820997,0.20101735,0.79313385,0.00006390941,0.00025318947,0.0010589589,0.000010351021,0.0020279994],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968066,0.00039828257,0.0014131081,0.00052759034,0.0005957384,0.00025864688],"domain_scores_gemma":[0.9818474,0.014873475,0.0010503057,0.001795808,0.00022600923,0.0002070195],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0048480746,0.00018316456,0.00022402301,0.0005327441,0.00065040134,0.0038381934,0.0018633099,0.00007728488,0.00024667845],"category_scores_gemma":[0.040619705,0.00015540319,0.000037526046,0.0015828364,0.00005993198,0.40359977,0.0016035221,0.00016232891,0.00015683321],"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":[0.0003927946,0.00006816815,0.00044798333,0.000070164904,0.000027214006,8.5771563e-7,0.00016019802,0.000040382278,0.0000031606598,0.2899219,0.6432469,0.06562025],"study_design_scores_gemma":[0.00025741375,0.000055131117,0.007867843,0.00019761221,0.000051687424,0.0000041996536,0.0027670565,0.0010943771,0.00022446869,0.0025362116,0.98474777,0.00019624611],"about_ca_topic_score_codex":0.000006883641,"about_ca_topic_score_gemma":6.0635506e-7,"teacher_disagreement_score":0.3997616,"about_ca_system_score_codex":0.0000139244385,"about_ca_system_score_gemma":0.0008652415,"threshold_uncertainty_score":0.9971959},"labels":[],"label_agreement":null},{"id":"W4414244142","doi":"10.2218/ijdc.v19i1.906","title":"A Maturity Model for Urban Dataset Metadata","year":2025,"lang":"en","type":"article","venue":"International Journal of Digital Curation","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Metadata; Documentation; Maturity (psychological); Capability Maturity Model; Relevance (law); Graph; Plug-in; Software","score_opus":0.2141903317703833,"score_gpt":0.4785366575588719,"score_spread":0.2643463257884886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414244142","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":[0.002133158,0.0000491664,0.9800603,0.007966633,0.0009948907,0.000111906156,0.006940398,0.000005273505,0.0017383035],"genre_scores_gemma":[0.98939437,0.000010541612,0.0032160291,0.0010466509,0.00017710976,0.0000041138333,0.0018770165,0.000003425577,0.0042707296],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979696,0.00002877164,0.0007531368,0.00015143745,0.0010227802,0.00007426737],"domain_scores_gemma":[0.99800473,0.00039788647,0.00045467506,0.00023320355,0.0008715678,0.0000379319],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014521793,0.00006764754,0.00013923638,0.0003243488,0.000040753286,0.0018568835,0.0012243174,0.00002635149,0.000019363997],"category_scores_gemma":[0.003281104,0.000050745657,0.00010534367,0.00014095228,0.000030039198,0.0098719755,0.0002063727,0.000068941554,0.000016524567],"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":[0.0002582959,0.00015559363,0.0001708632,0.0000046771593,0.00015711982,0.000004612083,0.00008910746,0.0013124911,0.000059772632,0.22445163,0.738119,0.0352168],"study_design_scores_gemma":[0.00065154984,0.000042085692,0.0002039174,0.000025270538,0.000030444338,0.000008720334,0.00018485995,0.06703707,0.00014940422,0.41544506,0.51614624,0.0000753836],"about_ca_topic_score_codex":0.0000020754635,"about_ca_topic_score_gemma":0.000012510139,"teacher_disagreement_score":0.98726124,"about_ca_system_score_codex":0.000051292674,"about_ca_system_score_gemma":0.00010153944,"threshold_uncertainty_score":0.9991793},"labels":[],"label_agreement":null},{"id":"W4414313280","doi":"10.25300/misq/2025/18361","title":"Understanding and Improving Data Repurposing","year":2025,"lang":"en","type":"article","venue":"MIS Quarterly","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Repurposing; Scope (computer science); Drug repositioning; Big data; Data modeling; Reuse; Frontier","score_opus":0.5739900091310471,"score_gpt":0.45580669865034407,"score_spread":0.11818331048070307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414313280","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":[0.01854545,0.0005303603,0.92704284,0.0066746953,0.0008236249,0.00028758735,0.000091658105,0.00010067936,0.045903098],"genre_scores_gemma":[0.99238825,0.00000649732,0.0022338193,0.0009931681,0.000041436106,0.0000027926183,0.000029315781,0.000004987516,0.0042997412],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99833673,0.00012597219,0.00037537227,0.0005684122,0.00042008,0.00017343085],"domain_scores_gemma":[0.99794066,0.00051091594,0.0000932194,0.0013774505,0.000029535393,0.000048233953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034090218,0.000081180726,0.00014750974,0.00019829048,0.00025493055,0.0009091031,0.0009378714,0.000033309814,0.00005910319],"category_scores_gemma":[0.0005055075,0.00006656756,0.00002014601,0.00036802937,0.000078859026,0.0007686959,0.0002553671,0.00007358131,0.000040182582],"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":[0.000017830374,0.00002857268,0.0005560787,0.000031130756,0.000027269789,0.000011346853,0.001674736,0.0000010350399,0.0005242283,0.09747564,0.09362404,0.80602807],"study_design_scores_gemma":[0.001078413,0.00024158212,0.003328263,0.0001348691,0.00008368007,0.0000075891235,0.06882701,0.028926779,0.00008553575,0.4460867,0.45076755,0.0004320145],"about_ca_topic_score_codex":0.00015036386,"about_ca_topic_score_gemma":0.00029218776,"teacher_disagreement_score":0.9738428,"about_ca_system_score_codex":0.000039327442,"about_ca_system_score_gemma":0.000029120763,"threshold_uncertainty_score":0.8766502},"labels":[],"label_agreement":null},{"id":"W4414509393","doi":"10.29173/iq1138","title":"Adventures in data literacy: When the gap you were trying to identify turns out to be a chasm.","year":2025,"lang":"en","type":"article","venue":"IASSIST Quarterly","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Adventure; Knowledge production; The Internet; Data collection; Qualitative research","score_opus":0.2517956435020109,"score_gpt":0.4942851364603817,"score_spread":0.2424894929583708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414509393","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":[0.1902346,0.000982694,0.063177906,0.7064588,0.007147071,0.003086046,0.0023137312,0.0002470106,0.026352147],"genre_scores_gemma":[0.94984376,0.0000042497168,0.0013089099,0.025047436,0.0001770314,0.00011767429,0.00014341327,0.00001567547,0.023341851],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958167,0.00048455398,0.000978716,0.0010613435,0.0012083558,0.0004503412],"domain_scores_gemma":[0.9952551,0.0007643275,0.00016012671,0.0035422156,0.00011511444,0.00016313171],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0052439817,0.00022240444,0.00036989307,0.0005579655,0.00020380404,0.002141765,0.0047503687,0.00006924081,0.00031255875],"category_scores_gemma":[0.001260044,0.00014975725,0.00010207599,0.00092643726,0.00005767534,0.0010315625,0.0010263153,0.00023623953,0.00095494994],"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":[0.0000813196,0.00015487199,0.00055332755,0.000029383673,0.000044486216,0.00003089758,0.04916878,0.00001546975,0.00008357684,0.0069881533,0.61627096,0.32657874],"study_design_scores_gemma":[0.0003421812,0.000094600786,0.032738928,0.00012726201,0.000025351277,0.0000010993557,0.017412301,0.00032020887,0.000008441897,0.02537727,0.92334485,0.00020748258],"about_ca_topic_score_codex":0.00063274545,"about_ca_topic_score_gemma":0.014903455,"teacher_disagreement_score":0.75960916,"about_ca_system_score_codex":0.00006732493,"about_ca_system_score_gemma":0.00007376931,"threshold_uncertainty_score":0.9998229},"labels":[],"label_agreement":null},{"id":"W4414929510","doi":"10.56830/ijsie202407","title":"&lt;b&gt;Data Quality as a Service (DQaaS): A Paradigm Shift in &lt;/b&gt; &lt;b&gt;Enterprise Data Management &lt;/b&gt;","year":2025,"lang":"en","type":"article","venue":"International Journal of Sustainability and Innovation in Engineering","topic":"Data Quality and Management","field":"Decision Sciences","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":"EVERSANA (Canada)","funders":"","keywords":"Counterfactual thinking; Paradigm shift; Data quality; Schema (genetic algorithms); Enterprise data management; Anomaly detection; Quality of service; Service (business); Quality (philosophy)","score_opus":0.06432688146556595,"score_gpt":0.3927846794780049,"score_spread":0.3284577980124389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414929510","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":[0.6267657,0.0010952314,0.2988341,0.06464011,0.0031478265,0.0014870884,0.0005423964,0.00009360929,0.00339393],"genre_scores_gemma":[0.99548566,0.00030371457,0.0019469066,0.0013398711,0.00017960343,0.00003081346,0.00032469892,0.000020121397,0.00036860048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99182975,0.00037378803,0.003845556,0.0010700937,0.002361341,0.00051943975],"domain_scores_gemma":[0.9936928,0.0011913014,0.0011180228,0.0021623296,0.0017051754,0.0001303788],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.019221844,0.00038381648,0.00069342455,0.0036407534,0.00011254191,0.0008444699,0.0050338632,0.00016954116,0.00012149708],"category_scores_gemma":[0.008262602,0.00037356844,0.00008757824,0.0045423904,0.0001248205,0.003970262,0.0036965664,0.00053594867,0.000014325702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000834889,0.0009675501,0.0056553683,0.0007765134,0.00043146557,0.00029356923,0.0017053522,0.018320218,0.00038300987,0.9071967,0.007841221,0.055594128],"study_design_scores_gemma":[0.0034312583,0.00009518089,0.18498802,0.000689498,0.000056077522,0.000030203078,0.0017761247,0.043382376,0.00003480788,0.17428896,0.59063023,0.000597287],"about_ca_topic_score_codex":0.000108376305,"about_ca_topic_score_gemma":0.0005476529,"teacher_disagreement_score":0.7329078,"about_ca_system_score_codex":0.0009053404,"about_ca_system_score_gemma":0.00039685564,"threshold_uncertainty_score":0.9998716},"labels":[],"label_agreement":null},{"id":"W4415124422","doi":"10.1109/icisc65841.2025.11187811","title":"Stacked Neural Computing Model - Based Data Quality Analysis and Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data pre-processing; Artificial neural network; Principal component analysis; Preprocessor; Linear discriminant analysis; Feature extraction; Pattern recognition (psychology); Outlier; Missing data; Data quality","score_opus":0.5657591235788999,"score_gpt":0.5444405596649767,"score_spread":0.021318563913923172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415124422","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":[0.04441189,0.000010650243,0.94083434,0.00657445,0.0000487635,0.00009903069,0.0001419518,0.00004322984,0.007835675],"genre_scores_gemma":[0.9780027,0.0000018679718,0.016528679,0.0023928466,0.0000057334955,0.0000010874155,0.00033322282,0.0000014462299,0.0027323926],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976092,0.00037787887,0.0006028989,0.0006620937,0.00062177435,0.0001261593],"domain_scores_gemma":[0.9966718,0.0010760308,0.00015473377,0.0019342764,0.00011455228,0.000048626152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007594272,0.00007644688,0.00022952782,0.00038623033,0.00015648389,0.00047119844,0.0011076796,0.000029567651,0.000087877765],"category_scores_gemma":[0.0015137672,0.0000571109,0.000045941226,0.0016375626,0.00007414062,0.00046978355,0.0009023715,0.0000584722,0.000019273151],"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":[0.00007140998,0.0002401695,0.054523658,0.000040895342,0.0003758073,0.0000010363215,0.00024260166,0.034178,0.00026602673,0.33951977,0.09255772,0.4779829],"study_design_scores_gemma":[0.00014529038,0.0000025557315,0.10434709,0.0000013376739,0.00009073965,1.0332134e-8,0.0005349277,0.88597304,0.000010048493,0.006079741,0.0027553623,0.00005984773],"about_ca_topic_score_codex":0.00025038977,"about_ca_topic_score_gemma":0.0008545672,"teacher_disagreement_score":0.9335908,"about_ca_system_score_codex":0.000013867893,"about_ca_system_score_gemma":0.000039736216,"threshold_uncertainty_score":0.45437774},"labels":[],"label_agreement":null},{"id":"W4415231396","doi":"10.1609/aies.v8i3.36712","title":"A Principled Approach for Data Bias Mitigation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI/ACM Conference on AI Ethics and Society","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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":"Canada Excellence Research Chairs, Government of Canada; National Science Foundation","keywords":"Measure (data warehouse); Table (database); Tuple; Key (lock); Work (physics); Data collection","score_opus":0.5508003255245804,"score_gpt":0.4892577970435352,"score_spread":0.06154252848104513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415231396","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":[0.16046156,0.00036969403,0.13710032,0.548507,0.0013838738,0.0063702143,0.001356434,0.00022751678,0.14422339],"genre_scores_gemma":[0.95482457,0.0005219649,0.02858078,0.010190074,0.000049547587,0.000066348504,0.000051073377,0.000009432411,0.005706191],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977249,0.00005429603,0.0004911061,0.0006255506,0.0009156163,0.00018853594],"domain_scores_gemma":[0.99604285,0.001460309,0.0003850436,0.00090721354,0.0011524457,0.000052127107],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013602943,0.00013616744,0.00026642458,0.00005094034,0.0005264643,0.0005542681,0.0030103533,0.00019527107,0.000010060023],"category_scores_gemma":[0.016365105,0.00008661476,0.0001311839,0.0005112547,0.00037649513,0.0004040895,0.0023444681,0.0005689173,0.0000019036854],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025846794,0.00007322827,0.0007806822,0.00025282585,0.00005354943,7.653544e-9,0.0031634632,0.0000019764216,0.00045308835,0.9181263,0.070834905,0.0062341453],"study_design_scores_gemma":[0.0010111063,0.00009908732,0.0034231136,0.00026735538,0.000113195005,4.978041e-7,0.019132959,0.123685434,0.0018681943,0.7569813,0.093137465,0.00028028493],"about_ca_topic_score_codex":0.000026926798,"about_ca_topic_score_gemma":0.000005423344,"teacher_disagreement_score":0.794363,"about_ca_system_score_codex":0.00001941254,"about_ca_system_score_gemma":0.00020166504,"threshold_uncertainty_score":0.9919205},"labels":[],"label_agreement":null},{"id":"W4416034664","doi":"10.18653/v1/2025.findings-emnlp.481","title":"Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs","year":2025,"lang":"","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Training (meteorology); Quality (philosophy); Data quality; Data retrieval; Training set; Information system","score_opus":0.5712677946581087,"score_gpt":0.48605393596481217,"score_spread":0.08521385869329656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416034664","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":[0.0011169959,0.0002726478,0.92390907,0.040106896,0.0008815175,0.0021391516,0.0033545538,0.00012836102,0.028090836],"genre_scores_gemma":[0.12794322,0.0012365931,0.7538687,0.027845843,0.000921963,0.00016285521,0.009372514,0.000073426534,0.0785749],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9906761,0.0010513212,0.0034367517,0.0016143664,0.0023186458,0.0009027815],"domain_scores_gemma":[0.98715794,0.005548277,0.001676215,0.0042099147,0.0011612419,0.0002464117],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038992822,0.00051277253,0.001091521,0.0006255954,0.0012843809,0.004425523,0.00422833,0.00021702674,0.0006581152],"category_scores_gemma":[0.026642215,0.0004003501,0.00018433352,0.002626767,0.00044703146,0.013126024,0.0026215261,0.0004451643,0.00018169453],"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":[0.0011506295,0.000076314216,0.00010199067,0.00071892084,0.00029792913,0.0000019135334,0.0041410043,0.0005405003,0.000016420021,0.23375936,0.07503345,0.68416154],"study_design_scores_gemma":[0.0033877834,0.00024524465,0.005135177,0.0013590981,0.00032209684,0.0000027255633,0.12499934,0.081724204,0.00013772023,0.008836158,0.7729941,0.0008563638],"about_ca_topic_score_codex":0.0002841774,"about_ca_topic_score_gemma":0.00016154129,"teacher_disagreement_score":0.6979606,"about_ca_system_score_codex":0.00016530031,"about_ca_system_score_gemma":0.001012815,"threshold_uncertainty_score":0.99984485},"labels":[],"label_agreement":null},{"id":"W4417070120","doi":"10.1145/3769829","title":"ST-Raptor: LLM-Powered Semi-Structured Table Question Answering","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"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":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Table (database); Correctness; Tree (set theory); Set (abstract data type); Benchmark (surveying); Pipeline (software); Question answering","score_opus":0.13736906533177068,"score_gpt":0.41139771770102107,"score_spread":0.2740286523692504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417070120","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":[0.4741293,0.0012327136,0.010661748,0.0632491,0.0070010796,0.0076644095,0.005984611,0.0005818234,0.42949522],"genre_scores_gemma":[0.953068,0.00039096255,0.029081939,0.00090741034,0.00006657454,0.000030002517,0.00016621033,0.00002413148,0.016264753],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996578,0.000025929723,0.00082799577,0.0007839422,0.0015262396,0.00025789413],"domain_scores_gemma":[0.99513865,0.00018057018,0.0006581854,0.0037233424,0.00025708447,0.000042187985],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0045893774,0.00019026989,0.00034693017,0.00033531626,0.0001466706,0.00023050007,0.013541919,0.000055053366,0.00010361574],"category_scores_gemma":[0.002736851,0.00013198791,0.000077240664,0.0014119896,0.00013719634,0.0011872721,0.0139251575,0.0001364371,0.000017382607],"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":[0.0002094153,0.00028344244,0.0027638937,0.0007572036,0.00034407622,7.503498e-7,0.00010468664,0.00006004163,0.0022272882,0.32255965,0.6057335,0.064956],"study_design_scores_gemma":[0.001309752,0.00015224097,0.019957216,0.0011844047,0.0003417159,6.4920494e-7,0.004922315,0.0011816588,0.012212787,0.42798182,0.5303765,0.00037891752],"about_ca_topic_score_codex":0.000039390507,"about_ca_topic_score_gemma":0.000008334242,"teacher_disagreement_score":0.47893873,"about_ca_system_score_codex":0.000040175928,"about_ca_system_score_gemma":0.000017435414,"threshold_uncertainty_score":0.99405},"labels":[],"label_agreement":null},{"id":"W4417510432","doi":"10.1109/eecsi67060.2025.11290640","title":"A Novel Approach to Responding to Key Data Anomalies Using Unsupervised Learning: Work In Progress","year":2025,"lang":"","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Key (lock); Data pre-processing; Preprocessor; Confusion; Data quality; Anomaly detection; Hyperparameter; Data modeling","score_opus":0.36765431070543214,"score_gpt":0.4582932247787897,"score_spread":0.09063891407335756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417510432","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":[0.14671949,0.00077463425,0.7684606,0.014250941,0.0013710837,0.0038353868,0.00020373227,0.0001536881,0.06423048],"genre_scores_gemma":[0.52384096,0.000026282933,0.3976501,0.004684257,0.000114054455,0.000101580685,0.00013847764,0.000042058007,0.07340224],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9908891,0.0010196572,0.0019763364,0.0029829287,0.0019683954,0.0011636232],"domain_scores_gemma":[0.9938718,0.0011671593,0.00022914451,0.0040814304,0.00023687363,0.00041357122],"candidate_categories":["metaepi_narrow","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.017781503,0.00050933,0.0008866144,0.005367431,0.00060881546,0.0033573727,0.007053295,0.00019685026,0.00031957997],"category_scores_gemma":[0.0072178342,0.00045834025,0.00009995183,0.023361724,0.00021984208,0.001782273,0.01489991,0.00049563195,0.00032779117],"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":[0.005881707,0.0055017765,0.05308182,0.000720764,0.00046095342,0.00006677088,0.039172404,0.053667434,0.0012516662,0.26078975,0.086373486,0.49303147],"study_design_scores_gemma":[0.0015652208,0.00017344809,0.011972444,0.0012420553,0.000094145485,0.000002672285,0.054481942,0.08625728,0.000114358314,0.0004368859,0.84263927,0.0010202542],"about_ca_topic_score_codex":0.00041189822,"about_ca_topic_score_gemma":0.00021458245,"teacher_disagreement_score":0.7562658,"about_ca_system_score_codex":0.0002420101,"about_ca_system_score_gemma":0.0004217292,"threshold_uncertainty_score":0.99978685},"labels":[],"label_agreement":null},{"id":"W44195261","doi":"10.1007/978-3-319-11851-2_1","title":"Integrating Trust and Economic Theories with Knowledge Science for Dependable Service Automation","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Service (business); Knowledge management; Automation; Computational trust; Domain (mathematical analysis); Domain knowledge; Service design; Service provider; Computer security; Reputation; Business; Engineering; Marketing","score_opus":0.04662471210549109,"score_gpt":0.3351982024288138,"score_spread":0.28857349032332275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W44195261","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":[0.001213253,0.00008008265,0.9862752,0.00075957546,0.0008427187,0.0005296136,0.000028147162,0.00005405801,0.010217339],"genre_scores_gemma":[0.63186693,0.00001403073,0.3632394,0.0020487187,0.0005526038,0.00004173016,0.00001963568,0.000043022952,0.0021739134],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644417,0.000045411358,0.0005999713,0.0015271796,0.00092870137,0.00045455573],"domain_scores_gemma":[0.99582845,0.0020868513,0.0004301962,0.0010103317,0.00051235734,0.00013180228],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0089288,0.00033302192,0.00046543046,0.0009327867,0.0006960767,0.0020680695,0.0025888311,0.00011493684,0.000037794194],"category_scores_gemma":[0.00078600855,0.00022741596,0.000043913646,0.00060024613,0.0016975914,0.0010756574,0.0011551087,0.00024950068,0.00006284516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017819833,0.0000076270094,0.00006911441,0.000050876886,0.0000050205776,0.0000013312861,0.001423895,0.0060092905,0.000028045342,0.3585242,0.000049065668,0.63381374],"study_design_scores_gemma":[0.00026190982,0.0001730983,0.00013392048,0.00020708634,0.000010283908,0.000015314674,0.000012124843,0.5380396,0.00041937546,0.44708008,0.013271267,0.00037593022],"about_ca_topic_score_codex":0.000069073736,"about_ca_topic_score_gemma":0.0027681137,"teacher_disagreement_score":0.63343775,"about_ca_system_score_codex":0.00023336224,"about_ca_system_score_gemma":0.00074983423,"threshold_uncertainty_score":0.9989679},"labels":[],"label_agreement":null},{"id":"W44227490","doi":"10.1007/978-3-642-29461-7_31","title":"Reliability in the Thresholded Dempster-Shafer Algorithm for ESM Data Fusion","year":2012,"lang":"en","type":"book-chapter","venue":"Advances in intelligent and soft computing","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; Université de Montréal","funders":"","keywords":"Reliability (semiconductor); Information fusion; Fusion; Dempster–Shafer theory; Computer science; Data mining; Sensor fusion; Process (computing); Quality (philosophy); Measure (data warehouse); Algorithm; Artificial intelligence; Machine learning; Pattern recognition (psychology)","score_opus":0.21533567593208625,"score_gpt":0.4279537358832521,"score_spread":0.21261805995116584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W44227490","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":[0.00060017256,0.027223136,0.91377664,0.00082812057,0.0025705078,0.0024775926,0.0004768371,0.000059965754,0.05198701],"genre_scores_gemma":[0.3660892,0.07640311,0.34942073,0.014164981,0.008980208,0.00030191508,0.007734898,0.00054666394,0.17635831],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960198,0.00017037669,0.0013522902,0.0010983038,0.0009351027,0.00042417127],"domain_scores_gemma":[0.9920893,0.0054901554,0.00046990011,0.0017605998,0.00012450606,0.000065568696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012626398,0.00033652099,0.0005767472,0.00026309714,0.00021097084,0.0002510004,0.0024787344,0.00018869691,0.00008950875],"category_scores_gemma":[0.0012089846,0.00022310665,0.0001009202,0.00014171154,0.00022809404,0.0008347188,0.002128841,0.00048231988,0.00004835057],"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":[0.000020001264,0.000047533023,0.00026439852,0.000045332763,0.0000077062305,0.000004343664,0.0010640973,0.00013307223,1.8294678e-7,0.026220106,0.0011793687,0.97101384],"study_design_scores_gemma":[0.000176087,0.000033986606,0.00015267864,0.00020634264,0.00001969222,0.0000028705836,0.00074809894,0.02919324,0.000002483329,0.19818501,0.77100927,0.00027026783],"about_ca_topic_score_codex":0.00002770816,"about_ca_topic_score_gemma":0.00036218602,"teacher_disagreement_score":0.9707436,"about_ca_system_score_codex":0.00005158721,"about_ca_system_score_gemma":0.00002612646,"threshold_uncertainty_score":0.9098025},"labels":[],"label_agreement":null},{"id":"W656573153","doi":"","title":"A pre and post data warehouse cleaning technique.","year":2002,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data warehouse; Computer