{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003807776,0.001812111,0.0008574888,0.005651872,0.001148102,0.001706575,0.002670683,0.001562111,0.002325095],"category_scores_gemma":[0.01064171,0.0005875077,0.00169837,0.004201506,0.0008304684,0.003002143,0.001835473,0.002177485,0.002578687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001422443,"about_ca_system_score_gemma":0.002221655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00616542,"about_ca_topic_score_gemma":0.0154586,"domain_scores_codex":[0.9968425,0.001011234,0.0003473281,0.0009966583,0.0006573189,0.0001450127],"domain_scores_gemma":[0.9913231,0.004701853,0.0008724103,0.001021963,0.001830707,0.0002499603],"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":[0.0003695407,0.0006070289,0.006193593,0.0010679,0.0002568476,0.00045948,0.00175841,0.04761277,0.01977978,0.009842055,0.02765651,0.8843961],"study_design_scores_gemma":[0.00005601404,0.0001772413,0.002265059,0.0001130257,0.00006898333,0.0002612018,0.0005418247,0.9443088,0.008795933,0.02726797,0.01608994,0.00005419213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01191313,0.0002803919,0.9745201,0.0002569164,0.00006592385,0.0005322193,0.003104129,0.008372925,0.0009542599],"genre_scores_gemma":[0.09028237,0.0001422759,0.8929914,0.0001341301,0.00009173572,0.0009675248,0.01361008,0.0002702485,0.001510279],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00616542,"threshold_uncertainty_score":0.02013767,"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."}}