{"id":"W2125590838","doi":"10.2481/dsj.4.106","title":"The long-term preservation of accurate and authentic digital data: the INTERPARES project","year":2005,"lang":"en","type":"article","venue":"Data Science Journal","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scope (computer science); Computer science; Usability; Transparency (behavior); Implementation; Metadata; Digital preservation; Open data; Data science; Reuse; World Wide Web; Data publishing; Electronic publishing; Publishing; Open science; Data curation; Political science; Software engineering; Engineering; The Internet; Computer security","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":[0.0006010377,0.00005217662,0.00004470365,0.00004623296,0.0008391248,0.003074821,0.002039686,0.000001990089,0.00001614487],"category_scores_gemma":[0.00009573165,0.00002337088,0.00001094142,0.00004708541,0.001239047,0.01115321,0.001179028,0.0000805684,0.000005583385],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007263287,"about_ca_system_score_gemma":0.00006701525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007380647,"about_ca_topic_score_gemma":0.00009935794,"domain_scores_codex":[0.9991996,0.00001087382,0.0001768641,0.0001483735,0.0003319795,0.0001322699],"domain_scores_gemma":[0.9992553,0.00008725054,0.000125036,0.0004563351,0.00004769373,0.00002840515],"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":[0.00005490146,0.0002129315,0.001634297,0.00003198324,0.00009267937,0.000006438699,0.009719093,0.00001263478,0.00002119266,0.4779778,0.03215406,0.478082],"study_design_scores_gemma":[0.0003588116,0.0001840977,0.1382102,0.0001682535,0.00005863684,0.0001176531,0.00351674,0.01732137,0.000018211,0.02022396,0.8195981,0.0002239937],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8409565,0.0004070523,0.0006918022,0.01452676,0.001101797,0.0006038491,0.004029919,0.00003146939,0.1376509],"genre_scores_gemma":[0.9984393,0.0001128123,0.00002406557,0.00006143337,0.0003057558,0.000001196558,0.0001831411,0.000002238743,0.0008701152],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7874441,"threshold_uncertainty_score":0.9979601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1383611772689184,"score_gpt":0.3153712717204733,"score_spread":0.1770100944515549,"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."}}