{"id":"W2795677445","doi":"10.1080/01639374.2018.1438551","title":"Dealing with False Friends to Avoid Errors in Subject Analysis in Slavic Cataloging: An Overview of Resources and Strategies","year":2018,"lang":"en","type":"article","venue":"Cataloging & Classification Quarterly","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Cataloging; Slavic languages; Subject (documents); Workflow; Computer science; World Wide Web; Linguistics; Meaning (existential); Psychology; 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":[],"consensus_categories":[],"category_scores_codex":[0.000748368,0.0001958812,0.0003334619,0.001082729,0.00009092056,0.0002524065,0.0007359934,0.00009781073,0.000001874016],"category_scores_gemma":[0.00003325588,0.0001695036,0.00003115682,0.002390454,0.0001751532,0.001072589,0.0000511836,0.0001950562,0.000002468108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007210932,"about_ca_system_score_gemma":0.00007538139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001342158,"about_ca_topic_score_gemma":0.007166953,"domain_scores_codex":[0.9982491,0.0001356484,0.0004376506,0.0006435222,0.0002453813,0.0002886769],"domain_scores_gemma":[0.9987143,0.00008591387,0.0002455914,0.00072538,0.0001376114,0.00009119973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002280812,0.0004873412,0.1434012,0.0006187239,0.0002135982,0.0001158709,0.2318029,0.0003354021,0.106931,0.2773138,0.00002590286,0.2385262],"study_design_scores_gemma":[0.001489866,0.004372508,0.8007871,0.001401233,0.0002705621,0.00007769915,0.04173086,0.08505125,0.02322756,0.03894598,0.0003446236,0.002300791],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8957847,0.001088488,0.1023495,0.0003001714,0.00002172684,0.0001788463,0.000007582501,0.0002067995,0.00006216407],"genre_scores_gemma":[0.9413083,0.000009423296,0.05851579,0.00006457341,0.00001551653,0.00002884063,0.00004163844,0.00001111164,0.000004832086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6573859,"threshold_uncertainty_score":0.6912155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04421775578432104,"score_gpt":0.3324192626887967,"score_spread":0.2882015069044757,"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."}}