{"id":"W2160802334","doi":"10.1007/3-540-44888-8_4","title":"Optimal Spaced Seeds for Hidden Markov Models, with Application to Homologous Coding Regions","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Coding (social sciences); Markov chain; Computer science; Hidden Markov model; Markov model; Computational biology; Artificial intelligence; Biology; Mathematics; Machine learning; Statistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055709,0.0005101575,0.0004846677,0.0006323979,0.0004396254,0.0004775961,0.002794197,0.0002736059,0.000003023426],"category_scores_gemma":[0.00003001756,0.000424683,0.0000911785,0.0006296378,0.0002858628,0.0007126932,0.001041399,0.0004568442,0.00001026118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002699352,"about_ca_system_score_gemma":0.0003585716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002713927,"about_ca_topic_score_gemma":0.00003903249,"domain_scores_codex":[0.9964206,0.00002444719,0.0003706792,0.001772901,0.0007229577,0.000688469],"domain_scores_gemma":[0.9971588,0.0002985965,0.0002491417,0.001706842,0.0003245584,0.0002620211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004157073,0.00004954711,0.000006336432,0.00004980653,0.00001909948,0.00004410686,0.0006982409,0.2650209,0.0001834358,0.09528571,0.0006362635,0.637965],"study_design_scores_gemma":[0.0003212006,0.0003311183,0.00001067515,0.0002549002,0.00001116544,0.0001241207,3.649826e-7,0.9368829,0.0004230221,0.05767029,0.003326579,0.0006436343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002185925,0.0001501994,0.9953526,0.001556185,0.0005339689,0.00116915,0.00002182431,0.0001662825,0.001027931],"genre_scores_gemma":[0.01080714,0.00002157473,0.9868465,0.001524856,0.0002331247,0.00009321998,0.00002234817,0.00004141347,0.0004098108],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.671862,"threshold_uncertainty_score":0.9998205,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01756825757284889,"score_gpt":0.2431983991690264,"score_spread":0.2256301415961776,"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."}}