{"id":"W2142905080","doi":"10.1145/2094072.2094073","title":"Word-based self-indexes for natural language text","year":2012,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico; Xunta de Galicia; Ministerio de Ciencia e Innovación","keywords":"Computer science; Word (group theory); Phrase; Search engine indexing; Inverted index; Natural language processing; Space (punctuation); Artificial intelligence; Natural language; Index (typography); Sequence (biology); Full text search; Information retrieval; Search engine; Linguistics; World Wide Web","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":[0.0002856528,0.0001265708,0.000123366,0.0001998757,0.0002736227,0.0002583488,0.0005615967,0.00007163437,0.000008799624],"category_scores_gemma":[0.00001826845,0.0001032318,0.00007636529,0.0002504124,0.000009674152,0.003988056,0.00001016769,0.0001203656,0.0001927469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006745898,"about_ca_system_score_gemma":0.00004098146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003905144,"about_ca_topic_score_gemma":0.00000134409,"domain_scores_codex":[0.9990122,0.00003384971,0.000313949,0.0001007715,0.0002797494,0.0002595129],"domain_scores_gemma":[0.9988409,0.0001747132,0.0001316994,0.0006611908,0.00009629678,0.0000951454],"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":[0.000105992,0.00050104,0.0002053997,0.0006070426,0.0001485472,9.011568e-7,0.01854375,0.02220205,0.0002554792,0.0121897,0.008516783,0.9367233],"study_design_scores_gemma":[0.001693199,0.0001182417,0.0007294498,0.0001302552,0.00002426454,0.00002796518,0.001219958,0.7470699,0.003239516,0.00003297873,0.2452134,0.0005008821],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00132267,0.0001401203,0.9951617,0.0001676941,0.002077803,0.0004337243,0.00005805436,0.000370257,0.0002680534],"genre_scores_gemma":[0.9378502,0.00000304065,0.06144348,0.0002676128,0.0001000397,0.0001766823,0.00005066651,0.00000602214,0.0001023024],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9365275,"threshold_uncertainty_score":0.420967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01209488053201561,"score_gpt":0.2518274829218977,"score_spread":0.2397326023898821,"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."}}