science; Warehouse; Database; Business; Marketing","score_opus":0.18775769131166392,"score_gpt":0.3325709532629921,"score_spread":0.14481326195132815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W656573153","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":[0.98276347,0.00037182454,0.00352663,0.003762624,0.00014359849,0.0005765067,0.0007686538,0.00016240923,0.007924273],"genre_scores_gemma":[0.9791212,0.00009857039,0.0069755698,0.0003198391,0.00003480607,4.8228554e-7,0.00007066562,0.000019072468,0.013359759],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99649423,0.0004343305,0.00036883328,0.0010045478,0.0013269652,0.0003711141],"domain_scores_gemma":[0.9962731,0.00047990057,0.0003529336,0.0024102535,0.00023287207,0.00025093954],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004461715,0.00020871684,0.00038742227,0.00048550824,0.0006643987,0.00021065382,0.0034139478,0.00017834787,0.0022240158],"category_scores_gemma":[0.0014603194,0.0002218205,0.000099830664,0.000786026,0.00038357897,0.0032028886,0.0043204795,0.0003774461,0.00057688024],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016761235,0.002008485,0.30582336,0.00047975118,0.00078754465,0.00070257817,0.036004283,0.00009672221,0.040143155,0.015000768,0.18463123,0.41264603],"study_design_scores_gemma":[0.002114829,0.0003969215,0.54757535,0.00017508671,0.00019525725,0.00007396549,0.013281984,0.00094011927,0.00062463566,0.004740414,0.42898557,0.0008958796],"about_ca_topic_score_codex":0.00018177449,"about_ca_topic_score_gemma":0.00045802284,"teacher_disagreement_score":0.41175014,"about_ca_system_score_codex":0.000052199128,"about_ca_system_score_gemma":0.000023761802,"threshold_uncertainty_score":0.9986881},"labels":[],"label_agreement":null},{"id":"W6886023238","doi":"10.14288/1.0398457","title":"Prospective data linkage to facilitate COVID-19 trials : A call to action","year":2021,"lang":"en","type":"article","venue":"Open Collections","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Bespoke; Observational study; Record linkage; Clinical trial; Linkage (software); Data collection; Medical record; Call to action; Health care; Cohort","score_opus":0.8115006908315471,"score_gpt":0.5764589460544908,"score_spread":0.2350417447770563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6886023238","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032531391,0.000026094547,0.5239893,0.062281266,0.0020952465,0.0053806766,0.009003294,0.00012181197,0.39677697],"genre_scores_gemma":[0.0026151252,0.000018499326,0.010669286,0.008785522,0.00012422776,0.0005525889,0.00022830878,0.000010406754,0.97699606],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954019,0.0014109602,0.0008422557,0.001223561,0.0008603371,0.0002609543],"domain_scores_gemma":[0.9939266,0.002571295,0.00016227382,0.0023867318,0.00042135717,0.0005317673],"candidate_categories":["metaresearch","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.013297359,0.0001375342,0.00049331185,0.00023052703,0.002244192,0.0061013782,0.0022983567,0.000054316155,0.0054519027],"category_scores_gemma":[0.070011765,0.00011811053,0.000082585095,0.005197536,0.000031025065,0.0010119019,0.004075842,0.00013418426,0.0014033812],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012638087,0.00014461314,0.000018186416,0.00000428562,0.000055451335,0.000015115952,0.0010149629,0.0004558625,0.00009740205,0.0004329964,0.9909145,0.0067202463],"study_design_scores_gemma":[0.0005964182,0.00010422113,0.00030675356,0.000007807284,0.000033820827,0.000006756796,0.004492381,0.00014057462,0.0001852849,0.009036586,0.98492724,0.00016216982],"about_ca_topic_score_codex":0.014559022,"about_ca_topic_score_gemma":0.080505826,"teacher_disagreement_score":0.58021903,"about_ca_system_score_codex":0.00032238217,"about_ca_system_score_gemma":0.0009307624,"threshold_uncertainty_score":0.99937415},"labels":[],"label_agreement":null},{"id":"W6886994811","doi":"10.15468/dl.nydmw7","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type); Data set","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6886994811","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6892677843","doi":"10.5281/zenodo.11395625","title":"Canadian Urban Data Catalogue","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Metadata; Data element; Metadata repository; Open data; Meta Data Services; Data management plan; Upload; Data management","score_opus":0.2547176194894219,"score_gpt":0.37294990165352887,"score_spread":0.11823228216410697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892677843","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026589853,0.0008941973,0.028935025,0.030732527,0.0015530653,0.0010031742,0.024191368,0.0022949688,0.90773666],"genre_scores_gemma":[0.92615026,0.000108401255,0.0004300956,0.0014677506,0.00051922887,3.590389e-8,0.046861842,0.001313946,0.023148445],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99726665,0.00040686227,0.0003309456,0.00077166077,0.0008475027,0.0003763659],"domain_scores_gemma":[0.99734336,0.00009478882,0.00004380647,0.0018829637,0.00028869614,0.0003463692],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0048478297,0.00010463168,0.0001164917,0.0005790909,0.0015897973,0.005156903,0.004977277,0.000043607433,0.027153922],"category_scores_gemma":[0.0030875765,0.0000936315,0.000033829998,0.0012597499,0.00012103829,0.0009970324,0.0038135967,0.00020920385,0.093826704],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034384125,0.000014266816,0.0000010892503,0.00001244916,0.00001678463,0.00003884209,0.000491442,0.0000050795284,0.000025164083,0.028382732,0.7959315,0.17507719],"study_design_scores_gemma":[0.0000720359,0.000036438596,0.00016319088,0.000015314221,0.000008755398,0.00003499108,0.0005391349,0.0016356369,0.000011316299,0.0019926154,0.99537426,0.00011628434],"about_ca_topic_score_codex":0.0073125716,"about_ca_topic_score_gemma":0.0012036328,"teacher_disagreement_score":0.9234913,"about_ca_system_score_codex":0.00018501889,"about_ca_system_score_gemma":0.000018865163,"threshold_uncertainty_score":0.99971},"labels":[],"label_agreement":null},{"id":"W6902080693","doi":"10.6084/m9.figshare.16909630","title":"Additional file 2 of Assessing the suitability of general practice electronic health records for clinical prediction model development: a data quality assessment","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Calgary","funders":"","keywords":"Data quality; Record linkage; Health records; General practice; Quality (philosophy); Health data; Data collection; Quality assessment","score_opus":0.6515578119347073,"score_gpt":0.5949122324697573,"score_spread":0.05664557946494997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902080693","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003398335,0.000051944848,0.0051504653,0.0012149174,0.000057908237,0.00036197092,0.9914119,0.000013149823,0.0017037279],"genre_scores_gemma":[0.0007647444,0.000007436012,0.064401746,0.000737238,0.00008591441,0.00037168036,0.93268263,0.000006089073,0.00094251626],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947143,0.0014458866,0.001675484,0.00065082096,0.0012522878,0.00026121704],"domain_scores_gemma":[0.96092707,0.03368889,0.0018466358,0.0019537355,0.0014905746,0.0000930967],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009209263,0.00010254048,0.00034520333,0.000040738694,0.0002239953,0.00014405641,0.001041858,0.0000651772,0.73352045],"category_scores_gemma":[0.12679788,0.000076791715,0.00011318038,0.00035959645,0.000029228662,0.0010563246,0.0009792642,0.00021864673,0.000057915222],"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":[0.000013647547,0.00028121882,0.000014769363,0.00008546634,0.000042423704,1.7930863e-7,0.00004658763,0.00007344095,4.4918116e-7,0.00031121902,0.95365953,0.04547104],"study_design_scores_gemma":[0.00016933838,0.000048361744,0.016625475,0.0002286645,0.00000870385,0.0000012722991,0.00056882197,0.035382632,0.000006774457,0.0018777112,0.9450108,0.00007143502],"about_ca_topic_score_codex":0.000013074542,"about_ca_topic_score_gemma":0.00019529404,"teacher_disagreement_score":0.7334625,"about_ca_system_score_codex":0.00012140389,"about_ca_system_score_gemma":0.004459825,"threshold_uncertainty_score":0.8805575},"labels":[],"label_agreement":null},{"id":"W6902186868","doi":"10.6084/m9.figshare.16909630.v1","title":"Additional file 2 of Assessing the suitability of general practice electronic health records for clinical prediction model development: a data quality assessment","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Calgary","funders":"","keywords":"Data quality; Record linkage; Health records; General practice; Quality (philosophy); Health data; Data collection; Quality assessment","score_opus":0.6515578119347073,"score_gpt":0.5949122324697573,"score_spread":0.05664557946494997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902186868","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003398335,0.000051944848,0.0051504653,0.0012149174,0.000057908237,0.00036197092,0.9914119,0.000013149823,0.0017037279],"genre_scores_gemma":[0.0007647444,0.000007436012,0.064401746,0.000737238,0.00008591441,0.00037168036,0.93268263,0.000006089073,0.00094251626],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947143,0.0014458866,0.001675484,0.00065082096,0.0012522878,0.00026121704],"domain_scores_gemma":[0.96092707,0.03368889,0.0018466358,0.0019537355,0.0014905746,0.0000930967],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009209263,0.00010254048,0.00034520333,0.000040738694,0.0002239953,0.00014405641,0.001041858,0.0000651772,0.73352045],"category_scores_gemma":[0.12679788,0.000076791715,0.00011318038,0.00035959645,0.000029228662,0.0010563246,0.0009792642,0.00021864673,0.000057915222],"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":[0.000013647547,0.00028121882,0.000014769363,0.00008546634,0.000042423704,1.7930863e-7,0.00004658763,0.00007344095,4.4918116e-7,0.00031121902,0.95365953,0.04547104],"study_design_scores_gemma":[0.00016933838,0.000048361744,0.016625475,0.0002286645,0.00000870385,0.0000012722991,0.00056882197,0.035382632,0.000006774457,0.0018777112,0.9450108,0.00007143502],"about_ca_topic_score_codex":0.000013074542,"about_ca_topic_score_gemma":0.00019529404,"teacher_disagreement_score":0.7334625,"about_ca_system_score_codex":0.00012140389,"about_ca_system_score_gemma":0.004459825,"threshold_uncertainty_score":0.8805575},"labels":[],"label_agreement":null},{"id":"W6905913842","doi":"10.15468/dl.929c6n","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type)","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6905913842","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6906122283","doi":"10.15468/dl.ypxg32","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type)","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6906122283","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6912622565","doi":"10.5281/zenodo.5181064","title":"Mathematics, Risk, and Messy Survey Data","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Western University","funders":"","keywords":"Government (linguistics); Workflow; Session (web analytics); Population; Work (physics); Publication; Survey data collection","score_opus":0.3731738872220772,"score_gpt":0.39507498187539863,"score_spread":0.021901094653321407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912622565","genre_codex":"other","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":[0.07334925,0.0013112935,0.30892897,0.007132995,0.00085854065,0.0014140351,0.024498884,0.0016467763,0.58085924],"genre_scores_gemma":[0.90853727,0.0024393296,0.013749358,0.0014871465,0.00038537144,5.524167e-8,0.040950224,0.00255721,0.029894007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963773,0.0014985362,0.0003805445,0.0006554145,0.0008647826,0.00022344157],"domain_scores_gemma":[0.9966645,0.00036828444,0.00016018991,0.00191705,0.00074221176,0.00014776898],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01055384,0.00009293684,0.00016649414,0.00013985952,0.0014544778,0.0025848292,0.002484778,0.000034100754,0.015874293],"category_scores_gemma":[0.024542976,0.00008339967,0.000021105145,0.00076280907,0.00015304498,0.0005824973,0.008353525,0.00016951509,0.010791633],"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":[0.000013230882,0.00013870775,0.00005692563,0.000023732206,0.000034004155,0.00001718152,0.0008447756,0.000006222479,0.00008913883,0.0068787825,0.77322483,0.21867247],"study_design_scores_gemma":[0.00021560754,0.000029166178,0.005249958,0.000008860727,0.000011086497,0.000030461906,0.0013571788,0.001387388,0.000051651325,0.0037516921,0.9878018,0.00010517715],"about_ca_topic_score_codex":0.000055521927,"about_ca_topic_score_gemma":0.000013168837,"teacher_disagreement_score":0.83518803,"about_ca_system_score_codex":0.000023294888,"about_ca_system_score_gemma":0.0000044084813,"threshold_uncertainty_score":0.9998455},"labels":[],"label_agreement":null},{"id":"W6912667207","doi":"10.5281/zenodo.3596718","title":"DDI 4 Core: Describing and managing data for traditional and modern data platforms","year":2019,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Statistics Canada","funders":"","keywords":"Interoperability; XML; Scope (computer science); Data management; Data model (GIS); Data system; Metadata; Core (optical fiber)","score_opus":0.8478209347699858,"score_gpt":0.4379830149435481,"score_spread":0.4098379198264377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912667207","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002527029,0.00028749925,0.0016255488,0.00045533612,0.00009143242,0.00047129474,0.99256265,0.000027696251,0.0019515308],"genre_scores_gemma":[0.1351508,0.000014368937,0.003091586,0.0010775635,0.000117777316,0.000031389005,0.85929835,0.000014077406,0.0012040939],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983783,0.000010741135,0.00023848099,0.000720262,0.0004796588,0.00017255243],"domain_scores_gemma":[0.9971456,0.0009016998,0.00009880561,0.001736127,0.000043357933,0.000074387804],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009374965,0.000092197726,0.0001455406,0.00007490504,0.00013148437,0.00049703533,0.0016968313,0.0000336108,0.015050712],"category_scores_gemma":[0.0021070985,0.000072221934,0.000012613096,0.00009771921,0.000012163701,0.0022593846,0.0021472562,0.000062858795,0.000488389],"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":[0.0000133533185,0.0000125855595,0.00006386849,0.00007572037,0.000013949897,0.0000022218105,0.000084104155,0.000008476771,0.000006342655,0.0022748436,0.904192,0.09325257],"study_design_scores_gemma":[0.00058168976,0.00003780726,0.0020415075,0.00037256547,0.000013237931,0.000010050765,0.00054851,0.30973437,0.000005215476,0.06786211,0.6185783,0.00021461151],"about_ca_topic_score_codex":0.000004495433,"about_ca_topic_score_gemma":0.00002923378,"teacher_disagreement_score":0.30972588,"about_ca_system_score_codex":0.0000072247485,"about_ca_system_score_gemma":0.000019414363,"threshold_uncertainty_score":0.9858497},"labels":[],"label_agreement":null},{"id":"W6920969057","doi":"10.6084/m9.figshare.15063757.v1","title":"Additional file 2 of Assessing record linkage between health care and Vital Statistics databases using deterministic methods","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Institute of Health Economics; University of Calgary","funders":"","keywords":"Record linkage; Linkage (software); Health care; Data collection; MEDLINE; Data source; Health data","score_opus":0.5070898105060758,"score_gpt":0.552299466771692,"score_spread":0.04520965626561613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920969057","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014216563,0.000106622596,0.009701904,0.000020894615,0.000038901613,0.00007343734,0.989317,0.000011253348,0.00071578653],"genre_scores_gemma":[0.00011108012,9.413559e-7,0.36571908,0.00014054737,0.000058740894,0.000017613562,0.63379705,0.0000053567073,0.00014957051],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787104,0.00051656924,0.0005226538,0.00038490948,0.00053105736,0.00017378942],"domain_scores_gemma":[0.9824333,0.016298177,0.00040673357,0.0004135062,0.0003360587,0.00011219299],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033641278,0.000103054335,0.00029583118,0.00009246239,0.00018584577,0.000265918,0.00023406609,0.00003134423,0.95025104],"category_scores_gemma":[0.04089658,0.00009780863,0.000041243067,0.00029081036,0.000023375003,0.00039510304,0.00059053744,0.000101354446,0.0002240084],"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":[5.965148e-7,0.000007723255,0.00000666883,0.00013264353,0.0000068610875,0.000015345899,0.00006362148,9.820675e-7,0.0000012233716,0.000012603464,0.74976563,0.2499861],"study_design_scores_gemma":[0.0000621226,0.00003160624,0.0029306712,0.0012821875,0.000009401891,0.000005315949,0.0014571428,0.00049130304,0.000033388773,0.0003487351,0.9932339,0.000114220675],"about_ca_topic_score_codex":0.000013560908,"about_ca_topic_score_gemma":0.000054302138,"teacher_disagreement_score":0.95002705,"about_ca_system_score_codex":0.000035043402,"about_ca_system_score_gemma":0.00038100907,"threshold_uncertainty_score":0.96718234},"labels":[],"label_agreement":null},{"id":"W6920990162","doi":"10.6084/m9.figshare.22729174.v1","title":"Additional file 2 of Identifying dementia using medical data linkage in a longitudinal cohort study: Lothian Birth Cohort 1936","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Cohort; Record linkage; Linkage (software); Longitudinal data; Cohort study; Dementia; Data file; Cohort effect","score_opus":0.4652379535492501,"score_gpt":0.46450192286259634,"score_spread":0.000736030686653788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920990162","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011261157,0.000016133663,0.000017183173,0.000061320265,0.00008734049,0.00051988615,0.9966273,0.0000535666,0.0014912095],"genre_scores_gemma":[0.0163873,0.000001952722,0.0003237406,0.00011268648,0.00013053176,0.00031810187,0.98172325,0.000013808348,0.0009886484],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941301,0.00029714423,0.0009238641,0.00089661893,0.003415121,0.00033714983],"domain_scores_gemma":[0.9940161,0.003817498,0.00035474938,0.0014794474,0.00018217128,0.00015000375],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029309457,0.00015259556,0.0003663489,0.00050888065,0.00014723734,0.00025099708,0.00242247,0.000086155305,0.99391276],"category_scores_gemma":[0.040194657,0.00013900969,0.00006694395,0.0018157786,0.000032881602,0.0007853416,0.00356395,0.00022407866,0.01193663],"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":[0.0000044292806,0.00013083252,0.019191837,0.00004514386,0.00008705061,0.00018948475,0.000054028722,0.000017118347,2.0593508e-7,0.0000065655054,0.9782447,0.0020285675],"study_design_scores_gemma":[0.00016487091,0.000016964765,0.48637667,0.00084688206,0.000015295349,0.00000306719,0.00039743158,0.0060578766,7.1881317e-7,0.00014972998,0.50585055,0.00011993782],"about_ca_topic_score_codex":0.000114834926,"about_ca_topic_score_gemma":0.0015159467,"teacher_disagreement_score":0.98197615,"about_ca_system_score_codex":0.00003645726,"about_ca_system_score_gemma":0.00021634648,"threshold_uncertainty_score":0.9888327},"labels":[],"label_agreement":null},{"id":"W6923691801","doi":"10.14288/1.0177589","title":"Daily Building Record","year":2016,"lang":"en","type":"article","venue":"Open Collections","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Publishing; Historical record; Project commissioning; Architecture; Record keeping","score_opus":0.2122230395360295,"score_gpt":0.4337421082766022,"score_spread":0.2215190687405727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6923691801","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044341225,0.000004449334,0.11182445,0.006021929,0.00087212375,0.00030828617,0.000071509385,0.000036925605,0.8804169],"genre_scores_gemma":[0.011513273,0.00001603016,0.0071469867,0.00051367836,0.00006136221,0.000065018525,9.182327e-7,0.0000052824075,0.9806774],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986143,0.00016061634,0.00031249673,0.0003531501,0.00040185318,0.00015756696],"domain_scores_gemma":[0.9983099,0.0007767391,0.00009419041,0.0006339501,0.000111087036,0.000074146075],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021868916,0.00006097202,0.00012662425,0.000105436215,0.0015891239,0.0030604524,0.0013017503,0.000024680783,0.009602734],"category_scores_gemma":[0.0018620973,0.00003608651,0.00004664498,0.0014816205,0.000044381017,0.0008674486,0.00080132793,0.00003622589,0.0008824679],"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":[0.000010467605,0.000027590035,0.000051339666,2.3543379e-7,0.000008087229,0.0000011214587,0.000019648132,0.000001188999,0.00009702288,0.005438542,0.9047559,0.08958886],"study_design_scores_gemma":[0.00025336051,0.00003255728,0.00023923296,0.000008807503,0.000004389739,0.0000017825412,0.0002252253,0.000018831684,0.00014564098,0.09989019,0.8991105,0.00006950669],"about_ca_topic_score_codex":0.0027814398,"about_ca_topic_score_gemma":0.0038219912,"teacher_disagreement_score":0.10467747,"about_ca_system_score_codex":0.000054151922,"about_ca_system_score_gemma":0.000059843787,"threshold_uncertainty_score":0.99989545},"labels":[],"label_agreement":null},{"id":"W6931726075","doi":"10.5281/zenodo.6710583","title":"Phenacomys ungava Merriam 1889","year":2017,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Vole; Subspecies; Boreal; Dorsum; Snout; Bay","score_opus":0.2581520943643967,"score_gpt":0.3944198436953972,"score_spread":0.1362677493310005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931726075","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007417501,0.000043584838,0.019431345,0.008561442,0.00056796125,0.00048852636,0.000415407,0.0006238173,0.96245044],"genre_scores_gemma":[0.9750386,0.00007018727,0.0006663878,0.0007005167,0.00034055253,3.9917882e-8,0.0006675924,0.000808278,0.02170787],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9968244,0.0005660146,0.0004145597,0.00060900464,0.0012174187,0.00036862362],"domain_scores_gemma":[0.9965224,0.00008371516,0.00031503147,0.0022355223,0.0006270295,0.000216282],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0050493157,0.00013058985,0.00018730958,0.00023657148,0.0066860546,0.006566997,0.0055461954,0.00004934729,0.032439828],"category_scores_gemma":[0.008239847,0.00011505682,0.00007739878,0.00029708765,0.00034250377,0.0010267078,0.0050839884,0.00020271055,0.061773285],"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":[0.000025910786,0.000074146774,0.0000058907044,0.0000082296165,0.00002164714,0.0000115328485,0.0004615314,0.000010997541,0.00032926595,0.039907154,0.6729893,0.28615436],"study_design_scores_gemma":[0.0003746809,0.000080853744,0.002216886,0.000010600001,0.000008980804,0.000013804093,0.0005554111,0.000266741,0.00015779355,0.006961911,0.9892074,0.00014494383],"about_ca_topic_score_codex":0.00004881658,"about_ca_topic_score_gemma":0.000002043229,"teacher_disagreement_score":0.9676211,"about_ca_system_score_codex":0.000065957836,"about_ca_system_score_gemma":0.0000033139534,"threshold_uncertainty_score":0.9998343},"labels":[],"label_agreement":null},{"id":"W6939481667","doi":"10.6084/m9.figshare.15063754","title":"Additional file 1 of Assessing record linkage between health care and Vital Statistics databases using deterministic methods","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Institute of Health Economics; University of Calgary","funders":"","keywords":"Record linkage; Linkage (software); Health care; Data collection; MEDLINE; Data source; Health data","score_opus":0.5172368392236222,"score_gpt":0.5531341020742365,"score_spread":0.03589726285061434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939481667","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014316676,0.0001048501,0.009922705,0.000021006741,0.000038660844,0.0000735679,0.98911464,0.00001125512,0.0006989809],"genre_scores_gemma":[0.00011260396,9.126549e-7,0.36818564,0.00014003759,0.000057633355,0.00001791162,0.6313314,0.0000053454464,0.00014852133],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787056,0.00051675044,0.00052240473,0.00038521088,0.0005311941,0.00017385582],"domain_scores_gemma":[0.9821886,0.016541736,0.00040618112,0.00041438823,0.0003368833,0.00011222268],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003383542,0.0001030888,0.00029575505,0.00009252608,0.00018583145,0.00026531264,0.00023420312,0.000031344036,0.95118815],"category_scores_gemma":[0.041400366,0.000097842254,0.000041251456,0.0002910482,0.000023375342,0.00039481866,0.00059062475,0.00010137899,0.0002265486],"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":[6.0300124e-7,0.000007765212,0.0000069337616,0.00013205978,0.000006895926,0.000014992249,0.00006388848,9.821001e-7,0.0000012760113,0.000012437355,0.7534129,0.24633926],"study_design_scores_gemma":[0.00006182364,0.000031675085,0.0029880218,0.0013020773,0.000009460052,0.0000053160666,0.0014763986,0.0004959442,0.0000336877,0.000346655,0.9931342,0.00011474291],"about_ca_topic_score_codex":0.000013418687,"about_ca_topic_score_gemma":0.00005396626,"teacher_disagreement_score":0.9509616,"about_ca_system_score_codex":0.000035032852,"about_ca_system_score_gemma":0.00038279945,"threshold_uncertainty_score":0.9666743},"labels":[],"label_agreement":null},{"id":"W6939837085","doi":"10.6084/m9.figshare.16909645","title":"Additional file 7 of Assessing the suitability of general practice electronic health records for clinical prediction model development: a data quality assessment","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Calgary","funders":"","keywords":"Data quality; Record linkage; Quality (philosophy); Health records; General