{"id":"W1499594845","doi":"10.1002/9780470253441.ch4","title":"Advances in Hidden Markov Models for Sequence Annotation","year":2007,"lang":"en","type":"other","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Hidden Markov model; Viterbi algorithm; Annotation; Sequence (biology); Computer science; Maximum-entropy Markov model; Sequence labeling; Forward algorithm; Markov model; Markov chain; Artificial intelligence; Viterbi decoder; Decoding methods; Variable-order Markov model; Machine learning; Algorithm; Engineering; Biology; Genetics","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":[0.0002182943,0.0001695911,0.0001780235,0.0005372215,0.00001703673,0.00006957971,0.0008395279,0.0002109385,0.00003486811],"category_scores_gemma":[0.00002964856,0.0001447644,0.00003528526,0.0003644008,0.00002556481,0.0006346843,0.00009196984,0.0001298641,0.000006158537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006179769,"about_ca_system_score_gemma":0.00005410548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000833369,"about_ca_topic_score_gemma":0.0002078006,"domain_scores_codex":[0.9989865,0.00001511478,0.0001698914,0.0004091451,0.0001892926,0.0002299913],"domain_scores_gemma":[0.9993952,0.00006149475,0.0001399727,0.0003250223,0.0000481465,0.00003015295],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003825481,0.00001145633,0.000002683026,0.0001325039,0.000001957106,0.00001070816,0.00006204142,0.000003500955,0.00004039493,0.1385043,0.03855439,0.8226722],"study_design_scores_gemma":[0.0003522596,0.00007734796,8.299768e-7,0.0008517333,0.000005537236,0.0000132683,0.00001313596,0.1191745,0.002086461,0.699595,0.1769881,0.0008418493],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[1.03016e-7,0.008949208,0.7182404,0.00007967251,0.0000992846,0.000293835,0.000004602848,0.000762845,0.27157],"genre_scores_gemma":[0.0001103645,0.0003155745,0.8370798,0.0002258015,0.00006576131,0.00004905463,0.00001158953,0.00007162656,0.1620704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8218304,"threshold_uncertainty_score":0.5903319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02145920373684719,"score_gpt":0.3228139653249338,"score_spread":0.3013547615880866,"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."}}