{"id":"W2142590039","doi":"10.1145/2063576.2063646","title":"Indexes for highly repetitive document collections","year":2011,"lang":"en","type":"article","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Compression (physics); Data compression; Encoding (memory); Software versioning; Grammar; Inverted index; Space (punctuation); Information retrieval; Data mining; Algorithm; Artificial intelligence; Programming language; Software; Search engine indexing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006880659,0.0005672729,0.0007480012,0.003254649,0.0008311297,0.001834762,0.001724003,0.0005719971,0.003695791],"category_scores_gemma":[0.006165827,0.000367243,0.0004357579,0.005133605,0.000789246,0.004502088,0.002041113,0.001235913,0.002091755],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008124979,"about_ca_system_score_gemma":0.001237471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001008799,"about_ca_topic_score_gemma":0.002083093,"domain_scores_codex":[0.9984365,0.0001469329,0.0001606039,0.0001763633,0.0009809011,0.00009872484],"domain_scores_gemma":[0.9955485,0.000935244,0.0004029226,0.001876467,0.001094698,0.0001421449],"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":[0.0003386117,0.0002109169,0.001447109,0.0007457723,0.00008243375,0.0006828122,0.0004409362,0.01568977,0.07131166,0.08046609,0.02595108,0.8026329],"study_design_scores_gemma":[0.000223075,0.0006053614,0.003867085,0.0002796192,0.0002283069,0.004421038,0.000451986,0.3383453,0.2441086,0.1804104,0.2268249,0.0002343368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04898269,0.002786168,0.9271458,0.0006156914,0.000403295,0.0004249752,0.002746862,0.007421806,0.009472839],"genre_scores_gemma":[0.1442233,0.001910242,0.8365719,0.0003172809,0.0005366525,0.0003421233,0.007029464,0.0009202453,0.00814875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003695791,"threshold_uncertainty_score":0.01236361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02842593801195017,"score_gpt":0.2432859569559241,"score_spread":0.2148600189439739,"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."}}