{"id":"W2110322986","doi":"10.1145/2078861.2078864","title":"A study of practical deduplication","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Storage","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":472,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Data deduplication; Backup; Computer file; Versioning file system; Database; Metadata; Operating system; File system; Journaling file system; Torrent file; Redundancy (engineering); Unix file types; Block (permutation group theory); Stub file","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":[0.008402991,0.0004716424,0.0004793516,0.002015965,0.0009261788,0.001257423,0.00133257,0.0005665778,0.0006816568],"category_scores_gemma":[0.07018141,0.0004047461,0.0003068864,0.00280376,0.001156633,0.002901182,0.000708422,0.0007868598,0.0001665108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00176311,"about_ca_system_score_gemma":0.0008710726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002417899,"about_ca_topic_score_gemma":0.003451248,"domain_scores_codex":[0.9932201,0.003170369,0.0005914083,0.0009969479,0.001684224,0.000336938],"domain_scores_gemma":[0.8600186,0.1111225,0.009345085,0.00853995,0.01005273,0.0009212191],"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":[0.001794028,0.00179563,0.559924,0.00165631,0.0004872513,0.00152121,0.005451429,0.117568,0.02766211,0.01352853,0.004664433,0.2639471],"study_design_scores_gemma":[0.0002571162,0.006874252,0.4772958,0.0003944696,0.0003204404,0.007589681,0.009591543,0.4191463,0.04707152,0.01306481,0.01817642,0.0002176207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924015,0.001052893,0.004472035,0.0002843181,0.00001473321,0.0001020837,0.0003032485,0.00005770761,0.001311344],"genre_scores_gemma":[0.9934181,0.0003273407,0.005608622,0.00003492953,0.00001767452,0.00004207214,0.000320626,0.00001895993,0.0002117306],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008402991,"threshold_uncertainty_score":0.04443979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06082571660711811,"score_gpt":0.3419166987417186,"score_spread":0.2810909821346005,"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."}}