cadf vs adf on residuals

Question

I was wondering how I could interpret the results from the Spatial Econometric library's cadf and adf. Running cadf(TS1,TS2,0,1), I obtain the following:

Augmented DF test for co-integration variables:       
CADF t-statistic        # of lags   AR(1) estimate 
     -5.20337048                1        -0.037845 

   1% Crit Value    5% Crit Value   10% Crit Value 
          -5.287           -4.728           -4.462 

I then regress with: res = ols(TS1,TS2); And finally, I run adf(res.resid,0,1):

Augmented DF test for unit root variable:                 
 ADF t-statistic       # of lags   AR(1) estimate 
       -4.939345               1         0.965756 

   1% Crit Value    5% Crit Value   10% Crit Value 
          -3.458           -2.871           -2.594 

Why is the AR(1) estimate different between cadf and adf (1-0.965756 = 0.034244) ?

Thank you