practice; Health data; Quality assessment; Data collection","score_opus":0.6550559088450293,"score_gpt":0.5950021434766101,"score_spread":0.06005376536841922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939837085","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003444429,0.000051585575,0.0053102663,0.0012201059,0.00005763588,0.0003628038,0.9912798,0.000013156488,0.0016702496],"genre_scores_gemma":[0.00079411454,0.0000073683427,0.06506292,0.00073808176,0.0000848708,0.0003715935,0.93200254,0.000006098703,0.0009324118],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947128,0.0014456843,0.0016760492,0.0006512269,0.0012528516,0.00026135944],"domain_scores_gemma":[0.9608333,0.033792317,0.0018412458,0.0019516731,0.0014885124,0.00009295499],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009264524,0.00010258154,0.00034529646,0.000040770527,0.00022408378,0.00014412764,0.001042252,0.00006517828,0.72640026],"category_scores_gemma":[0.12585923,0.000076819575,0.00011321154,0.0003598054,0.000029240473,0.0010566905,0.000979195,0.00021868834,0.000057702076],"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":[0.000013739838,0.00028163512,0.000015235841,0.000086311076,0.000042439966,1.7756068e-7,0.000046683024,0.000073195195,4.6371952e-7,0.00031462952,0.9538747,0.04525079],"study_design_scores_gemma":[0.00016979927,0.000048545742,0.01680132,0.00023388014,0.000008727698,0.0000012711237,0.0005735886,0.035771612,0.0000069010193,0.0018869218,0.94442576,0.00007164802],"about_ca_topic_score_codex":0.000013100975,"about_ca_topic_score_gemma":0.00019700958,"teacher_disagreement_score":0.72634256,"about_ca_system_score_codex":0.00012142786,"about_ca_system_score_gemma":0.0044712215,"threshold_uncertainty_score":0.88150406},"labels":[],"label_agreement":null},{"id":"W6943470697","doi":"10.15468/dl.sgpwu4","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type)","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6943470697","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6943651574","doi":"10.15468/dl.vyqka7","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type)","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6943651574","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6945376458","doi":"10.25384/sage.7275083","title":"804276_App_4_online_supp – Supplemental material for Health care providers’ roles and responsibilities in management of polypharmacy: Results of a modified Delphi","year":2018,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Health care; Delphi method; Delphi; Work (physics)","score_opus":0.20773870226602564,"score_gpt":0.4874709574046067,"score_spread":0.2797322551385811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945376458","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":[0.6113619,0.006466843,0.010052077,0.027372424,0.0009864251,0.004292988,0.33884266,0.000036507343,0.0005881672],"genre_scores_gemma":[0.9768362,0.0015573675,0.019267812,0.0003511051,0.0001323771,0.000021018272,0.0015739393,0.000015317915,0.00024485643],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9956704,0.00047273596,0.0018987216,0.00062124414,0.0009937875,0.00034310695],"domain_scores_gemma":[0.9970455,0.0004237186,0.00081888214,0.0014088256,0.00019331335,0.00010975582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0106843505,0.00015963646,0.00048208976,0.00044696056,0.00012139903,0.00017343806,0.0015208531,0.000036158566,0.00042522323],"category_scores_gemma":[0.0006430973,0.00012772124,0.000053084183,0.00035013302,0.0002469902,0.000890488,0.0017635771,0.000079289945,0.0000027606307],"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":[0.016939772,0.0007229488,0.0009564249,0.0015718652,0.00036610774,0.00003774683,0.029756367,0.000023280081,0.0020299663,0.0014808468,0.20781218,0.7383025],"study_design_scores_gemma":[0.03765336,0.004392722,0.02604559,0.0051925336,0.00032149028,0.000041928433,0.48945785,0.0043533146,0.020798992,0.039208356,0.3712053,0.0013285626],"about_ca_topic_score_codex":0.00066171953,"about_ca_topic_score_gemma":0.0024512715,"teacher_disagreement_score":0.73697394,"about_ca_system_score_codex":0.000044778706,"about_ca_system_score_gemma":0.00014147768,"threshold_uncertainty_score":0.5208321},"labels":[],"label_agreement":null},{"id":"W6945405604","doi":"10.25384/sage.25817337","title":"sj-docx-1-cjk-10.1177_20543581241249365 – Supplemental material for Development and Validation of a Treatment Algorithm for Osteoarthritis Pain Management in Patients With End-Stage Kidney Disease Undergoing Hemodialysis","year":2024,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Kidney disease; Osteoarthritis; Hemodialysis; Disease; Pain management","score_opus":0.07973810082204656,"score_gpt":0.36019133820789767,"score_spread":0.2804532373858511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945405604","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":[0.081199236,0.0014703994,0.5163753,0.0021207924,0.0009252261,0.0066655567,0.39102885,0.00007370417,0.00014093872],"genre_scores_gemma":[0.36245352,0.0024955228,0.36620888,0.001075617,0.0005929498,0.0020462058,0.25746012,0.00020874459,0.0074584456],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963339,0.00029942844,0.0011453008,0.00086370914,0.00096385926,0.000393794],"domain_scores_gemma":[0.9977761,0.0006839952,0.00032513865,0.00085373886,0.000098544944,0.00026246428],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0057473164,0.00027178117,0.0004277374,0.0005668131,0.00019998134,0.0009203542,0.0007116949,0.000039312552,0.005570965],"category_scores_gemma":[0.00030030197,0.0002062077,0.00008335728,0.0004092444,0.00005850317,0.0012553204,0.00062160235,0.000049014256,0.000010188704],"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":[0.00035475643,0.00030063916,0.0011668673,0.00017958347,0.00030267023,0.00002877764,0.00036645448,0.000019020523,0.000010697469,0.000088077926,0.018272338,0.9789101],"study_design_scores_gemma":[0.011516953,0.0013949905,0.0038678362,0.001313715,0.00053061417,0.0000018387889,0.0025559182,0.0060566254,0.0013172281,0.0024877053,0.96830595,0.00065060065],"about_ca_topic_score_codex":0.000037171707,"about_ca_topic_score_gemma":0.00021406023,"teacher_disagreement_score":0.9782595,"about_ca_system_score_codex":0.0002327971,"about_ca_system_score_gemma":0.0002283208,"threshold_uncertainty_score":0.9953381},"labels":[],"label_agreement":null},{"id":"W6945450956","doi":"10.24435/materialscloud:x1-d9","title":"Computational optimization of a drafter for spunbonding polymeric filaments","year":2025,"lang":"en","type":"dataset","venue":"NCCR MARVEL","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Computational fluid dynamics; Solver; Airflow; Drag; Breakage; Flow (mathematics); Set (abstract data type); Energy consumption; Finite element method","score_opus":0.10265269435027939,"score_gpt":0.428189467569574,"score_spread":0.3255367732192946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945450956","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017054458,0.00004591193,0.28509814,0.00026623742,0.000556686,0.0003575633,0.71342754,0.000007970809,0.0002382507],"genre_scores_gemma":[0.000025396092,0.000024511195,0.017990451,0.000902552,0.0000661753,0.00006421326,0.9755981,0.000005094316,0.0053234836],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99711144,0.00013610115,0.0008952085,0.0005266625,0.0011334768,0.00019711343],"domain_scores_gemma":[0.9971891,0.0012268687,0.0006163787,0.000703579,0.00021456601,0.000049504375],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012920196,0.0001917442,0.0004421711,0.00063338934,0.000099508485,0.00020889084,0.001047242,0.00013714565,0.0010198371],"category_scores_gemma":[0.0014034597,0.00016577382,0.00016787715,0.0005953378,0.000067288136,0.0002354913,0.000528317,0.00009677047,0.000022986986],"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":[0.000041724124,0.00009351781,0.000005099431,0.00012982743,0.0000571913,0.0000010364486,0.000015658346,0.014334828,4.4141456e-7,0.00041423837,0.9774997,0.007406737],"study_design_scores_gemma":[0.0004387837,0.000045277007,0.000075656026,0.00010299898,0.00006847754,4.1108498e-7,0.00006199238,0.008654911,0.000003972771,0.0026410487,0.9877449,0.0001615186],"about_ca_topic_score_codex":0.00010786851,"about_ca_topic_score_gemma":0.000023092265,"teacher_disagreement_score":0.26710767,"about_ca_system_score_codex":0.000047572932,"about_ca_system_score_gemma":0.0001398895,"threshold_uncertainty_score":0.99989337},"labels":[],"label_agreement":null},{"id":"W6945541623","doi":"10.25384/sage.c.7264408.v1","title":"Representational Style Across National and Constituency Contexts: Members of Parliament in Australia, Canada, New Zealand and the United Kingdom","year":2024,"lang":"en","type":"other","venue":"Sage Journals Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Parliament; Style (visual arts); Variation (astronomy); Sample (material); Kingdom; Focus (optics)","score_opus":0.2704352597502669,"score_gpt":0.4756283452452875,"score_spread":0.20519308549502063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6945541623","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015229647,0.16724229,0.004062576,0.16299482,0.009477337,0.007979697,0.408355,0.00014797681,0.22451065],"genre_scores_gemma":[0.012427988,0.004580955,0.00054309174,0.00135824,0.00032555955,0.000010495241,0.0009776372,0.00006556872,0.97971046],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963428,0.00033818636,0.00083062216,0.00051561045,0.0017805943,0.00019220922],"domain_scores_gemma":[0.99747217,0.0009746892,0.00060036,0.00074417645,0.00008376967,0.00012484704],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00595536,0.00016748294,0.0004000963,0.0003127948,0.0000531929,0.00050490163,0.0010574609,0.00007928041,0.00683062],"category_scores_gemma":[0.0019040135,0.00010622761,0.000027630585,0.0004688948,0.0004165645,0.0002542616,0.00094522926,0.00028193873,0.000020677926],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032383992,0.000013258313,0.0006772507,0.000024143867,0.0001393379,0.0000329047,0.00033892383,0.0000124046965,8.1126046e-7,0.0011740142,0.9937431,0.0038114467],"study_design_scores_gemma":[0.0014029152,0.0000060194207,0.0022161612,0.00081964454,0.000040572573,0.000020438943,0.0012602544,0.00010121816,7.993357e-7,0.010254551,0.9837534,0.00012403805],"about_ca_topic_score_codex":0.8141922,"about_ca_topic_score_gemma":0.87684476,"teacher_disagreement_score":0.7551998,"about_ca_system_score_codex":0.000047450965,"about_ca_system_score_gemma":0.00044883677,"threshold_uncertainty_score":0.99407727},"labels":[],"label_agreement":null},{"id":"W6946174898","doi":"10.25740/2zme-3q44","title":"2013 Machine Learning Data Set for NASA's Solar Dynamics Observatory - Atmospheric Imaging Assembly","year":2019,"lang":"en","type":"dataset","venue":"Stanford Digital Repository","topic":"Data Quality and Management","field":"Decision Sciences","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":"Lockheed Martin (Canada)","funders":"","keywords":"Deliverable; Observatory; Data set; Set (abstract data type); Solar observatory; Scientific instrument; Data processing","score_opus":0.12196196066090455,"score_gpt":0.37230123974075524,"score_spread":0.2503392790798507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946174898","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010662511,0.0009950484,0.012745974,0.00016449591,0.0036781016,0.0010353633,0.9788295,0.00012527306,0.0023196246],"genre_scores_gemma":[0.0003324587,0.0001378126,0.00071255426,0.00040771815,0.0003522848,0.000046270925,0.9752217,0.00007917213,0.02271001],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919138,0.00025052595,0.0019014311,0.002187391,0.002854658,0.00089217117],"domain_scores_gemma":[0.98927724,0.0021031562,0.0016315554,0.0062170085,0.00046385152,0.00030718718],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.003265706,0.0007679795,0.0010724643,0.00013144003,0.0005612868,0.0050683906,0.007109551,0.0003207782,0.000062826264],"category_scores_gemma":[0.0039295503,0.00067860936,0.000372058,0.00054778246,0.00021536517,0.0051710396,0.005429561,0.0008604034,0.0007485294],"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":[0.00010643951,0.00008760656,0.0010953007,0.00025805275,0.00013530345,0.00007308333,0.000016683372,0.00015966374,0.0000012379153,0.00006132426,0.9826408,0.015364476],"study_design_scores_gemma":[0.00045334434,0.00012686197,0.00012427809,0.00008823492,0.00012863796,0.000023757273,0.0007429154,0.045349907,0.000001221897,0.0004059458,0.9517786,0.0007763331],"about_ca_topic_score_codex":0.0006705974,"about_ca_topic_score_gemma":0.00063648506,"teacher_disagreement_score":0.045190245,"about_ca_system_score_codex":0.00039533369,"about_ca_system_score_gemma":0.0004917107,"threshold_uncertainty_score":0.9995665},"labels":[],"label_agreement":null},{"id":"W6946232968","doi":"10.3389/fnagi.2021.646807.s003","title":"Table_1_Mind-Body Exercise Modulates Locus Coeruleus and Ventral Tegmental Area Functional Connectivity in Individuals With Mild Cognitive Impairment.doc","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Locus coeruleus; Ventral tegmental area; Insula; Montreal Cognitive Assessment; Dopamine; Functional magnetic resonance imaging; Amygdala; Cognition; Norepinephrine","score_opus":0.10382324318799008,"score_gpt":0.33725385093992155,"score_spread":0.23343060775193147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946232968","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036250656,0.00082277315,0.0000044024296,0.00007374682,0.00017610719,0.001123368,0.994066,0.000023932023,0.00008463436],"genre_scores_gemma":[0.0059361923,0.000054489694,0.000023033557,0.00034211302,0.000096959324,0.00061628286,0.99261665,0.000020416437,0.00029385052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99480766,0.00035311026,0.00075802003,0.001480135,0.0019777277,0.0006233251],"domain_scores_gemma":[0.99648756,0.0015447165,0.0005619707,0.0007941651,0.00029398245,0.00031759648],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00092722883,0.0005661047,0.0008837099,0.0005311047,0.00023194714,0.0009620541,0.0007351824,0.0003194747,0.22174658],"category_scores_gemma":[0.0026326233,0.0004643567,0.00012904046,0.0008444697,0.000082659695,0.00078935263,0.0013542443,0.0006070292,0.0016154713],"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":[0.00013101843,0.00049119676,0.00043225315,0.00019910312,0.00013148319,0.0003004467,0.00007337162,0.000033220844,4.1705383e-7,0.0000019221523,0.99703515,0.0011704387],"study_design_scores_gemma":[0.0029707083,0.00030457624,0.034905612,0.0067842887,0.00018861712,0.00005318384,0.0023223707,0.00008986955,0.0000997676,0.0002378798,0.9510763,0.0009667864],"about_ca_topic_score_codex":0.0001916574,"about_ca_topic_score_gemma":0.0006365771,"teacher_disagreement_score":0.22013111,"about_ca_system_score_codex":0.00014603995,"about_ca_system_score_gemma":0.00030217905,"threshold_uncertainty_score":0.99978083},"labels":[],"label_agreement":null},{"id":"W6946567227","doi":"10.34944/dspace/668","title":"Ultrasound induced destruction of emerging contaminants","year":2011,"lang":"en","type":"other","venue":"TUScholarShare (Temple University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Contamination; Groundwater; Surface water; Estrogen; Wastewater; Water treatment; Water pollution","score_opus":0.1919183951531109,"score_gpt":0.3472472640216878,"score_spread":0.1553288688685769,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6946567227","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01731235,0.00009726079,0.0014236212,0.000023639912,0.00093425566,0.0004922675,0.0013889137,0.00018287358,0.9781448],"genre_scores_gemma":[0.04207733,0.00013204601,0.0009984926,0.00006222712,0.000106881685,9.3428787e-7,0.00026415818,0.00014548871,0.95621246],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997326,0.00038192383,0.00041672945,0.0006788329,0.0009041905,0.00029231224],"domain_scores_gemma":[0.99745387,0.00023438959,0.00085282756,0.0011147324,0.0002101732,0.00013401321],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0011323689,0.00026264216,0.00051664823,0.0017639294,0.00015252792,0.00009449451,0.0016969584,0.00028711816,0.020282248],"category_scores_gemma":[0.00088951294,0.0002635482,0.00017259955,0.0011260271,0.0001032286,0.00066449854,0.0004795215,0.00029939198,0.0009449777],"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":[0.00010979426,0.00022184198,0.0037194765,0.00018329779,0.0003884617,0.0001608831,0.0011861087,8.7085004e-7,0.001590986,0.04212768,0.91286916,0.037441462],"study_design_scores_gemma":[0.00044140837,0.00005159264,0.003490197,0.00016226438,0.000074132884,0.0000048148295,0.0025422869,6.275735e-7,0.00039264647,0.0008252111,0.9917208,0.0002940397],"about_ca_topic_score_codex":0.001563847,"about_ca_topic_score_gemma":0.0015086543,"teacher_disagreement_score":0.07885164,"about_ca_system_score_codex":0.00007860683,"about_ca_system_score_gemma":0.000085677544,"threshold_uncertainty_score":0.9999817},"labels":[],"label_agreement":null},{"id":"W6947568337","doi":"10.3886/icpsr36744","title":"Health Reform Monitoring Survey, United States, First Quarter 2016","year":2016,"lang":"en","type":"dataset","venue":"ICPSR Data Holdings","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Robert Wood Johnson Foundation","keywords":"Quarter (Canadian coin); Health care; Respondent; Government (linguistics); Health insurance; Mental health; Medicaid; Health policy","score_opus":0.28556330728028534,"score_gpt":0.44662288177941817,"score_spread":0.16105957449913283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6947568337","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005806511,0.0005064129,0.00040669326,0.007032444,0.0030150712,0.0005162258,0.9883092,0.0001022708,0.00005359273],"genre_scores_gemma":[0.000031915373,0.009202381,0.00012486726,0.0018184674,0.00067413243,0.000026820106,0.98580784,0.000042255735,0.0022713493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898893,0.00092562434,0.0022052552,0.0024795085,0.0033193862,0.0011808964],"domain_scores_gemma":[0.98249,0.0021948845,0.0017831521,0.012590039,0.00038860468,0.00055331766],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02460183,0.00069884455,0.0012538254,0.0013082764,0.00061903376,0.0015666694,0.012743642,0.00034857955,0.00086791505],"category_scores_gemma":[0.0037538556,0.00046383354,0.00011909666,0.001569207,0.0002770158,0.002554038,0.0071188016,0.00064351846,0.00573607],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004985958,0.00009656645,0.00014180348,0.00012262145,0.000082347906,0.000022005583,0.000063327265,6.610515e-7,1.312468e-7,0.000023565926,0.99296737,0.0064297686],"study_design_scores_gemma":[0.00048886787,0.0001169902,0.0019856219,0.0005704853,0.000030091176,0.000005104697,0.0003439016,0.000010773026,0.0000015302111,0.0004268328,0.99540186,0.0006179331],"about_ca_topic_score_codex":0.07384144,"about_ca_topic_score_gemma":0.01595421,"teacher_disagreement_score":0.057887226,"about_ca_system_score_codex":0.00056432205,"about_ca_system_score_gemma":0.00031085275,"threshold_uncertainty_score":0.9997813},"labels":[],"label_agreement":null},{"id":"W6947633835","doi":"10.3897/zookeys.186.2655.map23","title":"Map 23 from: Webster R, Klimaszewski J, Sweeney J, DeMerchant I (2012) New Staphylinidae (Coleoptera) records with new collection data from New Brunswick, and an addition to the fauna of Quebec, Canada: Aleocharinae. ZooKeys 186: 83-118. https://doi.org/10.3897/zookeys.186.2655","year":2012,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fauna; Data collection; Biogeography; Projectile point","score_opus":0.13906613123295825,"score_gpt":0.3168371816246145,"score_spread":0.17777105039165625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6947633835","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006258202,0.0026051141,0.0906582,0.017517261,0.0024555575,0.0065013836,0.0075249653,0.0012324409,0.8652469],"genre_scores_gemma":[0.0026938375,0.00040940044,0.0020538045,0.00088990165,0.002002962,3.723039e-7,0.018920826,0.0017260129,0.97130287],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9934809,0.0010955443,0.0009553838,0.001642081,0.002131573,0.0006945076],"domain_scores_gemma":[0.9942416,0.00024421912,0.00084635976,0.0031992972,0.00047308786,0.0009954501],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019638408,0.00053986674,0.0006721798,0.00063449645,0.0009416398,0.0014829941,0.0043555666,0.00024004649,0.40708292],"category_scores_gemma":[0.00095596246,0.00043087572,0.000072628514,0.0010110242,0.00020825182,0.0012244156,0.0038643703,0.0005898066,0.039950106],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028887278,0.000104854465,0.00015357808,0.000032656288,0.00020317786,0.000006756232,0.00084762514,0.000011450092,0.000017674036,0.00037026228,0.96537846,0.032584634],"study_design_scores_gemma":[0.0008865549,0.0002943793,0.0137333395,0.0002462623,0.00012878349,0.0000011994046,0.0008717276,0.0001475823,0.00004396302,0.0003269819,0.9828143,0.00050493865],"about_ca_topic_score_codex":0.90861535,"about_ca_topic_score_gemma":0.7935857,"teacher_disagreement_score":0.3671328,"about_ca_system_score_codex":0.0002818087,"about_ca_system_score_gemma":0.00046692914,"threshold_uncertainty_score":0.99981433},"labels":[],"label_agreement":null},{"id":"W6947722435","doi":"10.48448/axzg-7v02","title":"One Wug, Two Wug+s Transformer Inflection Models Hallucinate Affixes","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Inflection; Transformer; Hallucinating; Reduplication; Hidden Markov model; Feature (linguistics); Pattern recognition (psychology); Inflection point","score_opus":0.21900728770946534,"score_gpt":0.4263552269300338,"score_spread":0.20734793922056846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6947722435","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009071412,0.00031131165,0.10202665,0.0024674973,0.0017223539,0.00076382834,0.00028959668,0.0003520802,0.891976],"genre_scores_gemma":[0.035223458,0.00047493502,0.010779018,0.0029050354,0.0005443919,0.00011870133,0.0002407252,0.00027020444,0.9494435],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9909059,0.00027910844,0.00094532355,0.0017230369,0.0053522135,0.00079440704],"domain_scores_gemma":[0.9969464,0.00026283468,0.0005714608,0.0017247199,0.00022058153,0.00027399953],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008557977,0.00040516083,0.0006063888,0.0025021934,0.00078708184,0.0009271954,0.0038497867,0.00014433448,0.02166198],"category_scores_gemma":[0.00052258297,0.00035508221,0.00016292594,0.0036972759,0.0011073385,0.0014233566,0.00073077437,0.0005272367,0.0011742742],"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":[0.00003539792,0.00048640656,0.000019633082,0.000049121296,0.00008202419,0.000015403619,0.0009545119,0.0066033457,0.0005110878,0.19428033,0.52556646,0.27139625],"study_design_scores_gemma":[0.0005162641,0.00013659912,0.000021845177,0.000039011364,0.000046623627,0.0000046379364,0.0010301722,0.014836999,0.00012108612,0.09133334,0.89139616,0.00051727187],"about_ca_topic_score_codex":0.0016599378,"about_ca_topic_score_gemma":0.0056143524,"teacher_disagreement_score":0.36582968,"about_ca_system_score_codex":0.00031087076,"about_ca_system_score_gemma":0.00055549375,"threshold_uncertainty_score":0.9998901},"labels":[],"label_agreement":null},{"id":"W6947781523","doi":"10.4224/40001251","title":"Code national de la plomberie : Canada : 2005","year":2008,"lang":"fr","type":"standard","venue":"NPARC","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"National library; Economic shortage","score_opus":0.08290995639327349,"score_gpt":0.38325158651255614,"score_spread":0.30034163011928267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6947781523","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023138608,0.00064125186,0.0055146134,0.02387017,0.0033395805,0.00027590684,0.018922543,0.000033091448,0.94717145],"genre_scores_gemma":[0.008236911,0.004502387,0.010755134,0.011972822,0.0016933184,0.000065164895,0.0012427061,0.00005896002,0.9614726],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918636,0.0009443544,0.00084221084,0.00076944934,0.004850327,0.0007300775],"domain_scores_gemma":[0.9952041,0.0029201491,0.00034902178,0.000666939,0.0004675268,0.00039228052],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053024995,0.000346968,0.00052936125,0.00020133858,0.0005061559,0.00036916713,0.0016538836,0.00030861338,0.026732497],"category_scores_gemma":[0.0040593185,0.0003338403,0.00015440886,0.00043494432,0.0006572043,0.00027945076,0.0005358018,0.00061130454,0.00054029905],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026774873,0.00006391749,0.00004712191,0.00003715649,0.00007486826,0.00022617477,0.00025000764,0.00015136457,0.00000776904,0.06206143,0.90006256,0.03699084],"study_design_scores_gemma":[0.00033993597,0.000022124264,0.00043818651,0.000073125244,0.000028919252,0.00004620998,0.0003656578,0.00040725296,0.000019883595,0.06800575,0.9299068,0.0003461511],"about_ca_topic_score_codex":0.20312372,"about_ca_topic_score_gemma":0.8183912,"teacher_disagreement_score":0.61526746,"about_ca_system_score_codex":0.0017354414,"about_ca_system_score_gemma":0.019235,"threshold_uncertainty_score":0.99991137},"labels":[],"label_agreement":null},{"id":"W6947916432","doi":"10.3897/zookeys.186.2491.map4","title":"Map 4 from: Webster R, Sweeney