{"id":"W4404788545","doi":"10.1145/3652892.3700766","title":"SeqCDC: Hashless Content-Defined Chunking for Data Deduplication","year":2024,"lang":"en","type":"article","venue":"","topic":"Cloud Data Security Solutions","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Data deduplication; Chunking (psychology); Computer science; Content (measure theory); Database; Artificial intelligence; Mathematics","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":[0.001550725,0.0006899797,0.0006218881,0.001283436,0.001106795,0.001491465,0.002034101,0.0007213472,0.007043667],"category_scores_gemma":[0.005475363,0.0003208025,0.0003237647,0.001228328,0.0008360572,0.001964654,0.00312831,0.0009762983,0.003766043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007607583,"about_ca_system_score_gemma":0.002257031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001673375,"about_ca_topic_score_gemma":0.00221004,"domain_scores_codex":[0.9988009,0.0001559594,0.0001426522,0.0001980906,0.0005588508,0.0001434934],"domain_scores_gemma":[0.9965802,0.0005905515,0.0001626646,0.001393471,0.001075234,0.0001978474],"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":[0.002645993,0.0003370498,0.004603804,0.001352513,0.0002051503,0.0008005673,0.0006958714,0.03388265,0.08918685,0.04525422,0.212349,0.6086863],"study_design_scores_gemma":[0.000610136,0.001059221,0.002451779,0.0002593805,0.0001113535,0.001726773,0.0004388609,0.3730031,0.2924704,0.04366732,0.2838851,0.0003165474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03295681,0.004083182,0.8922157,0.0007812987,0.001934461,0.001603836,0.005372849,0.04335644,0.01769543],"genre_scores_gemma":[0.5173709,0.001767425,0.4405249,0.00132982,0.0005650349,0.001148351,0.01271061,0.001977943,0.02260502],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007043667,"threshold_uncertainty_score":0.02356339,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2112468551892526,"score_gpt":0.3463124156165204,"score_spread":0.1350655604272678,"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."}}