Talk:String theory/Archive 4

Page contents not supported in other languages.
From Wikipedia, the free encyclopedia
Archive 1 Archive 2 Archive 3 Archive 4 Archive 5 Archive 6

Consciousness as vibrating strings

Is it true that in string theory consciousness is like electromagnetic waves and electromagnetic brain waves are the same thing as vibrating very long strings in space? So Consciousness in string theory is vibrating strings and sinusoid with many over waves of those vibrating strings is the same as electromagnetic brain waves sinusoid with many over waves? —Preceding unsigned comment added by 84.240.9.58 (talk) 17:57, 23 October 2010 (UTC)

No. 66.66.5.195 (talk) 02:29, 14 December 2010 (UTC)

That sounds more BS than string theory. But perhaps only slightly. —Preceding unsigned comment added by 121.209.152.190 (talk) 19:10, 2 January 2011 (UTC)

Exaggeration regarding testability and science

"The theory has yet to make testable experimental predictions, which a theory must do in order to be considered a part of science."

That sounds suspiciously like some kind of advocacy of a particular position. If mathematics is not "a part of science", then someone had better tell that to the College of Natural Sciences at my local university. Also, I've heard string theorists make all kinds of predictions, just mostly not ones that can be tested at any currently-reasonable cost. Can someone with less bias please find a more neutral way to phrase this? 146.6.204.155 (talk) 18:58, 7 February 2011 (UTC)

Possible strings as fibers instead of circles.

I have a proposal for those with open minds: If you look at the way a transmitting antenna works, different lengths produce different frequencies. I think it may be possible these strings are in fact different lengths of fibers, not circles, vibrating at different frequencies and different strengths that harmonically interact with one another and either attract or repel on a sonic level. — Preceding unsigned comment added by Dgm76513 (talk • contribs) 08:57, 11 March 2011 (UTC)

Testable?

Brian Greene was on NPR recently talking about how this maybe tested. That nasty little sentence is out of date.

As mentioned under falsifiability, Particle physicists from the Vienna University of Technology and Institut Laue-Langevin (ILL) have developed a new technique named Gravity Resonance Spectroscopy Netdragon (talk) 19:53, 23 April 2011 (UTC)

I'm removing that sentence. It's fallicious. Netdragon (talk) 19:53, 23 April 2011 (UTC)

Falsifiability

First, there's a question about whether Popper required that falsifiability be specific to the theory in question. The answer is no (at least to my knowledge), he didn't, because such a criterion would make no sense. How would you decide which theory is the "original", and therefore legitimately falsifiable, and which is the derivative one?

Second, someone asserted that falsifiability is necessary but not sufficient for a theory to be scientific. I don't think that's the case (and by the way, wiki contradicts itself on that - in one place at least it agrees with that, but in others it contradicts it and says theories are scientific by Popper's criteria if and only they are falsifiable). Popper himself says the following:

"In this way, the recognition of unilaterally decidable statements allows us to solve not only the problem of induction (note that there is only one type of argument which proceeds in an inductive direction: the deductive modus tollens), but also the more fundamental problem of demarcation, a problem which has given rise to almost all the other problems of epistemology. For our criterion of falsifiability dis- tinguishes with sufficient precision the theoretical systems of the empirical sciences from those of metaphysics..." (The Logic of Scientific Discovery, op. 316)

This seems quite clear to me - falsifiability is (according to Popper) sufficient (and of course necessary) to distinguish between science and metaphysics. Therefore as far as I can tell that section is correct as written, and I will remove those tags after some time unless someone else comments here and disagrees.Waleswatcher (talk) 18:28, 14 January 2011 (UTC)

  • Correct. Popper didn't intend for it to be a strict requirement. IN FACT, Popper was a stark critic of logical positivism even though logical positivism was founded off Popper falsifiability. Netdragon (talk) 19:52, 23 April 2011 (UTC)
  • Correct. Falsifiability is sufficient but can be overkill
    • I think the way it was described is fine and left it alone. The original writer isn't saying falsifiability isn't enough, but that it just isn't compelling if there are no unique predictions. See if the way I re-organized things makes this more clear (and didn't make a direct statement that string theory has no unique predictions (yet it still is implied so maybe a slight rewording is in order) Netdragon (talk) 20:39, 23 April 2011 (UTC)
  • Furthermore, the argument that there is no way to test quantum gravity is bogus and outdated. Particle physicists from the Vienna University of Technology and Institut Laue-Langevin (ILL) have developed a new technique named Gravity Resonance Spectroscopy which will serve that purpose Netdragon (talk) 19:52, 23 April 2011 (UTC)
  • Hence, the whole section on testability needs to be overhauled Netdragon (talk) 19:52, 23 April 2011 (UTC)
    • I cleaned it up, but only removed quotes (note references). The rest was just moving things around other than adding a note about Gravity Resonance Spectroscopy. Netdragon (talk) 20:39, 23 April 2011 (UTC)

"11-dimensional space" was corrected to "11-dimensional spacetime"

In the opening introduction, it mistakenly referred to "11-dimensional space". I corrected it to "11-dimensional spacetime". - Brad Watson, Miami 72.153.60.84 (talk) 12:47, 14 April 2011 (UTC)

I would agree with 11 dimensions. — Preceding unsigned comment added by 203.83.248.32 (talk) 05:55, 3 June 2011 (UTC)

Good Article

How do you nominate an article to be good? --Gilderien (talk) 06:43, 9 May 2011 (UTC)

See WP:GAN.TR 12:03, 9 May 2011 (UTC)

Formula?

What's the central formula of this theory? I mean, there has to be something likem a Lagrange density or something similar... --91.4.236.151 (talk) 18:09, 20 July 2011 (UTC)

To start, check out the pages on Nambu-Goto action or Polyakov action. Isocliff (talk) 21:31, 20 July 2011 (UTC)
I was just looking over this article and the talk page. Im thinking this article could benefit from a little more meat, i.e. specific formulas. This question came to mind, and seems to reinforce the need. Im thinking the article could benefit from at least a few of the basic formulas, i.e. how the p-brane worldvolume action generalizes the point particle worldline action, and just a few basic statements about the Nambu-Goto action and Polyakov action.... Im aware that this article shouldn't be a treatise on all the math of string theory, but these definitely seem appropriate. Thoughts? Isocliff (talk) 23:21, 4 September 2011 (UTC)

How to test it.

One way to test string theorys predictions about hidden dimensions would be to produce photons with a wavelength shorter than the size of the hidden dimensions. The energy problem can be solved by firing multiple laser beams at a single nanoparticle, heating it to locally extreme temperatures. The ultra-hot nanoparticle would radiate a small number of ultra-short photons, but the photons would make up in energy what they lack in numbers. Since string theory predict that gravity and electromagnetism unify in hidden dimensions, the test should involve gravimeters. — Preceding unsigned comment added by 109.58.249.18 (talk) 08:26, 29 July 2011 (UTC)

"Correct"

From the lead section:

"Five major string theories were formulated. The main differences among them were the number of dimensions in which the strings developed and their characteristics. All of them appeared to be correct, however."

