{"id":"W3102870242","doi":"10.1109/dcc50243.2021.00027","title":"PHONI: Streamed Matching Statistics with Multi-Genome References","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; National Institutes of Health; IFP Energies Nouvelles","keywords":"Computer science; Pointer (user interface); Pattern matching; Matching (statistics); Task (project management); Data mining; Theoretical computer science; Artificial intelligence; Statistics; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001417423,0.0003158032,0.0003658326,0.00008320108,0.0001414853,0.001026889,0.001578246,0.0001501488,0.0001415236],"category_scores_gemma":[0.00001211685,0.0002227623,0.00004187914,0.0001400376,0.00004157865,0.0003327458,0.003698559,0.000557862,0.00002334566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004955149,"about_ca_system_score_gemma":0.0004161935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001900703,"about_ca_topic_score_gemma":0.0005772936,"domain_scores_codex":[0.9979299,0.00008114436,0.0002968874,0.0009122366,0.0004729896,0.0003068573],"domain_scores_gemma":[0.9980305,0.00008821227,0.0002108768,0.001335539,0.0001907027,0.0001441546],"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":[0.00006855658,0.002085353,0.001253469,0.001519088,0.0009873251,0.002717678,0.01903525,0.03641969,0.002055139,0.07392032,0.004909917,0.8550282],"study_design_scores_gemma":[0.001938816,0.0003583489,0.0223204,0.001603967,0.000108478,0.0001217373,0.0019244,0.9454809,0.001525225,0.0145899,0.006627186,0.003400666],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005341579,0.0002688036,0.992283,0.00009079797,0.0005439501,0.0001652438,0.0002025069,0.0002216279,0.0008824961],"genre_scores_gemma":[0.05536975,0.0001613782,0.942488,0.0001136521,0.000067092,0.00002196108,0.0005299358,0.00001623137,0.001232062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9090612,"threshold_uncertainty_score":0.990231,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03412598368677618,"score_gpt":0.2702090828813435,"score_spread":0.2360830991945674,"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."}}