{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000658152,0.00005521037,0.00007049506,0.00009175738,0.00003029951,0.00003158658,0.0006910229,0.00001966885,0.0001509643],"category_scores_gemma":[0.000005696482,0.00004226146,0.00001798064,0.0002497059,0.00002415237,0.0005110829,0.0001650535,0.00002500355,0.00002320143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003450582,"about_ca_system_score_gemma":0.0000137667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001127805,"about_ca_topic_score_gemma":0.000005468133,"domain_scores_codex":[0.9994819,0.00001837804,0.0001177566,0.0001414664,0.0001566123,0.00008389175],"domain_scores_gemma":[0.9995397,0.000018788,0.00007200926,0.0003016272,0.00003696911,0.00003087821],"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":[0.00002783273,0.00120625,0.1899267,0.0002220572,0.000107661,0.0000221902,0.003168649,0.0001015574,0.003866829,0.5220918,0.0128386,0.2664198],"study_design_scores_gemma":[0.001192164,0.0001674954,0.1117946,0.00007421104,0.00001471579,3.014065e-7,0.0000887206,0.7267393,0.1494849,0.006028034,0.004008278,0.0004072431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006143768,0.000006246007,0.980023,0.0000360208,0.000174498,0.0000650273,0.000002868911,0.00009318378,0.01345536],"genre_scores_gemma":[0.9562439,0.000001607171,0.04339812,0.0001292311,0.000008040374,0.000001842119,0.0000153259,0.000002411703,0.000199535],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9501001,"threshold_uncertainty_score":0.1723372,"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."}}