{"id":"W4385570555","doi":"10.18653/v1/2023.findings-acl.355","title":"A Customized Text Sanitization Mechanism with Differential Privacy","year":2023,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Differential privacy; Security token; Metric (unit); Benchmark (surveying); Set (abstract data type); Similarity (geometry); Information privacy; Mechanism (biology); Measure (data warehouse); Data mining; Information retrieval; Theoretical computer science; Artificial intelligence; Computer security; Programming language","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":[0.005353966,0.001120334,0.001527042,0.002133721,0.00197151,0.003401587,0.003632078,0.002145177,0.005363069],"category_scores_gemma":[0.02080351,0.0005755797,0.00155498,0.002679006,0.00309171,0.008981354,0.008206483,0.00347932,0.002420567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001282045,"about_ca_system_score_gemma":0.002153963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006223088,"about_ca_topic_score_gemma":0.0005699399,"domain_scores_codex":[0.989949,0.002158785,0.001124664,0.002699799,0.003396144,0.0006716544],"domain_scores_gemma":[0.9800054,0.00488204,0.001741436,0.01073115,0.002037423,0.0006025991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002052097,0.0008613196,0.005396566,0.0007929107,0.0003609225,0.001309832,0.002220459,0.05306129,0.08059284,0.2428702,0.04146649,0.5690151],"study_design_scores_gemma":[0.0004224981,0.0005279121,0.002088967,0.0001414769,0.0003218217,0.001984686,0.0005496584,0.4827789,0.1260219,0.3200744,0.06484873,0.0002390743],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0334857,0.0004965963,0.9506641,0.001344191,0.000252561,0.0005148441,0.0007808125,0.007344467,0.005116698],"genre_scores_gemma":[0.6259289,0.000409568,0.3519741,0.001450417,0.0004672642,0.0007773694,0.0024225,0.0009041833,0.0156658],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005363069,"threshold_uncertainty_score":0.02831483,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02375159056233295,"score_gpt":0.2524997814363451,"score_spread":0.2287481908740122,"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."}}