I find the statement "All of them appeared to be correct" slightly strange and at odds with the rest of the article, which says that the theory has not even made any testable experimental predictions. So, in what sense is "correct" being used? 86.179.1.213 (talk) 01:29, 2 September 2011 (UTC)

It's being used in a theoretical sense Dauto (talk) 02:10, 2 September 2011 (UTC)
And what does correct mean in a theoretical sense? (I think this sentence should be rephrases.)TR 05:52, 2 September 2011 (UTC)
(OP) I agree. Perhaps it just means "consistent"?? 86.160.208.79 (talk) 11:17, 2 September 2011 (UTC)
Since there have been no further comments, and pending clarification of exactly what it means, I have removed the sentence. At the moment I feel it does more harm than good because to the ordinary reader "correct" means "an accurate model of the real physical world". 86.160.212.182 (talk) 17:02, 6 September 2011 (UTC)

Unified Strings (u21s19) Theory - NASA Conference Presentation

I added the following to Online Material...

  • Watson II, Richard 'Brad'shaw. Identifying 'True Earth-like Planets' - All New Worlds Are Built On 7_4 (like Earth) Or 6_4 http://exep.jpl.nasa.gov/exep_exoMtgPosters.cfm Presentation at the NASA Conference Missions for Exoplanets 2010-2020 held in Pasadena, CA on April 21-23, 2009 - Unified Strings (u21s19) Theory is presented with the aspects of 1-dimensional time symmetry. Indirect evidence of strings is documented for the first time and u21s19 theory is used to predict the characteristics of all 'true Earth-like planets'. - Brad Watson, Miami 66.229.56.118 (talk) 13:31, 16 September 2011 (UTC)

That's a very strange paper. I wonder how stuff like that gets on a NASA conference. It reminds me of the timecube guy Bhny (talk) 14:30, 16 September 2011 (UTC)

Bhny, your comment reminds me of those that attacked Galileo's, Newton's, and Einstein's theories. - Brad Watson, Miami 66.229.56.118 (talk) 14:42, 16 September 2011 (UTC)

How is the string theory scientific?

This article claims that the string theory is a scientific theory even though the string theory does not adhere to the scientific method (has no testable predictions) and is by definition pseudo-scientific.

It's possible for something to be falsifiable and still have no testable predictions. According to this article I can say that anything is scientific if it relies on the truth of General Relativity or Quantum Mechanics even if it has no testable predictions, which is obviously nonsense.

Using this article's reasoning we can conclude that Intelligent Design is scientific.

So why are the authors of this article biased towards making the string theory appear scientific? --96.255.71.164 (talk) 04:42, 4 September 2011 (UTC)

You're just misinformed. String theory has testable predictions. Dauto (talk) 04:53, 4 September 2011 (UTC)

The article has a lot of criticism and the intro doesn't say that it is a "scientific theory", it says it's a research framework that is a contender for a theory of everything. I think it's safe to call it scientific research. Bhny (talk) 15:20, 4 September 2011 (UTC)

It would also be safe to call it a scientific theory but the article chooses to be conservative which is fine. Dauto (talk) 15:28, 4 September 2011 (UTC)
For some reason the Wikipedia editors have blocked out my response, so go read it here http://en.wikipedia.org/wiki/User_talk:96.255.71.164#String_theory_not_scientific
--96.255.71.164 (talk) 05:54, 30 September 2011 (UTC)
If anything the article leans heavily to the conservative side. String theory is falsifiable which by definition means that it makes experimental predictions. The only question is how novel or significant those predictions are, which is debatable and under active research. So the last sentence of the first paragraph seems to be incorrect. Isocliff (talk) 22:23, 4 September 2011 (UTC)
In what way exactly is the sentence wrong? It says "testable predictions". Obviously string theory makes predictions. Isn't the big problem that the predictions haven't been testable?
(the weasel words- "some scientists" need to be fixed) Bhny (talk) 02:14, 5 September 2011 (UTC)
Well one important example is gravity and general relativity. These can be viewed as "obvious" today or "postdictions", but its still true that every time we test general relativity, as in the recent frame-dragging experiments by Gravity Probe B, we are doing experiments that could falsify string theory if they produced the wrong result. The same can be said of the experiments that have been done in recent years verifying the exactness of the Lorentz symmetry. So one could make a case that the ways to test string theory are so far not yet sufficiently convincing, but its wrong to assert categorically that its untestable, unfalsifiable, unscientific, or anything like that.
It would be nice to be able to say it predicts us to observe particle X at exactly Y energy, but there doesn't seem to be any justification for expecting this would be the case. Im not an expert on the phenomenology or anything, but its clear that string theory is compatible with all kinds of particle physics content, but there also exist a lot of very firm rules (such as dictated by dualities, etc) that can be checked in principle. To check them to a significant degree probably requires very high energy collisions, but the fact that these tests are economically inconvenient to humans is not the same thing as being untestable. Isocliff (talk) 04:22, 5 September 2011 (UTC)

String theory is scientific by any definition I know of, the best of which is Popper's. To be scientific, theories (according to Popper) only need to be falsifiable. But as is mentioned in the article, this is obviously the case for string theory. For instance string theory is locally Lorentz invariant. Many experiments have been done to check whether this holds for nature or not. If any of those experiments (past or future) show that nature isn't locally Lorentz invariant, string theory is falsified. So it's clearly scientific by that criterion. Obviously string theory is more than just Lorentz invariance, and so to convincingly confirm that it's right we need to do more than just check that nature is Lorentz invariant. There's a discussion of that in there too.

I don't think the fact that string theory is mathematical belongs in that section. Mathematics is too general to be falsified, it's just the logical consequences of various sets of axioms, and axioms cannot be falsified.Waleswatcher (talk) 14:07, 30 November 2011 (UTC)

Before further changes get made to the testability section, perhaps we should discuss them here. Something close to the language that's there now was extensively discussed and finally agreed on several years ago. There are some basic facts relevant here: string theory is quantum mechanical, all known versions of it reduce to Einstein's general relativity (the full, non-linear theory) in the low energy limit, and all string theories are fundamentally Lorentz invariant. That makes them falsifiable, full stop. Therefore, they are scientific according to Popper. There's no debate I'm aware of on that, because these really are basic facts about the theory. The problem of string theory is that it probably doesn't make predictions that are falsifiable with current technology AND that are "new", meaning not shared by other putative theories that are QM, Lorentz invariant, and reduce to GR (never mind that no other such theory exists....). Waleswatcher (talk) 17:04, 8 December 2011 (UTC)

Two small points on history

Useful article. Comments:

1. The term "bootstrap program" is used but undefined and meaningless to outsiders.

2. Has actually nothing worth noting happened since 1997? Or is the jury still out? Recent controversies would be of interest.

Burressd (talk) 21:14, 30 November 2011 (UTC)


I added a link to "bootstrap model". I find the wording redundant "...complete the bootstrap program for this model". Could we change it to "complete the bootstrap model"? Bhny (talk) 22:15, 30 November 2011 (UTC)

widely believed to be consistant?

Since string theory is widely believed[who?] to be a consistent theory of quantum gravity, many hope that it correctly describes our universe, making it a theory of everything.

