{"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,"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","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002161196,0.0001378097,0.0002443509,0.000174254,0.0001661236,0.007993273,0.002237656,0.00006186411,0.0002141402],"category_scores_gemma":[0.007950504,0.0001119978,0.00009556126,0.0003529169,0.000113494,0.0120503,0.001936166,0.0003088012,0.000120963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007694055,"about_ca_system_score_gemma":0.0002308036,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003336521,"about_ca_topic_score_gemma":0.00009093128,"domain_scores_codex":[0.9956418,0.000251455,0.001135609,0.0005413893,0.002186815,0.000242884],"domain_scores_gemma":[0.9971104,0.0009951978,0.0004939765,0.0008815677,0.0004321226,0.00008679413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008726743,0.001160201,0.0394472,0.00001517691,0.0002323454,0.001468677,0.003464002,0.0003116721,0.0001522557,0.7396085,0.1297334,0.08353385],"study_design_scores_gemma":[0.0006784792,0.00004429807,0.01555593,0.00006167451,0.000004462988,0.0001023477,0.00438292,0.000689899,0.0006395709,0.07895861,0.8986949,0.0001869363],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3167973,0.002794235,0.2636025,0.09106276,0.02494401,0.0005076742,0.01057187,0.0003076143,0.2894121],"genre_scores_gemma":[0.9784673,0.0001369116,0.005389538,0.003684867,0.001434701,0.000004193125,0.001104832,0.00002029587,0.009757346],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7689615,"threshold_uncertainty_score":0.9930365,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2067003591168642,"score_gpt":0.4259471446766152,"score_spread":0.219246785559751,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}