{"id":"W4406774579","doi":"10.3389/fbinf.2024.1489704","title":"A novel lossless encoding algorithm for data compression–genomics data as an exemplar","year":2025,"lang":"en","type":"article","venue":"Frontiers in Bioinformatics","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data compression; Lossless compression; Encoding (memory); Benchmark (surveying); Entropy encoding; Algorithm; Data mining; Compression (physics); Entropy (arrow of time); Bin; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006253666,0.000718401,0.0005743508,0.001163291,0.0004236911,0.001031543,0.0009396108,0.0008527369,0.001980867],"category_scores_gemma":[0.002732345,0.0002029581,0.0004275259,0.001691236,0.0006379587,0.001735568,0.0008922784,0.001329939,0.001573335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004479984,"about_ca_system_score_gemma":0.0006619472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006689076,"about_ca_topic_score_gemma":0.0006583165,"domain_scores_codex":[0.9993483,0.00008093153,0.00005613271,0.0001052536,0.00036436,0.00004500198],"domain_scores_gemma":[0.9992156,0.0002597508,0.00006941418,0.000171609,0.0002540177,0.00002955329],"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":[0.0004012308,0.0001337253,0.0007439199,0.0002648388,0.00004359685,0.0002897735,0.0001994172,0.03546631,0.09754638,0.0275843,0.008793931,0.8285326],"study_design_scores_gemma":[0.00007488942,0.0003933581,0.0009515104,0.00009251121,0.00004278741,0.002015429,0.000115216,0.7822582,0.1607366,0.01758883,0.03566666,0.00006415237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01192173,0.0008980245,0.9837137,0.0003778188,0.0002040437,0.00008369315,0.000189657,0.001008493,0.001602919],"genre_scores_gemma":[0.1126391,0.001133983,0.8786436,0.000377767,0.0002047498,0.0002066783,0.001112835,0.000176427,0.005504927],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.001980867,"threshold_uncertainty_score":0.006626666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04953632431663978,"score_gpt":0.3138358221403895,"score_spread":0.2642994978237497,"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."}}