The authors, who have successfully rebutted an earlier NFL investigation, think the DeflateGate investigation was too flawed to conclude with reasonable confidence that the Patriots cheated. For example:
The Wells report’s main finding is that the Patriots balls declined in pressure more than the Colts balls did in the first half of their game, and that the decline is highly statistically significant. For the sake of argument, let’s grant this finding for now. Even still, it alone does not prove misconduct. There are, after all, two possibilities. The first is that the Patriots balls declined too much. The second — overlooked by the Wells report — is that the Colts balls declined too little.
The latter possibility appears to be more likely.
Apparently the Colts' balls were measured later during half-time, so they had more of a chance to warm to room temperature. Also, the refs were used two different gauges to initially inflate the balls before the game and then to re-check them at half-time. The gauges don't quite agree, so...
For example, there is considerable uncertainty concerning the actual pressure of the footballs. The N.F.L. official who checked the pressure before the game used some combination of two pressure gauges to measure the Patriots and Colts balls, but it is not known which particular combination.
One of the gauges, as the report notes, records pressures that are higher than the other. If the official used that gauge to measure the Patriots balls (but not the Colts balls) pregame, then those balls may well have started out with too little air, which could explain a later appearance of intentional deflation. The report, however, does not consider that possibility.
None of which proves the Patriots are as pure as the driven snow, but it creates what may seem like reasonable doubt. Or at least, give the Commissioner an excuse to cut Brady's penalty.