{"id":"W4401943323","doi":"10.1109/cloud62652.2024.00025","title":"The Impact of Low-Entropy on Chunking Techniques for Data Deduplication","year":2024,"lang":"en","type":"article","venue":"","topic":"Cloud Data Security Solutions","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data deduplication; Computer science; Chunking (psychology); Entropy (arrow of time); Data mining; Artificial intelligence; Database","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":[0.003638558,0.00072804,0.000516448,0.001292464,0.0008232861,0.001474865,0.001139451,0.0004954495,0.0007282509],"category_scores_gemma":[0.02696471,0.0002608964,0.0002730893,0.0009972759,0.001012456,0.003009822,0.001453827,0.0006968005,0.0002473166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007329446,"about_ca_system_score_gemma":0.001046064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008929402,"about_ca_topic_score_gemma":0.001421559,"domain_scores_codex":[0.9971033,0.0007083198,0.0004003308,0.0003988751,0.001152633,0.0002365927],"domain_scores_gemma":[0.9677612,0.02209031,0.002603819,0.004258238,0.002825988,0.0004604911],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005061489,0.0006936535,0.0682797,0.00141613,0.000381143,0.0009809613,0.001285979,0.1602046,0.1963993,0.007048118,0.004109167,0.5541399],"study_design_scores_gemma":[0.0001769993,0.00286035,0.03101424,0.0002749449,0.0002217222,0.00175304,0.000967201,0.4784423,0.4706052,0.005900046,0.00761817,0.0001658127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8665679,0.007478936,0.1187957,0.0005068769,0.0003404955,0.0003716593,0.0004006825,0.002553311,0.002984463],"genre_scores_gemma":[0.9494375,0.0005870071,0.0490406,0.00008851872,0.00005863344,0.00005230007,0.0002507343,0.00009528297,0.0003894913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003638558,"threshold_uncertainty_score":0.0192427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04545354339114876,"score_gpt":0.3668004443069457,"score_spread":0.321346900915797,"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."}}