{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0001718622,0.0001533912,0.0001622674,0.0002560641,0.0001312729,0.0002320628,0.01662108,0.00009024593,0.000110427],"category_scores_gemma":[0.002994627,0.0001149225,0.00003150294,0.001188219,0.00004779087,0.0006255192,0.05165517,0.0001437997,0.0004797822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004176284,"about_ca_system_score_gemma":0.00004819201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002192243,"about_ca_topic_score_gemma":0.000007536103,"domain_scores_codex":[0.998566,0.00004659127,0.0001715645,0.000491677,0.0003675772,0.0003566177],"domain_scores_gemma":[0.9942754,0.0001091796,0.0000707689,0.005432233,0.00006073648,0.00005171404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000579034,0.0001275246,0.0003080749,0.00004173539,0.00009681055,0.0001108877,0.000282232,0.00001729879,0.01434318,0.5443315,0.3909581,0.04932477],"study_design_scores_gemma":[0.00128869,0.00008678523,0.0008219627,0.00002922691,0.000008851059,0.0000168455,0.00003791085,0.4639914,0.02398606,0.5082062,0.001214694,0.0003113391],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03731377,0.000003346102,0.942046,0.01281816,0.0002299683,0.0002404197,0.000004640143,0.005519963,0.001823768],"genre_scores_gemma":[0.7044893,0.00002384535,0.2947323,0.0001401158,0.0000303977,0.00004758417,0.00002941749,0.00001822093,0.0004888438],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6671755,"threshold_uncertainty_score":0.9886995,"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."}}