[A6] rmcorr via lm() with task_id as cluster; cluster bootstrap R = 10000, seeds as in FF2 v2
[A6] pooled            cyclomatic_complexity n = 1914 (383 tasks, 356 repeated) | pooled Spearman 0.948 [0.930, 0.963], Pearson 0.943 | rmcorr 0.887 [0.859, 0.913] (analytic [0.876, 0.897], df 1530, p < 2.2e-16) | rank rmcorr 0.919 [0.893, 0.942]
[A6] pooled            lines_of_code         n = 1914 (383 tasks, 356 repeated) | pooled Spearman 0.912 [0.894, 0.926], Pearson 0.879 | rmcorr 0.788 [0.726, 0.845] (analytic [0.769, 0.807], df 1530, p < 2.2e-16) | rank rmcorr 0.836 [0.803, 0.864]
[A6] pooled            code_smells           n = 1914 (383 tasks, 356 repeated) | pooled Spearman 0.168 [0.084, 0.251], Pearson 0.132 | rmcorr 0.056 [-0.092, 0.198] (analytic [0.006, 0.106], df 1530, p 2.76e-02) | rank rmcorr -0.062 [-0.131, 0.001]
[A6] Claude            cyclomatic_complexity n =  708 (369 tasks, 339 repeated) | pooled Spearman 0.928 [0.902, 0.951], Pearson 0.929 | rmcorr 0.883 [0.810, 0.936] (analytic [0.857, 0.904], df 338, p < 2.2e-16) | rank rmcorr 0.900 [0.822, 0.959]
[A6] Claude            lines_of_code         n =  708 (369 tasks, 339 repeated) | pooled Spearman 0.899 [0.876, 0.918], Pearson 0.884 | rmcorr 0.793 [0.657, 0.882] (analytic [0.750, 0.830], df 338, p < 2.2e-16) | rank rmcorr 0.758 [0.653, 0.834]
[A6] Claude            code_smells           n =  708 (369 tasks, 339 repeated) | pooled Spearman 0.170 [0.072, 0.266], Pearson 0.108 | rmcorr 0.237 [0.000, 0.445] (analytic [0.134, 0.335], df 338, p 1.00e-05) | rank rmcorr -0.009 [-0.138, 0.104]
[A6] Gemini            cyclomatic_complexity n =  604 (313 tasks, 291 repeated) | pooled Spearman 0.947 [0.925, 0.966], Pearson 0.943 | rmcorr 0.865 [0.807, 0.908] (analytic [0.833, 0.891], df 290, p < 2.2e-16) | rank rmcorr 0.878 [0.832, 0.918]
[A6] Gemini            lines_of_code         n =  604 (313 tasks, 291 repeated) | pooled Spearman 0.901 [0.879, 0.920], Pearson 0.869 | rmcorr 0.730 [0.594, 0.826] (analytic [0.671, 0.779], df 290, p < 2.2e-16) | rank rmcorr 0.788 [0.719, 0.842]
[A6] Gemini            code_smells           n =  604 (313 tasks, 291 repeated) | pooled Spearman 0.120 [0.017, 0.218], Pearson 0.081 | rmcorr 0.105 [-0.027, 0.247] (analytic [-0.010, 0.218], df 290, p 7.28e-02) | rank rmcorr 0.002 [-0.046, 0.046]
[A6] GPT               cyclomatic_complexity n =  602 (313 tasks, 289 repeated) | pooled Spearman 0.965 [0.950, 0.978], Pearson 0.951 | rmcorr 0.855 [0.760, 0.927] (analytic [0.820, 0.883], df 288, p < 2.2e-16) | rank rmcorr 0.937 [0.907, 0.966]
[A6] GPT               lines_of_code         n =  602 (313 tasks, 289 repeated) | pooled Spearman 0.930 [0.909, 0.947], Pearson 0.889 | rmcorr 0.781 [0.651, 0.886] (analytic [0.732, 0.823], df 288, p < 2.2e-16) | rank rmcorr 0.914 [0.873, 0.942]
[A6] GPT               code_smells           n =  602 (313 tasks, 289 repeated) | pooled Spearman 0.219 [0.118, 0.318], Pearson 0.210 | rmcorr 0.095 [-0.279, 0.478] (analytic [-0.020, 0.209], df 288, p 1.05e-01) | rank rmcorr -0.077 [-0.221, 0.018]
