{"id":"W1960827080","doi":"10.1109/icdar.1997.620559","title":"HMM word recognition engine","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hidden Markov model; Computer science; Word (group theory); Speech recognition; Feature (linguistics); Scheme (mathematics); Artificial intelligence; Cheque; Natural language processing; Word recognition; Pattern recognition (psychology); World Wide Web; Linguistics","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":[0.00005472575,0.00005514916,0.00004762398,0.0000614901,0.00003390653,0.00008369844,0.0003490494,0.00003374967,0.0003121841],"category_scores_gemma":[0.0000331081,0.00004436239,0.00001897562,0.0002455178,0.000008602673,0.000408514,0.00007553161,0.00007898334,0.0002819379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001356939,"about_ca_system_score_gemma":0.000002332252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006173779,"about_ca_topic_score_gemma":0.000001462746,"domain_scores_codex":[0.99955,0.00001048578,0.00007246595,0.0001515828,0.00009978269,0.0001156686],"domain_scores_gemma":[0.9996847,0.00002093483,0.00002077675,0.0002027792,0.00003954148,0.00003130041],"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":[2.273405e-7,0.00001466839,0.000008412986,0.000003347516,0.000001280041,0.000007617727,0.00007822576,1.013945e-7,0.0006568432,0.004535846,0.007093556,0.9875998],"study_design_scores_gemma":[0.0004597404,0.0001509763,0.00008115073,0.0001123808,0.000008359239,0.0001873273,0.00001483828,0.1415864,0.4510812,0.3804772,0.02495729,0.0008831186],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001027829,0.0009554854,0.980804,0.001718648,0.0001006319,0.00005749304,3.254147e-7,0.001773777,0.01356177],"genre_scores_gemma":[0.2088344,0.00001694858,0.7888257,0.0005746458,0.00003613923,0.000005136783,8.137989e-7,0.000003351525,0.001702892],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9867167,"threshold_uncertainty_score":0.3623836,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02499755585751904,"score_gpt":0.239480952739076,"score_spread":0.214483396881557,"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."}}