{"id":"W4411328365","doi":"10.1080/15228886.2025.2518369","title":"Using AI Tools for Slavic Transliteration to Support Cataloging Workflows: Potential Use Cases and Limitations","year":2025,"lang":"en","type":"article","venue":"Slavic & East European Information Resources","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Transliteration; Cataloging; Workflow; Slavic languages; Computer science; World Wide Web; Information retrieval; Natural language processing; Linguistics; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"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":[0.0004005324,0.0001698281,0.0001361648,0.0004741109,0.0004388216,0.002781804,0.0004140891,0.00004442391,0.000002017955],"category_scores_gemma":[0.000832866,0.0001618667,0.00005582014,0.000523167,0.00003984942,0.005693891,0.0001287211,0.0001204481,0.0000122674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004793962,"about_ca_system_score_gemma":0.00006493367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002324748,"about_ca_topic_score_gemma":0.0000127644,"domain_scores_codex":[0.998806,0.00009320295,0.0004467717,0.0002249648,0.0001892642,0.0002397724],"domain_scores_gemma":[0.9989733,0.0002596105,0.000141031,0.0002895001,0.0002437204,0.00009282606],"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":[0.00007329858,0.0000425128,0.0002780694,0.0002041741,0.0000381237,0.0000268004,0.02953815,0.002007103,0.001971912,0.01527549,0.001845262,0.9486991],"study_design_scores_gemma":[0.004652034,0.00154574,0.01203763,0.002337285,0.0003675912,0.0008732031,0.006379226,0.2788062,0.007784976,0.00599075,0.6759496,0.003275755],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07035828,0.0001547724,0.9266323,0.001142446,0.0001316168,0.0005390902,0.00003468447,0.0004598759,0.0005469336],"genre_scores_gemma":[0.7500355,0.000004611195,0.2467006,0.002997372,0.00003814662,0.00002148444,0.000101366,0.000008881354,0.00009209964],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9454234,"threshold_uncertainty_score":0.9982534,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04921929063986303,"score_gpt":0.297691071386127,"score_spread":0.248471780746264,"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."}}