{"id":"W4415295489","doi":"10.1093/bioinformatics/btag362","title":"Movi 2: Fast and Space-Efficient Queries on Pangenomes","year":2025,"lang":"en","type":"preprint","venue":"Bioinformatics","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Memory footprint; Search engine indexing; Space (punctuation); Footprint; Compression (physics); Variety (cybernetics)","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":[0.0001284226,0.0003499221,0.0003435238,0.0002594332,0.0001443586,0.000311779,0.0008929994,0.0002162652,0.000002106742],"category_scores_gemma":[0.00004159329,0.0003025819,0.00009568595,0.0002815778,0.000112738,0.0001739803,0.002489233,0.0005076433,0.00002099645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006333183,"about_ca_system_score_gemma":0.0001044091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005167468,"about_ca_topic_score_gemma":0.00000386335,"domain_scores_codex":[0.9985539,0.00002565371,0.0004195755,0.0003334696,0.0003160144,0.0003513807],"domain_scores_gemma":[0.9983662,0.000140064,0.0002790074,0.001027581,0.00007327678,0.000113818],"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":[0.00002305972,0.00009557641,0.0001793145,0.001205384,0.0001071509,0.00002340759,0.007789748,0.2267214,0.000003995022,0.2562194,0.004737094,0.5028945],"study_design_scores_gemma":[0.0001837738,0.00007975924,0.0005139553,0.0003938199,0.00001484694,0.000009340167,0.0001681013,0.9808885,0.0001317134,0.005192775,0.01193244,0.0004909009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006484102,0.001353978,0.9728259,0.001359704,0.002245946,0.00080701,0.0001044637,0.0005508346,0.01426805],"genre_scores_gemma":[0.0836134,0.002449799,0.9079783,0.00281299,0.0002827163,0.0001318737,0.00007175787,0.00003725769,0.002621905],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7541672,"threshold_uncertainty_score":0.9999426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01504953401497884,"score_gpt":0.246185353972108,"score_spread":0.2311358199571291,"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."}}