{"id":"W2407396938","doi":"10.48550/arxiv.1605.08102","title":"Finding Synchronization Codes to Boost Compression by Substring Enumeration","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Substring; Lossless compression; Computer science; Synchronization (alternating current); Enumeration; Data compression; Benchmark (surveying); Compression (physics); Byte; Algorithm; Parallel computing; Data structure; Mathematics; Telecommunications; Computer hardware; Discrete mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001875942,0.0002959197,0.0002681546,0.0002351737,0.0003534247,0.0002765727,0.0014596,0.0002464112,0.00003266334],"category_scores_gemma":[0.00003195863,0.0002865808,0.00008312345,0.0003786743,0.00003780047,0.0008640221,0.002681,0.0002869565,0.0001135681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002956005,"about_ca_system_score_gemma":0.0001002337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007129239,"about_ca_topic_score_gemma":0.00000881861,"domain_scores_codex":[0.9980556,0.0001266832,0.0002219836,0.001104919,0.0001537099,0.0003370401],"domain_scores_gemma":[0.9982662,0.0001002625,0.0002471169,0.001024941,0.0001509997,0.0002105492],"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":[0.0002212251,0.0006221283,0.01812599,0.0004687481,0.0003032451,0.0004745924,0.001759928,0.5403416,0.03365563,0.2472986,0.06688927,0.089839],"study_design_scores_gemma":[0.0005814264,0.0000606605,0.0006458113,0.000799123,0.0000304707,0.000003437476,0.00002538137,0.9784405,0.005273562,0.008565765,0.004831885,0.000741998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04633811,0.00008282806,0.951539,0.0001519778,0.0006913218,0.0003061105,0.0001113003,0.0002547413,0.0005246153],"genre_scores_gemma":[0.9947903,0.0001080952,0.003960787,0.00006608389,0.0001189995,0.000001723332,0.0001950016,0.00001855846,0.0007405145],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9484521,"threshold_uncertainty_score":0.9999586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04989120929542976,"score_gpt":0.1978015915566203,"score_spread":0.1479103822611905,"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."}}