{"id":"W4300945279","doi":"10.7287/peerj.preprints.1448v2","title":"Ten simple rules for digital data storage","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Western University","funders":"","keywords":"Petabyte; Pace; Computer science; Data sharing; Data science; Computer data storage; Data collection; Currency; Digital data; Database; Data mining; Data transmission; Big data; Geography","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","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.006344113,0.0002418744,0.0003867534,0.0003277181,0.0001936313,0.004599313,0.009035353,0.0001095871,0.0007833877],"category_scores_gemma":[0.007738445,0.0001370634,0.0001590925,0.0001829021,0.0001108493,0.0006764843,0.0255188,0.0001255993,0.001758289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003670181,"about_ca_system_score_gemma":0.0001344101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000265215,"about_ca_topic_score_gemma":0.00002174725,"domain_scores_codex":[0.9947839,0.00005336897,0.000780853,0.002442047,0.001556434,0.0003834055],"domain_scores_gemma":[0.9880859,0.002142128,0.0003653427,0.008966242,0.0002939281,0.0001464734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006249828,0.00002484463,0.000227561,0.000008498382,0.00001918288,0.000001725741,0.00001747162,0.00004266563,9.132443e-7,0.001892006,0.7437876,0.2539713],"study_design_scores_gemma":[0.0001499649,0.00001055173,0.0005035203,0.00002291841,0.00001148455,6.462146e-7,0.0001306801,0.02766777,0.000003415855,0.2374004,0.7338851,0.000213587],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004563497,0.00006646918,0.9136393,0.002259186,0.004134896,0.0006833362,0.0194828,0.0002178469,0.05495268],"genre_scores_gemma":[0.6541033,0.00001157966,0.03748824,0.0007246951,0.002358976,0.00008667103,0.01591389,0.00008236586,0.2892302],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.876151,"threshold_uncertainty_score":0.999019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3370885306356489,"score_gpt":0.4442283729626144,"score_spread":0.1071398423269654,"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."}}