{"id":"W4318148204","doi":"10.1109/bigdata55660.2022.10020871","title":"Predicting Deduplication Performance: An Analytical Model and Empirical Evaluation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Data deduplication; Computer science; Data mining; Software versioning; Kernel (algebra); Database; Software; Operating system","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":[0.005261728,0.00243712,0.001340329,0.002538593,0.0008354508,0.002308005,0.002598772,0.002269363,0.001273411],"category_scores_gemma":[0.0354397,0.0009677552,0.0008685465,0.003184803,0.00114926,0.004590977,0.001050563,0.002639818,0.001201887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003419048,"about_ca_system_score_gemma":0.002290427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01831678,"about_ca_topic_score_gemma":0.01292454,"domain_scores_codex":[0.9972665,0.000566824,0.0001925051,0.0007603342,0.0008203724,0.0003934156],"domain_scores_gemma":[0.9695179,0.02132299,0.001875607,0.002342374,0.004431116,0.0005100341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000428867,0.0006129332,0.02592646,0.0003909711,0.0000989893,0.0001636365,0.000200661,0.9233492,0.003610071,0.002394123,0.006268713,0.03655542],"study_design_scores_gemma":[0.000008198243,0.00005717379,0.001195128,0.0000134008,0.000008916923,0.00004644111,0.00003031295,0.9963342,0.001223965,0.0007555789,0.0003149938,0.00001167374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7658339,0.004568174,0.2065862,0.003062312,0.0002286048,0.0007240386,0.005420077,0.008162227,0.005414494],"genre_scores_gemma":[0.8925783,0.001670466,0.09767785,0.0004612896,0.00009718475,0.0004259814,0.004873342,0.0003659511,0.001849739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01831678,"threshold_uncertainty_score":0.03642035,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5054255254777182,"score_gpt":0.4297697773039301,"score_spread":0.07565574817378812,"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."}}