{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006152193,0.0009932863,0.0007322036,0.001132002,0.0006508416,0.002166151,0.001194782,0.001494875,0.002472329],"category_scores_gemma":[0.03260499,0.0003020056,0.0005922641,0.0007048139,0.0006858785,0.00263888,0.001331428,0.002200357,0.00221538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006568084,"about_ca_system_score_gemma":0.0007589965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002441399,"about_ca_topic_score_gemma":0.002510987,"domain_scores_codex":[0.996847,0.001860488,0.0001394487,0.0007048766,0.0002360795,0.000212151],"domain_scores_gemma":[0.9815583,0.01297966,0.001382747,0.002080228,0.001488712,0.00051039],"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":[0.002778819,0.001015205,0.06006737,0.0005329744,0.0004197591,0.0004158845,0.002083062,0.1514935,0.02882894,0.002285995,0.008552332,0.7415262],"study_design_scores_gemma":[0.0000404229,0.0001781193,0.009033632,0.00006784711,0.00006738426,0.0001092492,0.000562207,0.9691664,0.01312855,0.006433697,0.001168805,0.00004370304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8448912,0.001660529,0.139593,0.001731259,0.0006534742,0.0001889277,0.001261804,0.003272704,0.006747118],"genre_scores_gemma":[0.9809574,0.0001452163,0.01593953,0.00008231399,0.00009870767,0.00004732312,0.001023944,0.00006876824,0.00163692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006152193,"threshold_uncertainty_score":0.03253633,"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."}}