{"id":"W2025882237","doi":"10.1093/llc/fqm023","title":"Bigrams of Syntactic Labels for Authorship Discrimination of Short Texts","year":2007,"lang":"en","type":"article","venue":"Literary and Linguistic Computing","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bigram; Library science; History; Computer science; Media studies; Artificial intelligence; Sociology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001250786,0.000822917,0.0006374476,0.007263493,0.0009023172,0.001277055,0.000798577,0.000958774,0.003384542],"category_scores_gemma":[0.009121668,0.000282069,0.0004195137,0.004150359,0.0005722203,0.002260718,0.001020239,0.00121426,0.00304708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002592934,"about_ca_system_score_gemma":0.0005707532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005190025,"about_ca_topic_score_gemma":0.001324931,"domain_scores_codex":[0.9986418,0.0004535987,0.0001337437,0.0002236856,0.0004291409,0.0001180817],"domain_scores_gemma":[0.9905875,0.005664883,0.0008117433,0.001184386,0.001259158,0.0004923127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005522504,0.000362426,0.02143077,0.0005938265,0.0001121744,0.0003604423,0.001017566,0.002243269,0.08248636,0.005700402,0.005188175,0.8799524],"study_design_scores_gemma":[0.0002026741,0.0009334332,0.1142479,0.0005148273,0.000375125,0.003041518,0.002585597,0.5718406,0.191836,0.07950472,0.03446101,0.0004566762],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3452111,0.002196694,0.6283318,0.0006810051,0.0004495041,0.0004274306,0.003670903,0.005651139,0.01338038],"genre_scores_gemma":[0.6679199,0.0004450398,0.3239074,0.00008117477,0.0002560789,0.0003016604,0.003426128,0.0003879197,0.003274735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007263493,"threshold_uncertainty_score":0.01132238,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03613429507286367,"score_gpt":0.3221275605100855,"score_spread":0.2859932654372218,"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."}}