{"id":"W4414616358","doi":"10.69554/bjvr8050","title":"Utilising machine-learning tools to increase access to archival collections","year":2025,"lang":"en","type":"article","venue":"Journal of digital media management","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Archivist; Metadata; Discoverability; Usability; Relevance (law); Archival science","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0001567905,0.0001748369,0.0002422723,0.001080106,0.0003110598,0.003176481,0.0005049387,0.000006250955,0.00009901072],"category_scores_gemma":[0.0001926816,0.0001477677,0.0001669377,0.0003164471,0.00006207475,0.001440188,0.0005119932,0.0001732006,0.00007002598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008064914,"about_ca_system_score_gemma":0.00003124629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000152154,"about_ca_topic_score_gemma":0.00003369556,"domain_scores_codex":[0.9985818,0.00002612381,0.0005016844,0.0001900199,0.0004399413,0.0002604545],"domain_scores_gemma":[0.9991584,0.000229582,0.0001341943,0.0001301714,0.0001063429,0.0002412467],"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":[0.0003296795,0.0005388387,0.0001836072,0.0001188598,0.0005677656,0.0001961449,0.002572044,0.001390091,0.000002824477,0.5953553,0.07577122,0.3229736],"study_design_scores_gemma":[0.0005271272,0.0003026922,0.007917604,0.0003737686,0.0001131984,0.000007622824,0.001250732,0.00006823819,0.00001397578,0.05397674,0.9352212,0.0002270929],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.030642,0.00001513928,0.002595369,0.003970284,0.001083522,0.000388325,0.0001172688,0.00004300681,0.9611451],"genre_scores_gemma":[0.9627823,0.00001642326,0.0004194532,0.001497677,0.0003826405,0.00002235424,0.00003129625,0.00001570181,0.03483212],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9321404,"threshold_uncertainty_score":0.9978583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0416562147117167,"score_gpt":0.2565219195807883,"score_spread":0.2148657048690716,"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."}}