{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.002840619,0.0001299016,0.000181248,0.0002446605,0.00003763167,0.000878303,0.006953285,0.00003836358,0.00003702487],"category_scores_gemma":[0.0002605827,0.0000856429,0.00001804786,0.00006228959,0.0002031854,0.005016809,0.004950133,0.0003053885,0.0000158564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006238844,"about_ca_system_score_gemma":0.00008422874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001317708,"about_ca_topic_score_gemma":0.0006318319,"domain_scores_codex":[0.9983802,0.00009555829,0.000242043,0.0005776912,0.0005162965,0.000188155],"domain_scores_gemma":[0.9962038,0.0006221876,0.0001410002,0.002983767,0.00001958888,0.00002963385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004436372,0.000006109755,0.000005271557,0.00003487417,0.00002543832,0.00007991812,0.0006604985,4.902143e-8,0.000002727613,0.7514772,0.005761807,0.2419417],"study_design_scores_gemma":[0.0001063917,0.0000999637,0.0002661352,0.00007957857,0.000008821536,0.0000101899,0.00008716821,0.0008034828,9.786864e-7,0.05138846,0.9470186,0.0001302317],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0000157744,0.00005148687,0.07323571,0.001090418,0.0001446387,0.0002200296,0.00003748057,0.00001659628,0.9251879],"genre_scores_gemma":[0.003387421,0.005158465,0.08378876,0.001036708,0.0007900618,0.00001181431,0.0004755465,0.00004101561,0.9053102],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9412568,"threshold_uncertainty_score":0.9984196,"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."}}