{"id":"W2952553535","doi":"10.48550/arxiv.1304.2798","title":"Optimal DNA shotgun sequencing: Noisy reads are as good as noiseless reads","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Shotgun sequencing; Shotgun; DNA sequencing; Sequence (biology); DNA; Computational biology; Noise (video); Computer science; Channel (broadcasting); Algorithm; Biology; Genetics; Artificial intelligence; Gene; Computer network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003323879,0.0007318362,0.0007492685,0.000400784,0.0003932033,0.0005357157,0.004778431,0.000718531,0.0002231522],"category_scores_gemma":[0.00006038838,0.0007750366,0.0003393606,0.0007361508,0.0001896806,0.001392468,0.006999923,0.001216594,0.001389002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005595898,"about_ca_system_score_gemma":0.0007135535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001880008,"about_ca_topic_score_gemma":0.00003754601,"domain_scores_codex":[0.9958256,0.0002281084,0.0004113623,0.002380684,0.0003465299,0.0008076525],"domain_scores_gemma":[0.9949442,0.0001352049,0.0006345104,0.003294222,0.0004356005,0.0005563214],"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":[0.000169565,0.0006794057,0.003450483,0.0004712341,0.0005404253,0.007091336,0.001760484,0.2839963,0.001297022,0.6826504,0.013004,0.00488928],"study_design_scores_gemma":[0.001294149,0.0003326637,0.001729998,0.000859996,0.0002019803,0.0001431202,0.0005296591,0.9334043,0.002618525,0.04477674,0.01159082,0.002517993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6382639,0.0001046708,0.3410191,0.0002202438,0.001331379,0.0005998381,0.00007695142,0.0006959034,0.01768799],"genre_scores_gemma":[0.9787746,0.0002715491,0.01094663,0.0002887893,0.0002872983,0.000005423184,0.000125566,0.00005545182,0.009244714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.649408,"threshold_uncertainty_score":0.9994701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06393007705734222,"score_gpt":0.1989365968999761,"score_spread":0.1350065198426339,"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."}}