{"id":"W2950603471","doi":"10.48550/arxiv.1101.5376","title":"Succincter Text Indexing with Wildcards","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Compressed suffix array; Search engine indexing; Suffix; Suffix array; Space (punctuation); Computer science; Combinatorics; Binary logarithm; Matching (statistics); Alphabet; Word (group theory); Algorithm; Data structure; Mathematics; Theoretical computer science; Suffix tree; Information retrieval; 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":[0.0001581524,0.0003464745,0.0003221152,0.0002239616,0.0001785022,0.0001629594,0.002358832,0.0002643274,0.00006217102],"category_scores_gemma":[0.000006726908,0.0003109182,0.000123016,0.000389855,0.00009397582,0.0007303274,0.003999637,0.000643761,0.0001078891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001025107,"about_ca_system_score_gemma":0.0002070145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000417482,"about_ca_topic_score_gemma":0.00003582714,"domain_scores_codex":[0.9980378,0.00008660842,0.0001523467,0.001222177,0.0001257653,0.0003752805],"domain_scores_gemma":[0.9975572,0.00003993526,0.0002209302,0.001845155,0.0001428792,0.0001938767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003852885,0.000761656,0.04735568,0.0003864143,0.000822084,0.005538132,0.002724182,0.0927619,0.00009072399,0.8065546,0.008156829,0.03446251],"study_design_scores_gemma":[0.002351681,0.0004312738,0.03051208,0.001050022,0.000244592,0.00008117345,0.0001329858,0.8419238,0.0006303178,0.1008318,0.01880983,0.003000502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07280155,0.00005516706,0.9148403,0.00003460051,0.0004733646,0.0002028311,0.00001705906,0.0003001884,0.01127489],"genre_scores_gemma":[0.987255,0.00005182905,0.01061628,0.0001046754,0.00009847965,8.733915e-7,0.00002192433,0.00002195084,0.001829019],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9144534,"threshold_uncertainty_score":0.9999343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06240961777366939,"score_gpt":0.1682849665940609,"score_spread":0.1058753488203915,"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."}}