{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002225777,0.0002931063,0.0003372683,0.000114022,0.0002253042,0.0006470613,0.001615591,0.0002376377,0.00005795927],"category_scores_gemma":[0.0000225061,0.0002409618,0.0001083552,0.0001010618,0.00005179686,0.000811394,0.007433086,0.0004600647,0.00004292679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005860439,"about_ca_system_score_gemma":0.0001208517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003418155,"about_ca_topic_score_gemma":0.000002408669,"domain_scores_codex":[0.9982522,0.00008449781,0.0003146104,0.0005881133,0.0003598192,0.000400718],"domain_scores_gemma":[0.9980586,0.00009892639,0.0002182407,0.001378973,0.00008116345,0.0001640914],"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":[0.00002882832,0.0008659764,0.002796493,0.0007856796,0.0002691235,0.0001265606,0.00466486,0.02903128,0.00776144,0.04986707,0.01541253,0.8883901],"study_design_scores_gemma":[0.0001855569,0.00000480194,0.0007992443,0.0002287801,0.00001522898,0.00001335446,0.000009891115,0.9867083,0.001661235,0.002427176,0.007500115,0.0004463062],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004557472,0.001558055,0.9888579,0.00008613354,0.002518489,0.0001892547,0.00002027007,0.0003776065,0.001834846],"genre_scores_gemma":[0.2288722,0.00002899822,0.7703232,0.0001317755,0.0003896791,0.000007748983,0.00003734326,0.00001807998,0.0001909561],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.957677,"threshold_uncertainty_score":0.9826136,"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."}}