{"id":"W3027407410","doi":"10.1108/rmj-09-2019-0055","title":"Natural language processing and machine learning as practical toolsets for archival processing","year":2020,"lang":"en","type":"article","venue":"Records Management Journal","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Workflow; Artificial intelligence; Computer science; Machine learning; Implementation; Interoperability; USable; Natural language processing; Originality; Software engineering; Database; World Wide Web","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":[0.003644425,0.000206251,0.0003121591,0.0002317632,0.0006672253,0.002225462,0.0005468421,0.00003150825,0.0001365922],"category_scores_gemma":[0.002644413,0.0001562892,0.0001096582,0.0004127052,0.00007160268,0.001306865,0.0005400683,0.0005811941,0.00006499424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003692517,"about_ca_system_score_gemma":0.00005710226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005315168,"about_ca_topic_score_gemma":0.000005692501,"domain_scores_codex":[0.9968684,0.0002756636,0.00070416,0.0005451378,0.001185383,0.0004212474],"domain_scores_gemma":[0.9985427,0.0003588313,0.0005202235,0.0001703333,0.000128519,0.0002794536],"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":[0.0002661269,0.00004857598,0.0003650838,0.0001757201,0.00005030523,0.0001667946,0.001446404,0.00003551192,0.0000412975,0.002552994,0.008066369,0.9867848],"study_design_scores_gemma":[0.002957636,0.0007704983,0.003116479,0.0002787467,0.0002656212,0.0003363569,0.02094398,0.2236353,0.00006814349,0.0432634,0.7035859,0.0007779321],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06128354,0.004252434,0.7740122,0.08171159,0.001204507,0.002015748,0.00004105868,0.0003486263,0.07513027],"genre_scores_gemma":[0.9330345,0.0002434759,0.0558437,0.004509829,0.0006453341,0.0000211487,0.00002683833,0.00003427298,0.005640829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9860069,"threshold_uncertainty_score":0.9988104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1476724865815801,"score_gpt":0.4358033820896567,"score_spread":0.2881308955080766,"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."}}