{"id":"W2144687917","doi":"10.1145/2063576.2063628","title":"Factorization-based lossless compression of inverted indices","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inverted index; Lossless compression; Term (time); Computer science; Compression (physics); Algorithm; Factorization; Matrix (chemical analysis); Matrix decomposition; Greedy algorithm; Sparse matrix; Space (punctuation); Data compression; Search engine indexing; Artificial intelligence","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":[0.001381165,0.0009302606,0.001034925,0.001931759,0.0007584484,0.001249123,0.001490672,0.0008582257,0.001876138],"category_scores_gemma":[0.00891408,0.0003904283,0.0005971671,0.003086377,0.0008984665,0.003022614,0.001484705,0.001048461,0.001326391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009050941,"about_ca_system_score_gemma":0.001349938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003141096,"about_ca_topic_score_gemma":0.00532274,"domain_scores_codex":[0.9983296,0.0002864592,0.0001458339,0.0001764957,0.0008917717,0.000169958],"domain_scores_gemma":[0.9957668,0.001420202,0.0003627896,0.001359932,0.001005321,0.00008507079],"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":[0.0009820586,0.0004135386,0.00250029,0.0003301595,0.00009252739,0.0004891768,0.0004535109,0.1005459,0.0839555,0.02898808,0.0191781,0.7620713],"study_design_scores_gemma":[0.0001322124,0.0003582644,0.001295768,0.00005201956,0.00005628289,0.0008601962,0.0002050771,0.8684598,0.08801807,0.03149593,0.008995653,0.00007080613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06154972,0.001170882,0.9302252,0.0005428786,0.0001521281,0.0003057359,0.0006880673,0.002586352,0.002778993],"genre_scores_gemma":[0.3222931,0.0008681016,0.669716,0.0003320025,0.0002480418,0.0004346461,0.001682876,0.0002406258,0.004184653],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003141096,"threshold_uncertainty_score":0.00730437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05061894065099384,"score_gpt":0.2270028101498782,"score_spread":0.1763838694988843,"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."}}