{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001768939,0.0001133119,0.0002188706,0.0001405238,0.0001230173,0.00004447315,0.0002384513,0.00007293835,0.000001705877],"category_scores_gemma":[0.0009336573,0.0001090485,0.00006195995,0.0002952953,0.00004834296,0.00009917378,0.0001177393,0.0001207636,3.176784e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001152079,"about_ca_system_score_gemma":0.00002947087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007942479,"about_ca_topic_score_gemma":0.000001508049,"domain_scores_codex":[0.9987777,0.0000608036,0.00051015,0.0002562767,0.0001559971,0.0002391083],"domain_scores_gemma":[0.9981607,0.001165709,0.0001860576,0.0002005784,0.000200797,0.00008621241],"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":[0.00005050294,0.00009908898,0.01356507,0.0007849694,0.00002864339,0.000009259262,0.01657419,0.00002538156,0.001605839,0.5971708,0.000006987048,0.3700792],"study_design_scores_gemma":[0.001245464,0.0008945992,0.09015773,0.002131891,0.000132652,0.00007672492,0.0003259668,0.5982283,0.06466258,0.2374502,0.003743768,0.0009501211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2262995,0.000434484,0.7719418,0.00004814701,0.0004536559,0.0001619965,0.000005612556,0.00004867072,0.0006060609],"genre_scores_gemma":[0.9360153,0.000002009279,0.06371047,0.00004027513,0.0001665833,0.000001146627,0.00001274404,0.000006005603,0.00004546303],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7097158,"threshold_uncertainty_score":0.4446867,"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."}}