{"id":"W2251483280","doi":"10.18653/v1/d15-1088","title":"Mr. Bennet, his coachman, and the Archbishop walk into a bar but only one of them gets recognized: On The Difficulty of Detecting Characters in Literary Texts","year":2015,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Character (mathematics); Archbishop; Computer science; Bar (unit); State (computer science); Artificial intelligence; Natural language processing; History; Mathematics; Algorithm; Physics","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":[0.002761591,0.001117562,0.0006308522,0.004826061,0.003365069,0.003647454,0.001113653,0.002055708,0.01047466],"category_scores_gemma":[0.01604456,0.0004406537,0.0004359698,0.003534223,0.0009580225,0.005553405,0.002659669,0.002807271,0.01725922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008679103,"about_ca_system_score_gemma":0.0009461151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003874379,"about_ca_topic_score_gemma":0.01937169,"domain_scores_codex":[0.9973798,0.0006148397,0.0001915596,0.0006944467,0.0009595206,0.0001598044],"domain_scores_gemma":[0.9899673,0.003162258,0.0006760785,0.002536406,0.002791465,0.0008664445],"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":[0.0005927154,0.0001736402,0.03094416,0.0003640252,0.00007079679,0.001148703,0.002053243,0.002306619,0.0145085,0.01502109,0.2756159,0.6572007],"study_design_scores_gemma":[0.00003202046,0.0001661045,0.02244587,0.0005555462,0.00005343902,0.006041253,0.005543214,0.05542721,0.05148065,0.03914984,0.8188731,0.0002317133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3115061,0.01685191,0.3901984,0.105176,0.01614972,0.00047865,0.01503196,0.02090503,0.1237023],"genre_scores_gemma":[0.5025133,0.004655847,0.2989618,0.006847105,0.001763149,0.0002465022,0.01572971,0.002424044,0.1668585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01047466,"threshold_uncertainty_score":0.03504121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06396051724858276,"score_gpt":0.2615950096518417,"score_spread":0.197634492403259,"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."}}