The fallacy of the possible proof consists in an attempt to demonstrate that a factual statement is true or false by establishing the possibility of its truth or falsity. "One of the greatest fallacies of evidence," a logician has observed, "is the disposition to dwell on the actual possibility of its being false; a possibility which must exist when it is not demonstrative. Counsel can bewilder juries in this way till they almost doubt their own senses." This tactic may indeed prove to be forensically effective in an Anglo-American court of law, but it never proves a point at issue. Valid empirical proof requires not merely the establishment of possibility, but of probability. Moreover, it demands a balanced estimate of probabilities pro and con. If historians, like lawyers, must respect the doctrine of reasonable doubt, they must equally be able to recognize an unreasonable doubt when they see one.Deniers apply this fallacy most commonly to torture and forgery. Hargis has done the former most recently in this thread, in which he also reveals his hypocrisy concerning perpetrator witnesses [suddenly two perpetrator witnesses are enough to establish proof].
The rule here is simple. Unless the claimant can show that Hoess was probably being tortured, or acting under fear of torture, at the moment of his confessions, the claim has no merit. Deniers will get nowhere until they accept that they have a burden of proof to demonstrate probability. All else is just conjecture, not history.