{"id":"W1980628172","doi":"10.1109/itw.2012.6404756","title":"Compressing multisets using tries","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Multiset; Sequence (biology); Encoding (memory); Cardinality (data modeling); Decoding methods; Encoder; Combinatorics; Computer science; Lossless compression; Discrete mathematics; Permutation (music); Mathematics; Algorithm; Theoretical computer science; Data compression; Artificial intelligence; Data mining","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":[0.001500811,0.0008683736,0.001356366,0.001468882,0.0007588363,0.001917679,0.001385382,0.001420835,0.003452042],"category_scores_gemma":[0.008507956,0.0006720446,0.001052404,0.002394981,0.001497391,0.004091276,0.002956933,0.00181291,0.001298822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006836854,"about_ca_system_score_gemma":0.0008366904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006020385,"about_ca_topic_score_gemma":0.0007492494,"domain_scores_codex":[0.9983785,0.000397147,0.0001548343,0.0003023427,0.0005970565,0.0001700551],"domain_scores_gemma":[0.9950581,0.003084761,0.0003130048,0.001051317,0.0003890982,0.0001038178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001248601,0.0001803191,0.001709736,0.0007959806,0.0001841933,0.001616433,0.001060642,0.5107179,0.02221547,0.1992523,0.007223948,0.2537944],"study_design_scores_gemma":[0.00006814153,0.0002398227,0.000237395,0.0001080022,0.00005905932,0.0005436849,0.0002062364,0.8523998,0.0178977,0.122353,0.00584101,0.00004617216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1208135,0.00160982,0.866961,0.00109814,0.0002905951,0.0001626097,0.0005806736,0.001437103,0.007046521],"genre_scores_gemma":[0.6207184,0.001498206,0.3641817,0.0005171091,0.000332459,0.0004361153,0.001258412,0.0003342014,0.01072341],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003452042,"threshold_uncertainty_score":0.01154822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08606859197094394,"score_gpt":0.3232464009550376,"score_spread":0.2371778089840937,"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."}}