{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000172332,0.000219999,0.0001629161,0.0001295701,0.00006876089,0.000259468,0.0008081105,0.00008360177,0.00003105829],"category_scores_gemma":[0.0001071399,0.0001958623,0.00005921471,0.0002917898,0.000009428623,0.001127413,0.0002468994,0.0004385067,0.00004856339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001497417,"about_ca_system_score_gemma":0.00001292107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572432,"about_ca_topic_score_gemma":0.000001639616,"domain_scores_codex":[0.9986805,0.00001467594,0.0002127352,0.0003492375,0.0003099728,0.0004328938],"domain_scores_gemma":[0.9993882,0.00005321521,0.00007094934,0.0003632827,0.00003808533,0.00008626459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004510795,0.00004754789,0.00006028066,0.00008939359,0.00004614429,0.00009539269,0.001388289,0.0001045901,0.5649291,0.007009497,0.003308122,0.4229171],"study_design_scores_gemma":[0.0009252927,0.00005486893,0.0002310745,0.0003124717,0.00002768702,0.0001825479,0.00005498858,0.4112251,0.5360843,0.0001253919,0.04911159,0.001664675],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1009885,0.07203068,0.8167299,0.001349984,0.001158045,0.0004962252,0.00001636378,0.006267217,0.0009631183],"genre_scores_gemma":[0.683963,0.00000617535,0.314693,0.000314484,0.0001634298,0.00001048546,0.00001505179,0.00001867854,0.0008156957],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5829745,"threshold_uncertainty_score":0.7987034,"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."}}