{"id":"W1973228454","doi":"10.1007/s00453-012-9726-3","title":"Efficient Fully-Compressed Sequence Representations","year":2012,"lang":"en","type":"article","venue":"Algorithmica","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Combinatorics; Disjoint sets; Substring; Mathematics; Amortized analysis; Redundancy (engineering); Data structure; Binary logarithm; Compressed suffix array; Subsequence; Algorithm; Sequence (biology); Discrete mathematics; Suffix tree; Computer science","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":[0.0002740744,0.0001765267,0.0001669856,0.0001028534,0.0002765175,0.0001448167,0.001061176,0.0000679394,0.00008029395],"category_scores_gemma":[0.00005186108,0.0001541232,0.00007746761,0.0004570392,0.00006765857,0.0005519423,0.0006095032,0.0001765823,0.0004504621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004581799,"about_ca_system_score_gemma":0.00004738678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000735282,"about_ca_topic_score_gemma":4.40812e-7,"domain_scores_codex":[0.998221,0.00008619486,0.0002681795,0.0004225496,0.0004304347,0.000571613],"domain_scores_gemma":[0.9982771,0.0001499023,0.0001011431,0.001093574,0.00009196372,0.000286275],"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":[0.00002380693,0.001918913,0.001935476,0.00005530307,0.0001395582,0.00009803516,0.004524322,0.007493769,0.02747012,0.2807833,0.04523374,0.6303236],"study_design_scores_gemma":[0.0004802762,0.00004455754,0.005934398,0.00002942679,0.00001416964,0.00009452357,0.00005839847,0.9443334,0.009760491,0.001653682,0.0371241,0.0004725951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008075523,0.000368615,0.9850438,0.0006820436,0.001158187,0.0002044051,0.00002454724,0.0003667996,0.004076037],"genre_scores_gemma":[0.6952435,0.000008352711,0.3035261,0.0003579762,0.0004409746,0.0000453886,0.00002676687,0.00001606004,0.0003349261],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9368396,"threshold_uncertainty_score":0.6284963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03079680232543067,"score_gpt":0.2926913199302248,"score_spread":0.2618945176047941,"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."}}