{"id":"W2151422907","doi":"10.1145/1562090.1562094","title":"Finding optimal parameters for edit distance based sequence classification is NP-hard","year":2009,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Edit distance; Parametric statistics; Sequence (biology); Computer science; Measure (data warehouse); Matching (statistics); Heuristic; Data mining; Algorithm; Pattern recognition (psychology); Artificial intelligence; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001892088,0.0001173869,0.0001101605,0.0000526021,0.0001694623,0.0001761828,0.0006995646,0.00005114547,0.00002136436],"category_scores_gemma":[0.00003628285,0.0000983956,0.00006178467,0.0002027914,0.00002445077,0.0007583617,0.00004607375,0.00006983164,0.00001931708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005048677,"about_ca_system_score_gemma":0.0000489637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006218019,"about_ca_topic_score_gemma":4.455315e-7,"domain_scores_codex":[0.9988648,0.00001788319,0.000194998,0.0004486297,0.0002228148,0.0002508154],"domain_scores_gemma":[0.9990717,0.000111221,0.00009584145,0.0005663943,0.00007103323,0.00008378112],"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":[0.0001149223,0.0003859012,0.0007297891,0.00006121722,0.00002346576,0.00001140898,0.0006230456,0.00433855,0.0377188,0.1964432,0.3393998,0.4201499],"study_design_scores_gemma":[0.0002452075,0.0001131856,0.001344223,0.00002152347,0.000003013396,0.000001461825,0.000008922637,0.9654626,0.006415367,0.00149587,0.02471792,0.000170663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002354238,0.00001900443,0.992996,0.003434735,0.0003351794,0.0001992812,0.00002928428,0.0001507401,0.0004815877],"genre_scores_gemma":[0.2045959,0.000004592792,0.7931608,0.001634625,0.000078694,0.00002398241,0.00003107014,0.000004592981,0.000465803],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9611241,"threshold_uncertainty_score":0.4012456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0852972519177814,"score_gpt":0.3137873692057326,"score_spread":0.2284901172879512,"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."}}