{"id":"W2585172182","doi":"10.5555/1960475.1960476","title":"A study of practical deduplication","year":2011,"lang":"en","type":"article","venue":"File and Storage Technologies","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":193,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data deduplication; Computer science; Backup; Computer file; Database; Metadata; Versioning file system; Operating system; File system; Redundancy (engineering); Torrent file; Journaling file system","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":[],"consensus_categories":[],"category_scores_codex":[0.008042281,0.0004262156,0.0004441436,0.001985553,0.0008716874,0.001187486,0.001156131,0.0005109147,0.0006728041],"category_scores_gemma":[0.06441621,0.0003497087,0.000294789,0.002688466,0.001037249,0.002517774,0.0006468376,0.0007120727,0.000167511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001631247,"about_ca_system_score_gemma":0.0007907999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002174333,"about_ca_topic_score_gemma":0.003201759,"domain_scores_codex":[0.9936255,0.00301485,0.0005657,0.0008852793,0.00161708,0.0002915835],"domain_scores_gemma":[0.8651387,0.1069835,0.009066306,0.007911202,0.01002547,0.0008748],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001686976,0.001783773,0.5765004,0.001514166,0.0004667397,0.001389927,0.005140923,0.09715451,0.02534457,0.01258722,0.004140757,0.2722902],"study_design_scores_gemma":[0.0002478691,0.007880242,0.5346584,0.0003886483,0.000322903,0.007851092,0.009398248,0.3584636,0.04982452,0.01200396,0.01874346,0.0002170163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9929568,0.0009423246,0.004113819,0.0002392944,0.00001330798,0.00009964161,0.0002836363,0.00005108788,0.001300229],"genre_scores_gemma":[0.9935799,0.0003240838,0.00544771,0.00003183978,0.00001699553,0.00004121241,0.0003178958,0.00001706318,0.000223435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008042281,"threshold_uncertainty_score":0.04253215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05731833433081558,"score_gpt":0.2888952090245492,"score_spread":0.2315768746937337,"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."}}