{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005833763,0.0006073044,0.000627386,0.005969229,0.001032129,0.005660858,0.001937169,0.001037003,0.00705408],"category_scores_gemma":[0.0322637,0.0004263367,0.0005354158,0.004095333,0.001426457,0.00932448,0.00431671,0.001539667,0.002723031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000904227,"about_ca_system_score_gemma":0.001147836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001826977,"about_ca_topic_score_gemma":0.003689213,"domain_scores_codex":[0.996815,0.001194709,0.0002402242,0.0005503679,0.001062749,0.0001368986],"domain_scores_gemma":[0.9758567,0.01689153,0.001445793,0.00354022,0.001942821,0.0003228794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001125371,0.0003228734,0.007006909,0.0008960687,0.00006424409,0.0002772936,0.005618543,0.00559072,0.007297834,0.01436927,0.007320691,0.951123],"study_design_scores_gemma":[0.0001388096,0.0007407955,0.02671313,0.002898675,0.0003231383,0.002778938,0.01343272,0.2312768,0.06949227,0.2101268,0.4416464,0.000431482],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1009653,0.002780575,0.8196317,0.003795093,0.0002127611,0.0005546007,0.0008693176,0.01365965,0.05753107],"genre_scores_gemma":[0.3171586,0.001749788,0.6709743,0.0004821702,0.0001763101,0.0002456606,0.0009315202,0.0005207138,0.007760944],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00705408,"threshold_uncertainty_score":0.03085226,"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."}}