J, DeMerchant I (2012) New Staphylinidae (Coleoptera) records with new collection data from New Brunswick and eastern Canada: Tachyporinae. ZooKeys 186: 55-82. https://doi.org/10.3897/zookeys.186.2491","year":2012,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data collection; Topographic map (neuroanatomy); Aerial photography; Projectile point","score_opus":0.16529916422116495,"score_gpt":0.31402023718519045,"score_spread":0.1487210729640255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6947916432","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002071626,0.0020410637,0.03803537,0.005756124,0.0020370027,0.0024518648,0.0018524629,0.0010108089,0.9447437],"genre_scores_gemma":[0.0011089405,0.00048666453,0.0024469388,0.0007021622,0.0023113594,1.647222e-7,0.010193309,0.002503079,0.9802474],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99240834,0.00095470453,0.0010681587,0.0021251198,0.0024785988,0.00096506503],"domain_scores_gemma":[0.993679,0.00021566593,0.0009566851,0.0033305641,0.00042971043,0.0013883976],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018544853,0.0007085383,0.0008364094,0.0007322576,0.001088163,0.0024584674,0.004709339,0.00032730596,0.5079026],"category_scores_gemma":[0.0009772512,0.00063732907,0.00008573673,0.0009656446,0.00022714275,0.001300734,0.0057761176,0.0008259348,0.13023393],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028329782,0.00008540835,0.0008115435,0.000048024256,0.00030776055,0.000021885051,0.00046650306,0.0000032918224,0.000006647209,0.00018532015,0.96366614,0.034114167],"study_design_scores_gemma":[0.001555819,0.00023257357,0.010790408,0.00026703693,0.00015474133,0.0000028772822,0.00045376204,0.00015380153,0.000017107805,0.00034264923,0.98530686,0.0007223646],"about_ca_topic_score_codex":0.81977856,"about_ca_topic_score_gemma":0.28363836,"teacher_disagreement_score":0.5361402,"about_ca_system_score_codex":0.00036774852,"about_ca_system_score_gemma":0.0005577234,"threshold_uncertainty_score":0.9996078},"labels":[],"label_agreement":null},{"id":"W6948106637","doi":"10.48550/arxiv.1607.02187","title":"Cosmological constraints on dark matter annihilation and decay: Cross-correlation analysis of the extragalactic $γ$-ray background and cosmic shear","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Dark matter; Annihilation; Cosmology; Weak gravitational lensing; Galaxy; COSMIC cancer database; Dark energy; Observational cosmology","score_opus":0.21804777028805916,"score_gpt":0.3104967252092525,"score_spread":0.09244895492119332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948106637","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":[0.92494446,0.000018029423,0.0662038,0.00030717097,0.00023937134,0.0003014068,0.00020092045,0.000015976937,0.00776885],"genre_scores_gemma":[0.9981435,0.000038976348,0.000049757735,0.00024251679,0.000013569375,5.9224624e-7,0.000030821542,0.0000061484943,0.0014741475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976247,0.00044749316,0.00044198276,0.000976479,0.00032128792,0.00018806281],"domain_scores_gemma":[0.9969955,0.0010997882,0.0006014785,0.0009872784,0.0002222886,0.00009363447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017566141,0.00021545884,0.00044097434,0.0004850109,0.00020099278,0.00024634355,0.0006286466,0.00023389743,0.0004984914],"category_scores_gemma":[0.00024343001,0.00014540702,0.00017554905,0.00088965875,0.0010638864,0.0003511175,0.0010146813,0.00027490666,0.00007166336],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003459779,0.00016408485,0.82012546,0.000053385247,0.0008261923,0.00003755883,0.0003347145,0.0684665,0.000038500686,0.10370705,0.0021778545,0.0037227268],"study_design_scores_gemma":[0.00039992615,0.000033488064,0.89958245,0.000049114347,0.0005654,0.0000014935773,0.00020734157,0.015528358,0.000007760986,0.08319388,0.00023737496,0.00019339613],"about_ca_topic_score_codex":0.000044232394,"about_ca_topic_score_gemma":0.000028000159,"teacher_disagreement_score":0.079457015,"about_ca_system_score_codex":0.00008894306,"about_ca_system_score_gemma":0.000049529295,"threshold_uncertainty_score":0.5929526},"labels":[],"label_agreement":null},{"id":"W6948428539","doi":"10.48550/arxiv.2408.02877","title":"First Indication of Solar $^8$B Neutrinos via Coherent Elastic Neutrino-Nucleus Scattering with XENONnT","year":2024,"lang":"en","type":"preprint","venue":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Neutrino; Solar neutrino; Elastic scattering; Dark matter; Neutrino detector; Time projection chamber; Solar neutrino problem; Standard solar model; Scattering","score_opus":0.11327971253805466,"score_gpt":0.3253196217973527,"score_spread":0.21203990925929803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948428539","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":[0.9331964,0.0004798359,0.04150866,0.0136197135,0.00032420404,0.0020882539,0.0025308526,0.00011333233,0.006138708],"genre_scores_gemma":[0.9903195,0.0015403653,0.0032746072,0.000015002732,0.000043651566,5.278564e-8,0.00017669961,0.000025016401,0.0046051247],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9935514,0.0010060049,0.0005731876,0.0012071282,0.0030267485,0.0006355486],"domain_scores_gemma":[0.99290794,0.0015173063,0.0013776028,0.0022193294,0.0016498212,0.0003280035],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.00394944,0.00042969466,0.0012420646,0.0022290943,0.00093202374,0.00006579873,0.006294014,0.0005516842,0.001007942],"category_scores_gemma":[0.00013292504,0.00045618907,0.00063467637,0.0022052068,0.0035753374,0.00045962335,0.010701859,0.0020201223,0.00008659086],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.029838653,0.016791383,0.031618223,0.028921848,0.014219297,0.0029986978,0.2917908,0.25570655,0.0075495276,0.03124429,0.10779086,0.18152986],"study_design_scores_gemma":[0.011457057,0.004894563,0.10867516,0.009317254,0.0040124683,0.000044040153,0.62825316,0.050693158,0.0008607587,0.008595114,0.17031239,0.0028848464],"about_ca_topic_score_codex":0.0157342,"about_ca_topic_score_gemma":0.017814633,"teacher_disagreement_score":0.33646238,"about_ca_system_score_codex":0.00035697393,"about_ca_system_score_gemma":0.00074431463,"threshold_uncertainty_score":0.9999053},"labels":[],"label_agreement":null},{"id":"W6948502869","doi":"10.5281/zenodo.10492961","title":"The Relationship Between Electron Precipitation and the Population of Trapped Electrons in LEO: New Evidence Supporting a Natural Limit to the Flux of Energetic Electrons","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Alberta","funders":"","keywords":"Electron; Adiabatic invariant; Flux (metallurgy); Electron precipitation; Population; Adiabatic process; Energy flux; Momentum (technical analysis); Magnetosphere","score_opus":0.14089040277308085,"score_gpt":0.38362487861749023,"score_spread":0.24273447584440938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948502869","genre_codex":"other","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":[0.11396642,0.038506497,0.044126783,0.2636482,0.0019772388,0.025899637,0.0015172219,0.0022303904,0.50812757],"genre_scores_gemma":[0.9093812,0.00020767996,0.00007719506,0.00005972965,0.00012995629,4.395807e-7,0.00035828416,0.00065783225,0.089127675],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958738,0.0016287097,0.00075131096,0.00044465443,0.00097001815,0.00033149152],"domain_scores_gemma":[0.99696183,0.0015251326,0.0005307607,0.0007244382,0.00019298383,0.000064861095],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075282548,0.00015389638,0.00026023106,0.00048133844,0.0006233275,0.0006722015,0.0016029638,0.00007409252,0.00056203274],"category_scores_gemma":[0.013599615,0.00008913663,0.00007283103,0.0015892416,0.00020178003,0.00018599708,0.00072310114,0.00044718827,0.0005180823],"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":[0.00016844741,0.00002229865,0.00014062012,0.000077734374,0.00007488123,5.3564804e-7,0.0028294877,0.000048707017,0.00015536704,0.090276234,0.84089357,0.0653121],"study_design_scores_gemma":[0.0003760276,0.00023365312,0.014830047,0.0002640654,0.00008953765,0.000004779465,0.0006556591,0.00021282407,0.000109083296,0.019047104,0.96401495,0.00016229361],"about_ca_topic_score_codex":0.0003542745,"about_ca_topic_score_gemma":0.0002387054,"teacher_disagreement_score":0.7954148,"about_ca_system_score_codex":0.0000891008,"about_ca_system_score_gemma":0.000019269417,"threshold_uncertainty_score":0.99470925},"labels":[],"label_agreement":null},{"id":"W6948828368","doi":"10.5281/zenodo.10167355","title":"Oxypoda pseudolacustris Klimaszewski","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Natural Resources Canada; Agriculture and Agri-Food Canada; Canadian Forest Service","funders":"","keywords":"Sphagnum; Litter; Plant litter; Alder; Beech; Epiphyte; Habitat","score_opus":0.25279138494398545,"score_gpt":0.37728972088856466,"score_spread":0.12449833594457921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948828368","genre_codex":"other","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":[0.043867867,0.00005834443,0.021543603,0.016240349,0.00080725574,0.0010754139,0.0013996047,0.0047201556,0.9102874],"genre_scores_gemma":[0.93783206,0.00022505557,0.00057667325,0.0013230627,0.00043785523,1.1152914e-7,0.0044177687,0.0017400234,0.053447377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640584,0.0006746226,0.00046002647,0.00062272284,0.0013873918,0.00044940147],"domain_scores_gemma":[0.9978692,0.00016963668,0.00014261503,0.0010479694,0.00056286517,0.00020769096],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0059074187,0.00012704638,0.0001741655,0.00061966345,0.0021640547,0.0023081433,0.0027165245,0.000054027252,0.03012687],"category_scores_gemma":[0.005786273,0.00011417828,0.00007886531,0.0027392977,0.00016522587,0.0005581916,0.00343261,0.0002050818,0.20039116],"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":[0.000017638575,0.000041242936,0.0000033794859,0.000008178072,0.000013909601,0.00001547921,0.0004915037,0.000047379825,0.00031068063,0.014611769,0.77865404,0.20578481],"study_design_scores_gemma":[0.00028034527,0.00008540405,0.0013629749,0.0000076120223,0.0000064356827,0.00001652722,0.0015885578,0.0006129828,0.00010047621,0.005370008,0.99043036,0.00013834012],"about_ca_topic_score_codex":0.000016954104,"about_ca_topic_score_gemma":5.5451864e-7,"teacher_disagreement_score":0.89396423,"about_ca_system_score_codex":0.00007335305,"about_ca_system_score_gemma":0.0000031210727,"threshold_uncertainty_score":0.999135},"labels":[],"label_agreement":null},{"id":"W6948865110","doi":"10.5281/zenodo.12086753","title":"Candide bernstein pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Musical; Lyrics; Comics; George (robot); Subject (documents); Novella; Symphony; Elegance; Highbrow; Style (visual arts)","score_opus":0.12548051046160175,"score_gpt":0.3517303639041754,"score_spread":0.22624985344257365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948865110","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005485609,0.00035837834,0.0029744566,0.0013370351,0.0005219549,0.00042202984,0.0012513143,0.0010106252,0.9921187],"genre_scores_gemma":[0.00046168125,0.00014140607,0.00016766724,0.00033946015,0.00039963896,3.5117456e-8,0.0018464675,0.005313013,0.9913306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996167,0.0005809467,0.00046431433,0.00091474556,0.001491556,0.00038140384],"domain_scores_gemma":[0.99794537,0.00004892364,0.00022707098,0.0013241154,0.0002451122,0.00020943403],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029428874,0.0002250144,0.00029155784,0.00093025534,0.000624784,0.003319253,0.0030574873,0.00014040073,0.4676388],"category_scores_gemma":[0.0019695857,0.00019798953,0.000109316185,0.0010108809,0.00020247864,0.00016958451,0.0036441134,0.0003558134,0.70194876],"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":[0.00000811508,0.000037160637,8.6430624e-8,0.00006672769,0.000057460948,0.000035330962,0.00024032779,0.0000015653001,0.000014005039,0.012313936,0.90259415,0.08463116],"study_design_scores_gemma":[0.00016233638,0.00006571797,0.000006198317,0.000102468126,0.000026102745,0.000022582573,0.00037532416,0.00003082093,0.0000082131455,0.003366116,0.9956111,0.00022307422],"about_ca_topic_score_codex":0.00015376936,"about_ca_topic_score_gemma":0.000012709503,"teacher_disagreement_score":0.23430994,"about_ca_system_score_codex":0.000111629255,"about_ca_system_score_gemma":0.0000047372096,"threshold_uncertainty_score":0.9977154},"labels":[],"label_agreement":null},{"id":"W6948976783","doi":"10.5281/zenodo.11863378","title":"liebeslied rachmaninoff pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Piano; MIDI; Musical; Cadenza; Sheet music; Singing","score_opus":0.13724015622244878,"score_gpt":0.3544642453132534,"score_spread":0.2172240890908046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948976783","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000003169787,0.0004001225,0.0024705157,0.0014218278,0.00062615203,0.00046821116,0.0008263589,0.0013737566,0.9924099],"genre_scores_gemma":[0.00050303293,0.00013531125,0.00021114471,0.00048295627,0.0005129707,4.287861e-8,0.0021979243,0.0061240047,0.98983264],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99574244,0.00063755334,0.00052237173,0.0010589199,0.0016198619,0.0004188821],"domain_scores_gemma":[0.9976272,0.00005849601,0.0002670306,0.0015466766,0.0002817012,0.00021891129],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003189241,0.00026065164,0.00033289977,0.0010804605,0.0007222232,0.00412003,0.0036720524,0.00017189306,0.5929168],"category_scores_gemma":[0.0016616925,0.00023167054,0.00012937124,0.0011503478,0.00022391537,0.00020027829,0.004414594,0.00042802913,0.7888198],"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":[0.000011084033,0.000059102305,5.4128034e-8,0.00007474486,0.00006665633,0.00003179475,0.00021044763,0.0000017794824,0.000019598536,0.0293117,0.9024771,0.06773595],"study_design_scores_gemma":[0.00019124355,0.00007787672,0.00000946165,0.00008514357,0.000031062045,0.000022197582,0.00032344164,0.00003522051,0.0000069256184,0.004690257,0.99426866,0.00025853072],"about_ca_topic_score_codex":0.000035541107,"about_ca_topic_score_gemma":0.0000021657054,"teacher_disagreement_score":0.195903,"about_ca_system_score_codex":0.000097151395,"about_ca_system_score_gemma":0.00000402291,"threshold_uncertainty_score":0.9969138},"labels":[],"label_agreement":null},{"id":"W6948989222","doi":"10.5281/zenodo.12636746","title":"Dataset for the Synaptotagmin-1 antibody screening study","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Immunofluorescence; Antibody; Immunoprecipitation; Western blot; Raw data","score_opus":0.21869895440489648,"score_gpt":0.4276522099314848,"score_spread":0.2089532555265883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6948989222","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001019013,0.00015667097,0.008588496,0.0017870719,0.00060056144,0.0020741492,0.9856942,0.0002035426,0.00088507915],"genre_scores_gemma":[0.00018756205,0.00013389406,0.00009099631,0.00048078856,0.00038871847,4.1865752e-7,0.9968136,0.0007307428,0.0011732928],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9940584,0.0011201235,0.00086119125,0.0013384612,0.0020804068,0.0005414243],"domain_scores_gemma":[0.9948323,0.0008097127,0.00035911982,0.003162681,0.00065343594,0.00018277827],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012026162,0.00033319317,0.000405911,0.0006452252,0.003918136,0.007880839,0.008259973,0.0001175136,0.018379774],"category_scores_gemma":[0.007817249,0.00023405196,0.00014612092,0.0013013749,0.0002803361,0.00045608528,0.009887727,0.0006559999,0.085315324],"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":[0.000068099675,0.00023134063,1.2871423e-7,0.000084857515,0.0002282712,0.000034676556,0.00020397497,0.000025275236,0.0000056938266,0.00025253312,0.9556263,0.04323884],"study_design_scores_gemma":[0.0003781393,0.00038423474,0.00003142008,0.000042328218,0.00019905859,0.000026151885,0.002791408,0.00026438368,0.0000015308544,0.00032458015,0.9952783,0.00027847668],"about_ca_topic_score_codex":0.00011051154,"about_ca_topic_score_gemma":0.000011275832,"teacher_disagreement_score":0.06693555,"about_ca_system_score_codex":0.00007721641,"about_ca_system_score_gemma":0.000008301297,"threshold_uncertainty_score":0.9981201},"labels":[],"label_agreement":null},{"id":"W6949522698","doi":"10.5281/zenodo.12752219","title":"Report on the observed climate, projected climate, and projected biodiversity changes for Riding Mountain National Park of Canada under differing levels of warming","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"National park; Biodiversity; Climate change; Precipitation; Global warming; Ecosystem; Air temperature","score_opus":0.28875004947777655,"score_gpt":0.34342703711877737,"score_spread":0.05467698764100082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949522698","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":[0.96098906,0.00007490148,0.0037559324,0.0082793115,0.00033144007,0.0022448646,0.008755516,0.0003760808,0.015192871],"genre_scores_gemma":[0.9989032,0.000027786222,0.0001532134,0.00012265408,0.000027999266,1.6972393e-7,0.00044250276,0.00010128941,0.00022116854],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99777913,0.00029631882,0.00036892094,0.00038678764,0.0009241381,0.00024470635],"domain_scores_gemma":[0.9982548,0.00044136518,0.00019954436,0.00029395023,0.00075949036,0.000050850784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044619488,0.000096888085,0.00015659303,0.00024198931,0.0010674893,0.00046296272,0.000626754,0.000029503273,0.0005602705],"category_scores_gemma":[0.003530122,0.0000718757,0.00003167795,0.0007472876,0.000115216666,0.00020012702,0.0010744034,0.00009969966,0.000027099073],"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":[0.00087248144,0.0004938162,0.00050079264,0.0028035105,0.0006675525,0.00011425677,0.009490537,0.00061536056,0.04077768,0.22349174,0.6492041,0.07096819],"study_design_scores_gemma":[0.0008776933,0.0004825603,0.03428909,0.00038889563,0.000065490596,0.000078670906,0.012124755,0.0089759,0.010319629,0.0025257373,0.9294185,0.00045307854],"about_ca_topic_score_codex":0.0012419315,"about_ca_topic_score_gemma":0.00052193407,"teacher_disagreement_score":0.28021443,"about_ca_system_score_codex":0.00014678262,"about_ca_system_score_gemma":0.000029707418,"threshold_uncertainty_score":0.8210373},"labels":[],"label_agreement":null},{"id":"W6949727091","doi":"10.5281/zenodo.3596717","title":"DDI 4 Core: Describing and managing data for traditional and modern data platforms","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Statistics Canada","funders":"","keywords":"Interoperability; XML; Scope (computer science); Data management; Data model (GIS); Data system; Metadata; Core (optical fiber)","score_opus":0.6154124851776948,"score_gpt":0.3743942424592931,"score_spread":0.24101824271840167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949727091","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":[0.18220362,0.00078720343,0.6341493,0.009872888,0.00084475166,0.004485432,0.043058738,0.0012196788,0.12337838],"genre_scores_gemma":[0.9456076,0.00027968292,0.006127536,0.0009451685,0.00021796467,9.2249245e-8,0.04340613,0.0007536772,0.0026621514],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977746,0.0000839072,0.0003160523,0.0008816713,0.000683086,0.00026068042],"domain_scores_gemma":[0.9975126,0.00022042094,0.000117235824,0.0018235035,0.0001911707,0.00013506561],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004522624,0.000106766325,0.00015363735,0.00019735144,0.0011939629,0.001944866,0.0031586767,0.000033396915,0.0021900667],"category_scores_gemma":[0.0018563682,0.00009451608,0.000014222704,0.00027765575,0.00014518722,0.001951154,0.0063022585,0.00012173319,0.0011313413],"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":[0.00008974049,0.000066368215,0.000019906955,0.000067035886,0.00004311755,0.00000383126,0.0006131373,0.000029987563,0.0003870423,0.06588905,0.41164908,0.5211417],"study_design_scores_gemma":[0.00059467007,0.00010048236,0.00050999824,0.000025099169,0.000014698161,0.000036622787,0.0009778967,0.0795122,0.000007851774,0.027995983,0.89007926,0.00014521736],"about_ca_topic_score_codex":0.000010107236,"about_ca_topic_score_gemma":0.0000013995651,"teacher_disagreement_score":0.76340395,"about_ca_system_score_codex":0.0000267512,"about_ca_system_score_gemma":0.0000035580188,"threshold_uncertainty_score":0.99964637},"labels":[],"label_agreement":null},{"id":"W6958119743","doi":"10.6084/m9.figshare.15063754.v1","title":"Additional file 1 of Assessing record linkage between health care and Vital Statistics databases using deterministic methods","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Institute of Health Economics; University of Calgary","funders":"","keywords":"Record linkage; Linkage (software); Health care; Data collection; MEDLINE; Data source; Health data","score_opus":0.5172368392236222,"score_gpt":0.5531341020742365,"score_spread":0.03589726285061434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958119743","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014316676,0.0001048501,0.009922705,0.000021006741,0.000038660844,0.0000735679,0.98911464,0.00001125512,0.0006989809],"genre_scores_gemma":[0.00011260396,9.126549e-7,0.36818564,0.00014003759,0.000057633355,0.00001791162,0.6313314,0.0000053454464,0.00014852133],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787056,0.00051675044,0.00052240473,0.00038521088,0.0005311941,0.00017385582],"domain_scores_gemma":[0.9821886,0.016541736,0.00040618112,0.00041438823,0.0003368833,0.00011222268],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003383542,0.0001030888,0.00029575505,0.00009252608,0.00018583145,0.00026531264,0.00023420312,0.000031344036,0.95118815],"category_scores_gemma":[0.041400366,0.000097842254,0.000041251456,0.0002910482,0.000023375342,0.00039481866,0.00059062475,0.00010137899,0.0002265486],"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":[6.0300124e-7,0.000007765212,0.0000069337616,0.00013205978,0.000006895926,0.000014992249,0.00006388848,9.821001e-7,0.0000012760113,0.000012437355,0.7534129,0.24633926],"study_design_scores_gemma":[0.00006182364,0.000031675085,0.0029880218,0.0013020773,0.000009460052,0.0000053160666,0.0014763986,0.0004959442,0.0000336877,0.000346655,0.9931342,0.00011474291],"about_ca_topic_score_codex":0.000013418687,"about_ca_topic_score_gemma":0.00005396626,"teacher_disagreement_score":0.9509616,"about_ca_system_score_codex":0.000035032852,"about_ca_system_score_gemma":0.00038279945,"threshold_uncertainty_score":0.9666743},"labels":[],"label_agreement":null},{"id":"W6958213133","doi":"10.6084/m9.figshare.15063757","title":"Additional file 2 of Assessing record linkage between health care and Vital Statistics databases using deterministic methods","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Institute of Health Economics; University of Calgary","funders":"","keywords":"Record linkage; Linkage (software); Health care; Data collection; MEDLINE; Data source; Health data","score_opus":0.5070898105060758,"score_gpt":0.552299466771692,"score_spread":0.04520965626561613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958213133","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014216563,0.000106622596,0.009701904,0.000020894615,0.000038901613,0.00007343734,0.989317,0.000011253348,0.00071578653],"genre_scores_gemma":[0.00011108012,9.413559e-7,0.36571908,0.00014054737,0.000058740894,0.000017613562,0.63379705,0.0000053567073,0.00014957051],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787104,0.00051656924,0.0005226538,0.00038490948,0.00053105736,0.00017378942],"domain_scores_gemma":[0.9824333,0.016298177,0.00040673357,0.0004135062,0.0003360587,0.00011219299],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033641278,0.000103054335,0.00029583118,0.00009246239,0.00018584577,0.000265918,0.00023406609,0.00003134423,0.95025104],"category_scores_gemma":[0.04089658,0.00009780863,0.000041243067,0.00029081036,0.000023375003,0.00039510304,0.00059053744,0.000101354446,0.0002240084],"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":[5.965148e-7,0.000007723255,0.00000666883,0.00013264353,0.0000068610875,0.000015345899,0.00006362148,9.820675e-7,0.0000012233716,0.000012603464,0.74976563,0.2499861],"study_design_scores_gemma":[0.0000621226,0.00003160624,0.0029306712,0.0012821875,0.000009401891,0.000005315949,0.0014571428,0.00049130304,0.000033388773,0.0003487351,0.9932339,0.000114220675],"about_ca_topic_score_codex":0.000013560908,"about_ca_topic_score_gemma":0.000054302138,"teacher_disagreement_score":0.95002705,"about_ca_system_score_codex":0.000035043402,"about_ca_system_score_gemma":0.00038100907,"threshold_uncertainty_score":0.96718234},"labels":[],"label_agreement":null},{"id":"W6958319911","doi":"10.6084/m9.figshare.26558063","title":"Additional file 7 of Molecular machineries of ciliogenesis, cell survival, and vasculogenesis are differentially expressed during regeneration in explants of the demosponge Halichondria panicea","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Alberta","funders":"","keywords":"Regeneration (biology); Explant culture; Vasculogenesis; Cell; Cell culture; Stem