Quite often authors make some claims with some "to the best of our knowledge" disclaimer.


"To the best of our knowledge this is the first time this approach has been used to address this problem".

Is there any research/study/survey that tried to look at how often such claims are false? (e.g. some counterexample can be found)

I am mostly interested in the field of machine learning / data mining in English-speaking venues, however any reference on occurrence of such false assertions would be of value.

  • 3
    Quite often, I would hope. Appending or prepending "AFAIK" to a phrase is really only appropriate when you have a pretty good idea - but just aren't 100% certain - that what you're saying is true. – Moriarty Nov 30 '14 at 18:31
  • 8
    The example you give is of a statement that can be shown to be false, but can't be shown to be true (which is why the authors qualify it in the first place). So I don't know what it means to ask "how often such claims are true." – ff524 Nov 30 '14 at 18:32
  • 2
    A meta-comment: @FranckDernoncourt, you frequently ask questions about researches or studies on a variety of topics which, really, do not seem to attract much research, at least by judging the answers you get, which, AFAIK, are mostly based on personal experience. If there is a thread connecting this series of questions, which do not seem to be driven only by curiosity, it would be nice to mention it explicitly, maybe you'd get more (meaningful/useful?) answers. Moreover, it would be nice if you add to each question which publications or databases you've already searched to find an answer. – Massimo Ortolano Nov 30 '14 at 23:08
  • 2
    Like @MassimoOrtolano says, in most SE communities, when someone requests surveys or solutions to his particular problem he must also provide a) evidence of his efforts so far or b) share the information he has acquired so far to the community. You seem to do neither of those two things, which to my eyes is a bit rude. – Alexandros Dec 1 '14 at 16:54
  • 5
    @Alexandros Yes of course I keep all the information to myself, it's very valuable and one day I'll become rich thanks to it. – Franck Dernoncourt Dec 1 '14 at 17:13

To the best of my knowledge, it is unlikely anyone has done the gruelling work of trawling through the literature, looking for such statements, and then doing the detailed work of finding out if the claim was true. On the other hand, if I state such, you'd have to prove I did have prior knowledge to refute my statement. In itself, that could come close to an accusation of plagiarism in the context you cite. Or at least of sloppy checking of previous work.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.