In Theory

When a distinguished but elderly scientist states that something is possible, he is almost certainly right. When he states that something is impossible, he is very probably wrong.

—Clarke's first law

Whenever a scientist character says that something could "theoretically" have happened, it's a perfect explanation of what actually happened, even if everyone else says how unlikely it is. Similarily, if a scientist character proposes a "theoretical" solution to a problem, it'll always solve the problem, but not without a lot of tension over whether or not it will work.

For a reason as to why "theoretical" explanations and solutions are so often successful, see Gravity Is Only a Theory.

This is a corollary of The Law of Conservation of Detail, and is often found around Techno Babble. Compare with Crazy Enough to Work.

Examples of In Theory include:

Film

Sunshine: In a (partial) subversion, the characters pick up a second bomb, purely because they think "two have a better chance than one". Their computer simulation even shows that what exactly will happen is completely unknowable.
Subverted in Back to The Future: Doc explains that a Temporal Paradox caused by you seeing yourself could theoretically destroy the universe ("Granted, that's a worst-case scenario. The effects may be limited to just our own galaxy.") When one such paradox actually does occur... all that happens is both people faint on the spot (which he also predicted as a possible outcome).

Live Action TV

Fringe: Walter (as an actual "distinguished" but elderly scientist) does this all the time, with Peter pointing out how crazy it seems.
Star Trek: Every series, every episode.
- This is prevalent to the point where the Federation hires theoretical scientists as engineers. The TNG Enterprise was largely designed by theoretical physicist Dr. Leah Brahms, who demonstrates a contempt for applied science that's altogether unhealthy for an engineer, to say the least. One fan lambastes her character here.