cell","score_opus":0.06700869981059077,"score_gpt":0.28772446760745163,"score_spread":0.22071576779686086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958319911","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0889111,0.0003788736,0.000009277492,0.00003261782,0.000049087354,0.00014204843,0.9102788,0.0000074982386,0.00019068038],"genre_scores_gemma":[0.6720979,0.000026392952,0.00020676792,0.00001850187,0.000029576395,0.00023616481,0.32632837,0.000014170951,0.0010421213],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981535,0.00026092035,0.0004886015,0.00030101632,0.0006940059,0.00010197049],"domain_scores_gemma":[0.9979395,0.0012153711,0.0002636068,0.00043169034,0.0001222623,0.000027557804],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018923686,0.00010691299,0.00023832147,0.00014696298,0.000040563475,0.000058699803,0.0004262012,0.00005439688,0.6722394],"category_scores_gemma":[0.0022806064,0.00007570818,0.000106749074,0.0004313803,0.000022516839,0.00017985592,0.0003599834,0.00004573716,0.000045665427],"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":[0.00002141681,0.000055195815,0.000070979084,0.0005527106,0.000028485207,0.0000069333682,0.00015949424,0.0001082403,0.03279718,0.00003473073,0.96533334,0.0008313113],"study_design_scores_gemma":[0.0005833199,0.000049209044,0.26701012,0.005671871,0.000051630712,0.0000033526335,0.0011830567,0.001276314,0.5554503,0.00092332636,0.16740222,0.00039526957],"about_ca_topic_score_codex":0.000017653052,"about_ca_topic_score_gemma":0.00026283925,"teacher_disagreement_score":0.7979311,"about_ca_system_score_codex":0.000008585985,"about_ca_system_score_gemma":0.00004155903,"threshold_uncertainty_score":0.3280602},"labels":[],"label_agreement":null},{"id":"W6958411204","doi":"10.6084/m9.figshare.12875673.v3","title":"Additional file of Sequencing and characterization of the guppy (Poecilia reticulata) transcriptome","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Transcriptome; DNA sequencing; Guppy; Selection (genetic algorithm); De novo transcriptome assembly","score_opus":0.2049489606917039,"score_gpt":0.316554761196525,"score_spread":0.11160580050482108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958411204","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00059010606,0.000003205577,0.0000075705116,0.000591859,0.0000134807515,0.000103573984,0.9974846,0.0000063102566,0.0011992736],"genre_scores_gemma":[0.043037757,4.5216765e-7,0.00013681104,0.0009103611,0.000037389247,0.000055286422,0.9551399,0.0000036313124,0.0006784538],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989227,0.00006655013,0.00027227812,0.00016221062,0.00051706884,0.00005919494],"domain_scores_gemma":[0.99880475,0.0006250914,0.0002015868,0.00020639958,0.00012619181,0.000035989644],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000084901614,0.00004844658,0.00010939946,0.000025944819,0.000038721686,0.000033983073,0.00033586647,0.000025603964,0.9835798],"category_scores_gemma":[0.0066277664,0.00003275215,0.000048253627,0.0002965409,0.0000188216,0.00021570153,0.00013715176,0.000043494212,0.0003924014],"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":[0.0000033123972,0.000003927915,0.0000018732768,0.00004258818,0.0000037055815,4.200422e-7,0.00025748083,0.0000013574719,0.0016012831,0.000038818023,0.9966052,0.0014400092],"study_design_scores_gemma":[0.00005415723,0.000017458804,0.012604943,0.00037410104,0.000002671258,5.6687986e-7,0.0001543597,0.00069352455,0.0008969018,0.00016886312,0.98498964,0.000042782507],"about_ca_topic_score_codex":8.7492174e-7,"about_ca_topic_score_gemma":0.0000017823958,"teacher_disagreement_score":0.98318744,"about_ca_system_score_codex":0.000005993834,"about_ca_system_score_gemma":0.000033846925,"threshold_uncertainty_score":0.7934534},"labels":[],"label_agreement":null},{"id":"W6958856114","doi":"10.6084/m9.figshare.c.5328121.v1","title":"simATAC: a single-cell ATAC-seq simulation framework","year":2021,"lang":"en","type":"other","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Chromatin; R package; In silico; ChIA-PET; Statistical model","score_opus":0.3902381974541558,"score_gpt":0.4439022374497102,"score_spread":0.05366403999555441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958856114","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.7164018e-7,0.0011069751,0.00096142595,0.000113026574,0.00030881417,0.00030102662,0.33115765,0.00013487124,0.665916],"genre_scores_gemma":[0.00014731348,0.000005519541,0.0013932915,0.0010230837,0.00050935283,0.0000477318,0.24761724,0.00015321677,0.74910325],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99655044,0.00021647145,0.0005094639,0.00088292884,0.0015424575,0.00029822713],"domain_scores_gemma":[0.9954845,0.0018136718,0.00057804823,0.0018398302,0.00015892861,0.00012505922],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003418744,0.0002917115,0.00043391366,0.0003201795,0.000072934236,0.0007893398,0.0013418833,0.00044790248,0.9349816],"category_scores_gemma":[0.012503284,0.00025507258,0.00018722855,0.0006879599,0.000010690722,0.00016097778,0.0009455477,0.0002946109,0.05998411],"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":[0.000002175218,0.000072206705,0.0000017330042,0.00018685537,0.000017028964,0.000035370762,0.000049052956,0.00024217242,5.982388e-7,0.000091277885,0.9900485,0.009252988],"study_design_scores_gemma":[0.000100501966,0.000017510778,0.000018091585,0.0025672505,0.0000113592905,4.3563367e-7,0.00009299041,0.0006147692,0.00001078879,0.0015044108,0.9947541,0.00030784062],"about_ca_topic_score_codex":0.000010260446,"about_ca_topic_score_gemma":0.00006588385,"teacher_disagreement_score":0.8749975,"about_ca_system_score_codex":0.000043052398,"about_ca_system_score_gemma":0.000055096963,"threshold_uncertainty_score":0.99999017},"labels":[],"label_agreement":null},{"id":"W6961817835","doi":"10.15468/dl.mr5nx7","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Matching (statistics); Download; Range (aeronautics); Set (abstract data type); Data set","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6961817835","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6961866467","doi":"10.15468/dl.6qnkf9","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type)","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6961866467","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6961979184","doi":"10.15468/dl.euav2u","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type)","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6961979184","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6962016178","doi":"10.15468/dl.ew6sm2","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Set (abstract data type)","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6962016178","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6962023329","doi":"10.15468/dl.ccy9ce","title":"Occurrence Download","year":2025,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Matching (statistics); Range (aeronautics); Set (abstract data type); Identification (biology); Download","score_opus":0.06370320266780717,"score_gpt":0.32470061285242874,"score_spread":0.2609974101846216,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6962023329","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022811962,0.00001608867,0.000100695506,0.00083424326,0.0014151377,0.0003898544,0.9958346,0.000069888316,0.0013166685],"genre_scores_gemma":[0.0000024544113,0.000057488603,0.000002811741,0.0024903733,0.0000013523908,0.000004041896,0.9974379,3.4780507e-9,0.0000035890034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957655,0.00027540157,0.0010344158,0.00048171703,0.0021026905,0.00034029337],"domain_scores_gemma":[0.99657655,0.00020160493,0.0006296705,0.0017709393,0.0006451199,0.00017610846],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002791755,0.0003116584,0.00045775672,0.00031514713,0.00041436136,0.0009313707,0.0027265467,0.00033525942,0.00442163],"category_scores_gemma":[0.0032456128,0.0002750442,0.00025222838,0.0011896114,0.00024073428,0.0021652055,0.002074546,0.00030204808,0.22375852],"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":[0.000041743606,0.00004343983,0.00020591395,0.00008780855,0.000031251464,0.0000018732214,0.00002893708,0.000009883648,2.064827e-9,0.0000025287009,0.98749423,0.012052391],"study_design_scores_gemma":[0.00026748463,0.000021287977,0.000058367117,0.000003120637,0.000048936367,7.8781295e-7,0.0004237697,2.2212994e-7,4.971146e-7,0.000032366424,0.9988845,0.00025866175],"about_ca_topic_score_codex":0.0007070946,"about_ca_topic_score_gemma":0.000061427025,"teacher_disagreement_score":0.2193369,"about_ca_system_score_codex":0.0002826376,"about_ca_system_score_gemma":0.00026008117,"threshold_uncertainty_score":0.9999702},"labels":[],"label_agreement":null},{"id":"W6968550496","doi":"10.5281/zenodo.4015732","title":"GLUT1 Inhibitor, A New Therapy For Triple-negative Breast Cancer","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Breast cancer; Cancer; Clinical trial; Cancer therapy; MEDLINE; Cancer treatment","score_opus":0.2110105876347001,"score_gpt":0.37012737040253113,"score_spread":0.15911678276783103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968550496","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":[0.034351677,0.00092671777,0.3258705,0.37719056,0.0022492255,0.011364743,0.020303935,0.0045669223,0.22317569],"genre_scores_gemma":[0.9338464,0.0011012454,0.0040931287,0.023548264,0.0038034879,0.0000012848018,0.0027931125,0.0035778626,0.02723522],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99726975,0.0004092174,0.00042664667,0.00065056456,0.00090757513,0.0003362605],"domain_scores_gemma":[0.99809897,0.00014448106,0.00019042523,0.00048418663,0.00073341624,0.0003484942],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016313189,0.00014767965,0.00021412648,0.00016554682,0.0012953632,0.0016111869,0.0018604911,0.000047418365,0.025139894],"category_scores_gemma":[0.0029096082,0.00012556512,0.00009670647,0.0010971793,0.00012536984,0.0005854761,0.0011369433,0.00016080624,0.0068890844],"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":[0.00029481982,0.000050459046,0.0000016623623,0.000009128739,0.000029466708,0.0000016865557,0.0016648117,0.000024043391,0.0005478641,0.00429277,0.65216506,0.3409182],"study_design_scores_gemma":[0.0014978317,0.00026288364,0.00053463614,0.000011279208,0.00000787259,0.0000062360577,0.0010626995,0.0005425684,0.0005708896,0.0027582787,0.99258643,0.0001584176],"about_ca_topic_score_codex":0.00008038795,"about_ca_topic_score_gemma":0.0000020673479,"teacher_disagreement_score":0.8994947,"about_ca_system_score_codex":0.0000790406,"about_ca_system_score_gemma":0.000014170703,"threshold_uncertainty_score":0.99942523},"labels":[],"label_agreement":null},{"id":"W6968753945","doi":"10.5281/zenodo.3665755","title":"MINTED: Making Identifiers Necessary for Tracking Evolving Data","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Victoria","funders":"","keywords":"Software; Tracking (education); Identification (biology); Identifier; Software development; Tracking system","score_opus":0.43594237454996726,"score_gpt":0.4156393998529078,"score_spread":0.02030297469705944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968753945","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":[0.0031986334,0.00027202026,0.85229087,0.021550706,0.00061541394,0.0015309717,0.0033215394,0.001340609,0.11587923],"genre_scores_gemma":[0.98487663,0.000035890294,0.003861914,0.002936009,0.0004708853,8.035787e-8,0.0053312406,0.001019431,0.0014679059],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966781,0.00045098743,0.0005457171,0.0009186777,0.0010329129,0.00037356484],"domain_scores_gemma":[0.9973863,0.00023574103,0.0002359979,0.0012640595,0.00068698666,0.0001909471],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0048041525,0.00013262824,0.00019740207,0.00022363539,0.0020210056,0.004249255,0.0054095243,0.000045470955,0.011088729],"category_scores_gemma":[0.016908674,0.00012952148,0.00006429085,0.00095616526,0.00012638325,0.0017059401,0.0057866573,0.00019461387,0.006379705],"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":[0.000047765192,0.000034302433,0.0000033831063,0.00004711457,0.00002875574,0.000008035009,0.0012676689,0.000050317314,0.00061966374,0.0032997495,0.76374763,0.23084562],"study_design_scores_gemma":[0.0003227878,0.00008084242,0.0001938814,0.000027600036,0.00001879904,0.000008950217,0.003960472,0.01424943,0.00009357081,0.0013145246,0.97957313,0.00015601689],"about_ca_topic_score_codex":0.000008141773,"about_ca_topic_score_gemma":0.0000010399085,"teacher_disagreement_score":0.981678,"about_ca_system_score_codex":0.000054838565,"about_ca_system_score_gemma":0.0000047574486,"threshold_uncertainty_score":0.9999717},"labels":[],"label_agreement":null},{"id":"W6976977831","doi":"10.6084/m9.figshare.22729174","title":"Additional file 2 of Identifying dementia using medical data linkage in a longitudinal cohort study: Lothian Birth Cohort 1936","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Cohort; Record linkage; Linkage (software); Longitudinal data; Cohort study; Dementia; Data file; Cohort effect","score_opus":0.4652379535492501,"score_gpt":0.46450192286259634,"score_spread":0.000736030686653788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976977831","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011261157,0.000016133663,0.000017183173,0.000061320265,0.00008734049,0.00051988615,0.9966273,0.0000535666,0.0014912095],"genre_scores_gemma":[0.0163873,0.000001952722,0.0003237406,0.00011268648,0.00013053176,0.00031810187,0.98172325,0.000013808348,0.0009886484],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941301,0.00029714423,0.0009238641,0.00089661893,0.003415121,0.00033714983],"domain_scores_gemma":[0.9940161,0.003817498,0.00035474938,0.0014794474,0.00018217128,0.00015000375],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029309457,0.00015259556,0.0003663489,0.00050888065,0.00014723734,0.00025099708,0.00242247,0.000086155305,0.99391276],"category_scores_gemma":[0.040194657,0.00013900969,0.00006694395,0.0018157786,0.000032881602,0.0007853416,0.00356395,0.00022407866,0.01193663],"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":[0.0000044292806,0.00013083252,0.019191837,0.00004514386,0.00008705061,0.00018948475,0.000054028722,0.000017118347,2.0593508e-7,0.0000065655054,0.9782447,0.0020285675],"study_design_scores_gemma":[0.00016487091,0.000016964765,0.48637667,0.00084688206,0.000015295349,0.00000306719,0.00039743158,0.0060578766,7.1881317e-7,0.00014972998,0.50585055,0.00011993782],"about_ca_topic_score_codex":0.000114834926,"about_ca_topic_score_gemma":0.0015159467,"teacher_disagreement_score":0.98197615,"about_ca_system_score_codex":0.00003645726,"about_ca_system_score_gemma":0.00021634648,"threshold_uncertainty_score":0.9888327},"labels":[],"label_agreement":null},{"id":"W6977134819","doi":"10.6084/m9.figshare.16909645.v1","title":"Additional file 7 of Assessing the suitability of general practice electronic health records for clinical prediction model development: a data quality assessment","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Calgary","funders":"","keywords":"Data quality; Record linkage; Quality (philosophy); Health records; General practice; Health data; Quality assessment; Data collection","score_opus":0.6550559088450293,"score_gpt":0.5950021434766101,"score_spread":0.06005376536841922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977134819","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003444429,0.000051585575,0.0053102663,0.0012201059,0.00005763588,0.0003628038,0.9912798,0.000013156488,0.0016702496],"genre_scores_gemma":[0.00079411454,0.0000073683427,0.06506292,0.00073808176,0.0000848708,0.0003715935,0.93200254,0.000006098703,0.0009324118],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947128,0.0014456843,0.0016760492,0.0006512269,0.0012528516,0.00026135944],"domain_scores_gemma":[0.9608333,0.033792317,0.0018412458,0.0019516731,0.0014885124,0.00009295499],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009264524,0.00010258154,0.00034529646,0.000040770527,0.00022408378,0.00014412764,0.001042252,0.00006517828,0.72640026],"category_scores_gemma":[0.12585923,0.000076819575,0.00011321154,0.0003598054,0.000029240473,0.0010566905,0.000979195,0.00021868834,0.000057702076],"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":[0.000013739838,0.00028163512,0.000015235841,0.000086311076,0.000042439966,1.7756068e-7,0.000046683024,0.000073195195,4.6371952e-7,0.00031462952,0.9538747,0.04525079],"study_design_scores_gemma":[0.00016979927,0.000048545742,0.01680132,0.00023388014,0.000008727698,0.0000012711237,0.0005735886,0.035771612,0.0000069010193,0.0018869218,0.94442576,0.00007164802],"about_ca_topic_score_codex":0.000013100975,"about_ca_topic_score_gemma":0.00019700958,"teacher_disagreement_score":0.72634256,"about_ca_system_score_codex":0.00012142786,"about_ca_system_score_gemma":0.0044712215,"threshold_uncertainty_score":0.88150406},"labels":[],"label_agreement":null},{"id":"W6979330234","doi":"","title":"A Unified Model for Cardinality Estimation by Learning from Data and Queries via Sum-Product Networks","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Data Quality and Management","field":"Decision Sciences","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":"Simon Fraser University","funders":"","keywords":"Cardinality (data modeling); Key (lock); Inference; Component (thermodynamics); Node (physics); Data modeling; Computation; Distributed database; Limiting","score_opus":0.2847290431817994,"score_gpt":0.41813153751461796,"score_spread":0.13340249433281853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979330234","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":[0.23426147,0.00037134916,0.76255184,0.0019127077,0.00018487622,0.00022396936,0.0001752964,0.000042430194,0.00027604037],"genre_scores_gemma":[0.990838,0.000054115655,0.0042356206,0.0004701234,0.00004520352,0.000019930327,0.0010298239,0.0000059004237,0.0033013043],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981397,0.00019531384,0.0004169371,0.00074838597,0.000310356,0.00018934175],"domain_scores_gemma":[0.99772525,0.00076066237,0.00014774784,0.0012122762,0.00010495425,0.000049119484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003352003,0.000119079836,0.00024779508,0.000063076375,0.00029745002,0.0002576084,0.0007646635,0.00004973038,0.000016784643],"category_scores_gemma":[0.0024655166,0.000102084465,0.000033609624,0.0002511215,0.00010541572,0.0007812466,0.00084326795,0.00012485641,0.000017893639],"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":[0.00031727852,0.00013005083,0.25055552,0.00007643918,0.00025009268,0.0000022900567,0.001200942,0.11641127,0.00050899055,0.008742624,0.37698844,0.24481605],"study_design_scores_gemma":[0.0002452637,0.000012344145,0.021403765,0.000013770473,0.000050052542,1.00463346e-7,0.00039061086,0.92001474,0.00006164985,0.016327096,0.04136633,0.00011425115],"about_ca_topic_score_codex":0.00059394387,"about_ca_topic_score_gemma":0.00024181804,"teacher_disagreement_score":0.8036035,"about_ca_system_score_codex":0.00001887734,"about_ca_system_score_gemma":0.00003410264,"threshold_uncertainty_score":0.41628838},"labels":[],"label_agreement":null},{"id":"W6997218280","doi":"","title":"A Weighted-Tree Simplicity Algorithm for Similarity Matching of Partial Product Descriptions","year":2005,"lang":"en","type":"article","venue":"NPARC","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Simplicity; Tree (set theory); Matching (statistics); Similarity (geometry); Product (mathematics); Measure (data warehouse); Simple (philosophy); Order (exchange)","score_opus":0.1405199667415054,"score_gpt":0.3890718620059818,"score_spread":0.2485518952644764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6997218280","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":[0.054382075,0.000028007524,0.92509615,0.008953398,0.00026583363,0.0006651781,0.0004954404,0.00006773457,0.01004615],"genre_scores_gemma":[0.68069977,0.00000883557,0.31594026,0.00076714205,0.0004098911,0.00006636267,0.000037182002,0.000010365537,0.0020601782],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977359,0.00013826283,0.0006185799,0.00045246235,0.00078497274,0.0002698146],"domain_scores_gemma":[0.99835247,0.00040376117,0.00020242433,0.000731624,0.00022098597,0.000088706816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003182236,0.00011210466,0.00025970608,0.00013138085,0.00019263483,0.00012844153,0.00066988834,0.000039663442,0.000509096],"category_scores_gemma":[0.00067137356,0.000089647634,0.00013525582,0.00033808957,0.000094524476,0.0005183776,0.0002444771,0.0000930319,0.000093637966],"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":[0.000020391204,0.00026870533,0.000101957834,0.000011810976,0.000025873433,6.4756256e-7,0.00049635494,0.000052025018,0.0030856002,0.029847391,0.086817645,0.8792716],"study_design_scores_gemma":[0.00051423296,0.00006976581,0.001628487,0.000011892484,0.00004261374,0.0000019127544,0.00042543767,0.032386668,0.011058516,0.35301298,0.60065454,0.00019292995],"about_ca_topic_score_codex":0.000046757465,"about_ca_topic_score_gemma":0.00020993807,"teacher_disagreement_score":0.8790787,"about_ca_system_score_codex":0.00003174878,"about_ca_system_score_gemma":0.00004302941,"threshold_uncertainty_score":0.5574244},"labels":[],"label_agreement":null},{"id":"W6999452055","doi":"","title":"Data Quality Through Active Constraint Discovery and Maintenance","year":2012,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Leverage (statistics); Constraint (computer-aided design); Data integrity; Data quality; Set (abstract data type); Domain (mathematical analysis); Class (philosophy)","score_opus":0.184695293736358,"score_gpt":0.41658034300572705,"score_spread":0.23188504926936904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6999452055","genre_codex":"other","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":[0.17529947,0.0026019674,0.017100759,0.0028808834,0.0018931986,0.0009770149,0.01004626,0.00008183591,0.7891186],"genre_scores_gemma":[0.88164467,0.0013809437,0.0030033737,0.00008141413,0.00006813567,3.8431568e-7,0.0027728793,0.000014819825,0.111033395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9972609,0.00032285947,0.00029811176,0.00081886066,0.0010113852,0.00028782897],"domain_scores_gemma":[0.9964682,0.0005251831,0.00088428834,0.0018069285,0.00020533943,0.00011005305],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021213717,0.00022841601,0.00061489467,0.000045524503,0.00021851865,0.00011048272,0.0020082162,0.00019549848,0.007886572],"category_scores_gemma":[0.00059673155,0.00022976745,0.0001118053,0.000093493334,0.00035743267,0.0052493378,0.0009948356,0.00018197738,0.000058978647],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014791824,0.0003982772,0.00041966795,0.00041806794,0.000608357,0.000027071834,0.077897765,0.0000017513202,0.00031885583,0.15111503,0.07709093,0.69022506],"study_design_scores_gemma":[0.0005561104,0.000047120764,0.45699695,0.000103252176,0.00017014326,0.0000012672396,0.44181743,0.000024956817,0.000018812632,0.0020643438,0.09782004,0.0003795639],"about_ca_topic_score_codex":0.15234777,"about_ca_topic_score_gemma":0.40600878,"teacher_disagreement_score":0.7063452,"about_ca_system_score_codex":0.00015203051,"about_ca_system_score_gemma":0.00013091123,"threshold_uncertainty_score":0.99302036},"labels":[],"label_agreement":null},{"id":"W7009593967","doi":"","title":"Évaluation d’Apache Ozone et de son intégration du protocole de consensus RAFT avec la librairie Apache Ratis afin d'obtenir un système distribué fiable et cohérent","year":2024,"lang":"fr","type":"article","venue":"R-libre (Université Téluq)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Université de Saint-Boniface","funders":"","keywords":"Environmental policy; Air pollutants","score_opus":0.054902433307739605,"score_gpt":0.3312633851535205,"score_spread":0.2763609518457809,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009593967","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":[0.27232262,0.0028748275,0.48215178,0.20792615,0.0018240698,0.011184465,0.0029119228,0.0009094381,0.017894732],"genre_scores_gemma":[0.9187611,0.00093058904,0.013206673,0.0023455292,0.00044643288,0.00063437154,0.0016629457,0.0001255356,0.06188687],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9917373,0.0043066605,0.0007296606,0.0010741362,0.0013789438,0.0007732721],"domain_scores_gemma":[0.99579644,0.0023830147,0.00036581588,0.0008299999,0.00023435387,0.00039035003],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009906201,0.00047667164,0.000554202,0.00033446858,0.00050391443,0.001830931,0.00093799114,0.00044884434,0.0015403599],"category_scores_gemma":[0.0010732944,0.0004951642,0.00029692883,0.0018851515,0.00041512097,0.0022882782,0.00079726183,0.00064901344,0.0006760141],"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":[0.00028036314,0.0004643783,0.00052835274,0.00051870814,0.00029518997,0.0006242997,0.013048914,0.0024728412,0.00052406965,0.18730396,0.18611564,0.60782325],"study_design_scores_gemma":[0.0017935548,0.0003746133,0.02768792,0.0009061956,0.00038176015,0.00014240047,0.0035955692,0.1406617,0.0009196828,0.030682996,0.7921995,0.0006541461],"about_ca_topic_score_codex":0.0012327842,"about_ca_topic_score_gemma":0.000768695,"teacher_disagreement_score":0.6464384,"about_ca_system_score_codex":0.001028635,"about_ca_system_score_gemma":0.0020125401,"threshold_uncertainty_score":0.99975},"labels":[],"label_agreement":null},{"id":"W7009691967","doi":"","title":"Evaluating