{"id":"W2973402705","doi":"10.5539/mas.v13n10p26","title":"Scaled Pearson’s Correlation Coefficient for Evaluating Text Similarity Measures","year":2019,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pearson product-moment correlation coefficient; Similarity (geometry); Correlation; Correlation coefficient; Outlier; Metric (unit); Statistics; Mathematics; Spearman's rank correlation coefficient; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002793418,0.0001984756,0.0002588143,0.0002757,0.0005186755,0.0003243401,0.001817258,0.00006999171,0.000008869338],"category_scores_gemma":[0.0001996513,0.000185954,0.00008950158,0.001200512,0.0002321497,0.0007004487,0.0004388737,0.0001727732,0.00007568383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002559847,"about_ca_system_score_gemma":0.0002416718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005245788,"about_ca_topic_score_gemma":0.000005734938,"domain_scores_codex":[0.9966652,0.00003251466,0.0003342034,0.001072163,0.001336704,0.0005591828],"domain_scores_gemma":[0.9980422,0.0001806091,0.000221585,0.001038434,0.0003883966,0.0001288186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002478714,0.0001038686,0.0005705575,0.0000176384,0.000007938833,4.108106e-7,0.001389881,0.04720849,0.6969073,0.07265757,0.00008566014,0.1810259],"study_design_scores_gemma":[0.0003010912,0.00006481366,0.0007808551,0.00001155381,0.000008439773,0.000001514787,0.00002501305,0.9380786,0.02437464,0.03597237,0.0001486044,0.0002325118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03099556,0.00003173887,0.9634887,0.0001485489,0.0001491616,0.000979358,0.000001659861,0.0004109823,0.003794305],"genre_scores_gemma":[0.7692155,0.000001233798,0.2303078,0.0001902246,0.00001582053,0.00009011389,0.000001756651,0.00001029387,0.0001671761],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8908701,"threshold_uncertainty_score":0.7582983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03021596462251229,"score_gpt":0.3165010133162091,"score_spread":0.2862850486936968,"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."}}