Really? It widely believed to be consistant? Consistant with itself? That means no divergences or infinities? Did somebody prove that? Or it's widely believed that somebody has proved that, even though nobody has actually proven that? I suppose we need a cite that many people believe something that isn't true. SBHarris 06:20, 8 December 2011 (UTC)

The phrase "consistent with itself" is a tautology. These questions are the subject of countless papers that you may read, and yes all conceivable kinds of self-consistency checks have been passed. In practice, establishing consistency means checking in detail that all rigorously derivable conclusions are consistent with one another, its much more difficult to prove that all possible logical inferences that may ever be drawn will all be consistent, but so far there is no consistency problem whatsoever. If you want to be precise, the consistency of quantum field theory isn't a rigorously derivable truth either, but that doesn't mean its inconsistent. In fact there's a huge amount of evidence that it is consistent. So you're "who" tag doesn't make much sense. – Isocliff (talk) 06:47, 8 December 2011 (UTC)
QFT (or more precisely, non-Abelian guage theories without anomalies) are renormalizable and free of infinities. This basically makes the entire standard model (all forces but gravity), renormalizable, as t'Hooft proved in 1971. [1] No string theory that predicts fermions has been proven finite and free of divergences beyond the 3-loop case. So the idea that string theories that are candidates to be theories of everything are "consistent," is rather like claiming that Fermat's theorum has so far passed all consistancy checks because the integers 3, 4 and 5 have been checked! [2]. (Yes, I know Fermat's theory was finally proven for all integers, but that's not what has happened to any string theory that has any chance of being a discription of nature). Smolin's paper on these problems, that later was expanded into a popular book (The Trouble With Physics) is available here: [3]. Here's what is says about consistancy, and it quotes from the group that has actually computed terms.

(from page 34) "As it does not appear to be widely appreciated that the consistency of string perturbation theory is still open [26], I quote here from a recent paper by experts in the field, which announced the proof of consistency at the two loop level: (quote follows) Despite great advances in superstring theory, multiloop amplitudes are still unavailable, almost twenty years after the derivation of the one-loop amplitudes by Green and Schwarz for Type II strings and by Gross et al. for heterotic strings. The main obstacle is the presence of supermoduli for world-sheets of non-trivial topology. Considerable efforts had been made by many authors in order to overcome this obstacle, and a chaotic situation ensued, with many competing prescriptions proposed in the literature. These prescriptions drew from a variety of fundamental principles such as BRST invariance and the picture-changing formalism, descent equations and Cechco homology, modular invariance, the light-cone gauge, the global geometry of the Teichmueller curve, the unitary gauge, the operator formalism, group theoretic methods, factorization, and algebraic supergeometry. However, the basic problem was that gauge-fixing required a local gauge slice, and the prescriptions ended up depending on the choice of such slices, violating gauge invariance. At the most pessimistic end, this raised the undesirable possibility that superstring amplitudes could be ambiguous, and that it may be necessary to consider other options, such as the Fischler-Susskind mechanism[131].

As Smolin makes clear, the problem with the (infinite number of) string theories is not what they show, but what people THINK they show. No, Mandelstam did NOT show that any string theory is free of all infinities, or even that it is free to the extent of what t'Hooft did for guage theories. Smolin himself believed prior to his review what this colleagues had been telling him, that at least some versions of 3-D string theory that describe actual known particles, or are capable of it, were free of infinities (which means they might possibly be true). So far, none has actually been proven to be so.

So, string theory is DIFFERENT from guage theory QFTs describing the 3 non-gravity forces of the standard model. So, in what sense does your sentence make sense?

As a second problem, what is this stuff about "theories of everything"? Because all string theories are dependent on a Minkowski SR background which does not change in time, so far there are no quantum gravity theories that are free of infinities for even strong field gravity waves, which are the needed kind to deal with. After all, the flat-space-limit weak-field spin-2 gravity quantum was presented in 1930, and nobody needs strings to describe it-- you can read about weak field "gravitons" in Misner-Thorne-Wheeler. The "gravitons" in all string theories today are this same weak-field gravity quanta, so the fact these particular gravitons have no infinities, is not very interesting, since weak gravity waves are obviously not strong enough to have any contact with a "theory of everything," and certainly are not "quantum gravity" as we need it. Plain old general relativity describes gravitational waves far more powerful than this, but of course by that time, the field is not quantizable. Weak field gravitons never had any infinities before anybody had thought of string theories, but then, they also never had enough energy to need anything but a linearized GR field description anyway-- so what's the point? In other words, if string theories reduce to linearized gravity (as they all do), but not general relativity (which they most certainly by definition do NOT do, as Smolin points out), then what's the point? All that means, is these theories reduce to a field theory that isn't even as accurate as the field theory Einstein came up with, in 1915. Einstein's generalization has passed tests (linear gravity doesn't predict Mercury's precession). String theory (if you can call it a theory) has passed no tests, but if it reduces in the end to linear gravity, as all 101500 versions of it do, it can't be a candidate for a theory of everything (TOE), since it isn't even a candidate for describing the orbit of Mercury, let alone more interesting physics. So again, which people hope which string theory will be a theory of everything, and which theory is it, that they have hopes for? There are more string theories than particles in the universe by far, but the right one certainly cannot be any of the background dependent-ones. And if Smolin is right, all proposed classes of string theories are background dependent (they live in 4-d asymptotically flat space-time, even if they do have extra dimensions), which means NONE of them can possibly be candidates for TOEs.

To put this another way: You see those loops that are supposed to be the "gravitons" in string theories? Do you see them actually bending the space-time through which they move? No? That's right, you don't. And that's a HUGE problem. Since in any "Theory of Everything," they must. SBHarris 21:42, 9 December 2011 (UTC)

