{"meta":{"query_hash":"a4d764b4c8fc","filters":{"venue":"Data Technologies and Applications"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"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/a4d764b4c8fc","api":"https://metacan.xera.ac/api/v1/cohort?venue=Data+Technologies+and+Applications"},"results":[{"id":"W3115843551","doi":"10.1108/dta-07-2020-0154","title":"Assessment of national innovation capabilities of OECD countries using trapezoidal interval type-2 fuzzy ELECTRE III method","year":2020,"lang":"en","type":"article","venue":"Data Technologies and Applications","topic":"Multi-Criteria Decision Making","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":"ELECTRE; Interval (graph theory); Fuzzy set; Fuzzy logic; Originality; Value (mathematics); Set (abstract data type); Multiple-criteria decision analysis; Operations research; Computer science; Mathematics; Data mining; Actuarial science; Statistics; Economics; Artificial intelligence; Social science; Sociology","score_opus":0.33265751442714514,"score_gpt":0.5056090366198612,"score_spread":0.1729515221927161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3115843551","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":[0.21133812,0.00030512334,0.7814872,0.0033605692,0.000050412844,0.0005988357,0.002076443,0.00017847306,0.00060481817],"genre_scores_gemma":[0.8479625,0.000039915565,0.15173522,0.00007951857,0.000021360629,0.000023527507,0.00012342338,0.0000060630446,0.0000084775775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772114,0.000054312946,0.00087424193,0.00048350793,0.0007475227,0.000119302604],"domain_scores_gemma":[0.9968877,0.0009703517,0.00050298206,0.00079111505,0.00083008566,0.000017768238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015073086,0.00011123808,0.00031508712,0.00034438903,0.00011711789,0.000092985996,0.0012675755,0.00010310556,0.000065530214],"category_scores_gemma":[0.0017793672,0.00009037153,0.000025789515,0.0014130343,0.00032016612,0.00036615532,0.00086055003,0.00013967621,0.000003428852],"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":[0.00004302675,0.000112972346,0.005731204,0.00007538864,0.0000621567,4.0186254e-7,0.00033168425,0.00037370715,0.086541526,0.65627396,0.00391793,0.24653606],"study_design_scores_gemma":[0.0013314207,0.00033880965,0.010646431,0.00008028343,0.00008831207,0.000025512516,0.033177454,0.35464266,0.036109515,0.34805742,0.21480483,0.00069735944],"about_ca_topic_score_codex":0.000023460763,"about_ca_topic_score_gemma":0.000007805504,"teacher_disagreement_score":0.6366244,"about_ca_system_score_codex":0.000025910951,"about_ca_system_score_gemma":0.00016306149,"threshold_uncertainty_score":0.3685244},"labels":[],"label_agreement":null},{"id":"W3144823608","doi":"10.1108/dta-12-2020-0298","title":"A systematic review of machine learning-based missing value imputation techniques","year":2021,"lang":"en","type":"review","venue":"Data Technologies and Applications","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":99,"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":"Imputation (statistics); Missing data; Computer science; Data mining; Cluster analysis; Mean squared error; Machine learning; Artificial intelligence; Information retrieval; Statistics; Mathematics","score_opus":0.12576228665755548,"score_gpt":0.4470710314993138,"score_spread":0.3213087448417583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3144823608","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":[5.929556e-10,0.52998424,0.46764863,0.00007082995,0.0000030394442,0.0012475357,0.0007740229,0.00024384585,0.000027861188],"genre_scores_gemma":[5.364807e-8,0.59905046,0.399057,0.000012577826,0.0000056877934,0.0008138639,0.0010381795,0.000018367286,0.0000038138733],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9978617,0.0002572091,0.0010687422,0.00049219694,0.00017162708,0.00014854781],"domain_scores_gemma":[0.99458003,0.0025745106,0.0010096454,0.001693479,0.00011537709,0.0000269538