{"id":"W4414090146","doi":"10.1101/2025.09.08.674958","title":"A novel Vector-Symbolic Architecture for graph encoding and its application to viral pangenome-based species classification","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"ENCODE; Representation (politics); Encoding (memory); Graph; Genome; Pattern recognition (psychology); Sequence (biology); Architecture","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":[0.0003612099,0.000429687,0.0003475858,0.0002824235,0.0001765713,0.0001222827,0.0004448563,0.0005078695,0.00000256605],"category_scores_gemma":[0.0003260741,0.0004721371,0.0001299388,0.0002389663,0.00005528654,0.000006150513,0.0003349973,0.0003506925,0.000004091502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007992807,"about_ca_system_score_gemma":0.0003029113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000938971,"about_ca_topic_score_gemma":0.000005887204,"domain_scores_codex":[0.9982078,0.00004824055,0.0004160918,0.0007765639,0.0001844514,0.0003668319],"domain_scores_gemma":[0.9983491,0.00003814607,0.0003217686,0.0008361514,0.0002901869,0.0001646585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006367511,0.00004875709,0.001175333,0.0007327493,0.00007310064,1.569486e-7,0.00001453674,0.00122718,0.994756,0.001817275,0.00007649446,0.0000147091],"study_design_scores_gemma":[0.001062653,0.0002143427,0.1106642,0.000304201,0.0001616538,3.32357e-8,0.000005589397,0.01499312,0.8021235,0.000007252323,0.06926531,0.001198137],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.520548,0.0005675519,0.4738853,0.001009027,0.0003930648,0.00242717,0.0009787136,0.0001503832,0.00004081904],"genre_scores_gemma":[0.9740208,0.00006491171,0.02411139,0.0005035456,0.0003569299,0.0008442805,0.00001553897,0.00005764951,0.00002499045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4534728,"threshold_uncertainty_score":0.999773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01340911375852166,"score_gpt":0.2393449661134086,"score_spread":0.225935852354887,"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."}}