{"id":"W2207671015","doi":"10.1055/s-0038-1638748","title":"Key Concepts to Assess the Readiness of Data for International Research: Data Quality, Lineage and Provenance, Extraction and Processing Errors, Traceability, and Curation","year":2011,"lang":"en","type":"article","venue":"Yearbook of Medical Informatics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":48,"is_retracted":false,"has_abstract":true,"ca_institutions":"Algoma University; Esri (Canada)","funders":"Directorate-General for Information Society and Media; European Commission","keywords":"Metadata; Computer science; Data quality; Data science; Data curation; Metadata repository; Data warehouse; Traceability; Data extraction; Information retrieval; Data element; Database; World Wide Web; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02872652,0.00005720144,0.0001567532,0.0001293178,0.0001023424,0.0002046893,0.001657325,0.0000495034,0.00002099953],"category_scores_gemma":[0.01619265,0.000035268,0.00000761537,0.0002302223,0.0004987241,0.00152248,0.002506461,0.0001267795,0.000001201318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006427063,"about_ca_system_score_gemma":0.0001087933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006653494,"about_ca_topic_score_gemma":0.00007162452,"domain_scores_codex":[0.996799,0.0001238294,0.000850208,0.0002613523,0.001851278,0.0001143438],"domain_scores_gemma":[0.9964468,0.001554827,0.0003456744,0.001056399,0.0005005477,0.00009575216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001373334,0.0001865297,0.003411078,0.0005221889,0.00003092294,6.988435e-7,0.01743882,0.000005837673,0.00005720524,0.01248452,0.04888732,0.9168375],"study_design_scores_gemma":[0.0007493138,0.0001377698,0.01554105,0.0003751873,0.0000233393,0.000008204738,0.01910456,0.8701441,0.0001984728,0.006830948,0.08674761,0.0001394361],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4996351,0.0002514053,0.4857316,0.005676058,0.001021455,0.001838109,0.0009464913,0.00004160436,0.004858143],"genre_scores_gemma":[0.9408955,0.0000717476,0.05839094,0.0001299788,0.0001152102,0.00001020496,0.0001754086,0.000005112038,0.0002059047],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9166981,"threshold_uncertainty_score":0.9956096,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8142543360737813,"score_gpt":0.6175428778911553,"score_spread":0.196711458182626,"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."}}