{"id":"W3161267034","doi":"10.1109/dcc50243.2021.00027","title":"PHONI: Streamed Matching Statistics with Multi-Genome References","year":2021,"lang":"en","type":"article","venue":"CINECA IRIS Institutial research information system (University of Pisa)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Human Genome Research Institute; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Israel Institute for Biological Research; Japan Society for the Promotion of Science; Agencia Nacional de Investigación y Desarrollo; IFP Energies Nouvelles; National Institutes of Health; National Science Foundation","keywords":"Computer science; Pointer (user interface); Pattern matching; Matching (statistics); Code (set theory); Source code; Data mining; Theoretical computer science; Artificial intelligence; Statistics; Programming language; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001369123,0.001481907,0.001029137,0.003645167,0.0008279718,0.002742433,0.004286685,0.001249013,0.01413512],"category_scores_gemma":[0.01041414,0.001006588,0.001112459,0.005494436,0.0007778784,0.003381835,0.003858993,0.001485899,0.008097962],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519419,"about_ca_system_score_gemma":0.002150422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004977029,"about_ca_topic_score_gemma":0.005521219,"domain_scores_codex":[0.9986444,0.0001080949,0.000143853,0.0003438001,0.0006305946,0.0001293118],"domain_scores_gemma":[0.9972742,0.0007232833,0.0002017852,0.001213008,0.0004614608,0.0001262063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001194366,0.0001935618,0.004229089,0.0003735637,0.0001776082,0.00040495,0.0003784135,0.02755628,0.01744537,0.02573394,0.1248411,0.7974716],"study_design_scores_gemma":[0.000443476,0.0002564181,0.002293736,0.00009981624,0.00008584084,0.000780536,0.0002129687,0.7639308,0.08558862,0.05104363,0.09512198,0.0001422802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01749999,0.0007934143,0.7361737,0.0005235785,0.0004902571,0.0003513304,0.008000399,0.2297905,0.00637685],"genre_scores_gemma":[0.09709445,0.0003227211,0.8731238,0.0002627506,0.0001635918,0.0005910118,0.01637178,0.006262875,0.005807016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01413512,"threshold_uncertainty_score":0.04728669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06942308776856505,"score_gpt":0.289860813260637,"score_spread":0.220437725492072,"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."}}