Despite your frequent use of the caps lock, almost every sentence you wrote is wrong. All string theories (or more precisely, all corners of string theory) possess general relativity as their low energy limits, not linearized gravity. This is a completely unambiguous, quantitative conclusion you can see worked out in detail in any string theory textbook. You should not be using a popular level book as you singular resource in order to dispute the most basic facts about what string theory implies, especially if its a book written by a person whose sole purpose is to reduce the stature of string theory and get more people to work on his own idea. String theories are fully diffeomorphism-invariant, i.e. they possess the same gauge symmetry as general relativity, and frequently this freedom is used to gauge fix to flat space in order to make calculation easier, but any suggestion that string theory is wedded to flat space is quite far removed from reality. If this was true, string theory would not have anything remotely approaching the interest and activity that it does. (and again its pretty hard not to notice if you step one inch into actually learning the subject)
This means that string theory is fully background-independent in any physical sense of the word, because any change in the background is shown to be equivalent to a particular condensation of matter within it. The only case you can really make, and its a legitimate one, is that we should try to find a language that makes the background-independence manifest. As Joe Polchinski (who wrote one of the best textbooks on the subject) has said [4] "In string theory it has always been clear that the physics is background-independent even if the language being used is not, and the search for a more suitable language continues."
Im not going to debate the merits of string theory with you here, but your statements are demonstrably, factually wrong. If you want to get any kind of informed opinion about string theory then reading some textbooks on the subject would be advisable. Or if you will only read popular level accounts I strong suggest taking Smolin with a grain of salt and get some other books. For example, Hawking's book is mentioned in the introduction of this article. But I would not recommend reading any books that get major facts wrong. Disclaimer: I am not promising to correct all your misimpressions and you seem to have quite a few others remaining. For example, you seem to think that stabilizing moduli is some kind of major unsolved problem. Well its not. – Isocliff (talk) 00:49, 10 December 2011 (UTC)
Stabalizing moduli is a major unsolved problem. And since you quote Polchinski on Smolin, I may as well quote Smolin's answer back [5]:
Regarding background independence, Polchinski claims that, “(as Smolin belatedly notes), Maldacena duality provides a solution to this problem, one that is unexpected and powerful.” This exaggerates and distorts the situation. What is true-and what I acknowledge, is that if the strong form of the AdS/CFT conjecture is shown to be correct, then a very weak, and limited form of background will have been achieved. But for reasons just mentioned, which I explain in detail in the book, this is still a big if.
What has been shown so far relies on the fact that one can use the fact that SUSY N=4 Yang-Mills has the same global super-symmetry as perturbative physics on a background AdS5 X S5 spacetime, to express some physical quantities in the latter in terms of observables of the former. This is great mathematical physics and a great achievement, but the whole point of general relativity and quantum gravity is that the generic solutions are governed by no global symmetries because the geometry of spacetime is completely dynamical. This has two implications. First it makes it very non-trivial to show the strong form of the Maldacena conjecture, because it must extend to solutions of supergravity arbitrarily far from those with global symmetries in the bulk. However, if this is possible at all it will be because the full algebra of global super-symmetries remain on the boundary. The case of asymptotically flat will be much harder because there the asymptotic symmetries of the generic case are very different from the global symmetries of the ground state, and indeed there are no proposals for a gauge-gravity duality in this case. The case of positive cosmological constant-which appears to be the physical case-is harder still. And we have not even yet touched the real meaning of background independence, which is that fixed classical fields or global symmetries play absolutely no role in the formulation of the dynamics or observables of the theory.
The latter is what is meant by background independence in the rest of the classical and quantum gravity world, and so far string theory and the AdS/CFT conjectures do not come close to addressing it. It was in fairness to string theory that I was willing to acknowledge that the strong form of the AdS/CFT conjecture, if true, would provide a very limited and weak form of background independence. One would hope that in fairness to the truth string theorists who make this point would also hasten to acknowledge how far this would be from the real, full meaning of background independence. Brian Greene does acknowledge this when he proposes that the latter idea be distinguished by calling it “manifest background independence.”
Polchinski also acknowledges the difference, when he says, “In string theory it has always been clear that the physics is background-independent even if the language being used is not, and the search for a more suitable language continues.” But this is not the most accurate way to put it. It would be more accurate to say, “Some string theorists believe that the formulations of perturbative string theories and dualities between them that they study concretely are approximations to a deeper, background independent formulation. This missing background independent formulation is not just a different t language for the theory, it is hoped to be the statement of the principles and laws that define the theory, from which everything studied so far would be derived as an approximation. Despite this belief, only a few concrete proposals have been made for the laws and principles of this conjectural background independent formulation of string theory and none has gained wide support.” [end of quote]
You can read the whole thing on the link. String theory is not wedded to flat space, but neither is it completely free of needing a space to back it. Indeed as you know, the various anti de Sitter spaces in AdS/CFT become more and more difficult to use in theories when the global universe they are supposed to explain is a manifestly de Sitter universe, with a positive cosmological constant. Something just being discovered by the Hubble Space Telescope as Maldacina made his first conjecture (alas). Which is still a conjecture. At least Ed Witten has admitted that string theories giving rise to de Sitter universes like ours, don't look like anything thought of, so far. SBHarris 03:59, 10 December 2011 (UTC)
Again, Im not going to sort through all of your misconceptions and resolve them all for you, but what you say is wrong and demonstrably so. You can quote Smolin all day long, but these are quantitative questions that have been decided in papers, not in popular-level books. The AdS/CFT is not in any way critical to these arguments and I didn't bring it up. The key point was that string theory possesses the same diffeomorphism symmetry as general relativity, and implies Einstein's equations as a low energy limit. Those are two unambiguous facts that are true of string theory as it exists today, not some dreamed about completion of it. They are pretty important things to know about it, and I cant guarantee I will continue conversing with someone who wont acknowledge these basic characteristics of the topic in question. Again, your wrong statements include your assertion that de Sitter space and moduli are "major unsolved problems". Does the actual literature written on these topics matter at all? I will leave a few recommended selections here. [6] [7] [8] [9] – Isocliff (talk) 05:06, 11 December 2011 (UTC)

Popper and testability

An editor named "8digits" keeps modifying the testability section and having the edits reverted. Rather than continuing with such fruitless activity, maybe he/she would care to discuss the issues here? First of all, s/he keeps asserting that Popper said that QM isn't testable. I find that very difficult to believe since it's manifestly false, and Popper wrote extensively on QM and its interpretation. Do you have a reference? Waleswatcher (talk) 17:57, 11 December 2011 (UTC).

Do a google search on Popper on QM, like this one http://www.google.com.au/search?hl=en&q=popper+quatum+mechanics

I did put the references in, I left your stuff till you come up with something other then an introductory book. 8digits (talk) 11:55, 12 December 2011 (UTC)

