{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005485428,0.000471975,0.0005185399,0.0007624029,0.0004372548,0.000691411,0.0007452708,0.0007977844,0.002188771],"category_scores_gemma":[0.006062514,0.0002342318,0.00032832,0.001214577,0.0009838655,0.00176738,0.0009414882,0.0009700417,0.0004076675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006773853,"about_ca_system_score_gemma":0.001065776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00142197,"about_ca_topic_score_gemma":0.002394404,"domain_scores_codex":[0.9996334,0.00008497509,0.00002408085,0.00005766154,0.0001490984,0.00005078331],"domain_scores_gemma":[0.9979948,0.001237942,0.0001816711,0.0003153042,0.0002077414,0.00006261577],"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":[0.0003611039,0.0001949957,0.003116036,0.0002859092,0.00003758327,0.0002306669,0.0002513148,0.5185113,0.04034728,0.2310837,0.007054099,0.198526],"study_design_scores_gemma":[0.00002378868,0.00004772052,0.000137917,0.00001685669,0.000005656582,0.00005248421,0.00003284557,0.9296617,0.01450916,0.05387717,0.001623793,0.0000107972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.18476,0.0004994874,0.8068452,0.0005948664,0.00008752567,0.00008295604,0.0001341983,0.001013828,0.005981791],"genre_scores_gemma":[0.6807745,0.0003713201,0.3151117,0.0002107836,0.00006288777,0.0001128583,0.0003824858,0.0003163861,0.002657196],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002188771,"threshold_uncertainty_score":0.007322192,"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."}}