{"id":"W1820209741","doi":"10.1007/978-3-642-20662-7_12","title":"Compressed String Dictionaries","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; String (physics); Search engine indexing; Theoretical computer science; Set (abstract data type); RDF; Space (punctuation); Information retrieval; Programming language; Mathematics; Semantic 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004674216,0.0005182689,0.0004876722,0.0006758034,0.000427284,0.0006065412,0.004191908,0.0002894379,0.00006752349],"category_scores_gemma":[0.00003999575,0.0004554953,0.0001162048,0.0004088165,0.0006513016,0.001173925,0.002967305,0.0008069188,0.00007646756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00016705,"about_ca_system_score_gemma":0.0003913291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006164599,"about_ca_topic_score_gemma":0.00002447727,"domain_scores_codex":[0.9963645,0.00002611008,0.0004911431,0.001529913,0.0009654724,0.0006228986],"domain_scores_gemma":[0.9972355,0.0002861426,0.0002800973,0.001779303,0.0002177749,0.0002011719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006728193,0.00003761681,0.00004962747,0.00002703017,0.00001298841,0.00009758287,0.0005579806,0.006805926,0.00007675556,0.1433952,0.0001090561,0.8488235],"study_design_scores_gemma":[0.0003643156,0.0001760526,0.0004021846,0.0005770869,0.000009918965,0.00009160941,1.172257e-7,0.4874244,0.001686729,0.4899233,0.0183242,0.001020086],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001476864,0.0006551059,0.9897724,0.0001994532,0.002411252,0.000249672,0.0000130162,0.000277783,0.006406578],"genre_scores_gemma":[0.1008442,0.0001960178,0.8954721,0.00119319,0.001083166,0.00001691028,0.00002891616,0.00006937623,0.001096103],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8478034,"threshold_uncertainty_score":0.9997897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02309863926162234,"score_gpt":0.2329824740614884,"score_spread":0.2098838347998661,"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."}}