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088842347,0.00028475848,0.0021502413,0.00013864579,0.00010982257,0.000048334514,0.0008383213,0.00026743382,0.000010523813],"category_scores_gemma":[0.0072285887,0.00020475936,0.00012312242,0.00060995156,0.00016698414,0.000046284298,0.0005145343,0.00040143912,0.0000019399045],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.0143168e-8,0.00001901517,3.0726618e-8,0.47087237,0.000028200946,5.834811e-7,4.5182557e-7,2.1557884e-9,1.18217244e-7,0.06993457,0.00009989082,0.45904472],"study_design_scores_gemma":[0.000021615493,0.000022186996,9.26133e-9,0.7156589,0.0023373333,0.000025057981,0.000026479955,0.0003235488,0.000009454176,0.06833693,0.21300732,0.0002311376],"about_ca_topic_score_codex":0.000007136005,"about_ca_topic_score_gemma":6.1820026e-7,"teacher_disagreement_score":0.45881358,"about_ca_system_score_codex":0.000028262755,"about_ca_system_score_gemma":0.00012856886,"threshold_uncertainty_score":0.86538184},"labels":[],"label_agreement":null},{"id":"W3200559481","doi":"10.1108/dta-02-2021-0055","title":"Using the playful consumption experience model to uncover behavioral intention to play Multiplayer Online Battle Arena (MOBA) games","year":2021,"lang":"en","type":"article","venue":"Data Technologies and Applications","topic":"Technology Adoption and User Behaviour","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 Waterloo; Wilfrid Laurier University","funders":"","keywords":"Psychology; Escapism; Gratification; Pleasure; Social psychology; Test (biology); Originality; Structural equation modeling; Consumption (sociology); Applied psychology; Computer science; Creativity","score_opus":0.4263691920710254,"score_gpt":0.4811568638250117,"score_spread":0.0547876717539863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200559481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6990918,0.00012277414,0.29485875,0.0037813452,0.00006224912,0.00036522993,0.0013911462,0.0003199842,0.000006734131],"genre_scores_gemma":[0.9475492,0.000103652674,0.051327508,0.00031430004,0.000012117685,0.00024441374,0.00026714054,0.000010827152,0.00017083244],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980993,0.000027175469,0.00040896886,0.00084255915,0.00037897224,0.00024297724],"domain_scores_gemma":[0.99703926,0.00016920295,0.00012260447,0.00238205,0.0002216255,0.000065232074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030025793,0.00016001337,0.00018915608,0.00023009791,0.00041937677,0.00023544421,0.0016659498,0.00019240614,0.000044667377],"category_scores_gemma":[0.0006789019,0.00011462215,0.000035262005,0.0009577694,0.0002772851,0.00034407934,0.002195176,0.00025520576,0.000078469355],"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":[0.000057142337,0.0012088169,0.19829117,0.000010811774,0.000037188915,0.00001967659,0.0013494757,0.0044026054,0.101272,0.026390921,0.027854858,0.6391053],"study_design_scores_gemma":[0.0016536759,0.00021784572,0.15580997,0.00016744422,0.00026753586,0.00038776113,0.14388637,0.18419144,0.042592213,0.023849472,0.44489542,0.002080826],"about_ca_topic_score_codex":0.00004061529,"about_ca_topic_score_gemma":0.0004478191,"teacher_disagreement_score":0.6370245,"about_ca_system_score_codex":0.00003875064,"about_ca_system_score_gemma":0.000043337943,"threshold_uncertainty_score":0.46741557},"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":"W4406847525","doi":"10.1108/dta-08-2023-0461","title":"PyBibX – a Python library for bibliometric and scientometric analysis powered with artificial intelligence tools","year":2025,"lang":"en","type":"article","venue":"Data Technologies and Applications","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":35,"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":"Python (programming language); Computer science; Data science; Library science; Information retrieval; Operating