the Service Quality of Information Services Using a New 'P-C-P' Attributes Model","year":2001,"lang":"en","type":"article","venue":"Research Portal (Queen's University Belfast)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Information system; Quality (philosophy); Service (business); Service quality; Information quality; Information technology; Services computing; Key (lock); Context (archaeology)","score_opus":0.3957820113264607,"score_gpt":0.48819290166093615,"score_spread":0.09241089033447547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7009691967","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":[0.9525644,0.0000108385575,0.026929643,0.010270763,0.000064568194,0.00063550274,0.00020553927,0.000049551032,0.009269159],"genre_scores_gemma":[0.98881453,0.00006772198,0.0041967477,0.0004072878,0.000058463458,0.0000010386703,0.00011668595,0.000008732685,0.00632879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99266964,0.001358954,0.00074088655,0.00038501807,0.0043077953,0.0005376972],"domain_scores_gemma":[0.99477977,0.0013610581,0.00052533427,0.0011034047,0.0019889064,0.00024155626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016926205,0.00015223025,0.00030770915,0.0005937094,0.00079835876,0.00031460036,0.0021611506,0.00009740435,0.0004309998],"category_scores_gemma":[0.0013676218,0.00011867563,0.00012848963,0.0030378348,0.00018860558,0.003281637,0.0017300135,0.00036833124,0.0001620848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003379193,0.0009834813,0.044509996,0.0010997107,0.00066220487,0.000118166914,0.03334534,0.33115378,0.0028794715,0.44196698,0.044040587,0.0958611],"study_design_scores_gemma":[0.0033633055,0.00049662264,0.05288424,0.00027048367,0.00012242887,0.0000095732275,0.15244183,0.6427575,0.00046729358,0.05641459,0.089927964,0.00084417075],"about_ca_topic_score_codex":0.025057402,"about_ca_topic_score_gemma":0.0008333575,"teacher_disagreement_score":0.38555238,"about_ca_system_score_codex":0.00012206478,"about_ca_system_score_gemma":0.0005973241,"threshold_uncertainty_score":0.9814348},"labels":[],"label_agreement":null},{"id":"W7020951295","doi":"","title":"Miracle Cure: How to Solve America's Health Care Crisis and Why Canada Isn't the Answer","year":2004,"lang":"en","type":"other","venue":"DigitalGeorgetown (Georgetown University Library)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Miracle; Health care; Public health; Key (lock); Health services","score_opus":0.019644823314013363,"score_gpt":0.2453423860444746,"score_spread":0.2256975627304612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020951295","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002685437,0.0021829691,0.003129104,0.39249113,0.0018296369,0.0025517796,0.00924954,0.000768256,0.587529],"genre_scores_gemma":[0.0036132617,0.00058363745,0.0016975127,0.03386733,0.00030052176,0.0000067916194,0.00084909453,0.00034668614,0.95873517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99423474,0.0003079404,0.0005585322,0.0017861861,0.0020695075,0.0010430943],"domain_scores_gemma":[0.99561477,0.00031256917,0.00072620873,0.0022447754,0.00013131186,0.00097039377],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00037052538,0.0007993208,0.0010836779,0.00085857883,0.00089428964,0.0013219676,0.0034282354,0.00026751572,0.0024683503],"category_scores_gemma":[0.00023150128,0.0006319209,0.00028835496,0.0022878598,0.00040602815,0.0018302236,0.0033839308,0.0004890977,0.00017586525],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040010265,0.000060092254,0.00028929234,0.000082032435,0.00012654423,0.0001143061,0.0014437848,0.000010573706,1.4560929e-7,0.0048623285,0.9852722,0.0076986733],"study_design_scores_gemma":[0.00044585677,0.00012049074,0.000578579,0.00013142514,0.000048097627,0.0000032814526,0.020662274,0.0000019997572,0.000007184679,0.0007095811,0.9765386,0.0007526206],"about_ca_topic_score_codex":0.3022556,"about_ca_topic_score_gemma":0.32894027,"teacher_disagreement_score":0.37120613,"about_ca_system_score_codex":0.00040266625,"about_ca_system_score_gemma":0.0017105358,"threshold_uncertainty_score":0.99971473},"labels":[],"label_agreement":null},{"id":"W7023783286","doi":"","title":"Prenatal diagnoses lead to more abortions in Canada","year":2002,"lang":"en","type":"other","venue":"DigitalGeorgetown (Georgetown University Library)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Triacetin; Emperipolesis; Durvalumab","score_opus":0.03365306956211648,"score_gpt":0.25270563497599535,"score_spread":0.21905256541387888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023783286","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019779927,0.00020816324,0.00018513326,0.01565348,0.0010233396,0.0010878006,0.007982423,0.00046867438,0.971413],"genre_scores_gemma":[0.005655516,0.00026790678,0.0006418209,0.0018893535,0.00015856014,0.0000082539855,0.0009506883,0.0002848464,0.99014306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99405146,0.0002588373,0.0008518467,0.0017164223,0.0020927708,0.0010286624],"domain_scores_gemma":[0.99598426,0.0006789962,0.00048817086,0.0020653945,0.000073238174,0.000709924],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00029275147,0.00072945474,0.0010343564,0.0022908049,0.00016221456,0.0005797081,0.0038783792,0.00030889746,0.018288616],"category_scores_gemma":[0.0007574811,0.00072907953,0.00026411793,0.0035189607,0.00019828636,0.0024111457,0.0021797945,0.00047278713,0.0018863643],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026718684,0.00016439654,0.0064242636,0.000043969005,0.000066126886,0.0008282317,0.00014831903,0.000079194,1.9674178e-7,0.0036018144,0.97771585,0.010900897],"study_design_scores_gemma":[0.0004674594,0.000033188277,0.0053573875,0.0002604426,0.000028952887,0.00000263976,0.001792933,0.000041771757,0.000028141161,0.00052536465,0.9905828,0.00087889115],"about_ca_topic_score_codex":0.53283274,"about_ca_topic_score_gemma":0.7896515,"teacher_disagreement_score":0.2568188,"about_ca_system_score_codex":0.00051643996,"about_ca_system_score_gemma":0.0012497068,"threshold_uncertainty_score":0.999516},"labels":[],"label_agreement":null},{"id":"W7025214214","doi":"","title":"Top smart cities in Canada, India and beyond","year":2015,"lang":"en","type":"other","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.08843154607919923,"score_gpt":0.34236116211156,"score_spread":0.25392961603236075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025214214","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011129562,0.00036324782,0.000031059186,0.0006185505,0.00043389766,0.000121367426,0.00031379538,0.000013927413,0.9979929],"genre_scores_gemma":[0.000585316,0.000044405246,0.00021325567,0.0020984658,0.00004270761,0.0000044786943,0.00004134051,0.000027094851,0.99694294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982872,0.00008506345,0.00026752433,0.00031045356,0.0008973669,0.00015237615],"domain_scores_gemma":[0.99920684,0.00014755494,0.000097068645,0.0004349139,0.000023927534,0.00008966898],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012956882,0.00011136514,0.0002573674,0.0003276489,0.000013165827,0.000120001154,0.0004454271,0.000063957355,0.010335822],"category_scores_gemma":[0.00026863793,0.00007963511,0.00001072425,0.00022230622,0.00004910568,0.00006897556,0.00031232976,0.00007699978,0.0001887855],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011480073,0.0000032751063,0.0016657084,0.0000057148177,0.0000059291383,0.000012612284,0.00009233383,9.760743e-8,1.1961515e-8,0.0053889593,0.9839268,0.008897457],"study_design_scores_gemma":[0.000110225905,0.0000057440493,0.0021830944,0.000010614863,0.00000264364,4.8472015e-7,0.0034741939,0.000003811219,3.5454283e-7,0.0058222245,0.98827404,0.00011254762],"about_ca_topic_score_codex":0.9574662,"about_ca_topic_score_gemma":0.9988403,"teacher_disagreement_score":0.041374084,"about_ca_system_score_codex":0.00007704412,"about_ca_system_score_gemma":0.0006230983,"threshold_uncertainty_score":0.9905689},"labels":[],"label_agreement":null},{"id":"W7025225528","doi":"","title":"Turning Open Government Data Portals into Interactive Databases","year":2022,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Upload; Key (lock); Governor; Set (abstract data type); Download; Table (database); Open data; Publication; Web application","score_opus":0.13103167425199025,"score_gpt":0.37989511964050693,"score_spread":0.24886344538851668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7025225528","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91252977,0.00038650015,0.00082142657,0.006177091,0.004088814,0.0027568142,0.020429421,0.00012462332,0.052685555],"genre_scores_gemma":[0.025571108,0.00021270865,0.004130938,0.00014107375,0.000037043028,0.0000019463957,0.026328465,0.000027214934,0.9435495],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99528575,0.00042311667,0.00041037705,0.0012840593,0.0023385896,0.00025812676],"domain_scores_gemma":[0.9951198,0.00051285274,0.0012009628,0.002888303,0.00015413486,0.00012393409],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0032741758,0.00026698655,0.0006524921,0.000246109,0.00052406586,0.0003140388,0.00889858,0.00007660509,0.012366109],"category_scores_gemma":[0.0005859719,0.00027770904,0.000121608864,0.00045535236,0.00008929136,0.0031177187,0.010175872,0.00036827291,0.0002472603],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014421623,0.0005748042,0.00040265653,0.00024083062,0.0007602313,0.00038144158,0.24254426,0.00012614677,0.0007657086,0.0044232616,0.6098332,0.13850531],"study_design_scores_gemma":[0.00031069395,0.00006623666,0.00087902276,0.00008351913,0.00013259954,9.1125696e-7,0.60615987,0.00022188292,0.0001530989,0.0006323373,0.39110324,0.00025661584],"about_ca_topic_score_codex":0.12161744,"about_ca_topic_score_gemma":0.27635363,"teacher_disagreement_score":0.89086396,"about_ca_system_score_codex":0.0002069792,"about_ca_system_score_gemma":0.00014979625,"threshold_uncertainty_score":0.9999675},"labels":[],"label_agreement":null},{"id":"W7034066571","doi":"","title":"SinglePoint publishes its monetary effects for the moment of the 2021 quarter and reports on its business","year":2021,"lang":"en","type":"other","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Moment (physics); Monetary policy; Business cycle; Monetary system","score_opus":0.1146221513617565,"score_gpt":0.35108818676756753,"score_spread":0.23646603540581101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034066571","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005632839,0.013611568,0.012123407,0.050248798,0.010391026,0.0065421145,0.00026451144,0.000070723174,0.90618455],"genre_scores_gemma":[0.0071755606,0.00026108327,0.0003230341,0.0019795303,0.00031554018,0.00014967949,0.000058428468,0.00008085965,0.98965627],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967619,0.00026303416,0.0006602842,0.00072918244,0.0013702447,0.00021536462],"domain_scores_gemma":[0.9956936,0.0016126736,0.00069223583,0.0016890977,0.0002582624,0.000054120686],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002824595,0.00024866735,0.00047536672,0.00017569063,0.000119461685,0.0005550187,0.0007278061,0.00013016183,0.0029311934],"category_scores_gemma":[0.0024231724,0.00010822646,0.00016348792,0.0005593864,0.00009503385,0.00014703517,0.0006014899,0.0001074389,0.000020040125],"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":[0.0000085688935,0.000096626034,0.000030867413,0.00021060256,0.0001180598,0.000014918281,0.00008606472,0.000016406906,0.00002388001,0.0028681895,0.9792956,0.017230224],"study_design_scores_gemma":[0.00019672819,0.000051094845,0.0033642058,0.0003612531,0.00007555847,0.000006390309,0.000404002,0.00008909244,0.00033725894,0.0014579433,0.993484,0.00017247611],"about_ca_topic_score_codex":0.00018285183,"about_ca_topic_score_gemma":0.00051942765,"teacher_disagreement_score":0.083471715,"about_ca_system_score_codex":0.000016357491,"about_ca_system_score_gemma":0.000063082196,"threshold_uncertainty_score":0.99798024},"labels":[],"label_agreement":null},{"id":"W7037404654","doi":"","title":"Dougal - Live at Liquid Adrenaline Timewarp 5 Part 1 08-05-2000","year":2000,"lang":"en","type":"other","venue":"Internet Archive (Internet Archive)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Epinephrine; Liquid phase; Liquid liquid; Context (archaeology)","score_opus":0.05253383487044749,"score_gpt":0.3230119861615656,"score_spread":0.27047815129111813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037404654","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005222302,0.000772425,0.0067514195,0.0007318769,0.0026567748,0.0011248895,0.011099596,0.0005676182,0.97577316],"genre_scores_gemma":[0.0010136227,0.0006413432,0.0019199087,0.0027387482,0.0020056139,0.00014072975,0.0052935444,0.0006601374,0.98558635],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98786217,0.0019260531,0.0024741732,0.0033262218,0.0028919654,0.0015194133],"domain_scores_gemma":[0.9923771,0.0019498592,0.0013944304,0.0033449503,0.00008787846,0.00084577437],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["metaepi_narrow","insufficient_payload"],"category_scores_codex":[0.0014683221,0.0014994502,0.0019239178,0.0012308715,0.000104108614,0.00073769636,0.0056748274,0.00040617088,0.3924779],"category_scores_gemma":[0.0005957871,0.0012520761,0.001208724,0.00039569422,0.001180151,0.00030576368,0.0052576363,0.0012578451,0.19511014],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021051848,0.00041715163,0.000036774814,0.00008345786,0.0007640729,0.0008728906,0.003637981,0.000020034015,0.000036113823,0.0024646623,0.9868708,0.002690835],"study_design_scores_gemma":[0.0012331655,0.0009845699,0.00006373381,0.0010661156,0.00018524645,0.00016462718,0.00013230585,0.0006183809,0.0003527711,0.006101377,0.98775774,0.001339959],"about_ca_topic_score_codex":0.007985256,"about_ca_topic_score_gemma":0.060113695,"teacher_disagreement_score":0.19736776,"about_ca_system_score_codex":0.00015599822,"about_ca_system_score_gemma":0.00029579396,"threshold_uncertainty_score":0.99977547},"labels":[],"label_agreement":null},{"id":"W7039308945","doi":"","title":"Le lien entre la représentation des femmes aux conseils d'administration et l'efficacité des politiques d'investissement : cas des entreprises canadiennes","year":2021,"lang":"fr","type":"other","venue":"Archipelago (University of Quebec in Montreal)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Citizenship; Lien","score_opus":0.09419180032451427,"score_gpt":0.3403797823532314,"score_spread":0.24618798202871714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039308945","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":[0.8732417,0.0009900205,0.00542561,0.0028778212,0.00015506273,0.0006518522,0.00037717717,0.000050330957,0.11623041],"genre_scores_gemma":[0.77516747,0.0026180334,0.009745517,0.00016470317,0.000044910958,0.0000044969447,0.0005191599,0.000046517875,0.21168922],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9944821,0.0022278384,0.00074911746,0.0011282463,0.0007296087,0.0006830887],"domain_scores_gemma":[0.995881,0.001791674,0.00069607754,0.00086782244,0.00037087622,0.00039255762],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017086117,0.00047493196,0.000808791,0.00079279655,0.00056072196,0.00029449942,0.0009772198,0.00028424148,0.0024302073],"category_scores_gemma":[0.0013757235,0.000571583,0.0002822701,0.000702156,0.003158813,0.00078033906,0.00058207166,0.0003028055,0.000059840128],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018523795,0.00081510056,0.015729932,0.00046123014,0.000256219,0.0010515872,0.18485186,0.00029401865,0.0001317124,0.20184216,0.0023836708,0.59199727],"study_design_scores_gemma":[0.0011123902,0.00017870769,0.38531104,0.0012930072,0.00016593725,0.00004023831,0.4036264,0.00023179862,0.00026063056,0.19337726,0.013840788,0.0005618217],"about_ca_topic_score_codex":0.9565844,"about_ca_topic_score_gemma":0.9993334,"teacher_disagreement_score":0.59143543,"about_ca_system_score_codex":0.0003932572,"about_ca_system_score_gemma":0.0019925998,"threshold_uncertainty_score":0.99967355},"labels":[],"label_agreement":null},{"id":"W7039554015","doi":"","title":"Miller, Myrtle Alberta (Birth, 1893-10-23)","year":2012,"lang":"en","type":"other","venue":"Spectrum Research Repository (Concordia University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Natural (archaeology); Assemblage (archaeology); Feature (linguistics)","score_opus":0.11179679212113681,"score_gpt":0.35689595608931535,"score_spread":0.24509916396817855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039554015","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049463776,0.0005910931,0.00019079278,0.0012894046,0.00200014,0.0007638866,0.00013710132,0.00019861871,0.99433434],"genre_scores_gemma":[0.012693217,0.0003295805,0.000056507666,0.00005032996,0.0012785259,0.0000047314297,0.00007652646,0.00023944314,0.98527116],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99016654,0.0023250217,0.00059781695,0.001635411,0.0037246356,0.0015505557],"domain_scores_gemma":[0.9933285,0.0017268234,0.00049807446,0.0033145817,0.00026810434,0.0008638811],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003993432,0.00051055214,0.00083286763,0.00391737,0.0007243008,0.0006575381,0.0046487986,0.0005670386,0.02657119],"category_scores_gemma":[0.0009665648,0.00048191185,0.00043485395,0.002856806,0.0010220498,0.0006222319,0.0026387798,0.0010812581,0.018651435],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011676381,0.00016539473,0.0017849918,0.000053529802,0.00020483526,0.00041846276,0.00011772694,0.000001054627,0.0000339884,0.021095593,0.9739289,0.0020787455],"study_design_scores_gemma":[0.0005700958,0.00015280968,0.001197979,0.00007794822,0.00004809943,0.000013390112,0.0011060169,0.000011024341,0.00020795868,0.0012257057,0.99485433,0.0005346191],"about_ca_topic_score_codex":0.064345084,"about_ca_topic_score_gemma":0.0736182,"teacher_disagreement_score":0.02092544,"about_ca_system_score_codex":0.00054795376,"about_ca_system_score_gemma":0.0006077063,"threshold_uncertainty_score":0.99976325},"labels":[],"label_agreement":null},{"id":"W7042086444","doi":"","title":"Points de vue","year":2015,"lang":"en","type":"other","venue":"Summit (Simon Fraser University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Nucleofection; Gestational period; Hyporeflexia; Dysgeusia; TSG101; Diafiltration; Liquation; Fusible alloy","score_opus":0.06864641301097517,"score_gpt":0.30894447233753436,"score_spread":0.24029805932655918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042086444","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008390812,0.00011315136,0.0027869467,0.0006296212,0.00060753356,0.00022220511,0.0006987269,0.0002106715,0.99464726],"genre_scores_gemma":[0.00034650162,0.00009312607,0.00072231784,0.0006138539,0.0001750494,3.6205034e-7,0.00016118532,0.00009735681,0.9977902],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99705845,0.00043199674,0.00024609538,0.0007258703,0.0011522201,0.00038536196],"domain_scores_gemma":[0.9977517,0.00018901438,0.00030499438,0.0012937506,0.00013377663,0.00032674553],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016772852,0.00027049534,0.00041815953,0.0013736401,0.00008593529,0.0001607767,0.0022972818,0.00031938707,0.013947941],"category_scores_gemma":[0.0005316612,0.00026180368,0.00014340763,0.0012873579,0.00016071917,0.00027907974,0.0007993759,0.00025052813,0.0075107226],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002382599,0.000057001613,0.0034200703,0.00001272492,0.000060851977,0.00025050488,0.000020614718,0.000004058606,3.7794447e-8,0.0040088133,0.9886036,0.0035379177],"study_design_scores_gemma":[0.0004961707,0.000031259107,0.000019865733,0.000044650886,0.00005697631,2.351908e-9,0.015079283,0.000014324572,0.000004906054,0.004432369,0.9795169,0.00030325973],"about_ca_topic_score_codex":0.00090827263,"about_ca_topic_score_gemma":0.18443021,"teacher_disagreement_score":0.18352194,"about_ca_system_score_codex":0.00018436396,"about_ca_system_score_gemma":0.0002003775,"threshold_uncertainty_score":0.99998343},"labels":[],"label_agreement":null},{"id":"W7070961349","doi":"","title":"Research and application of wood-concrete in world practice: an overview","year":2022,"lang":"en","type":"article","venue":"Digital Library of Polotsk State University (Polotsk State University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Filler (materials); Thermal insulation; Material selection; Thermal; Selection (genetic algorithm)","score_opus":0.11628178061933599,"score_gpt":0.35739529290609434,"score_spread":0.24111351228675837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7070961349","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":[0.84912443,0.00028854277,0.0011056687,0.0033121328,0.0001548859,0.001005114,0.00800418,0.00013334933,0.13687171],"genre_scores_gemma":[0.93777835,0.00071713765,0.00059768505,0.00014736004,0.000009161925,5.4877444e-7,0.00034448784,0.000023723607,0.060381558],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956473,0.001197895,0.000517042,0.0008184654,0.0013487994,0.00047048155],"domain_scores_gemma":[0.99673027,0.001379147,0.0005494354,0.00084323995,0.0002404422,0.00025746596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018843068,0.00020567708,0.00046627256,0.0033213939,0.0004032856,0.0001745454,0.0019342983,0.000047049303,0.00029538263],"category_scores_gemma":[0.00016158751,0.0002437425,0.00009912563,0.005628981,0.00091840804,0.008596379,0.003459103,0.00046081783,0.000024796613],"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":[0.008168397,0.0014981332,0.03197316,0.0002676672,0.00032839327,0.0013551331,0.009442051,0.0017627081,0.00027420308,0.85675085,0.029545952,0.05863338],"study_design_scores_gemma":[0.0013121873,0.0007975059,0.006149763,0.000022805616,0.000017935705,0.0000052637306,0.050046485,0.00050130236,0.0001306668,0.015530084,0.92518246,0.0003035547],"about_ca_topic_score_codex":0.0009483796,"about_ca_topic_score_gemma":0.00017039706,"teacher_disagreement_score":0.8956365,"about_ca_system_score_codex":0.00016773723,"about_ca_system_score_gemma":0.0002625004,"threshold_uncertainty_score":0.99395305},"labels":[],"label_agreement":null},{"id":"W7084128860","doi":"10.64628/aam.hxurcjx5g","title":"The #advancedstyle movement celebrates and empowers stylish older women","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Movement (music); MEDLINE; Action (physics); Older people","score_opus":0.04357030514862068,"score_gpt":0.3660470867078004,"score_spread":0.3224767815591797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084128860","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":[0.58558834,0.0018372232,0.016172498,0.040099356,0.0015893636,0.00066616567,0.000075724245,0.0001574701,0.35381386],"genre_scores_gemma":[0.6305651,0.00093698874,0.0023807527,0.023463672,0.00008687091,0.00009427689,0.000016838389,0.000016107044,0.34243938],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980952,0.00014485951,0.0003353672,0.00038810493,0.00076090073,0.00027552884],"domain_scores_gemma":[0.9982226,0.0007969278,0.0000732297,0.0006696892,0.00013591834,0.00010166931],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025797382,0.00008453561,0.00012859679,0.000035852067,0.00029634335,0.0009467211,0.00042166293,0.00002034586,0.0019622357],"category_scores_gemma":[0.00080596044,0.00004850523,0.00003124492,0.0003396106,0.00010265045,0.0003844269,0.0005823755,0.00005721152,0.00018058982],"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":[0.000022137083,0.0001315154,0.0021423856,0.000009481599,0.00006975424,0.000022923436,0.0037111237,0.00003118039,0.00041934202,0.28416893,0.40000594,0.3092653],"study_design_scores_gemma":[0.00024917733,0.000023009925,0.004548799,0.0000029463727,0.0000024305643,5.912882e-7,0.051294494,0.000082880484,0.0011312522,0.08197647,0.86059165,0.000096307565],"about_ca_topic_score_codex":0.000024644796,"about_ca_topic_score_gemma":0.00030709663,"teacher_disagreement_score":0.46058568,"about_ca_system_score_codex":0.00002740303,"about_ca_system_score_gemma":0.000031336716,"threshold_uncertainty_score":0.9989501},"labels":[],"label_agreement":null},{"id":"W7092317075","doi":"","title":"FACTS: Table Summarization via Offline Template Generation with Agentic Workflows","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Data Quality and Management","field":"Decision Sciences","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":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Automatic summarization; Table (database); Workflow; Executable; Natural language; Key (lock); Robustness (evolution)","score_opus":0.18450859587016613,"score_gpt":0.2489525282214207,"score_spread":0.06444393235125456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7092317075","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":[0.108077295,0.00010144964,0.87429285,0.00041665562,0.0009689983,0.00067170913,0.00007393734,0.00006393819,0.015333176],"genre_scores_gemma":[0.8927749,0.00036896198,0.00050377136,0.0006143355,0.000071356684,0.0000011624421,0.00020649034,0.00001509501,0.10544395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963262,0.0005147818,0.00069101487,0.0015175489,0.00038729206,0.00056317815],"domain_scores_gemma":[0.9970916,0.0002900919,0.0004727032,0.0014438347,0.0004944806,0.0002072927],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0016989176,0.0003883153,0.0004653861,0.0007957472,0.0008312522,0.0006906922,0.0012445314,0.00020420979,0.0017350346],"category_scores_gemma":[0.00023121631,0.00037920583,0.00013029695,0.005338068,0.0002798779,0.002155202,0.00066149037,0.00025403057,0.0008481047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091115246,0.0010780515,0.013683915,0.00019959701,0.00077495445,0.00043836312,0.00051179767,0.6514819,0.0008799168,0.26529193,0.03521484,0.029533578],"study_design_scores_gemma":[0.002477529,0.00024995286,0.0016162791,0.00021350155,0.00065036985,0.0000027262174,0.0011636155,0.8760082,0.0007587245,0.013906883,0.10222449,0.0007277353],"about_ca_topic_score_codex":0.00044464789,"about_ca_topic_score_gemma":0.0012194506,"teacher_disagreement_score":0.8737891,"about_ca_system_score_codex":0.0002580811,"about_ca_system_score_gemma":0.00028092723,"threshold_uncertainty_score":0.99992985},"labels":[],"label_agreement":null},{"id":"W7095792784","doi":"","title":"CANADA S4S 0A2Expectation Propagation in ExGen Graphs for Summarization:","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Generalization; Heuristics; Node (physics); Domain (mathematical analysis); Process (computing)","score_opus":0.11973997131540226,"score_gpt":0.3703554875670823,"score_spread":0.25061551625168005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095792784","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":[0.05628535,0.000058212463,0.8123597,0.0066163903,0.001207071,0.0022451961,0.00009653904,0.000057097586,0.12107445],"genre_scores_gemma":[0.98692,0.0000031880472,0.003857251,0.0010962866,0.000011931727,0.00007660123,0.00008466524,0.0000041532603,0.007945953],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985519,0.00013182515,0.0003735323,0.0002447608,0.00057427055,0.0001237154],"domain_scores_gemma":[0.9991778,0.00031855569,0.000089363304,0.00023569928,0.000143526,0.00003503334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001702979,0.000055670404,0.0000894795,0.00013807915,0.00007397859,0.000110702844,0.0001909236,0.000021217198,0.0003062812],"category_scores_gemma":[0.0018907791,0.000043949396,0.000020814441,0.0006381971,0.000013218411,0.00033849673,0.000018367638,0.000022245944,0.000016059052],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010594684,0.000034250872,0.0039486405,0.0000073378374,0.000004305093,0.0000010468028,0.00020389826,0.00042867154,0.000043101696,0.8638519,0.11791197,0.013554275],"study_design_scores_gemma":[0.00088584406,0.000050873223,0.016018927,0.0000075134017,0.0000072184266,6.438591e-7,0.0052404865,0.0053268718,0.0021491153,0.22904179,0.7410266,0.00024414246],"about_ca_topic_score_codex":0.10281448,"about_ca_topic_score_gemma":0.8525884,"teacher_disagreement_score":0.9306346,"about_ca_system_score_codex":0.000063871885,"about_ca_system_score_gemma":0.00024501135,"threshold_uncertainty_score":0.90316},"labels":[],"label_agreement":null},{"id":"W7096274211","doi":"","title":"Author Name Co-Mention Analysis: Testing a Poor Man&amp;apos;s Author Co-Citation Analysis Method","year":2016,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"German; Quarter (Canadian coin); Citation; Citation analysis; Service (business); Work (physics)","score_opus":0.5682010533063319,"score_gpt":0.5671922909398469,"score_spread":0.0010087623664849499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096274211","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":[0.02590325,0.000018601719,0.9523593,0.008124853,0.00013826056,0.00030878425,0.00022797885,0.00019179558,0.012727179],"genre_scores_gemma":[0.5549855,0.000003947359,0.28437805,0.0010077877,0.000093276794,0.00007606251,0.00036946655,0.000019280942,0.1590666],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99256635,0.0016623002,0.0015310076,0.001226327,0.002533057,0.00048094257],"domain_scores_gemma":[0.99264663,0.004288777,0.0008231962,0.0013752991,0.0006095541,0.00025652145],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.020974906,0.00027353107,0.0007578075,0.0031814561,0.0003811409,0.00084464287,0.0010075483,0.00012574221,0.006267221],"category_scores_gemma":[0.008430334,0.00016695248,0.00066278916,0.009570494,0.00009971431,0.0011736589,0.00022487981,0.000103710474,0.003284837],"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":[0.00015253195,0.00051822054,0.043275993,0.000031572352,0.0106787495,0.000017483175,0.001765709,0.0016897968,0.0073603746,0.045665793,0.17513065,0.7137131],"study_design_scores_gemma":[0.0019010663,0.00028479233,0.24788241,0.00005771084,0.018345537,0.0000045969086,0.008209604,0.08074368,0.002135926,0.07115053,0.5677003,0.0015838313],"about_ca_topic_score_codex":0.0005509477,"about_ca_topic_score_gemma":0.0012607279,"teacher_disagreement_score":0.7121293,"about_ca_system_score_codex":0.00012713786,"about_ca_system_score_gemma":0.00004909672,"threshold_uncertainty_score":0.9999221},"labels":[],"label_agreement":null},{"id":"W7096613607","doi":"","title":"www.cihi.ca","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Information quality; Health care; Information system; Data quality; Health information","score_opus":0.4501617695756432,"score_gpt":0.46043866559688645,"score_spread":0.010276896021243265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096613607","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041189726,0.000023648783,0.03710959,0.0043138457,0.0003561163,0.000084784384,0.000011752379,0.00006688142,0.91684365],"genre_scores_gemma":[0.54979974,0.000024090585,0.0033491526,0.0046619964,0.0000620857,0.000003813479,0.000006116327,0.000003004942,0.44208997],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985359,0.00006176929,0.0002474304,0.00022684086,0.0008047555,0.0001233262],"domain_scores_gemma":[0.99904674,0.00023998946,0.000039614246,0.0005589288,0.000054157925,0.000060579834],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013413774,0.000046628073,0.00009186199,0.00008165027,0.000120186545,0.00007400848,0.0005735012,0.000017954402,0.013945388],"category_scores_gemma":[0.0006527326,0.000029588298,0.00004479308,0.00029650723,0.00006574167,0.00029277976,0.00021963341,0.000033569606,0.034930155],"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":[0.0000025289567,0.000025320916,0.00056616036,3.9287406e-7,0.0000027644023,0.000012320979,0.00009041248,0.000004669179,0.000010678041,0.051882852,0.93335456,0.014047343],"study_design_scores_gemma":[0.000086637665,0.000014224491,0.008587714,5.305333e-7,0.0000010295171,0.000004617366,0.00030320158,0.00019004151,0.00008677905,0.018148173,0.97252494,0.00005210574],"about_ca_topic_score_codex":0.000080306665,"about_ca_topic_score_gemma":0.00006803408,"teacher_disagreement_score":0.50861007,"about_ca_system_score_codex":0.0000062974955,"about_ca_system_score_gemma":0.000015267799,"threshold_uncertainty_score":0.986956},"labels":[],"label_agreement":null},{"id":"W7096721468","doi":"","title":"The Development of a Data Quality Framework and Strategy for the New Zealand Ministry of Health","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Data quality; Quality (philosophy); Christian ministry; Data governance; Quality management; Data management; Health data","score_opus":0.6633314680100575,"score_gpt":0.5505149266813276,"score_spread":0.11281654132872987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096721468","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":[0.05368443,0.0014495401,0.89692146,0.044590566,0.00023348934,0.0010280479,0.0003818476,0.000016617998,0.0016939953],"genre_scores_gemma":[0.8410889,0.0006471015,0.13001497,0.0014698209,0.000068617206,0.000016463116,0.00007041172,0.000008523429,0.026615217],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99783295,0.00018273726,0.00094665727,0.00025573207,0.0006391995,0.00014269036],"domain_scores_gemma":[0.9930583,0.0051469957,0.0004021286,0.0012687086,0.000070225775,0.000053617034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011283053,0.0000620125,0.00020367051,0.000019822975,0.0003399793,0.00006172651,0.0013251984,0.000027172035,0.000044657107],"category_scores_gemma":[0.0014183694,0.000027021257,0.000023080527,0.00016842046,0.0001985264,0.00014021942,0.0005385874,0.000050755516,0.000002693635],"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":[0.000063371626,0.000058192865,0.0012692248,0.000025913936,0.00004944399,9.26541e-8,0.0035355382,0.00000500774,0.0000031371392,0.049247634,0.27425745,0.671485],"study_design_scores_gemma":[0.0003260139,0.00007511977,0.073485404,0.00001739203,0.0000064336273,0.0000011361457,0.014253363,0.00016467457,0.00009210111,0.060657565,0.8508408,0.0000799884],"about_ca_topic_score_codex":0.00047530944,"about_ca_topic_score_gemma":0.0014071754,"teacher_disagreement_score":0.7874045,"about_ca_system_score_codex":0.000005354582,"about_ca_system_score_gemma":0.00044202074,"threshold_uncertainty_score":0.39105037},"labels":[],"label_agreement":null},{"id":"W7098475574","doi":"","title":"Final Report: British Columbia Problem Gambling Prevalence Study Submitted to: Gaming Policy and Enforcement Branch Ministry of Public Safety and Solicitor General Submitted by:","year":2010,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Christian ministry; Enforcement; Government (linguistics); Law enforcement","score_opus":0.08412132569334843,"score_gpt":0.3807746408175742,"score_spread":0.29665331512422577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098475574","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":[0.9907666,0.000038687802,0.0036066393,0.00095714204,0.00021509422,0.001212102,0.00017376174,0.00005166197,0.00297832],"genre_scores_gemma":[0.9601058,0.000042363794,0.001960768,0.00045659472,0.0001437522,0.000047454785,0.000034727127,0.00001439127,0.037194144],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9951916,0.00024459153,0.0015384121,0.0009995947,0.0015009322,0.0005248828],"domain_scores_gemma":[0.9974494,0.00039698786,0.00049492344,0.00088141183,0.00040217585,0.00037509663],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.006813123,0.00018668198,0.0004825518,0.00020754128,0.00037199818,0.0020440002,0.00069335924,0.00009856611,0.00081770425],"category_scores_gemma":[0.0030841334,0.00021872297,0.00005559801,0.0008943902,0.00021928082,0.0006553339,0.0009390524,0.00021094715,0.000006079452],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112693495,0.0013643019,0.5935344,0.0003210719,0.0001887563,0.00012942654,0.0032568437,0.00001155431,0.010150673,0.0037366527,0.08035281,0.3068408],"study_design_scores_gemma":[0.0030533758,0.00075290864,0.8423577,0.00009557517,0.00008225786,0.00029894031,0.0043539116,0.0009946851,0.00040817956,0.0026194653,0.14414774,0.000835285],"about_ca_topic_score_codex":0.034546673,"about_ca_topic_score_gemma":0.0549939,"teacher_disagreement_score":0.30600554,"about_ca_system_score_codex":0.000031485077,"about_ca_system_score_gemma":0.00016064793,"threshold_uncertainty_score":0.99899197},"labels":[],"label_agreement":null},{"id":"W7098571762","doi":"","title":"Digraph Description Of K-Interchange Technique For Optimization Over Permutations (Extended Abstract)","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Heuristics; Digraph; Travelling salesman problem; Permutation (music); Combinatorial optimization; Scheduling (production processes); Optimization problem","score_opus":0.2224664177847425,"score_gpt":0.4370657972583242,"score_spread":0.21459937947358168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7098571762","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":[0.0034650005,0.000008073814,0.9802098,0.00024345276,0.00013652489,0.0006269401,0.00006680511,0.00003512097,0.015208277],"genre_scores_gemma":[0.9061075,0.0000080457785,0.09093421,0.0002502297,0.000026770926,0.0000566288,0.000079781246,0.000006287354,0.00253058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985357,0.00002864035,0.0005666321,0.00023599595,0.00048751387,0.00014554393],"domain_scores_gemma":[0.99867,0.00046676115,0.00020263749,0.00032631095,0.00028822274,0.000046081626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041058795,0.000071815775,0.00012638127,0.00040611197,0.00007198544,0.000087683344,0.00029482355,0.000054391494,0.0007227025],"category_scores_gemma":[0.00078341854,0.00005604068,0.00009519765,0.00043299145,0.000055955898,0.00059632555,0.000061053586,0.000037531663,0.000014028859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005663909,0.0013754768,0.0014965577,0.00015843201,0.00012178216,0.00000609889,0.0038529506,0.009370173,0.04197585,0.6718275,0.12389568,0.14535311],"study_design_scores_gemma":[0.002936862,0.00092901627,0.19774462,0.0001432992,0.00015456998,0.000010595866,0.020060303,0.03745348,0.092161484,0.51742864,0.12985465,0.0011224567],"about_ca_topic_score_codex":0.00009642301,"about_ca_topic_score_gemma":0.00042411173,"teacher_disagreement_score":0.9026425,"about_ca_system_score_codex":0.00002412968,"about_ca_system_score_gemma":0.000012889921,"threshold_uncertainty_score":0.7913086},"labels":[],"label_agreement":null},{"id":"W7099523777","doi":"","title":"Correspondence","year":2004,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phylogenetic tree; Enzootic; Genome; Clade; Recombinant DNA; Phylogenetics; Virus; Sequence analysis; Genetic diversity","score_opus":0.320829081153056,"score_gpt":0.48382058703924946,"score_spread":0.1629915058861935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099523777","genre_codex":"other","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":[0.037250847,0.000018295405,0.446041,0.009269821,0.00054399547,0.000094106086,0.000006075084,0.00008010191,0.50669575],"genre_scores_gemma":[0.8907632,0.000002986689,0.0051946975,0.0045223697,0.000026712873,0.000002591958,0.0000013406875,0.0000017862092,0.09948427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99884015,0.000032387576,0.0001746022,0.00017987234,0.00068398897,0.00008899196],"domain_scores_gemma":[0.9992775,0.00017637316,0.000030494968,0.0004294465,0.00004279791,0.000043406777],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001765648,0.00003179652,0.000054742562,0.00007102634,0.000046221205,0.00015521515,0.000570874,0.000011559505,0.004260486],"category_scores_gemma":[0.0010719,0.00002025849,0.000025070958,0.00031557243,0.000035375448,0.00028378962,0.00016151195,0.000025380805,0.018857976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007506712,0.000030987765,0.00014137459,3.9555914e-7,0.0000016614556,0.000008594773,0.00015294373,0.0001999216,0.00006655076,0.83820283,0.11880227,0.042384956],"study_design_scores_gemma":[0.0001380604,0.00001747114,0.0032707024,0.0000013852147,8.1054355e-7,0.000001407854,0.00054054806,0.000022633369,0.00043488192,0.3834624,0.6120659,0.00004376435],"about_ca_topic_score_codex":0.00006751271,"about_ca_topic_score_gemma":0.00009591046,"teacher_disagreement_score":0.8535124,"about_ca_system_score_codex":0.000011300957,"about_ca_system_score_gemma":0.000020579333,"threshold_uncertainty_score":0.99664974},"labels":[],"label_agreement":null},{"id":"W7100239799","doi":"","title":"University of Castilla-La Mancha","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Maintainability; Metric (unit); Point (geometry); Software; Quality (philosophy); Order (exchange)","score_opus":0.3033654716840396,"score_gpt":0.3732940129860818,"score_spread":0.06992854130204218,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100239799","genre_codex":"other","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":[0.22721721,0.000015854583,0.06653022,0.0007865002,0.000107680804,0.00006227712,0.000019413013,0.000027105123,0.70523375],"genre_scores_gemma":[0.9429868,0.000029884488,0.0017645695,0.00010063494,0.0000051024313,2.2902277e-8,9.815012e-7,7.9665773e-7,0.05511122],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99924946,0.00006955759,0.00010435816,0.0001250773,0.0003951387,0.00005642007],"domain_scores_gemma":[0.99934745,0.00023266133,0.000046515237,0.00029082331,0.0000513675,0.000031186366],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00076141965,0.00002646535,0.00007708911,0.000060319315,0.000055382356,0.000008101802,0.0003605272,0.000015173358,0.002228369],"category_scores_gemma":[0.00016136901,0.000020838876,0.000032605378,0.00019254419,0.00011333539,0.00012877335,0.00018457934,0.000019657933,0.0006811999],"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":[0.00003095994,0.000102533755,0.005224215,0.00000571502,0.000017602795,0.00014352538,0.0018043004,0.00006402767,0.00006071651,0.18131475,0.74048674,0.070744894],"study_design_scores_gemma":[0.00015394675,0.000017485523,0.032827277,0.0000014812207,0.0000025272925,0.000006792598,0.0023520594,0.00017132961,0.00008330382,0.0042355796,0.96010464,0.00004355253],"about_ca_topic_score_codex":0.00022996285,"about_ca_topic_score_gemma":0.00011806279,"teacher_disagreement_score":0.7157696,"about_ca_system_score_codex":0.0000043625423,"about_ca_system_score_gemma":0.000014269006,"threshold_uncertainty_score":0.99868375},"labels":[],"label_agreement":null},{"id":"W7104182958","doi":"","title":"Relational Deep Dive: Error-Aware Queries Over Unstructured Data","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Schema (genetic algorithms); Unstructured data; Modular design; Completeness (order theory); Relational database; Information extraction; Population; Data extraction","score_opus":0.31773586256303454,"score_gpt":0.4352136701261027,"score_spread":0.11747780756306814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104182958","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":[0.71696,0.004693974,0.1839905,0.036539156,0.017133234,0.0019391273,0.0063438723,0.00032250248,0.032077603],"genre_scores_gemma":[0.9641014,0.00029414726,0.0012942035,0.0048634964,0.00027009213,0.000016060485,0.001405593,0.000022026872,0.027733011],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931723,0.0006101258,0.0016052275,0.0020092642,0.0019121546,0.0006909114],"domain_scores_gemma":[0.9924405,0.0015519647,0.0005471827,0.004892395,0.0003441168,0.00022379374],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003416417,0.00047774543,0.0006268437,0.00044624056,0.0010248652,0.00065156486,0.00463765,0.00030563556,0.009088774],"category_scores_gemma":[0.0047358773,0.00042005396,0.00018120233,0.0019010478,0.0008537373,0.0032231526,0.007392281,0.00054001354,0.0019528028],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019707852,0.0002029462,0.61559707,0.00010335761,0.0004129557,0.00004289694,0.0010360566,0.00021801193,0.00003162046,0.114749275,0.22310099,0.044307757],"study_design_scores_gemma":[0.00060598383,0.000028405459,0.5126013,0.00008202857,0.0001310455,0.0000015042081,0.0021932505,0.0033010794,0.00003489998,0.014595158,0.46610442,0.00032089648],"about_ca_topic_score_codex":0.00033821462,"about_ca_topic_score_gemma":0.0011726568,"teacher_disagreement_score":0.24714133,"about_ca_system_score_codex":0.00012911143,"about_ca_system_score_gemma":0.0004712878,"threshold_uncertainty_score":0.9998251},"labels":[],"label_agreement":null},{"id":"W7113234448","doi":"","title":"Content, Design and Structure of Major Databases with Historical Longitudinal Population Data","year":2023,"lang":"en","type":"article","venue":"KNAW Research Portal (The Royal Netherlands Academy of Arts and Sciences)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Institute for Public Safety Research and Treatment","funders":"","keywords":"Erasmus+; Population; Linkage (software); Crowdsourcing; Range (aeronautics); Relational database","score_opus":0.6723114842298782,"score_gpt":0.4992735101447177,"score_spread":0.17303797408516047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7113234448","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":[0.986902,0.00057641894,0.0033091782,0.007441019,0.00008354213,0.0006450405,0.0003249045,0.000022972423,0.00069493253],"genre_scores_gemma":[0.9976295,0.00008119503,0.0010874453,0.000047592457,0.000053030173,0.0000035222477,0.000035331905,0.0000051752,0.0010572112],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954585,0.00044005061,0.00051242515,0.0006776165,0.0025497621,0.00036168526],"domain_scores_gemma":[0.9973715,0.0016922002,0.00023541308,0.0004589123,0.00010244113,0.00013955608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013476556,0.00011528773,0.00028649648,0.00032611002,0.00050336175,0.00016281291,0.0013337334,0.000050654937,0.0001661728],"category_scores_gemma":[0.0010474545,0.00005755041,0.00002140199,0.0011371021,0.001265339,0.0005515788,0.0010441205,0.00026897708,0.00000437331],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008547348,0.0002240365,0.4714631,0.00019388368,0.0001716895,0.00006165273,0.0016898414,0.0028257258,0.0013411919,0.1369773,0.27767757,0.10651925],"study_design_scores_gemma":[0.0010849371,0.0010016535,0.85091984,0.00013706725,0.00005514522,0.000024200432,0.0033447552,0.060122285,0.00034988174,0.02319862,0.059406865,0.0003547396],"about_ca_topic_score_codex":0.0014380348,"about_ca_topic_score_gemma":0.0002618788,"teacher_disagreement_score":0.37945673,"about_ca_system_score_codex":0.0000093913795,"about_ca_system_score_gemma":0.000050114595,"threshold_uncertainty_score":0.46707323},"labels":[],"label_agreement":null},{"id":"W7118185187","doi":"10.1145/3731599.3787543","title":"10.1145/3731599.3787543","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Resource (disambiguation); Component (thermodynamics); Key (lock)","score_opus":0.07682765995816798,"score_gpt":0.32325578265318505,"score_spread":0.24642812269501707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118185187","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00050268444,0.000017509803,0.000027340833,0.0019844796,0.0000073609363,0.00016288333,0.00004655609,0.00008336702,0.9971678],"genre_scores_gemma":[0.00024309852,3.180268e-7,0.00030095788,0.0007063577,0.000078290024,0.000010708027,0.000015277223,0.000008167549,0.99863684],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790066,0.00013127406,0.00037700264,0.00040957256,0.000921224,0.00026026802],"domain_scores_gemma":[0.99855846,0.00026742494,0.000047586724,0.000891808,0.00006592266,0.00016878465],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019299621,0.00010859661,0.00018526436,0.00014419452,0.000107722895,0.00029000777,0.0010247085,0.000037101847,0.99823505],"category_scores_gemma":[0.0004757855,0.00008635405,0.0000695236,0.0005793585,0.000043417185,0.00030769137,0.0002065855,0.000060369523,0.9983443],"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":[0.00001853581,0.000022323411,8.594372e-8,5.5650355e-7,0.0000037187697,0.0000028056363,0.000015156829,0.00003362099,0.0000031624675,0.000037773298,0.48366088,0.5162014],"study_design_scores_gemma":[0.00013125065,0.000072308154,0.00009443734,0.0000042371935,0.0000064055207,0.0000015566028,0.000008578419,0.00017261512,0.000016976248,0.0006684626,0.99869543,0.0001277546],"about_ca_topic_score_codex":0.00003622924,"about_ca_topic_score_gemma":0.0000010133007,"teacher_disagreement_score":0.51607364,"about_ca_system_score_codex":0.000018635359,"about_ca_system_score_gemma":0.0000178099,"threshold_uncertainty_score":0.3521416},"labels":[],"label_agreement":null},{"id":"W7126398324","doi":"10.21428/594757db.564cdb72","title":"Comparing Traditional and Deep Learning Approaches for Product Matching: Performance on Unseen Entities","year":2025,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Guelph","funders":"","keywords":"Deep learning; Feature learning; Autoencoder; Matching (statistics); Transformer; Representation (politics); Feature (linguistics); Training set","score_opus":0.4048250354532657,"score_gpt":0.3676819528872744,"score_spread":0.0371430825659913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126398324","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":[0.6825736,0.000120799894,0.13473102,0.003091281,0.00033403435,0.00048615687,0.000009943363,0.00008488228,0.17856826],"genre_scores_gemma":[0.97321177,0.000014349108,0.0021843223,0.00027696675,0.000040249975,0.000032143267,0.000027968228,0.000002716862,0.024209525],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887514,0.00006333978,0.0002454614,0.0003289299,0.00035778448,0.00012935889],"domain_scores_gemma":[0.9991367,0.0005644966,0.000056381792,0.00018450175,0.00003317085,0.00002478283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019672913,0.000076194854,0.00014331329,0.00012819334,0.00031286443,0.0003271636,0.00025887246,0.000014897098,0.000055816552],"category_scores_gemma":[0.0002651717,0.000056888948,0.000032202013,0.00015456024,0.00006769116,0.0003437066,0.000082782644,0.0000789222,0.000022760601],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062713996,0.00008775246,0.009160319,0.00009826811,0.000033588203,1.944603e-7,0.00087109295,0.0055038515,0.000008549478,0.8427467,0.0073704477,0.13405654],"study_design_scores_gemma":[0.0010510519,0.0002440089,0.23803644,0.000098992066,0.00003888267,0.000002257409,0.015067915,0.16234897,0.00074791576,0.26227424,0.31970555,0.00038380251],"about_ca_topic_score_codex":0.000011746982,"about_ca_topic_score_gemma":0.00002913619,"teacher_disagreement_score":0.58047247,"about_ca_system_score_codex":0.00001351819,"about_ca_system_score_gemma":0.000012520874,"threshold_uncertainty_score":0.3154846},"labels":[],"label_agreement":null},{"id":"W7132922950","doi":"","title":"Essays in Computational Econometrics","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Data Quality and