{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0009309584,0.000256515,0.0003831504,0.0003413423,0.0003120743,0.0005086213,0.008756074,0.0001608548,0.000002386852],"category_scores_gemma":[0.000115727,0.0002348823,0.00003242559,0.0005013759,0.0000810719,0.004977183,0.006245144,0.0002443092,0.000006756262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009987785,"about_ca_system_score_gemma":0.0003352274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007649484,"about_ca_topic_score_gemma":0.00001004272,"domain_scores_codex":[0.9978227,0.00003060001,0.0007199498,0.0006336693,0.0003148788,0.0004781813],"domain_scores_gemma":[0.994668,0.0001148362,0.0002343834,0.004763963,0.00008237129,0.0001364447],"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":[0.00001520571,0.0001720923,0.0001746663,0.000107701,0.00003847426,0.000003846978,0.0006125771,0.000152338,0.00003406236,0.00258062,0.1022612,0.8938472],"study_design_scores_gemma":[0.0008964161,0.00003531494,0.00005261655,0.0001533002,0.00001478175,0.000009204959,0.0004952661,0.8802344,0.0001129429,0.002030865,0.1157085,0.0002564038],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009850233,0.0003239872,0.9939671,0.0001775833,0.002609696,0.0005517236,0.00151243,0.0001160535,0.0006429676],"genre_scores_gemma":[0.0001428995,0.0001499405,0.9958061,0.0005332688,0.00008245613,0.00001655694,0.003151359,0.00001272284,0.0001046822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8935908,"threshold_uncertainty_score":0.996607,"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."}}