{"id":"W2007351432","doi":"10.5555/2664398.2664399","title":"An accurate estimation of the Levenshtein distance using metric trees and Manhattan distance","year":2012,"lang":"en","type":"article","venue":"International Workshop on Software Clones","topic":"Software Engineering Research","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Levenshtein distance; Metric (unit); Precision and recall; Computer science; Edit distance; Software; Euclidean distance; Distance measurement; Data mining; Artificial intelligence; Engineering","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":[0.001897747,0.001037007,0.001113692,0.006246792,0.0007573121,0.001693954,0.001440268,0.001056086,0.00108253],"category_scores_gemma":[0.01584725,0.0005239113,0.0007026815,0.004086721,0.0008282042,0.00418226,0.001233338,0.001123688,0.001236388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009545948,"about_ca_system_score_gemma":0.000790544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003433818,"about_ca_topic_score_gemma":0.003221539,"domain_scores_codex":[0.995532,0.0008334024,0.0002610938,0.0007081924,0.00245687,0.0002083963],"domain_scores_gemma":[0.9917877,0.003510188,0.001002915,0.001055499,0.002464991,0.0001786405],"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":[0.0002769315,0.0001251264,0.01718274,0.0004335102,0.0002726095,0.0003689789,0.0007692234,0.07282839,0.05238182,0.03731692,0.004241253,0.8138024],"study_design_scores_gemma":[0.00002332282,0.0003939756,0.01518772,0.0000916693,0.00009338394,0.002006152,0.0003506833,0.8623321,0.05597183,0.03966514,0.02366162,0.0002223694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01880349,0.0008405914,0.9784676,0.00005274138,0.000050651,0.00002999565,0.00007707534,0.0008431784,0.0008345883],"genre_scores_gemma":[0.2482852,0.0008425491,0.7477258,0.00004911811,0.00009746249,0.00008805883,0.0005384202,0.0002762555,0.002097134],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006246792,"threshold_uncertainty_score":0.01003641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03618371373310392,"score_gpt":0.3293756478946939,"score_spread":0.29319193416159,"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."}}