{"id":"W6968326971","doi":"10.5281/zenodo.15758545","title":"The Utility of PIDs in Harvesting Open Data Repositories: Challenges in Operating a National Data Discovery Service","year":2025,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Dementia Research Alliance","funders":"","keywords":"Metadata; Identifier; Service (business); Service discovery; Data element; Linked data; Open data; Discoverability; Metadata modeling; Interoperability","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.1013892,0.0005319925,0.0009316906,0.004750892,0.01161558,0.02501931,0.008176807,0.00297931,0.003731449],"category_scores_gemma":[0.1181889,0.001373091,0.00140821,0.01267731,0.009123034,0.0317426,0.0170516,0.00563554,0.002657761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01714137,"about_ca_system_score_gemma":0.04994153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1459024,"about_ca_topic_score_gemma":0.1687119,"domain_scores_codex":[0.9422628,0.01381257,0.006585127,0.00446089,0.02887991,0.003998646],"domain_scores_gemma":[0.8142982,0.03619859,0.007305157,0.08758588,0.04708977,0.007522384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004648316,0.0003716097,0.03571881,0.001075957,0.00012969,0.001068265,0.02062973,0.005988686,0.009990629,0.3357356,0.07880646,0.5100197],"study_design_scores_gemma":[0.0001343517,0.0002882302,0.01293658,0.00107286,0.0001306333,0.0020536,0.02247581,0.02921054,0.02455562,0.1290089,0.7775888,0.0005441316],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0650764,0.00196503,0.778179,0.06579003,0.001125858,0.001661308,0.002122966,0.0158262,0.06825321],"genre_scores_gemma":[0.1561972,0.001526132,0.8136709,0.003738307,0.000254008,0.000653193,0.002706421,0.002583842,0.01866997],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9918232,"threshold_uncertainty_score":0.5362036,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.351872800780642,"score_gpt":0.3930437049634108,"score_spread":0.04117090418276875,"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."}}