I've read quite a bit of Popper, including some of what he wrote on QM. There's nothing anywhere like what you're saying. "Do a google search" isn't a reference. Do you have one?Waleswatcher (talk) 03:10, 13 December 2011 (UTC)
I must say I'm slightly confused by what the article means by falsifying that a theory is quantum mechanical. The statement that a theory is quantum mechanical is a statement about how the theory is formulated. Quantum mechanics applied to any physical model will lead to falsifiable predictions (some of which will differ from the predictions made . But what is falsifiable is the combination of quantum mechanics and the specific model. Of course, when people say "quantum mechanics" they mean quantum mechanics plus certain well-known models (Harmonic oscillator, free particle, spin systems), and this combination can clearly be falsified. (For example by a double slit experiment.) But will a low-energy limit of string theory always result in these models? That is not entirely clear. (Some string theory models certainly will, but all?)
8digits on the other hand seem to be confused by the well-known statement that it is impossible to falsify an interpretation of quantum mechanics (such as the Copenhagen interpretation). Clearly, string theory does not imply any specific interpretation, and as such it is irrelevant.
On a similar note, it appears to me that the statement that that it "is enough the falsify Lorentz invariance to falsify string theory" is not entirely true. People have studied all sorts models that might appear as low-energy effective theories for string theory that break Lorentz invariance. One of the most notable being Horava-Lifshitz gravity. As such, observation of Lorentz violation will not falsify string theory (although it will falsify many string theoretic models).TR 13:38, 12 December 2011 (UTC)
All string theories are fundamentally Lorentz invariant, or at least that's true of all the ones discussed in the article. It's true that many backgrounds break Lorentz invariance spontaneously, but that's a separate issue (and true in all Lorentz invariance theories). As for QM, if for instance it turned out that gravity wasn't quantized - something that could be tested in principle with something like the gravitational analog of the photoelectric effect - that would falsify string theory. Waleswatcher (talk) 03:10, 13 December 2011 (UTC)
Yes string theories are Lorentz invariant at the fundamental level, but this does not necessarily imply that they do not spontaneously break Lorentz invariance at low energies. Consequently, observation of Lorentz violations will not automatically falsify string theory. (As witnessed by the reaction to the OPERA superluminal neutrino result: people generally do not see this as a threat to string theory even though it implies some sort of Lorentz violation.)
As for, QM, not all spectra in quantum mechanics as discrete. In particular, it is a hot topic for debate whether geometrical observables obtain a discrete spectrum in quantized theories of gravity. Varying results have been found in the explicit quantizations preformed in 2+1 dimensions. So, again observing gravity with a continuous spectrum will not falsify quantum mechanics.TR 08:26, 13 December 2011 (UTC)
ALL solutions break Lorentz invariance at low energies except the state that is perfectly empty vacuum everywhere in the universe all the time, and we don't live or do experiments in such a state. That's true in all Lorentz invariant theories, string theory is no exception. Nevertheless, Lorentz invariance is among the most precisely tested facts about nature, and it's extremely easy to falsify. By the way OPERA does falsify Lorentz invariance if it's correct; faster than light propagation means back in time propagation in L. inv. theories, and that's inconsistent with causality (which is part of all such theories). No one is talking about it falsifying string theory because it would falsify a lot more than just string theory. Regarding QM, it's true that not all quantities are discrete, but particle number is, always. If gravity is quantized, there are gravitons, and you cannot have 1/2 a graviton. This could - in principle - be tested by looking for a gravitoelectric effect for instance, just as the quantization of electromagnetism won Einstein the Nobel prize as explaining the photoelectric effect. Waleswatcher (talk) 12:00, 13 December 2011 (UTC)
The point is that there is no fundamental need for the vacuum state of a low energy effective theory corresponding to string theory to preserve Lorentz invariance. Put more explicitly. String theory is fundamentally Lorentz invariant in 10 dimensions. Compactification will break this symmetry, and I'm not aware of any principle to would prevent breaking this further than the 4d Lorentz group. Consequently, observing 4D Lorentz violation would not falsify all of string theory. (It certainly would falsify a lot of string models.)TR 14:42, 13 December 2011 (UTC)
"there is no fundamental need for the vacuum state of a low energy effective theory corresponding to string theory to preserve Lorentz invariance" - sorry, but that's pretty much the definition of "vacuum", so you're pretty much tautologically wrong (not that it matters much). "Compactification will break this symmetry" - like I said, ALL non-empty solutions to string theory (or any other Lorentz invariant theories) break Lorentz invariance. We aren't in a vacuum. According to you, does that mean we can't test the Lorentz invariance of the standard model? "Consequently, observing 4D Lorentz violation would not falsify all of string theory. " - observing spontaneous breaking wouldn't, but observing fundamental breaking would. Again, that's the case in ALL Lorentz invariance theories, not just string theory. Waleswatcher (talk) 04:00, 14 December 2011 (UTC)
Of course we can test Lorentz invariance of the standard model. As can we test Lorentz invariance of any string theory model that has it. What I am saying is that not every string theory model needs to imply that there exist 4D Lorentz invariance. Hence string theory as a whole cannot be falsified by finding violations of Lorentz invariance. (Note that by your logic, violation of supersymmetry in the standard model would falsify string theory. That obviously is nonsense.) (Also note that from an observation of Lorentz violation (for example an anomoluous dispersion of the photon) you cannot tell whether it is caused by spontaneous or explicit breaking of the symmetry.)TR 15:56, 14 December 2011 (UTC)
"Of course we can test Lorentz invariance of the standard model. As can we test Lorentz invariance of any string theory model that has it." All string theory models are Lorentz invariant, it's built into the theory at the level of the worldsheet action. "What I am saying is that not every string theory model needs to imply that there exist 4D Lorentz invariance." No non-trivial solutions to string theory are 4D Lorentz invariant. No non-trivial solutions to the equations of the standard model are 4D Lorentz invariant. You still havent identified a logical difference. "Hence string theory as a whole cannot be falsified by finding violations of Lorentz invariance." It's on exactly the same footing as any other theory with fundamental Lorentz invariance, like the SM. "(Note that by your logic, violation of supersymmetry in the standard model would falsify string theory. That obviously is nonsense.)" Yes, it's nonsense, and no, it's not my logic, it's apparently yours. Waleswatcher (talk) 11:31, 15 December 2011 (UTC)
Of course, excitation of a theory are never lorentz invariant. The point I am making is that, the vacuum state of a low energy effective theory does not need to have the same symmetries as the vacuum state of the fundamental theory. For example, low energy effective theories for string theory do not need to have the same amount of supersymmetry as the fundamental theory. (Non Calabi-Yau compactifications of string theory have no supersymmetry in 4D) Similarly, the I see no reason why you could not construct compactifications that break Lorentz symmetry as well, causing Lorentz violating terms to appear in the low energy effective action.
Anyway, the onus is on YOU to provide a source to back your claim that all low energy effective actions for all string theory models are Lorentz invariant. I am done trying to educate you in basic field theory.TR 15:44, 15 December 2011 (UTC)
Here is a source that explicitly discusses the possibility of spontaneous breaking of Lorentz symmetry in String theory and shows that it is possible. This invalidates your blanket claim that ALL string theory models are Lorentz invariant.TR 13:42, 3 January 2012 (UTC)
OF course it's possible to spontaneously break LI. As I've already tried to explain to you (on this page), all but a very, very special subset of solutions spontaneously break LI in all LI theories. Waleswatcher (talk) 22:01, 3 January 2012 (UTC)
No, typically they don't. (Spontaneous symmetry breaking is not the same thing as excited states not being Lorentz invariant) In many theories (QCD, QED, the SM) if you derive a low energy effective action of theory, that effective action will be Lorentz invariant. The point here is that the low energy effective actions for some string theory vacua will not be Lorentz invariant. This is contrary to what the sentence currently in the article seemingly claims. The most pressing problem here is that the sentence in the article is badly phrased, making a much broader claim than is supportable by facts or sources. What is true, is that there are consequences of Lorentz invariance of the fundamental theory that might be falsified at low energies. What isn't true (but which is suggested by the current sentence) is that string theory is falsified by any experiment that shows that the low energy effective action contains Lorentz breaking terms.TR 22:31, 3 January 2012 (UTC)
Yes, they do. Forget string theory for a moment, take the standard model or any other LI QFT. Consider any state that isn't totally empty (i.e. anything other than the perfect, exact vacuum). Is that state LI? Nope, it's not. Now compute the effective action around that state. Is that effective action LI? Nope, of course not (a perfect example is the effective field theory of inflation, which is not LI because the background it expands around isn't either). The fact is, LI is a fundamental characteristic of string theory, and it's one that can be falsified. The Distler et al reference on WW-scattering is a perfect example and a more than adequate cite. Waleswatcher (talk) 05:00, 4 January 2012 (UTC)
Please go learn what spontaneous symmetry breaking is. Spontaneous symmetry breaking, is the violation of a symmetry of the action in a vacuum state. The point I have been making is that there exist string vacua that violate LI. TR 07:00, 4 January 2012 (UTC)
Sorry to contradict you, but you're wrong. SSB refers to any situation in which some symmetry (usually of the underlying Lagrangian) is broken by a solution to the theory. It can happen in the vacuum state of the theory (or metastable minima, which are also sometimes referred to as vacua), but it also happens in just about every other solution to the theory. That's the standard terminology. I gave you a simple and good example (inflation and effective field theories). I can give you many more. Waleswatcher (talk) 17:37, 4 January 2012 (UTC)


