{"id":"W4317860139","doi":"10.5281/zenodo.7566229","title":"Computing the Tandem Duplication Distance is NP-Hard","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tandem; Data deduplication; Computer science; Gene duplication; Tandem exon duplication; Parallel computing; Database; Biology; Engineering; Genetics","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":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007113483,0.00009143355,0.00008053084,0.00007260607,0.006120184,0.0008324588,0.002793288,0.00001732796,0.002650107],"category_scores_gemma":[0.00008833733,0.00007901694,0.00003670575,0.0006897012,0.00006659548,0.0003249421,0.00480821,0.0002825347,0.001065579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001201658,"about_ca_system_score_gemma":0.000004030619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001000248,"about_ca_topic_score_gemma":4.910064e-8,"domain_scores_codex":[0.9983411,0.0003102048,0.0001814655,0.0004165221,0.000496157,0.0002545723],"domain_scores_gemma":[0.9987556,0.00003228415,0.0001190374,0.0008196607,0.0001955488,0.00007782425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001216004,0.00009545642,0.000007215858,0.000009992715,0.00001534938,0.000006561207,0.002564474,0.0004690016,0.0008425355,0.04569786,0.5134848,0.4367946],"study_design_scores_gemma":[0.000164596,0.00006509473,0.0007634475,0.000004650023,0.000002343377,0.00007329715,0.0001335845,0.05490669,0.000111081,0.0006049481,0.9430698,0.0001004525],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00365699,0.0001650981,0.9658735,0.007048313,0.0002471753,0.0004146296,0.0001781546,0.001007107,0.02140908],"genre_scores_gemma":[0.9903682,0.00005125762,0.004713308,0.001983195,0.0002221987,1.720425e-7,0.0009141175,0.0005823151,0.001165262],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9867112,"threshold_uncertainty_score":0.9997122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03280414356947456,"score_gpt":0.2440039312811053,"score_spread":0.2111997877116307,"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."}}