{"id":"W4317602988","doi":"10.1007/s10502-023-09408-8","title":"Archivist in the machine: paradata for AI-based automation in the archives","year":2023,"lang":"en","type":"article","venue":"Archival Science","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Documentation; Archivist; Data science; Artificial intelligence; Multimedia; Library science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.002147554,0.0000697841,0.00008470223,0.0002838964,0.0002740661,0.0000595992,0.0005288611,0.000008775554,0.000002335382],"category_scores_gemma":[0.0008625757,0.00003895513,0.00003550979,0.00124768,0.00042375,0.0001076687,0.00002790735,0.0002043856,0.00002670701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002288528,"about_ca_system_score_gemma":0.000414237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006620745,"about_ca_topic_score_gemma":0.0004442107,"domain_scores_codex":[0.9986591,0.0001362616,0.0002439882,0.000238279,0.0003645117,0.0003579135],"domain_scores_gemma":[0.9978588,0.00167972,0.00003847785,0.0003597856,0.00001535803,0.00004788726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002572959,0.0003998554,0.1042486,0.0001887637,0.000002672014,0.00002399606,0.0539955,0.001285019,0.00524768,0.03579661,0.001869819,0.7966841],"study_design_scores_gemma":[0.00006030966,0.0001475539,0.7680022,0.00006793512,0.000003849701,0.00000866656,0.001447317,0.1893258,0.0009077329,0.03876096,0.001208817,0.00005880176],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9173035,0.00001007006,0.004019799,0.07513004,0.0001628553,0.001011538,0.00001067389,0.00003654374,0.002314959],"genre_scores_gemma":[0.9953859,0.00001280647,0.0007854607,0.00345603,0.00009600758,0.0001688294,0.0000574301,0.00000437964,0.0000331767],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7966254,"threshold_uncertainty_score":0.2107922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1932326004149269,"score_gpt":0.4808470610267683,"score_spread":0.2876144606118414,"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."}}