{"id":"W2047386086","doi":"10.1145/506147.506150","title":"On the closest string and substring problems","year":2002,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Substring; Hamming distance; Combinatorics; String (physics); Approximate string matching; Mathematics; String searching algorithm; String metric; Edit distance; Discrete mathematics; Set (abstract data type); Computer science; Algorithm; Pattern matching; Artificial intelligence","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":[0.004705356,0.002735355,0.003858953,0.003485045,0.003116192,0.004420795,0.005137142,0.005322376,0.01227862],"category_scores_gemma":[0.03338671,0.001095331,0.002508814,0.01004381,0.005448339,0.01993572,0.006539696,0.008332925,0.004292056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002790643,"about_ca_system_score_gemma":0.002128113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003003068,"about_ca_topic_score_gemma":0.001770585,"domain_scores_codex":[0.9931073,0.002262999,0.0004722649,0.001631538,0.001937905,0.0005881224],"domain_scores_gemma":[0.9790701,0.01627814,0.0008306561,0.002288523,0.001003204,0.0005293948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000790893,0.0003868366,0.001309627,0.000806519,0.0001553201,0.0003299323,0.000598982,0.1660438,0.001250052,0.544903,0.04592346,0.2375017],"study_design_scores_gemma":[0.000105861,0.00009279431,0.0001786048,0.0001049028,0.00003601711,0.0002532779,0.0001429365,0.1531081,0.0009227722,0.8295049,0.01551029,0.00003963572],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02192403,0.01149669,0.9340395,0.008127998,0.0009029029,0.0002402139,0.0008362872,0.001216461,0.0212158],"genre_scores_gemma":[0.2131836,0.01410462,0.7360367,0.003697814,0.003475992,0.0007446285,0.00411024,0.001135226,0.02351131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01227862,"threshold_uncertainty_score":0.04107606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03950130813966558,"score_gpt":0.2181354447543569,"score_spread":0.1786341366146914,"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."}}