{"id":"W2794631061","doi":"10.1108/s0065-28302018000044b010","title":"Archival Records and Training in the Age of Big Data","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Research Data Management Practices","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cyberinfrastructure; Archival science; Analytics; Computer science; Data science; Digital humanities; Big data; World Wide Web; Library science; Data mining","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05466083,0.000305519,0.0005956281,0.004087253,0.01160188,0.02059957,0.003257505,0.003944225,0.0147002],"category_scores_gemma":[0.1054466,0.0005870479,0.0004707187,0.006503764,0.0307189,0.04160068,0.02053103,0.009359387,0.002425652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007299035,"about_ca_system_score_gemma":0.01543848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003712198,"about_ca_topic_score_gemma":0.005835552,"domain_scores_codex":[0.9667435,0.02229874,0.001640248,0.001945569,0.005655595,0.001716354],"domain_scores_gemma":[0.8177026,0.1256323,0.007819063,0.02795878,0.0116799,0.009207333],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001029077,0.0002621968,0.007230729,0.001228562,0.00003216737,0.0003843982,0.2422759,0.0007997309,0.0006296585,0.3720171,0.07064805,0.3043886],"study_design_scores_gemma":[0.00002015786,0.0001001748,0.003849266,0.00309977,0.00001333556,0.000396393,0.2061782,0.001199506,0.001526296,0.2059628,0.5775811,0.00007291288],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.1561385,0.01440076,0.0600565,0.6027844,0.003025324,0.0003989374,0.0006537643,0.0008050383,0.1617368],"genre_scores_gemma":[0.8685187,0.01393979,0.06184278,0.02247205,0.001336557,0.0003881479,0.0005182747,0.0005092309,0.03047448],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9453391,"threshold_uncertainty_score":0.2890775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4102439094970225,"score_gpt":0.3841935006342329,"score_spread":0.02605040886278959,"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."}}