{"id":"W4385572805","doi":"10.18653/v1/2022.emnlp-main.153","title":"A Multifaceted Framework to Evaluate Evasion, Content Preservation, and Misattribution in Authorship Obfuscation Techniques","year":2022,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Obfuscation; Misattribution of memory; Computer science; Automatic summarization; Evasion (ethics); Identification (biology); Harm; Key (lock); Information retrieval; Data science; Computer security; Psychology; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003249098,0.0001335387,0.0001540801,0.0002700027,0.0003523369,0.0001163879,0.0004281786,0.00009171088,0.0001103206],"category_scores_gemma":[0.001003377,0.0001337102,0.00003155975,0.001217659,0.00001858753,0.0004617488,0.0005457237,0.000365699,0.00001568485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002432976,"about_ca_system_score_gemma":0.00008298095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001641874,"about_ca_topic_score_gemma":0.00002204765,"domain_scores_codex":[0.9977543,0.0006190433,0.0003831627,0.0004806216,0.0004731642,0.0002896585],"domain_scores_gemma":[0.9989182,0.0002114555,0.0001031461,0.0004016055,0.0002254764,0.0001400947],"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":[0.0001921903,0.0003592718,0.084622,0.00005669349,0.00002548192,0.000009887915,0.017104,0.001469359,0.02832993,0.7626513,0.00247443,0.1027054],"study_design_scores_gemma":[0.001373518,0.00079651,0.3345697,0.0001695339,0.00001941537,0.00003531124,0.001431561,0.3798219,0.07457758,0.1815423,0.02452054,0.001142185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2047929,0.00009051969,0.7788843,0.01478267,0.0001939002,0.0008100391,0.000006234731,0.0003317327,0.0001076802],"genre_scores_gemma":[0.9053898,0.000006410341,0.09239553,0.001372238,0.0000208003,0.0003834472,0.00002806852,0.000007160522,0.0003965609],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7005969,"threshold_uncertainty_score":0.5452545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1182747653482014,"score_gpt":0.3349044381315374,"score_spread":0.216629672783336,"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."}}