Regarding 8digits' edits and Smolin's book. First, Smolin's view is not neutral. Second, I looked in his book, and he does not say that string theory cannot be falsified. Instead, he says that it makes no NEW falsifiable predictions, a partially valid criticism that is already discussed at some length in the article. As for Woit (an even less neutral source), if he says what 8digits says he does (I haven't looked as I don't have his book), then he's flat-out wrong. For instance, no one disputes that string theory reduces to general relativity at low energies - that's a basic feature of the theory - and GR is very easy to falsify. If string theory isn't science because it can't be falsified, so is general relativity, which is absurd. Waleswatcher (talk) 03:17, 13 December 2011 (UTC)

Popper testability following from testability of dependent theories.

I have edited the following paragraph:

All string theory models are quantum mechanical, Lorentz invariant, unitary, and contain Einstein's General Relativity as a low energy limit.[1] Therefore, it would suffice to falsify quantum mechanics, Lorentz invariance, or general relativity.[2] Hence, string theory is falsifiable and therefore scientific according to Karl Popper's criterion.

First, it constitutes original research (concerning philosophy) and so should not be included.

Secondly, this position doesn't really make sense. Suppose I have a theory that an invisible collection of magical pink elephants with unlimited power exist all around us, and they use their magical power to make general relativity hold all the time. They will always do this because it is their purpose in life which they never waver from.

This theory can be falsified by showing general relativity is false. But, I do not think it is scientific in the sense of popper (it's differences with general relativity cannot be falsified.)

In any case, as previously mentioned, this constitutes original research and so has no place here. Wpegden (talk) 13:47, 13 December 2011 (UTC)

I respectfully disagree, and this precise issue was discussed at length years ago in the context of this sentence (or a very close variant) in this article. The consensus was that this does not constitute original research, or in fact research at all, because it follows trivially and immediately. If string theory is falsifiable, and Popper says falsifiable theories are scientific, then pointing out that therefore string theory is scientific according to Popper is not original research. A is B, and B is C, therefore A is C is not research.
As for your example, it is in fact scientific according to Popper. Whether or not your unicorn theory can be distinguished from another theory (GR) isn't part of and has no relevance to Popper's definition of science. Indeed, I don't know how you'd propose to implement such a criterion - how would you decide which theory was the original, and which just a copy that can't be easily distinguished from it? Popper's criterion to first approximation is just falsifiability. Try reading some Popper, or just thinking about how you would differentiate science from religion (and remember, neither temporal order nor existing evidence are relevant here - this is supposed to be a criterion that applies to abstract theories, not society, or theories plus evidence). Anyway, we're not debating whether Popper's definition is the best one. I'm reverting your edit. Waleswatcher (talk) 03:54, 14 December 2011 (UTC)
I find your viewpoint on this very interesting. (I'm serious.) However, I remain unconvinced that Popper would consider my elephant theory scientific. Anyways, as you point out, that is not the point. The point is whether or not this constitutes original research, and it does. Going from A->B, B->C to A->C is not allowed on wikipedia. (This is synthesis of published ideas.) Encyclopedia statements don't exist in an abstract axiomatic framework, and so such deductions are not uncontestable. If I find a published quote by Albert Einstein that "every single day it rained in in 1901, I wore a rain jacket", and another published source which asserted that "it rained in Dhaka, Bangladesh on February 3rd, 1901", it would not be valid for me to state without citation that Albert Einstein wore a rain jacket on Februrary 3rd, 1901, because it depends on my interpretation of the statements I am synthesizing. That string theory is scientific in the sense of Popper is an interesting idea, but Wikipedia is not the place for this to be advanced. I will revert the edit. Why not just give a citation for the claim? Or would you consider it appropriate that Wikipedia is the only advocate for this position? Wpegden (talk) 12:54, 15 December 2011 (UTC)
To keep things simple, I have just removed your final sentence. That is, I have left in your cited statements, and just removed the uncited conclusion you consider obvious. So it is still making a point you think is interesting (and I agree), but not doing so in such a way that the article is presenting a new viewpoint or perspective that is not given elsewhere. Wpegden (talk) 12:54, 15 December 2011 (UTC)
Your example isn't at comparable, because C doesn't follow from A and B given the standard English interpretation of those statements. The situation here is different. String theory is falsifiable, that's obvious and it's cited. Popper said scientific theories are those that are falsifiable again cited. To point out the obvious fact that string theory is therefore Popper falsifiable is clearly not research, nor is it an unjustified synthesis. Suppose we re-wrote the section to say that string theory is falsifiable, and Popper says that falsifiable theories are scientific, and... period. Any reader will immediately draw the missing conclusion themselves, because it's completely obvious, but would be left wondering why the writer of the article didn't finish their thought. It would be incoherent and do a worse job of explaining what it seeks to explain.
Here's wiki's statement on disallowed research/synthesis: "This includes any analysis or synthesis of published material that serves to advance a position not advanced by the sources. To demonstrate that you are not adding OR, you must be able to cite reliable, published sources that are directly related to the topic of the article, and directly support the material as presented." First, note that there is no prohibition there against what you termed "original synthesis". Second, this standard is clearly met here, because the Comins and Kauffman source clearly intended this. Here's a quote from that book: "[A lot of stuff explaining how string theory tries to describe gravity and matter, including some specific falsifiable predictions that have passed observational tests]...Superstring theories are, so far, consistent with observations, but it remains to be seen if any of them will continue to maintain consistency with future observations and to correctly predict observable things that have not yet been seen." Obviously they view string theory as science (like any non-zealot that knows anything about it, but never mind), and equally obviously they regard falsifiability as an important part of that, since they mention it explicitly and at some length.
Finally, let me point out that this statement has been in this article for years, and further, that this precise issue was discussed back then, and the consensus was that this statement is simply an obvious logical step and does not violate wiki's guidelines. It's not "my' statement, and you are the one coming in and suddenly deleting it after years of it being there. So I think the onus is entirely on you to establish beyond doubt that it shouldn't be there, and you haven't done so. I've undone your edit. Waleswatcher (talk) 13:09, 14 December 2011 (UTC)


