{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007048136,0.0001139962,0.0002257057,0.0003313296,0.000683499,0.0002252147,0.0009334297,0.00007852895,0.00004006598],"category_scores_gemma":[0.00008544067,0.0001090597,0.00003240626,0.0008106264,0.0002015283,0.003236172,0.0007116828,0.0002671041,0.0001335703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001847564,"about_ca_system_score_gemma":0.0008523752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001434611,"about_ca_topic_score_gemma":0.0002483081,"domain_scores_codex":[0.9980136,0.0001802493,0.0002441112,0.0002291493,0.001025489,0.0003074664],"domain_scores_gemma":[0.9977088,0.0001138381,0.0001948791,0.000590782,0.001210943,0.0001807503],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006193012,0.0005093433,0.001387153,0.003562552,0.0004031295,0.001289414,0.06173223,0.01158083,0.003536842,0.6189768,0.01195716,0.2844452],"study_design_scores_gemma":[0.01020369,0.0009968376,0.02946433,0.002206643,0.00005495646,0.0003535537,0.1212452,0.587509,0.001777127,0.0004518661,0.2443704,0.001366433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01403238,0.00003127708,0.9786839,0.0001411675,0.0001619959,0.0001947213,0.0002340095,0.00008281202,0.006437688],"genre_scores_gemma":[0.787764,0.00003803233,0.2117273,0.00001448192,0.00002756322,9.336624e-7,0.0001620061,0.00000327812,0.0002623485],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7737316,"threshold_uncertainty_score":0.5256991,"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."}}