{"id":"W4400678062","doi":"10.1162/tacl_a_00678","title":"Can Authorship Attribution Models Distinguish Speakers in Speech Transcripts?","year":2024,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Conversation; Punctuation; Natural language processing; Benchmark (surveying); Attribution; Spurious relationship; Task (project management); Speech recognition; Artificial intelligence; Transcription (linguistics); Suite; Construct (python library); Linguistics; Psychology; Machine learning; Communication","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":[],"consensus_categories":[],"category_scores_codex":[0.001284655,0.0001480712,0.0001973636,0.0001969506,0.0002481107,0.0001414305,0.0004550224,0.0001531631,0.000004519271],"category_scores_gemma":[0.0008720792,0.0001409839,0.0002517613,0.0009661184,0.00003507323,0.0001202238,0.00001378768,0.0003370621,0.000003904358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005749023,"about_ca_system_score_gemma":0.0003179518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007318935,"about_ca_topic_score_gemma":0.0001077337,"domain_scores_codex":[0.9982116,0.0001481288,0.0005489645,0.0003031255,0.0005108243,0.0002774223],"domain_scores_gemma":[0.997973,0.0008604901,0.0001899306,0.0001958289,0.0007189525,0.0000617457],"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":[0.000009986757,0.00005749702,0.0006129559,0.00008666189,0.00005262375,0.000001043218,0.001075135,0.3290814,0.00001855106,0.6671838,0.0001641117,0.001656216],"study_design_scores_gemma":[0.000262914,0.00002602803,0.002010627,0.00008797154,0.00004365476,0.000002142061,0.00002242694,0.6967576,0.0003692557,0.2968886,0.003390052,0.0001386819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001406393,0.0001016399,0.991105,0.002835135,0.002907874,0.0003794512,0.0003996857,0.0001679619,0.0006968419],"genre_scores_gemma":[0.9690908,0.000004606275,0.02990935,0.00006730719,0.0001574058,0.00002347971,0.00007339751,0.00001479927,0.0006588444],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9676844,"threshold_uncertainty_score":0.5749155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04126170943162795,"score_gpt":0.2890382353474506,"score_spread":0.2477765259158227,"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."}}