{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001149773,0.001409636,0.002739985,0.001447686,0.001748002,0.0056662,0.002457985,0.002609878,0.02914021],"category_scores_gemma":[0.009814644,0.0009199953,0.001383499,0.003912221,0.001528637,0.00574016,0.00220238,0.004627295,0.009382737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003074066,"about_ca_system_score_gemma":0.003361372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005980211,"about_ca_topic_score_gemma":0.008945007,"domain_scores_codex":[0.9981052,0.0002742448,0.0001093255,0.0007938353,0.0004505331,0.0002667514],"domain_scores_gemma":[0.9906023,0.00725445,0.0004412381,0.0007644089,0.0006317783,0.0003058909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008105871,0.0005642054,0.006789302,0.002451287,0.0005135547,0.0008804665,0.0005209077,0.2385783,0.007690254,0.09888581,0.2749442,0.3673711],"study_design_scores_gemma":[0.0003330089,0.0001297132,0.002160433,0.0001612051,0.0001630489,0.0009093161,0.0003959355,0.4405817,0.004022711,0.5176796,0.03339707,0.00006608276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2192791,0.009714762,0.5158995,0.03234576,0.001763968,0.0009800517,0.0333239,0.01117275,0.1755202],"genre_scores_gemma":[0.6176478,0.00557507,0.2526252,0.002951723,0.001530734,0.000879475,0.03817221,0.002695052,0.07792279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02914021,"threshold_uncertainty_score":0.09748369,"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."}}