{"id":"W1977597938","doi":"10.1155/2008/247354","title":"Arabic Handwritten Word Recognition Using HMMs with Explicit State Duration","year":2007,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Universitaire de la Francophonie","keywords":"Hidden Markov model; Computer science; Speech recognition; Word recognition; Viterbi algorithm; Word (group theory); Duration (music); Artificial intelligence; Sliding window protocol; Pattern recognition (psychology); Handwriting; Intelligent word recognition; Spotting; Handwriting recognition; Cursive; Natural language processing; Intelligent character recognition; Window (computing); Character recognition; Feature extraction; Mathematics; Image (mathematics); Reading (process)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001617404,0.000303831,0.0003027091,0.0007249842,0.0004147872,0.0006830887,0.0004914828,0.00008080879,0.00002420641],"category_scores_gemma":[0.00007101621,0.0002512694,0.00006368147,0.001178317,0.00007321678,0.005916784,0.00004932623,0.0007813919,0.00001832044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002869268,"about_ca_system_score_gemma":0.0001503121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002837035,"about_ca_topic_score_gemma":0.00002288771,"domain_scores_codex":[0.9971867,0.0001489268,0.0008498725,0.000482557,0.0007378559,0.000594108],"domain_scores_gemma":[0.9982578,0.0001811998,0.0007343346,0.0001726215,0.0004606488,0.0001934102],"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":[0.0001964813,0.0001051429,0.0008303447,0.00003735533,0.000005759117,0.0003024257,0.0004868564,0.0004961256,0.004563024,0.00002590707,0.00000655971,0.992944],"study_design_scores_gemma":[0.009906723,0.004855468,0.009431521,0.02024112,0.00009224917,0.01320023,0.002285576,0.1245199,0.6580397,0.1448515,0.007644461,0.004931544],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.159508,0.001121471,0.8380508,0.0001164672,0.0001130499,0.0001991643,0.000001110692,0.0001766249,0.0007132476],"genre_scores_gemma":[0.8054644,0.0002864894,0.1935316,0.0004296131,0.0002099064,0.000009459836,0.000002822774,0.00003182561,0.00003382526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9880125,"threshold_uncertainty_score":0.999994,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620825377583861,"score_gpt":0.2986640006173926,"score_spread":0.2724557468415539,"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."}}