One thing I forgot to address - "Or would you consider it appropriate that Wikipedia is the only advocate for this position?" The problem is that there can't be any doubt in any informed and neutral person's mind that string theory is science. String theory is done by scientists in science departments with funding from science granting agencies. The US National Science Foundation and the Department of Energy regularly and routinely fund string theory research, and there are hundreds or thousands of string theorists with permanent research positions at most of the best educational and research institutions around the world. As we've established, it's falsifiable - in fact much more easily so than many of the theories that scientists spend lots of their time on (scientists spend a lot of time trying to develop ideas, play with toy models, work with pure math, etc.). So there really shouldn't be any debate about whether it's science. The only reason there is any debate as far as I know is that two individuals with (for some reason) a very strong dislike for string theory wrote popular books about it. Smolin doesn't actually say it isn't science, and doesn't say it isn't falsifiable, he just says it doesn't make new testable predictions. Woit I'm not sure of, but his view is very far from neutral, and it's obviously not representative of what actual scientists and science policy professionals believe.
In any case, it's not so easy to find statements in print like "string theory is Popper falsifiable" because it's totally obvious, so people aren't going to bother to publish things like that. And more or less the whole point of an encyclopedia is to make scientific or specialized knowledge more accessible and clear to the public. That inevitably requires some translation and synthesis. Waleswatcher (talk) 13:29, 14 December 2011 (UTC)

The statement is logically incorrect.

Whether it has been here for years is irrelevant. If it is not available such statements that "string theory is Popper falsifiable", then it is original research and not allowed.

Beside it is wrong, the claims of string theory are much more then just QM and GR. QM and GR might be right and string theory wrong. Also it is misleading as Poper had grave doubts that QM was falsifiable? I think it should have a better reference then this beginners book you quote. 8digits (talk) 8digits (talk) 13:38, 14 December 2011 (UTC)

You keep saying Popper doubted QM was falsifiable. That's news to me, and you've provided exactly zero evidence for it. Popper was an expert in QM, he wrote extensively about it. I've read some of what he wrote, and I've never seen the slightest hint of what you say. So I think you're just flat-out wrong. Provide a reference to show otherwise, please. That the statement has been there for years is relevant because it was discussed at length before, and the consensus among several editors was that it does not constitute "research". Your assertion that it does is in conflict with wiki's guidelines quoted just above. As for this: " QM and GR might be right and string theory wrong" it illustrates a complete failure to comprehend what's being discussed here. Yes, QM might be right and string theory wrong. That's not relevant. The relevant point is that QM might be WRONG, and if so, string theory is wrong. That's sufficient to demonstrate that string theory is science according to Popper. Waleswatcher (talk) 11:38, 15 December 2011 (UTC)
Indeed, how long a statement has been here does not affect whether it needs a citation. (Indeed, we should be most suspicious of statements which haven't had citations found for them for several years, despite strong feelings that they should remain in the article.)
If you would really like a list of subjects that science departments have engaged research in which popper did not consider scientific let me know. This is part of the problem I have with your viewpoint... it misses the fact that "scientific according to popper" is a technical statement in philosophy, which cannot be supported by intuition like this.
I have now put in a cited statement that there are critics which consider string theory unfalsifiable. I know you think that its "obvious" that it is falsifiable but, in reality, I believe the extent to which string theory is falsifiable is a much discussed/debated topic. Your viewpoint seems to be that one side in that debate is obviously wrong, and you may be right about that, but this isn't the place to take a side.
Honestly, I am not here to say string theory is unfalsifiable. I think one can make interesting points that it might be. The "A is B, B is C, so A is C" deduction you've carried out trivializes the issue in a way which ignores the actual state of discourse on the topic. This is why you are having trouble with citations.
Really, the most sensible thing would be for Popper to not be mentioned in this article at all, except possibly in a separate "philosophy of string theory" section, which it unfortunately seems we don't have enough citations to write. He was a 20th century Philospher who is not alive today and has written nothing about string theory. This is another reason you are having trouble finding citations directly talking about Popper's criterion applied to string theory.
Well, I've tried a compromise by leaving your sentence and citation in. I changed the "However" to a "Despite this", because your summary of Woit's assertion directly contradicted the two (now three) sentences that came right before. In any case, looking at page 207 of Woit's book (I managed to find a copy), it's incoherent. In fact he contradicts himself in two successive sentences.
Quote from Woit: "...superstring theory is at the moment unarguably an example of a theory that can't be falsified, since it makes no predictions." OK, Woit thinks ST makes no predictions, noted. Next sentence: "No one has come up with a model within the superstring theory framework that agrees with known facts about particle physics." So let's see - it doesn't make any predictions, and its predictions don't agree with facts about the world. That's known as having your cake and eating it too. Do we really want to quote something like that in an article meant to make this clear? It's muddled nonsense.
And let me point out again that Woit is not a scientist, doesn't know string theory, and evidently (based on the fact that he seems to devote much of his life to trashing it) is an anti-string ideologue. So Woit saying something isn't really a very good guide to the facts, or good evidence that there is a real debate. Smolin is slightly more respectable (although he too has a very strong anti string motive, and in any case, he doesn't say it isn't testable, just that it doesn't make new testable predictions). Waleswatcher (talk) 11:51, 15 December 2011 (UTC)
I've removed your uncited statement again. This is a statement that not everyone agrees with. It's a statement whose relevance to the article is questionable.
You shouldn't be looking for the opinions of scientists on this issue, by the way.... its not a scientific question but a philosophical one, which is the primary reason it shouldn't be addressed at all in the article. If philosophy was all "A is B, B is C, so A is C", then Popper would not have been as prolific as he was... he would have just written one paper about falsifiability and everything else would have been an obvious consequence. Popper himself wrestled throughout his life with questions of which theories in science could be considered "falsifiable" (including things that all scientists agree are part of "science", such as evolution and natural selection) which could similarly be trivialized by the logic you have used here (aspects of heredity are falsifiable so evolution is falsifiable, etc.)
I am now getting the impression that you seriously believe that all physicists believe that string theory does not have issues with falsifiability. This is not even true for all string theorists, some of whom are consider it an interesting mathematical framework to study, and remain unconvinced of what its ultimate ability to impact physics will turn out to be. There are plenty of "real physicists" who criticize string theory as unscientific. That's not the point. I'm not here to criticize string theory---I think string theory is pretty cool, actually.
Right now, the problem with this article is that there is a statement regarding the status of string theory under a technical philosophical criterion of a 20th century philosopher which is present in the article (problem number 1, but whatever...) and has no citation (unacceptable).
Perhaps at this stage it would be wise for us to consult some Wikipedia editors unfamiliar with this article for their opinion on whether the sentence you are defending is acceptable as is? Wpegden (talk) 12:54, 15 December 2011 (UTC)
Go ahead and consult other editors. Please stop altering the article and edit warring until a consensus is reached. Better yet, look back in the history talk page and find the discussion among several people of precisely this statement, where it was decided that it does not constitute original research and this wording was decided on. There ARE of citations, so I don't know what you're talking about. The citations say that A) string theory is falsifiable, and B) Popper's criterion for science is falsifiability. That string theory is therefore science by Popper's standard is not "research" and does not require a citation, it is a patently obvious conclusion that follows trivially from the previous two statements (neither of which seems to be in dispute). The debate among physicists is not over that, it's over whether that's the right standard, or whether string theory is good science, etc. All of that can and should be and mostly is discussed in the article.
As for Popper, he struggled with theories that were in a gray area with regards to falsifiability, like evolution. This isn't anywhere close to that - there's nothing even slightly gray about it. Lorentz invariance for instance is one of the most easily falsifiable predictions any theory can make. Same goes for QM. In both cases there are tests that are more precise than any others in the history of human thought. Waleswatcher (talk) 13:18, 15 December 2011 (UTC)

