{"id":"W4413778076","doi":"10.1016/j.engappai.2025.112010","title":"A semi-supervised framework for generating multi-dimensional taxonomies from asset maintenance documents","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Asset (computer security); Information retrieval; Artificial intelligence; Data mining; Computer security","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":[0.0001712084,0.0001315011,0.0001632359,0.0001408926,0.0001668455,0.0001210266,0.0005086773,0.00008162929,0.000005151981],"category_scores_gemma":[0.0002020824,0.000140211,0.00006675215,0.000447255,0.0000497217,0.0002154023,0.00009400662,0.000137437,0.000009927662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003988059,"about_ca_system_score_gemma":0.00009078111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003910822,"about_ca_topic_score_gemma":0.000004309734,"domain_scores_codex":[0.9989305,0.00001054698,0.0004095361,0.0003597556,0.00009739157,0.0001922503],"domain_scores_gemma":[0.9989416,0.0003234059,0.000110226,0.0003931011,0.0001931747,0.00003848589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001033598,0.0001254515,0.00008012613,0.00009159061,0.00005929498,2.829208e-7,0.0002539474,0.1570031,0.03945355,0.2869136,0.0001445927,0.5158641],"study_design_scores_gemma":[0.0000263649,0.000008068348,0.0000231321,0.0001116401,0.000007556518,7.439907e-7,0.00004482124,0.8414388,0.1279502,0.02973625,0.0005375999,0.0001148926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005182606,0.0002456675,0.9934552,0.0002513507,0.0003659377,0.0003209343,0.00002014892,0.0001395883,0.00001852357],"genre_scores_gemma":[0.255054,0.00000624844,0.744453,0.00004255985,0.00006427839,0.0003127023,0.000008914581,0.000006393919,0.00005200116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6844357,"threshold_uncertainty_score":0.5717639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02093338350201118,"score_gpt":0.2834974543080583,"score_spread":0.2625640708060472,"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."}}