{"id":"W4320924434","doi":"10.1007/978-3-031-25448-2_54","title":"Improving Maintenance Data Quality: Application of Natural Language Processing to Asset Management","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in mechanical engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hydro-Québec; Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Asset (computer security); Asset management; Quality (philosophy); Data quality; Business; Computer security; Finance; Marketing","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004281417,0.0003475395,0.0006595826,0.0005799218,0.00003776128,0.0001486421,0.002429619,0.0002366145,0.00002539657],"category_scores_gemma":[0.003764671,0.0003008645,0.00009760494,0.0004845187,0.00002129345,0.0002214264,0.002373048,0.0006026912,0.00009645387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001153867,"about_ca_system_score_gemma":0.00002392956,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007846345,"about_ca_topic_score_gemma":0.0003608873,"domain_scores_codex":[0.9958477,0.000040235,0.001165595,0.001178544,0.001390586,0.000377353],"domain_scores_gemma":[0.9964111,0.0009069178,0.000389033,0.002101668,0.00009808811,0.00009321194],"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":[0.00002539015,0.00001433525,7.288858e-7,0.0005383627,0.0000416726,0.0000328101,0.0001197987,0.01027949,0.001707119,0.09219643,0.0001850354,0.8948588],"study_design_scores_gemma":[0.0006963701,0.00007899263,0.0001034228,0.001705703,0.0001342945,0.000006406281,0.0001759498,0.8563392,0.00122736,0.07437769,0.06365588,0.001498801],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00003120731,0.0002812998,0.9959897,0.0005843583,0.0004444844,0.0006788787,0.0002430267,0.0001514172,0.00159566],"genre_scores_gemma":[0.7637233,0.0001079832,0.2040686,0.001842844,0.0007547079,0.0001882719,0.001843654,0.0003762203,0.02709441],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.89336,"threshold_uncertainty_score":0.9999443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07670199170063244,"score_gpt":0.3735223383615675,"score_spread":0.296820346660935,"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."}}