{"id":"W4200552857","doi":"10.1101/2021.12.15.472871","title":"Matchtigs: minimum plain text representation of kmer sets","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"Academy of Finland; European Commission","keywords":"Representation (politics); Plain text; Computer science; Heuristic; Greedy algorithm; Theoretical computer science; Algorithm; Artificial intelligence; Operating system","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":[0.0009407095,0.001594554,0.001458071,0.002208521,0.0009552817,0.003446417,0.003265489,0.001854486,0.03021886],"category_scores_gemma":[0.008282029,0.000997848,0.001484901,0.003729186,0.0006889898,0.005106389,0.00278052,0.001849377,0.01733668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009232805,"about_ca_system_score_gemma":0.00121818,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001036829,"about_ca_topic_score_gemma":0.001532233,"domain_scores_codex":[0.998431,0.0002408855,0.0001597481,0.0004570864,0.0005327593,0.0001784551],"domain_scores_gemma":[0.997066,0.0008098152,0.0002077612,0.001438608,0.0003583689,0.0001195191],"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":[0.0028194,0.000428402,0.00225495,0.001808407,0.0001917543,0.0005976279,0.0006973674,0.04878712,0.06095597,0.04415454,0.2531027,0.5842017],"study_design_scores_gemma":[0.0006982898,0.0004483137,0.001404566,0.0002063491,0.00009659865,0.0007836974,0.0004578051,0.6390216,0.09877471,0.1338663,0.1240679,0.0001738058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03959332,0.0008529247,0.7824755,0.0009575571,0.0005041171,0.0003859272,0.02766363,0.1384279,0.009139048],"genre_scores_gemma":[0.1351676,0.0003220795,0.7813118,0.000390648,0.0001839854,0.0006356379,0.06241292,0.01126819,0.008307135],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03021886,"threshold_uncertainty_score":0.1010922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0143799075448074,"score_gpt":0.2365947783725539,"score_spread":0.2222148708277465,"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."}}