{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015091,0.001699613,0.001150366,0.003819812,0.0009827839,0.003412539,0.005070748,0.001584944,0.01461849],"category_scores_gemma":[0.01284523,0.001231571,0.001320217,0.006047505,0.0009706463,0.004408022,0.004669329,0.001986732,0.01111338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001592484,"about_ca_system_score_gemma":0.002365414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005044919,"about_ca_topic_score_gemma":0.005477422,"domain_scores_codex":[0.9982981,0.0001267169,0.0001703472,0.0004520233,0.0007907353,0.0001622265],"domain_scores_gemma":[0.9967428,0.0008451692,0.000218811,0.001533491,0.0005053643,0.0001543932],"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":[0.001122903,0.0002043431,0.004380326,0.0004713247,0.0002015119,0.0004133415,0.0004521797,0.03368881,0.01868214,0.040608,0.1671481,0.732627],"study_design_scores_gemma":[0.0004449916,0.0002079017,0.001997771,0.000113634,0.00008461397,0.0007008627,0.0002240898,0.7216741,0.08409967,0.08875113,0.1015326,0.0001686274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01372889,0.0007503998,0.7222788,0.000575019,0.0005079629,0.0002828304,0.009219251,0.247168,0.005488817],"genre_scores_gemma":[0.09201369,0.0003611147,0.8699385,0.0003353519,0.0001992581,0.0006145197,0.02161041,0.009311259,0.005615887],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01461849,"threshold_uncertainty_score":0.0489037,"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."}}