Management","field":"Decision Sciences","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 Toronto","funders":"Social Sciences and Humanities Research Council of Canada; National Institutes of Health","keywords":"Computational complexity theory; Computational problem; Matching (statistics); Probabilistic logic; Bayesian probability; Function (biology); Class (philosophy); Inference; Interval (graph theory)","score_opus":0.278320810239532,"score_gpt":0.4910467462801524,"score_spread":0.2127259360406204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132922950","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4192763,0.0021243496,0.05861401,0.0199951,0.028255286,0.0045881597,0.0010356127,0.00053658173,0.4655746],"genre_scores_gemma":[0.49465993,0.00111753,0.0028632018,0.0010177181,0.00029732008,0.00026443452,0.0071158027,0.00012644043,0.49253762],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9940993,0.0004078066,0.0015573257,0.0013129887,0.0020584636,0.000564123],"domain_scores_gemma":[0.9941008,0.0037513734,0.0008203161,0.0008263385,0.00031294225,0.00018820696],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0068484684,0.0004060557,0.0007527834,0.003629513,0.00022854158,0.0008646779,0.001639788,0.00032872934,0.0046168715],"category_scores_gemma":[0.004109959,0.00042858452,0.00021396771,0.0067623025,0.000099827135,0.00047993474,0.00040434752,0.0005025929,0.017050708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029607269,0.00092348637,0.0031130258,0.0006496262,0.00022961668,0.00023445455,0.06905995,0.15934624,0.0000031430443,0.22733818,0.2164866,0.3223196],"study_design_scores_gemma":[0.0020117883,0.00021357245,0.13495754,0.0004314668,0.000099418685,0.0000023085734,0.3107176,0.11048472,0.0000142043455,0.25764605,0.18177322,0.0016481105],"about_ca_topic_score_codex":0.0011830762,"about_ca_topic_score_gemma":0.0028234718,"teacher_disagreement_score":0.3206715,"about_ca_system_score_codex":0.00021769393,"about_ca_system_score_gemma":0.0003749889,"threshold_uncertainty_score":0.9998166},"labels":[],"label_agreement":null},{"id":"W7133042738","doi":"","title":"Facilitating Discovery in Open Data Repositories","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Data Quality and Management","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Metadata; Data element; Metadata repository; Discoverability; Metadata modeling; Open data; Linked data; Schema (genetic algorithms); Data mapping","score_opus":0.32456081942087717,"score_gpt":0.5522434291650822,"score_spread":0.227682609744205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133042738","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38530985,0.015144693,0.010813513,0.014670251,0.052978296,0.00830024,0.006035947,0.0002549403,0.50649226],"genre_scores_gemma":[0.16326514,0.0005653845,0.0033474152,0.0002748118,0.00038285658,0.000125354,0.011211101,0.00006675118,0.8207612],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9911826,0.00081192603,0.0019953547,0.0031473103,0.0022651108,0.00059767615],"domain_scores_gemma":[0.99046785,0.0029626098,0.0007329277,0.0055267625,0.0001703659,0.00013950057],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.012265056,0.0005517554,0.0009798714,0.00057433423,0.0003745601,0.015337386,0.012824812,0.00028469937,0.0005603689],"category_scores_gemma":[0.010873735,0.00048444944,0.0001187114,0.002111474,0.00015409106,0.007025572,0.01434283,0.00079412706,0.0019960145],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008209889,0.00052424084,0.0005413904,0.002283102,0.0003852788,0.00070955657,0.42027208,0.00023586099,0.0003977229,0.060564943,0.34081462,0.1724502],"study_design_scores_gemma":[0.000302394,0.000077624776,0.0007908004,0.001356711,0.00011343676,0.000002452191,0.6621501,0.002539519,0.0001186447,0.010933554,0.3210015,0.00061330845],"about_ca_topic_score_codex":0.018790517,"about_ca_topic_score_gemma":0.022383979,"teacher_disagreement_score":0.31426892,"about_ca_system_score_codex":0.00015903167,"about_ca_system_score_gemma":0.00068506744,"threshold_uncertainty_score":0.99976075},"labels":[],"label_agreement":null},{"id":"W7134187860","doi":"10.1109/bigdata66926.2025.11402509","title":"Explainable Retrieval and Graph Augmented Code Vulnerability Repair Recommendations","year":2025,"lang":"","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Code (set theory); Graph; Vulnerability (computing); Source code; Key (lock)","score_opus":0.10895485461058127,"score_gpt":0.4230902027042033,"score_spread":0.314135348093622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134187860","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052800238,0.0023772293,0.3539554,0.20935251,0.0077111055,0.0042068036,0.001538929,0.00094896305,0.36710882],"genre_scores_gemma":[0.46723863,0.0038419326,0.019311367,0.014655759,0.00010115479,0.00009166143,0.00026082364,0.000028417198,0.49447027],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99310863,0.0015559958,0.0019159323,0.0017204693,0.0010630161,0.00063596026],"domain_scores_gemma":[0.9937856,0.0028846147,0.00031252345,0.0022379619,0.0005067312,0.0002725544],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.016685987,0.00035756532,0.00061099377,0.00075222534,0.0014568256,0.0010421021,0.0010126935,0.00018835512,0.0077268793],"category_scores_gemma":[0.0070039732,0.0003117592,0.00026828106,0.003415054,0.0006063965,0.0014220072,0.0019356718,0.0003842871,0.00022239961],"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":[0.0004396988,0.00067887595,0.0014777774,0.00014074259,0.00022291261,0.000006553033,0.0004988429,0.000016996408,0.000033064887,0.22232676,0.72073144,0.05342633],"study_design_scores_gemma":[0.001095294,0.00015943634,0.0044218763,0.00009872514,0.00013352992,0.0000013716555,0.011856556,0.004524417,0.00037096607,0.12622455,0.8507823,0.00033103806],"about_ca_topic_score_codex":0.00045560623,"about_ca_topic_score_gemma":0.0007632229,"teacher_disagreement_score":0.4144384,"about_ca_system_score_codex":0.00016138094,"about_ca_system_score_gemma":0.00024280426,"threshold_uncertainty_score":0.99999493},"labels":[],"label_agreement":null},{"id":"W7162292117","doi":"10.63282/3050-9262.ijaidsml-v3i3p119","title":"Preparing Enterprise Data for LLM-Assisted Customer Issue Analysis: A Governance-Centric Framework","year":2022,"lang":"","type":"article","venue":"International Journal of Artificial Intelligence Data Science and Machine Learning","topic":"Data Quality and Management","field":"Decision Sciences","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":"Institute on Governance","funders":"","keywords":"Data governance; Enterprise data management; Scalability; Audit; Metadata; Corporate governance; Enterprise information system; Enterprise architecture; Customer intelligence; Enterprise information security architecture","score_opus":0.18746334802245912,"score_gpt":0.4515668028765007,"score_spread":0.2641034548540416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162292117","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":[0.0096697,0.0035421592,0.95067596,0.012128459,0.011362769,0.0008878518,0.011066181,0.000037253987,0.0006296713],"genre_scores_gemma":[0.9813529,0.002068702,0.013205209,0.0011221218,0.0009462686,0.000013637764,0.000833262,0.00002396767,0.0004338997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9859115,0.00068558514,0.0030563246,0.001959069,0.007632735,0.000754824],"domain_scores_gemma":[0.98831564,0.0025639331,0.0037546405,0.0026744106,0.0022575909,0.0004338003],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.037604727,0.00038457793,0.0008242946,0.0021538967,0.0020376272,0.0036203333,0.022669028,0.00008068932,0.0018732722],"category_scores_gemma":[0.032625627,0.00035225958,0.00024235186,0.0056446632,0.0009450489,0.0077153575,0.020281319,0.0014468757,0.0000653953],"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":[0.0012047277,0.0010901483,0.0016206345,0.000023685368,0.0012649836,0.00010107951,0.002285966,0.034101818,0.00021904166,0.010712903,0.008367887,0.9390071],"study_design_scores_gemma":[0.00013914637,0.0003726445,0.00046284928,0.00008740896,0.0006671526,0.00008318727,0.0070883166,0.5351363,0.000086932196,0.0029935474,0.45255518,0.00032734574],"about_ca_topic_score_codex":0.00068238983,"about_ca_topic_score_gemma":0.00028032705,"teacher_disagreement_score":0.9716832,"about_ca_system_score_codex":0.00046217948,"about_ca_system_score_gemma":0.0011591151,"threshold_uncertainty_score":0.99989295},"labels":[],"label_agreement":null},{"id":"W7162329119","doi":"10.63282/3050-922x.ijeret-v4i2p117","title":"A Scalable Architecture for Automated Data Classification and Sensitive Information Discovery Using Artificial Intelligence","year":2023,"lang":"","type":"article","venue":"International Journal of Emerging Research in Engineering and Technology","topic":"Data Quality and Management","field":"Decision Sciences","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":"Institute on Governance","funders":"","keywords":"Scalability; Data governance; Flexibility (engineering); Knowledge extraction; Data architecture; Cloud computing; Architecture; Data classification; Data warehouse","score_opus":0.28846272117441907,"score_gpt":0.49070007011040506,"score_spread":0.202237348935986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7162329119","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":[0.34603164,0.00037916115,0.61611944,0.034823775,0.0016787862,0.00046207706,0.00037461487,0.00010924192,0.000021245098],"genre_scores_gemma":[0.99043137,0.0008742777,0.0084465565,0.000020714902,0.00013623155,0.0000063806683,0.00006304517,0.000009653013,0.000011760925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970125,0.00011822504,0.001082716,0.00031964874,0.0010894028,0.00037753227],"domain_scores_gemma":[0.9967375,0.0014467024,0.0003293132,0.00034766586,0.0010668377,0.00007197993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009634071,0.00013299967,0.0002619532,0.00584746,0.00013428782,0.0007066203,0.0011933368,0.00015685889,0.0000025000845],"category_scores_gemma":[0.00825221,0.00012356056,0.000029906214,0.0022377092,0.0002814144,0.0020336325,0.0013215372,0.0006335366,0.0000050130393],"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":[0.00036090755,0.000102211125,0.0003232775,0.00021915491,0.00026632394,0.000116460884,0.0013768887,0.12174489,0.004300228,0.108498506,0.00093053194,0.7617606],"study_design_scores_gemma":[0.00020254718,0.00010898189,0.0003551812,0.000488951,0.000010874076,0.00008448832,0.006158448,0.95455337,0.00041788167,0.03065448,0.0068552974,0.000109511755],"about_ca_topic_score_codex":0.00004741322,"about_ca_topic_score_gemma":0.00002021463,"teacher_disagreement_score":0.83280843,"about_ca_system_score_codex":0.00012401582,"about_ca_system_score_gemma":0.00015820908,"threshold_uncertainty_score":0.98792624},"labels":[],"label_agreement":null},{"id":"W760598031","doi":"10.1007/s00778-015-0389-y","title":"Profiling relational data: a survey","year":2015,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":273,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Profiling (computer programming); Metadata; Computer science; Data mining; Data type; Information retrieval; Data science; World Wide Web","score_opus":0.8844173631534311,"score_gpt":0.5434835487839118,"score_spread":0.3409338143695193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W760598031","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":[0.352442,0.0016693377,0.5112038,0.05794158,0.009467906,0.0007046077,0.0010885082,0.00010324621,0.065379],"genre_scores_gemma":[0.96708786,0.000056730012,0.013368911,0.0025342165,0.0015712639,0.000002907286,0.00023726223,0.000017024146,0.015123808],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964501,0.0010763827,0.0004557821,0.0001861964,0.0016773121,0.00015419841],"domain_scores_gemma":[0.9971984,0.0011507034,0.0002507955,0.00093831756,0.00032821074,0.00013355103],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051777884,0.000058432397,0.0001057201,0.00008779347,0.00026479052,0.00056203816,0.0021243063,0.000021241096,0.00021321757],"category_scores_gemma":[0.010924824,0.000029404817,0.000027865372,0.00037724889,0.00007365708,0.00092525315,0.0007525229,0.00024893065,0.0009997596],"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":[0.00008279585,0.000048899212,0.021600956,7.1028927e-7,0.000038622038,0.000014581196,0.00047931462,0.00073710264,0.000007779039,0.022833709,0.9319591,0.022196447],"study_design_scores_gemma":[0.0006290396,0.000051446168,0.087574445,0.0000096129015,0.000018795108,0.00016900337,0.00230548,0.0066900337,0.000012826525,0.15588231,0.7465175,0.00013952529],"about_ca_topic_score_codex":0.0000394526,"about_ca_topic_score_gemma":0.00009459696,"teacher_disagreement_score":0.6146459,"about_ca_system_score_codex":0.000024826468,"about_ca_system_score_gemma":0.00018176564,"threshold_uncertainty_score":0.9997781},"labels":[],"label_agreement":null},{"id":"W85648037","doi":"","title":"Proceedings of the 2008 ACM SIGMOD international conference on Management of data","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":423,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Dynamism; Session (web analytics); Field (mathematics); Sentence; Data science; Operations research; World Wide Web; Artificial intelligence","score_opus":0.5943424653324738,"score_gpt":0.46913552352602683,"score_spread":0.12520694180644698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W85648037","genre_codex":"other","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":[0.101155065,0.000009802696,0.0023623514,0.011587931,0.00044632514,0.00042047014,0.00026235072,0.000021223512,0.88373446],"genre_scores_gemma":[0.96917456,0.00010095028,0.0057158433,0.00037261535,0.000016260405,0.0000036034505,0.000013034509,0.0000026018927,0.024600543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976973,0.000015962618,0.0004204046,0.00031646472,0.0014659285,0.0000839632],"domain_scores_gemma":[0.9982506,0.00010188029,0.00023653166,0.0011635183,0.00022452581,0.000022920325],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013592774,0.00006206545,0.000121102705,0.00008134522,0.0000498558,0.000037254697,0.005721446,0.000017107413,0.0011582611],"category_scores_gemma":[0.00037209192,0.000034511235,0.000035652858,0.00029682898,0.00016230001,0.00046107217,0.0034158202,0.00004503171,0.000079957485],"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":[0.000030349705,0.00017324013,0.0014018296,0.00001403051,0.00005170887,0.0000013275596,0.00020936021,0.000004941248,0.00013015638,0.61300135,0.368056,0.016925737],"study_design_scores_gemma":[0.001777237,0.00021540557,0.15972437,0.0002457738,0.00006243839,0.000010465152,0.015525807,0.005749364,0.007876202,0.18380019,0.62459636,0.00041642133],"about_ca_topic_score_codex":0.00003213449,"about_ca_topic_score_gemma":0.000010180346,"teacher_disagreement_score":0.86801946,"about_ca_system_score_codex":0.000008300795,"about_ca_system_score_gemma":0.000015066516,"threshold_uncertainty_score":0.9997548},"labels":[],"label_agreement":null},{"id":"W86472440","doi":"10.2139/ssrn.2367300","title":"Analyzing the 2004-2011 KFS Multiply Imputed Data","year":2013,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"Mathematics","score_opus":0.11393749553607897,"score_gpt":0.37751567357422133,"score_spread":0.2635781780381424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W86472440","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":[0.087161355,0.012157104,0.82566977,0.06491722,0.0019775415,0.0011477647,0.000098828,0.00014856711,0.006721825],"genre_scores_gemma":[0.98010284,0.0022423756,0.0008694952,0.0011352217,0.00064161693,0.000009753805,0.000043289798,0.000022595807,0.0149328],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99525404,0.00051006326,0.0007328577,0.0004898184,0.0010656731,0.001947572],"domain_scores_gemma":[0.99658716,0.00061357755,0.00041441846,0.0020124142,0.00024425532,0.00012815345],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01998164,0.00016277013,0.00022557219,0.00020860013,0.00057960255,0.001069275,0.0052182893,0.000051960284,0.0012743141],"category_scores_gemma":[0.0014353393,0.0000890075,0.0001113004,0.00050095795,0.000102175545,0.001769759,0.0010383171,0.0013929144,0.003605163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001988954,0.00009036748,0.0019030761,0.0000016229228,0.0002737783,0.0000037441553,0.00021376701,0.00009323016,0.00009753888,0.07456286,0.21369466,0.70904547],"study_design_scores_gemma":[0.0006613183,0.00012409958,0.0054436736,0.0000088067345,0.00006175906,0.00014316206,0.0070941723,0.008544784,0.000014113043,0.74910134,0.22853482,0.00026795172],"about_ca_topic_score_codex":0.0007630601,"about_ca_topic_score_gemma":0.0020725348,"teacher_disagreement_score":0.8929415,"about_ca_system_score_codex":0.00022159163,"about_ca_system_score_gemma":0.00076658814,"threshold_uncertainty_score":0.9999677},"labels":[],"label_agreement":null},{"id":"W89272820","doi":"","title":"Analysis of recurrent event data with environmental covariates.","year":2005,"lang":"en","type":"article","venue":"Scholarship at UWindsor (University of Windsor)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Covariate; Event (particle physics); Computer science; Machine learning","score_opus":0.10593478874036612,"score_gpt":0.3312888164567091,"score_spread":0.225354027716343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W89272820","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":[0.9899727,0.0001643083,0.004698705,0.0013487699,0.000077782526,0.0002450769,0.0020521546,0.000023038503,0.0014174598],"genre_scores_gemma":[0.9927604,0.000056570065,0.0038537474,0.000107533095,0.000022950442,2.1119297e-7,0.0006847632,0.000009098258,0.0025047353],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9956835,0.00042620685,0.0005396347,0.0009205302,0.002115654,0.00031446357],"domain_scores_gemma":[0.99597466,0.00037615455,0.00073524675,0.0026109547,0.00009993482,0.00020305408],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004611458,0.00020658525,0.0006374628,0.00091230375,0.000276696,0.000059617898,0.0034076865,0.0001097293,0.004430397],"category_scores_gemma":[0.00026022882,0.00019515946,0.00024676207,0.0017619471,0.00039245954,0.0018838682,0.002224723,0.00023524943,0.0003344155],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026834423,0.0029595613,0.78794056,0.000066776025,0.006550686,0.00007750784,0.007815495,0.0066829864,0.0025976878,0.0038167788,0.009799591,0.16900896],"study_design_scores_gemma":[0.0016038762,0.00024578246,0.8760317,0.000036269463,0.001913261,0.000003142678,0.0051913853,0.003950296,0.00034791158,0.00032736527,0.10995752,0.0003915035],"about_ca_topic_score_codex":0.00011915975,"about_ca_topic_score_gemma":0.002122155,"teacher_disagreement_score":0.16861746,"about_ca_system_score_codex":0.00013830936,"about_ca_system_score_gemma":0.000062766325,"threshold_uncertainty_score":0.9964797},"labels":[],"label_agreement":null},{"id":"W897078397","doi":"","title":"Proceedings of the ACM tenth international workshop on Data warehousing and OLAP","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Online analytical processing; Data warehouse; Computer science; Data science; Business intelligence; Database; Field (mathematics); Decision support system; Data quality; Data mining; Engineering","score_opus":0.3997951615933993,"score_gpt":0.4744954337782644,"score_spread":0.07470027218486514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W897078397","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":[0.6263504,0.00003357676,0.013168846,0.03895003,0.0013621569,0.00041974708,0.000100225356,0.000053804808,0.3195612],"genre_scores_gemma":[0.98737806,0.000009717521,0.00458624,0.0015562802,0.00006161646,4.5067105e-7,0.0000071061845,0.0000030176438,0.00639752],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850345,0.000007743746,0.00026754144,0.00026686265,0.0008662127,0.00008820147],"domain_scores_gemma":[0.9984352,0.00047295584,0.000118166885,0.0008489861,0.000096472184,0.000028234734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004185787,0.000045728422,0.00006831442,0.000086835535,0.00006288529,0.00018838013,0.003203603,0.000018670415,0.00015954139],"category_scores_gemma":[0.005774238,0.000023609884,0.000015730267,0.00025034198,0.00007496384,0.00045314492,0.0039294707,0.000055988767,0.000019414163],"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":[0.00007694561,0.00014645862,0.016493702,0.0000085823995,0.00003586624,0.0000012104897,0.0008482708,0.0000055123783,0.00052341144,0.12513904,0.45634395,0.40037704],"study_design_scores_gemma":[0.00046159915,0.00003007512,0.1170194,0.00009685837,0.000016449407,0.000003787146,0.015522485,0.0011713833,0.0022623355,0.0479509,0.81529915,0.00016556057],"about_ca_topic_score_codex":0.000019792955,"about_ca_topic_score_gemma":0.000062021856,"teacher_disagreement_score":0.40021148,"about_ca_system_score_codex":0.000008974725,"about_ca_system_score_gemma":0.0000063171715,"threshold_uncertainty_score":0.69127196},"labels":[],"label_agreement":null},{"id":"W984517805","doi":"","title":"What's in a name? Measuring use and non-use of Digital Resources in the Arts and Humanities through Log Analysis Techniques","year":2006,"lang":"en","type":"article","venue":"Durham Research Online (Durham University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"World Wide Web; The arts; Digital humanities; The Internet; Computer science; Resource (disambiguation); Transaction log; Library science; Database transaction; Visual arts; Art; Database","score_opus":0.37799285482890904,"score_gpt":0.4094065370243242,"score_spread":0.03141368219541518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W984517805","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":[0.99557006,0.00013188939,0.0003629785,0.0014551851,0.000013443541,0.0003644271,0.00013910599,0.000019504432,0.0019434063],"genre_scores_gemma":[0.9954722,0.00079842046,0.00063766714,0.00006127088,0.00002564997,0.0000019331344,0.000046397265,0.0000068572745,0.0029496343],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9963855,0.0006948971,0.00046724352,0.0005650081,0.0014946201,0.00039271425],"domain_scores_gemma":[0.99624234,0.002555531,0.00014257595,0.00067413604,0.00033570116,0.00004971717],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0037836554,0.00015266864,0.000383644,0.0029119833,0.00022957516,0.00198319,0.0008415285,0.00008314059,0.00001725944],"category_scores_gemma":[0.0012878375,0.00011887821,0.00008381607,0.0038176507,0.0008610288,0.0058560534,0.0010329982,0.00036782032,0.000002041567],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013192862,0.0039588264,0.8162567,0.00030702722,0.00056368037,0.0024297256,0.039598353,0.0010121772,0.00047259155,0.08123332,0.008738503,0.044109818],"study_design_scores_gemma":[0.0010446031,0.00030068783,0.5019189,0.00026938104,0.00009406475,0.0000071198915,0.13712713,0.0011163321,0.00024489217,0.015249642,0.34218138,0.0004458627],"about_ca_topic_score_codex":0.0061614974,"about_ca_topic_score_gemma":0.031631466,"teacher_disagreement_score":0.3334429,"about_ca_system_score_codex":0.00007615362,"about_ca_system_score_gemma":0.0000423569,"threshold_uncertainty_score":0.9990528},"labels":[],"label_agreement":null},{"id":"W98491823","doi":"","title":"The Impact of Conceptual Modeling on Dataset Completeness: A Field Experiment","year":2014,"lang":"en","type":"article","venue":"","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Completeness (order theory); Computer science; Context (archaeology); Conceptual model; Field (mathematics); Dimension (graph theory); Conceptual framework; Context model; Mathematics; Artificial intelligence","score_opus":0.3721302909571856,"score_gpt":0.4996081782359375,"score_spread":0.12747788727875192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W98491823","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":[0.29492193,0.00009084325,0.6429859,0.0044585764,0.0005188713,0.00055638904,0.0014304558,0.0000519624,0.054985058],"genre_scores_gemma":[0.99847764,0.0000051431757,0.0002503767,0.0009045869,0.00002795149,0.0000060258844,0.00008982578,0.0000023284344,0.00023612604],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983302,0.00020992903,0.0004066931,0.0002230462,0.0006820456,0.00014812968],"domain_scores_gemma":[0.99687856,0.0019459506,0.00009922106,0.0009659451,0.000059348047,0.00005096347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002763628,0.00007712718,0.00015587686,0.00004301288,0.00013331097,0.0001273904,0.00088769593,0.000019374427,0.0006382321],"category_scores_gemma":[0.0011619917,0.000035065827,0.00007654784,0.000111839654,0.00010743927,0.00013317865,0.00028655652,0.000047531335,0.00018958133],"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":[0.00012005292,0.000112689966,0.000047439946,0.0000013345197,0.000037755373,4.7982985e-7,0.0007006743,0.01812527,0.00021264153,0.26478076,0.68222326,0.03363764],"study_design_scores_gemma":[0.0007800165,0.0011751846,0.00015177748,0.000016744132,0.000009071563,7.4872423e-7,0.016273769,0.6591386,0.002383652,0.03655153,0.28328103,0.00023787911],"about_ca_topic_score_codex":0.0008872638,"about_ca_topic_score_gemma":0.00005844249,"teacher_disagreement_score":0.7035557,"about_ca_system_score_codex":0.000011964326,"about_ca_system_score_gemma":0.000015495254,"threshold_uncertainty_score":0.6988194},"labels":[],"label_agreement":null}]}