MEMORANDUM ***

David Benjamin Webster pled guilty to one count of bank fraud in violation of 18 U.S.C. § 1344. He appeals the *318district court’s calculation of his Guidelines-recommended sentence, arguing that the district court clearly erred by finding that Webster caused loss in excess of $200,000 and imposing an eight-level sentence enhancement under the relevant version of the United States Sentencing Guidelines. See U.S.S.G. § 2F1.1 (1998). Webster has been released from prison, but his challenge is not moot because he remains subject to a term of supervised release. See United States v. Verdin, 243 F.3d 1174, 1178 (9th Cir. 2001).

Although the guideline calculation was incorrect, the error is harmless. The “loss is the value of the money, property, or services unlawfully taken; it does not, for example, include interest the victim could have earned on such funds had the offense not occurred.” U.S.S.G. § 2F1.1 app. n. 8. At sentencing, the government’s own witness and supporting documentation clearly established that at most, the total demonstrated loss exclusive of interest was less than $200,000.

The government’s reliance on the application notes’ statements that “the loss need not be determined with precision” and that “[t]he court need only make a reasonable estimate of the loss, given the available information” is misplaced. Id. app. n. 9. Note 9 refers to the use of estimated loss figures. Cf. United States v. King, 257 F.3d 1013, 1025 (9th Cir. 2001) (approving the use of estimated losses in light of “the difficulty inherent in calculating loss caused by a mail fraud scheme”). It does not excuse the improper inclusion of a known amount of interest or the introduction of arithmetical errors while tallying determinate loss figures. Given the district court’s unequivocal statement that “even if it were to apply the advisory guideline range urged by the defendant, the Court would have sentenced the defendant to 24 months of incarceration” anyway, and the fact that Webster has not suggested that the loss computation’s relationship to a term of supervised release is anything but less direct than its connection to incarceration, the error was harmless. See United States v. Menyweather, 447 F.3d 625, 634 (9th Cir. 2006) (holding any possible error in a Guidelines calculation harmless where this court was “confident[ ]” that “the district court could — and would — impose the same sentence again under the now-advisory Guidelines regime”).

AFFIRMED.