{"id":"W2119140562","doi":"10.1007/s10032-007-0060-2","title":"Genre as noise: noise in genre","year":2007,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Noise (video); Perspective (graphical); Hierarchy; Feature (linguistics); Word error rate; Natural language processing; Artificial intelligence; Emphasis (telecommunications); Speech recognition; Selection (genetic algorithm); Pattern recognition (psychology); Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001893853,0.000174775,0.0002342474,0.001375255,0.0001640828,0.0005850069,0.0005228295,0.0001015651,0.000676151],"category_scores_gemma":[0.0001036044,0.0001491242,0.000254129,0.0008399211,0.00003054987,0.0006595626,0.0001129938,0.000411899,0.0001970449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001982498,"about_ca_system_score_gemma":0.00005374489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006036781,"about_ca_topic_score_gemma":0.00006776847,"domain_scores_codex":[0.997752,0.0001250738,0.0006543931,0.0003481379,0.0008372884,0.0002830891],"domain_scores_gemma":[0.9987441,0.0001436138,0.0003308768,0.0001500186,0.0003988502,0.000232578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005302676,0.000638478,0.09753013,0.00001326795,0.002851851,0.001587889,0.002168062,0.0009108754,0.002091705,0.02460363,0.0006022611,0.8664716],"study_design_scores_gemma":[0.009411152,0.001034442,0.7406067,0.0006664636,0.001060225,0.001720765,0.001709514,0.02540914,0.04034439,0.1440464,0.03126677,0.002723983],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7320476,0.0002571719,0.2585337,0.004357609,0.001117268,0.0001140931,0.00001022206,0.00004839269,0.00351395],"genre_scores_gemma":[0.9931297,0.0004812803,0.003487832,0.001619392,0.0003282775,0.000003878053,0.00005294586,0.000007230431,0.0008894525],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8637476,"threshold_uncertainty_score":0.740338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02048356387265479,"score_gpt":0.317666999386885,"score_spread":0.2971834355142302,"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."}}