{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.01062354,0.00009537597,0.0001333474,0.0002271129,0.001119924,0.01254067,0.02429402,0.00002880946,0.00004057751],"category_scores_gemma":[0.01304811,0.00008484009,0.000007722456,0.001633226,0.0000990255,0.03488038,0.07109956,0.0003122772,0.00003799897],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008975921,"about_ca_system_score_gemma":0.00005211723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006159472,"about_ca_topic_score_gemma":0.0001722918,"domain_scores_codex":[0.9966494,0.001133234,0.0004429272,0.0008640884,0.0006173464,0.0002929844],"domain_scores_gemma":[0.9953761,0.0004554144,0.0001665014,0.003461593,0.0004955169,0.00004488146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001285199,0.0006046872,0.0002925563,0.0005858517,0.0001173952,0.00004267008,0.001943646,0.0001967454,0.0007790775,0.5492735,0.06426606,0.3817693],"study_design_scores_gemma":[0.0004349075,0.00003783497,0.008148571,0.0001727235,0.000003248187,0.00000850659,0.00113836,0.09241522,0.00005472277,0.0006860181,0.8967904,0.0001095165],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005713464,0.001736494,0.1509712,0.06993111,0.00050392,0.003372829,0.001275585,0.0005071397,0.7659882],"genre_scores_gemma":[0.9729462,0.003659587,0.01405213,0.0004277588,0.0001444288,6.823227e-7,0.00518272,0.0004425973,0.003143893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9672328,"threshold_uncertainty_score":0.9952654,"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."}}