{"id":"W2103291633","doi":"10.1109/dcc.1991.213370","title":"Models for compression in full-text retrieval systems","year":2002,"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 Calgary","funders":"","keywords":"Lexicon; Computer science; Word (group theory); Natural language processing; Coding (social sciences); Artificial intelligence; Compression (physics); Information retrieval; Data compression; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001956304,0.0001083433,0.0001639451,0.00009403551,0.00009165881,0.000155796,0.0006689906,0.00007275985,0.0000311772],"category_scores_gemma":[0.00001240865,0.00008088522,0.00003958766,0.0002278954,0.00001315895,0.0008453655,0.0002764328,0.00008323834,0.00004142384],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002820082,"about_ca_system_score_gemma":0.000008529328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004651285,"about_ca_topic_score_gemma":0.000002754521,"domain_scores_codex":[0.9988737,0.00003812338,0.0002452675,0.0003573494,0.0002325022,0.0002530499],"domain_scores_gemma":[0.9992014,0.0001021626,0.00005670109,0.0005082394,0.00005300439,0.00007846906],"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":[0.0001490597,0.0009263027,0.0001196187,0.0002292475,0.00002682679,0.00005599316,0.001720618,0.1166641,0.008922304,0.534947,0.2083604,0.1278785],"study_design_scores_gemma":[0.0005019945,0.00006411778,0.00002389272,0.00005672205,9.161589e-7,0.000009426754,0.00001650421,0.9902223,0.0002009284,0.001871395,0.006905937,0.0001258495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001912412,0.0006827133,0.992301,0.0002341651,0.0005314783,0.0003166542,0.000006956744,0.0001273694,0.003887239],"genre_scores_gemma":[0.8863235,0.0000864881,0.1102585,0.0001657541,0.0001549241,0.00003263077,0.00001071499,0.00001458403,0.002952948],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8844111,"threshold_uncertainty_score":0.3298403,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04978943089054107,"score_gpt":0.2527467752001725,"score_spread":0.2029573443096314,"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."}}