{"id":"W2746538584","doi":"10.3897/tdwgproceedings.1.20380","title":"Using YesWorkflow hybrid queries to reveal data lineage from data curation activities","year":2017,"lang":"en","type":"article","venue":"Biodiversity Information Science and Standards","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"National Science Foundation","keywords":"Workflow; Computer science; Scripting language; Metadata; Python (programming language); Database; Annotation; World Wide Web; Information retrieval; Programming language","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","sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.01712209,0.0001067914,0.0001627267,0.0003896274,0.003853955,0.009045216,0.005951644,0.00002431403,0.00006780658],"category_scores_gemma":[0.01434715,0.00008722829,0.00001483119,0.0004516448,0.000740952,0.03504067,0.009612289,0.00007078123,0.0001179551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001334898,"about_ca_system_score_gemma":0.0005945378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006836758,"about_ca_topic_score_gemma":0.0001222792,"domain_scores_codex":[0.9943637,0.00004080632,0.0003708297,0.0006514338,0.004337118,0.0002361129],"domain_scores_gemma":[0.9936554,0.0001455095,0.0003972743,0.004443221,0.00118241,0.0001761576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009498465,0.00001674792,0.008801249,0.000007146535,0.00001214626,0.000004000313,0.003266192,0.0001738452,0.0001024234,0.0002102047,0.6991105,0.2882006],"study_design_scores_gemma":[0.0003510099,0.000032639,0.01697564,0.00002783478,0.00002074636,0.000002855764,0.006573059,0.1254636,0.0003985157,0.0001611792,0.8497334,0.0002595666],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7908955,0.00001535612,0.1469001,0.002298778,0.002153478,0.0002898531,0.05426662,0.00005830649,0.003122046],"genre_scores_gemma":[0.9871131,0.0000170103,0.01134434,0.0005875988,0.00008451873,4.224705e-7,0.0007855191,0.000001019207,0.00006646136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.287941,"threshold_uncertainty_score":0.9994266,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3728313323745507,"score_gpt":0.4466233665384567,"score_spread":0.073792034163906,"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."}}