system","score_opus":0.26719377436183595,"score_gpt":0.43531388107152375,"score_spread":0.1681201067096878,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406847525","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":[0.0122081535,0.0014561338,0.97841376,0.0041322103,0.000052479503,0.0007418699,0.0018876652,0.00046738895,0.00064036757],"genre_scores_gemma":[0.9184149,0.000794221,0.078588136,0.0001252752,0.000019400966,0.00029238415,0.0010174728,0.00000860683,0.00073962],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977834,0.000016632446,0.00039571576,0.0011797749,0.00040842136,0.00021602889],"domain_scores_gemma":[0.99560696,0.0014859438,0.00014923899,0.0026014133,0.00011604488,0.000040374933],"candidate_categories":["bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0017560442,0.00011054333,0.00022561292,0.049767062,0.0004460136,0.0022604149,0.0023284175,0.000059401045,0.000013007699],"category_scores_gemma":[0.0021868108,0.000076224635,0.000029938294,0.26913735,0.00038333726,0.0007162714,0.0029235114,0.00007612854,0.000008354261],"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":[0.000008773592,0.000040813113,0.0027030553,0.0000066673515,0.000048141046,2.7770525e-7,0.00000484348,0.00001784724,0.000006200319,0.06385104,0.010844524,0.9224678],"study_design_scores_gemma":[0.00011190746,0.000087884946,0.018579798,0.000014906721,0.00030219415,0.0000021896146,0.0049753604,0.05117306,0.00031813254,0.18014039,0.7440264,0.00026775536],"about_ca_topic_score_codex":0.000011047087,"about_ca_topic_score_gemma":0.000013908495,"teacher_disagreement_score":0.9222001,"about_ca_system_score_codex":0.0000071227846,"about_ca_system_score_gemma":0.00003827901,"threshold_uncertainty_score":0.99877536},"labels":[],"label_agreement":null},{"id":"W4408009686","doi":"10.1108/dta-12-2022-0477","title":"Research data management and FAIR compliance through popular research data repositories: an exploratory study","year":2025,"lang":"en","type":"article","venue":"Data Technologies and Applications","topic":"Research Data Management Practices","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Stephen's University","funders":"","keywords":"Compliance (psychology); Data management; Research data; Exploratory research; Data science; Computer science; World Wide Web; Internet privacy; Database; Data curation; Psychology; Sociology; Social science","score_opus":0.6078511899910557,"score_gpt":0.5405426048469305,"score_spread":0.06730858514412519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408009686","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":[0.0037343919,0.011050382,0.9176577,0.046013236,0.00018396467,0.009712439,0.004415707,0.0024180077,0.0048142215],"genre_scores_gemma":[0.4576792,0.06707183,0.4473183,0.00024236266,0.00023203644,0.0051879594,0.019136013,0.000073876035,0.0030584356],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941794,0.0004989455,0.00039215872,0.0032112435,0.0010744797,0.00064374454],"domain_scores_gemma":[0.96407264,0.0005155255,0.0000920883,0.035001077,0.00025106134,0.000067619505],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.009121058,0.00018149565,0.00021412628,0.0005474495,0.0017969747,0.004694194,0.038529743,0.000093789735,8.7488274e-7],"category_scores_gemma":[0.00085893326,0.00016818821,0.0000048324387,0.0034772982,0.0009264774,0.03081099,0.15793817,0.00087404036,0.000015405467],"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":[0.000010900289,0.00066676975,0.0013089984,0.00020646199,0.00012707771,0.00004012469,0.00013490181,6.636616e-7,0.000040920444,0.71401244,0.114006296,0.16944447],"study_design_scores_gemma":[0.00024597728,0.00011064946,0.0010014636,0.00005819583,0.000023049213,0.0000031740944,0.05122141,0.0064061694,0.00003125331,0.024444578,0.91626924,0.00018482129],"about_ca_topic_score_codex":0.00039556756,"about_ca_topic_score_gemma":0.00047393056,"teacher_disagreement_score":0.80226296,"about_ca_system_score_codex":0.00004924297,"about_ca_system_score_gemma":0.00008927816,"threshold_uncertainty_score":0.99950254},"labels":[],"label_agreement":null}]}