{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000339402,0.0001518335,0.0001402485,0.0001886329,0.0001141172,0.0001385894,0.0009926623,0.00005802332,0.00001010137],"category_scores_gemma":[0.00141184,0.0001190462,0.00005294675,0.0006876641,0.00009085233,0.0009221486,0.0002066133,0.000171339,0.00000490604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001308384,"about_ca_system_score_gemma":0.00002862022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001548962,"about_ca_topic_score_gemma":0.000008793866,"domain_scores_codex":[0.9985241,0.00006944512,0.0002455114,0.0002738531,0.0006326146,0.0002545257],"domain_scores_gemma":[0.9981475,0.0009634767,0.0001405349,0.0005134252,0.0001414439,0.00009356049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008912294,0.0005236954,0.4908326,0.00008430154,0.0001358475,0.00001147537,0.002545084,0.183301,0.0008492417,0.04479241,0.0002711834,0.276564],"study_design_scores_gemma":[0.0003087379,0.00004280374,0.698782,0.0003210737,0.000008620818,0.00002753722,0.00006970192,0.2957485,0.002456959,0.001256451,0.0006642214,0.0003134282],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3324058,0.0003234085,0.6661615,0.0002035715,0.0006919593,0.00009249817,0.00001217832,0.00009474679,0.00001430987],"genre_scores_gemma":[0.9495772,0.00001336643,0.05011926,0.0000427228,0.00009981553,0.00001256206,0.000004556387,0.00001569445,0.00011486],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6171713,"threshold_uncertainty_score":0.4854562,"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."}}