{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001641423,0.00009470329,0.00008423843,0.0006328901,0.0002709044,0.001673063,0.003527741,0.00002835551,0.000005248276],"category_scores_gemma":[0.0002553063,0.00008369382,0.00002677491,0.0006944463,0.00003039166,0.009709829,0.001393493,0.0001934713,0.000006592627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002962203,"about_ca_system_score_gemma":0.0002450318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001435648,"about_ca_topic_score_gemma":0.00002164773,"domain_scores_codex":[0.9980227,0.00001676664,0.0003465831,0.0005250669,0.000830217,0.0002587138],"domain_scores_gemma":[0.9990532,0.00005547331,0.00008518447,0.0004774053,0.000221141,0.0001076137],"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":[0.00005882229,0.0001086567,0.0310024,0.00004165608,0.00002839895,0.00008430884,0.0005233824,0.0375398,0.02444611,0.05531747,0.001062232,0.8497868],"study_design_scores_gemma":[0.0001266787,0.00002726329,0.02671529,0.0001570053,0.00000190604,0.00008231551,0.000007621911,0.9625881,0.0004485646,0.001463389,0.008268547,0.0001133625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1678434,0.00006351312,0.8248389,0.0007903174,0.006105322,0.0001431148,0.0001372223,0.00004730157,0.0000308743],"genre_scores_gemma":[0.8238891,0.00001788292,0.175548,0.000144482,0.0003280031,0.000002262013,0.00004211331,0.000006101169,0.00002199798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9250482,"threshold_uncertainty_score":0.9993633,"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."}}