{"id":"W2037378121","doi":"10.1109/isccsp.2012.6217760","title":"A novel segmentation technique for splitting a typed Persian text to sub-words","year":2012,"lang":"en","type":"article","venue":"","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Persian; Computer science; Natural language processing; Segmentation; Component (thermodynamics); Artificial intelligence; Character (mathematics); Word (group theory); Text segmentation; Text recognition; Speech recognition; Linguistics; Mathematics; Image (mathematics)","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":[0.000613781,0.0001233635,0.0001176415,0.0001899403,0.0001069165,0.00009798572,0.0003495995,0.0000727708,0.00003865465],"category_scores_gemma":[0.00007760716,0.0001167048,0.00006680509,0.000380287,0.00001229425,0.0006327063,0.0001308391,0.00006897609,0.00009392083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008563743,"about_ca_system_score_gemma":0.00003386303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002667045,"about_ca_topic_score_gemma":0.000007833211,"domain_scores_codex":[0.9990036,0.00002248484,0.0002007349,0.0002553112,0.0001572944,0.0003605076],"domain_scores_gemma":[0.9993105,0.00008068045,0.00005963953,0.0002755476,0.000116056,0.0001575615],"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":[0.000005339131,0.00009248109,0.0001464846,0.00001898161,0.000007558066,2.100862e-7,0.0009949969,2.803236e-7,0.9293747,0.0139319,0.001802492,0.05362457],"study_design_scores_gemma":[0.0001995513,0.0001231134,0.0004006924,0.00003075442,0.000005907759,0.00002573961,0.0001702323,0.000396795,0.995479,0.0008274736,0.002113939,0.0002267975],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001939005,0.00001097577,0.9911042,0.000766043,0.0001052952,0.001181729,0.000004529676,0.0004713338,0.004416836],"genre_scores_gemma":[0.329051,0.000001079524,0.6691231,0.00083993,0.00008458199,0.0005842687,0.000004564599,0.00001154163,0.000299932],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.327112,"threshold_uncertainty_score":0.4759083,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02718313247388557,"score_gpt":0.2942379434968472,"score_spread":0.2670548110229616,"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."}}