{"id":"W2468483945","doi":"10.29173/cais166","title":"An Assessment of Metadata Quality: A Case Study of the National Science Digital Library Metadata Repository","year":2013,"lang":"fr","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Metadata; Library science; Computer science; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.002510033,0.0003362292,0.0007201164,0.0003413113,0.0004046926,0.01845097,0.009344147,0.00012099,0.00002322138],"category_scores_gemma":[0.004915819,0.0002209361,0.0002191483,0.002351315,0.002254646,0.3105162,0.003818457,0.0003278469,0.000001691884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005840074,"about_ca_system_score_gemma":0.002912818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001507982,"about_ca_topic_score_gemma":0.000006428302,"domain_scores_codex":[0.9943616,0.0001524876,0.001833457,0.0006037732,0.002571174,0.0004774799],"domain_scores_gemma":[0.9563994,0.0002842976,0.003355301,0.0009000609,0.03881051,0.0002504688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003719482,0.002228876,0.6851281,0.001105631,0.0003370357,0.000006941872,0.1289536,0.00006587937,0.02382745,0.1489091,0.004171908,0.005228311],"study_design_scores_gemma":[0.001945465,0.00288266,0.6766912,0.00135855,0.0001959015,0.001618634,0.1390934,0.0428553,0.1101059,0.006391095,0.01565528,0.001206586],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879122,0.0001239739,0.0002023255,0.002119216,0.0005649453,0.001009537,0.0006065149,0.00002809628,0.007433164],"genre_scores_gemma":[0.99686,0.00001460491,0.0012283,0.0002154189,0.00008020391,0.00003284376,0.000004286332,0.00001259842,0.001551697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2920653,"threshold_uncertainty_score":0.9960158,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06358546659706449,"score_gpt":0.3194996839236473,"score_spread":0.2559142173265828,"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."}}