{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003775798,0.00005845807,0.00005378999,0.0000465042,0.0001159943,0.000231114,0.001561544,0.00002344794,0.000003771436],"category_scores_gemma":[0.0001113811,0.0000351065,0.00005063455,0.0002512709,0.0000241435,0.0003631751,0.0004341052,0.00005864692,0.00001253437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005454233,"about_ca_system_score_gemma":0.00008692344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001258716,"about_ca_topic_score_gemma":0.00002508516,"domain_scores_codex":[0.9993474,0.00001514313,0.0001350817,0.0002580094,0.0001119619,0.0001323294],"domain_scores_gemma":[0.9980136,0.0003655657,0.00003090634,0.001524189,0.00004238277,0.00002335749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003245306,0.00003626468,0.00001716664,0.00001510163,0.00002164534,2.403955e-7,0.00008337457,0.000006413617,0.003858621,0.8384181,0.0790481,0.07849171],"study_design_scores_gemma":[0.00004078363,0.0001110256,0.000311717,0.00005811803,0.000005036438,0.000004055425,0.000006202703,0.9291413,0.01166146,0.0264654,0.03211677,0.00007809738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001800237,0.0001656685,0.9941319,0.002472341,0.0001030784,0.0003312637,0.0001022078,0.0002900596,0.0006032711],"genre_scores_gemma":[0.9273086,0.00006486271,0.07217839,0.00008395921,0.0001084704,0.00005458497,0.0001160711,0.00000904364,0.00007607189],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9291349,"threshold_uncertainty_score":0.2901763,"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."}}