{"id":"W2973161955","doi":"10.2218/ijdc.v14i1.586","title":"Identifying Topical Coverages of Curricula using Topic Modeling and Visualization Techniques: A Case of Digital and Data Curation","year":2019,"lang":"en","type":"article","venue":"International Journal of Digital Curation","topic":"Research Data Management Practices","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Digital curation; Data curation; Syllabus; Computer science; Curriculum; Data science; Context (archaeology); Latent Dirichlet allocation; Metadata; Topic model; Cyberinfrastructure; World Wide Web; Visualization; Data management; Information retrieval; Database; Data mining","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0003367566,0.00006719592,0.0001186157,0.0002486134,0.00002283277,0.00165511,0.0005412665,0.00002822644,0.000001624424],"category_scores_gemma":[0.0004584183,0.00006090117,0.00002292569,0.0001188986,0.00002689034,0.07877155,0.0005667176,0.00007351315,2.495846e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003252118,"about_ca_system_score_gemma":0.0000436296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001465585,"about_ca_topic_score_gemma":0.000001849106,"domain_scores_codex":[0.9987735,0.0000316191,0.0004748438,0.0001718243,0.0004851472,0.00006312236],"domain_scores_gemma":[0.9986635,0.00009495238,0.0005134094,0.0002121766,0.0004831581,0.00003281716],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003279164,0.0007914151,0.0653547,0.0006160922,0.0006415649,0.0005911177,0.002338649,0.006109726,0.03164278,0.5558839,0.0000614193,0.3356407],"study_design_scores_gemma":[0.000421362,0.0002146859,0.0002460505,0.0002780725,0.00002072057,0.001114478,0.0002847425,0.9883304,0.001602943,0.007180777,0.0001868608,0.0001189103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4344739,0.00004684924,0.5651111,0.0001157237,0.00009007021,0.00007097544,0.00001960134,0.000004349919,0.00006739702],"genre_scores_gemma":[0.9942589,0.0001382309,0.00548444,0.000007252337,0.00005625709,3.966422e-7,0.00003777726,0.000003657338,0.00001309721],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9822206,"threshold_uncertainty_score":0.9993812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1482718394189735,"score_gpt":0.4454172668164202,"score_spread":0.2971454273974466,"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."}}