{"id":"W4386207778","doi":"10.1080/19386389.2023.2251857","title":"From Uncontrolled Keywords to FAST? Attempting Metadata Reconciliation for a Canadian Research Data Aggregator","year":2023,"lang":"en","type":"article","venue":"Journal of Library Metadata","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Metadata; Discoverability; Computer science; World Wide Web; Workflow; Subject (documents); Metadata repository; News aggregator; Service (business); Brainstorming; Information retrieval; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01569072,0.0002123888,0.0005398961,0.002183005,0.0004278281,0.01298478,0.01743144,0.00007848187,0.00008253157],"category_scores_gemma":[0.01242698,0.0001811708,0.0001081207,0.003392389,0.00004306277,0.2345672,0.006720659,0.0006410098,0.0001036767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001199442,"about_ca_system_score_gemma":0.002281118,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008351291,"about_ca_topic_score_gemma":0.005705931,"domain_scores_codex":[0.994114,0.001191852,0.001023824,0.0009391221,0.001789019,0.0009422305],"domain_scores_gemma":[0.989439,0.003979544,0.0006240039,0.004638733,0.0003667993,0.0009519038],"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":[0.0002053833,0.00004188542,0.0004118153,0.00003982207,0.0005823343,0.0003197309,0.0001757178,0.00007062285,0.00034892,0.006763101,0.9443644,0.04667624],"study_design_scores_gemma":[0.0009889754,0.000196683,0.0007862966,0.0001077966,0.00005691904,0.000009723741,0.000345276,0.01800166,0.0002693738,0.00179678,0.9772425,0.0001980631],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01689518,0.005627492,0.5879551,0.3680091,0.003727098,0.003525503,0.012324,0.0003023005,0.001634261],"genre_scores_gemma":[0.02142762,0.008637944,0.8910838,0.008814497,0.006653739,0.0001832531,0.01011285,0.000237213,0.05284902],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3591945,"threshold_uncertainty_score":0.9982522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4394956808097427,"score_gpt":0.4561766238239289,"score_spread":0.01668094301418621,"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."}}