{"id":"W4402391085","doi":"10.23889/ijpds.v9i5.2801","title":"Using Polars to Improve String Similarity Performance in Python","year":2024,"lang":"en","type":"article","venue":"International Journal for Population Data Science","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Python (programming language); Computer science; String (physics); Similarity (geometry); Programming language; Physics; Artificial intelligence; Theoretical physics","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":[0.005002317,0.002594684,0.001470332,0.002996851,0.001820119,0.005164126,0.005328964,0.0008902933,0.04032834],"category_scores_gemma":[0.02428513,0.001571396,0.003124915,0.006007712,0.001445414,0.00840081,0.007136353,0.003238246,0.03127623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001975829,"about_ca_system_score_gemma":0.004702414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006534243,"about_ca_topic_score_gemma":0.005043691,"domain_scores_codex":[0.9925391,0.0010213,0.0009504051,0.001333648,0.003550568,0.0006049765],"domain_scores_gemma":[0.9936789,0.001627548,0.0005677564,0.001815456,0.001914187,0.0003961938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001914056,0.0004568041,0.01470367,0.002597486,0.0005576542,0.0005247522,0.001477938,0.02526682,0.01404411,0.03491023,0.4652791,0.4382675],"study_design_scores_gemma":[0.0005630521,0.0004423035,0.007939671,0.0004321345,0.0001812919,0.0006364257,0.0006052529,0.3838324,0.08427584,0.08982948,0.4307647,0.0004975178],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01281966,0.0003448205,0.2853724,0.0004996428,0.0004462291,0.0002564058,0.01520631,0.6751629,0.009891641],"genre_scores_gemma":[0.1127677,0.0006123392,0.6377954,0.001005883,0.0002303737,0.001307233,0.07865972,0.1517678,0.01585365],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.04032834,"threshold_uncertainty_score":0.1349117,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1014231894988951,"score_gpt":0.4163351249224874,"score_spread":0.3149119354235923,"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."}}