{"id":"W4229699668","doi":"10.24124/2008/bpgub560","title":"Entropy of printed Bengali language texts.","year":2008,"lang":"en","type":"dissertation","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Library and Archives Canada","funders":"","keywords":"Bengali; Linguistics; Natural language processing; Art; Computer science; Artificial intelligence; Philosophy","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":[0.00005380358,0.0001564447,0.0002291365,0.0001171824,0.00005277049,0.00003164032,0.0008710853,0.00013251,0.0001616384],"category_scores_gemma":[0.00002214954,0.0001225786,0.00008478841,0.000167367,0.00001270707,0.0001995297,0.0001256778,0.0001670315,0.00005092271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001431414,"about_ca_system_score_gemma":0.00008854473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002310321,"about_ca_topic_score_gemma":0.00003508293,"domain_scores_codex":[0.9989319,0.00002673329,0.0002557064,0.0003169841,0.0003208549,0.0001477756],"domain_scores_gemma":[0.99898,0.00003116423,0.0001855713,0.000650346,0.00009904495,0.00005384786],"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":[0.0001035659,0.0008913124,0.0003255835,0.0006633804,0.0002393323,0.0002979151,0.01991765,0.00003339639,0.06100473,0.2296077,0.08903977,0.5978757],"study_design_scores_gemma":[0.003210408,0.000753425,0.05058213,0.001686632,0.0001059113,0.0001236692,0.003755942,0.09746084,0.708895,0.004671856,0.1253765,0.003377668],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2938088,0.006141207,0.4705584,0.0002040006,0.006278106,0.001488514,0.0001655543,0.001373862,0.2199815],"genre_scores_gemma":[0.4601556,0.001412107,0.3512277,0.0002935693,0.0005863358,0.00006500855,0.00585628,0.0001121374,0.1802913],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6478903,"threshold_uncertainty_score":0.4998612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008812604859882393,"score_gpt":0.2624486692435804,"score_spread":0.253636064383698,"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."}}