{"id":"W2101481293","doi":"10.1017/s1351324905003694","title":"Segmenting documents by stylistic character","year":2005,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"ca_institutions":"IBM (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Character (mathematics); Bigram; Natural language processing; Artificial intelligence; Vocabulary; Baseline (sea); Artificial neural network; Market segmentation; Information retrieval; Linguistics; Trigram","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":[0.0006575753,0.0007604807,0.0004301997,0.002581624,0.0005923781,0.001471111,0.0004751205,0.000698226,0.002570204],"category_scores_gemma":[0.004925962,0.0002410243,0.0003354486,0.001896269,0.0002685412,0.001561351,0.0004019001,0.0007431085,0.001841468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000708891,"about_ca_system_score_gemma":0.000600246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004763832,"about_ca_topic_score_gemma":0.008074566,"domain_scores_codex":[0.9994214,0.0001149906,0.00007405524,0.0002213641,0.000100911,0.00006726697],"domain_scores_gemma":[0.996298,0.001767239,0.0004156074,0.000437721,0.0009425578,0.000138972],"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":[0.001466354,0.0002434964,0.01975631,0.0005982485,0.00007541082,0.0005413112,0.00153913,0.01635694,0.152198,0.002612825,0.007200539,0.7974115],"study_design_scores_gemma":[0.0001509193,0.0005785497,0.03348251,0.0001342091,0.0001546173,0.001179779,0.002601127,0.6907223,0.2141464,0.01317678,0.04353256,0.0001403252],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8049209,0.001403977,0.1743625,0.000438691,0.0002283326,0.0006644359,0.004186722,0.005508958,0.008285484],"genre_scores_gemma":[0.7506734,0.0004629633,0.2357334,0.00006779058,0.00007567023,0.0001248842,0.006895785,0.0003061641,0.005659995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004763832,"threshold_uncertainty_score":0.009472251,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.002330387928883056,"score_gpt":0.2230677074953706,"score_spread":0.2207373195664875,"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."}}