{"id":"W4380986449","doi":"10.1016/j.eswa.2023.120745","title":"TDRLM: Stylometric learning for authorship verification by Topic-Debiasing","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Debiasing; Computer science; Artificial intelligence; Stylometry; Machine learning; Representation (politics); Natural language processing; Task (project management); Multi-task learning; Latent semantic analysis; Writing style; Information retrieval; Linguistics","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":[0.007546019,0.001915699,0.002366373,0.01148317,0.001601358,0.003915532,0.003003697,0.002577308,0.01143807],"category_scores_gemma":[0.0349763,0.0009487375,0.001837039,0.007061936,0.000884206,0.005110309,0.004488071,0.002477712,0.01680326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008157681,"about_ca_system_score_gemma":0.002210576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002284999,"about_ca_topic_score_gemma":0.005164509,"domain_scores_codex":[0.9938337,0.00174035,0.000692834,0.001750299,0.001521647,0.0004611376],"domain_scores_gemma":[0.9864674,0.005910633,0.00112703,0.004497906,0.00154591,0.0004511279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004142873,0.0003557044,0.008582203,0.0004118628,0.0002648115,0.000161855,0.0003190521,0.0131488,0.005832108,0.00634153,0.05104347,0.9131244],"study_design_scores_gemma":[0.000127713,0.0001245306,0.003446599,0.00007125636,0.00007210553,0.0003175416,0.0001870159,0.934383,0.01266966,0.02831921,0.02020233,0.00007896603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02017418,0.0008981007,0.8983823,0.0004251169,0.0004796718,0.0004055836,0.007953989,0.0687083,0.002572683],"genre_scores_gemma":[0.2145169,0.0004209861,0.7550112,0.0001923487,0.0005172745,0.0007062228,0.01814436,0.002289935,0.008200689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01148317,"threshold_uncertainty_score":0.03990763,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04554347233216235,"score_gpt":0.3100462451674291,"score_spread":0.2645027728352668,"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."}}