{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003763084,0.00008795317,0.00008826841,0.00007281818,0.0001306672,0.0005321247,0.001848583,0.00004049169,0.00001709594],"category_scores_gemma":[0.0001483062,0.00008110383,0.00003626926,0.0003371831,0.00002523108,0.001033608,0.0009271373,0.00007205641,0.0001358573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004317298,"about_ca_system_score_gemma":0.00009527374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001420997,"about_ca_topic_score_gemma":0.0002146667,"domain_scores_codex":[0.9988579,0.000015677,0.0001829383,0.0005790128,0.0001447707,0.0002197117],"domain_scores_gemma":[0.9978751,0.0002512427,0.00002491123,0.001722253,0.0000677836,0.00005869272],"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":[8.759777e-7,0.00002238359,0.00002945201,0.00002933791,0.00001676674,0.000001332485,0.000140819,0.000001533665,0.001678747,0.8992282,0.07264528,0.02620533],"study_design_scores_gemma":[0.0001148381,0.00001158116,0.0002036384,0.00002600739,0.00001096255,0.00001282158,0.00001760144,0.7923739,0.0003885689,0.007338839,0.1993871,0.0001141622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008496523,0.0004046199,0.9800414,0.01635017,0.0005673831,0.0003058618,0.0001938343,0.000627384,0.0006596855],"genre_scores_gemma":[0.4402245,0.00002177238,0.5549859,0.001586472,0.0003091362,0.0001498152,0.001178076,0.00002646015,0.001517835],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8918893,"threshold_uncertainty_score":0.5131291,"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."}}