An additional comment: the examples given in the article (QM, Lorentz invariance, GR) are just a few of many. String theory predicts the existence of strings, their scattering amplitudes, the existence of extra dimensions, etc. All of those are obviously falsifiable predictions. Unlike QM etc. they aren't falsifiable right now in the sense that we could do an experiment today to falsify them, but that's because of current technological limitations and has nothing to do with Popper's criterion (which is a criterion one applies to theories, not to the state of human technology on Dec. 15th 2011). If you like, this shows that Popper's criterion is rather weak - but it is still the most widely used definition of science I'm aware of (and the best in my opinion), and therefore it is clearly relevant to the question of whether string theory is science. If there's going to be a discussion of whether string theory is science in this article, it should be mentioned. Waleswatcher (talk) 13:57, 15 December 2011 (UTC)

The update by 8digits is a big improvement, primarily because the paragraph is now about string theory, instead of being about 20th century philosophy. I have removed the last sentence ("Critics argue that these two issues make string theory de-facto untestable") because it is uncited and I think it is a bit unbalanced, not giving the other perspective as well, and because it is uncited.
I don't plan to stop updating the article. I feel I am working to improve the article. I have worked hard to discuss the issue with you and I am not the only person who thinks you are wrong.
To keep things simple, I will try to focus on just a few issues per response. Maybe that will help us have a productive discussion. The issues for this response are: 1) the fact that Popper should not be in this article (except possibly in a separate "Philosophy of String Theory" section) and 2) that your simplistic reasoning regarding poppers criterion is original research, and unlikely to comport well with the body of Poppers work.
Regarding 1). In your earlier responses, you pointed out lots of reasons why string theory is part of science. Like, it is done in science departments, with science funding, etc. These have nothing to do with Popper. But they do have something do with what we consider to be science. Similarly, the views of most scientists today regarding string theory are not expressed in terms of Popper. Scientists do not typically discuss or care about what Popper would think about string theory. They often care about other things (like whether the scientists have evidence that string theory is correct, or whether they can imagine that happening, or whether string theory is having a positive impact on physics overall, etc.) which may or may not be related to Popper. This is why you find it so hard to find a citation of a scientist talking about popper and string theory in the way you want: most don't care. Maybe they should, but they don't. This is why it shouldn't be in the article at all. How Popper's criterion applies to string theory is a philosophical question, not a scientific one. For better or for worse, our current understanding of what constitutes science comes from "what scientists consider science", which has very little these days to do with Popper (although, no doubt, he affected today's scientists' views greatly through is impact on the intellectual discourse on the subject).
Regarding 2) Your logic really would trivialize lots of things that Popper did not consider trivial. Evolution really does imply that horses don't give birth to rabbits (and vice versa). That horses don't give birth to rabbits is falsifiable. Therefore, according to your logic, Evolution is falsifiable. What is wrong with my reasoning? Why doesn't this show Evolution is falsifiable? Stay on point mind you, the question is not whether Evolution is similar to string theory, the question is whether A is falsifiable, B implies A, always means B is falsifiable (since the original paragraph was depending on this logic being "obvious" and thus not requiring a citiation.) Not only is it not obvious, it is false. Or which is it: does evolution not imply that horses don't give birth to rabbits? Or is it that horses don't give birth to rabbits not a falsifiable statement? Wpegden (talk) 18:54, 15 December 2011 (UTC)
8digits deleted an entire paragraph about string theory, including citations, and replaced it with an uncited opinion that is redundant with the material that immediately follows that paragraph (the string harmonics section). That's a "big improvement", according to you? You're not displaying a neutral POV here, nor are these edits making the article better, clearer, or more correct.
In case you didn't notice Popper is already mentioned elsewhere in the article (not by me). I agree with you that most physicists don't care much about Popper. On the other hand, I think it's the case that Popper's criterion is the best definition of "science" we have ("done by scientists", while useful in ridiculous debates like "is string theory science", is circular). I think most people that care would agree with me that Popper is the best definition we have. So if we're going to discuss whether string theory is "testable" or "science", it makes a lot of sense to mention Popper.
I agree that Popper/not Popper is more of a philosophical question than a scientific one, but I don't understand why you think that's a problem. The wiki article isn't science, it's about science, so mentioning philosophy of science is very reasonable.
Regarding evolution, the issue that bothered Popper is whether in fact evolution actually predicts things like horses don't give birth to rabbits ("fossil rabbits from the pre-Cambrian" is actually famous quote, though I think that was Haldane). Once that is clear, it's perfectly clear that evolution is falsifiable. The trouble is that evolution, full stop, is such a general phenomenon - it's essentially tautological that it takes place - that it's not obvious that it actually predicts that (a world in which horses give birth to rabbits could conceivably contain evolution). In the end Popper decided (correctly, I think) that evolution does make such predictions, or rather the more specific theory that evolution by natural selection is the origin of species does. Waleswatcher (talk) 19:35, 15 December 2011 (UTC)


The reason I considered the edit a big improvement is because the paragraph was now actually---kind of---an on-topic introductory paragraph to the section it is heading. The previous paragraph was no such thing. It was about a topic most string theorists have no interest in, and so should not be in the article at all, let alone the introductory paragraph for a section which is not titled "the philosophy of string theory". I agree the new paragraph is not NPOV (and I even deleted the last sentence of it because of that) and a better paragraph would be more NPOV, discuss the issues with the testability of string theory in a neutral way mentioning possibilities and current limitations, without discussing the Popper criterion, which most scientists do not concern themselves with today. Would you like to collaborate on such a paragraph? I would not be opposed to discussing the fact that string theory implies well-testable and well-tested theories like QM, etc. I just don't like the connection with Popper (which I do think is a leap, but, more relevantly, is not really well-suited here).
(In fact, part of the silliness with the Popper statement is it sets up the idea that this is what string theorists have resigned themselves too: string theory is "popper falsifiable" for some technical reason. In fact, there are actually interesting avenues through which string theory might actually be verifiable in a way scientists would care about.) Wpegden (talk) 23:20, 15 December 2011 (UTC)
I agree that Popper falsifiability isn't all that compelling - as I said before, it's a rather weak criterion. Nevertheless, I think it is important to have in there because it shows definitively that string theory is science according to the most widely used and accepted definition of "science". Given that people keep trying to add references to Woit and others that assert that string theory isn't science, I think this is worth pointing out. I really (despite honestly trying) can't understand your arguments for why you think it's off topic or irrelevant, it's a statement about falsifiability in a section about testability, so it seems about as relevant as it gets.
This seems like the crucial point of disagreement. I'm not going to edit right now to show I'm serious about compromise (I'm putting in a dummy edit in case it's necessary to get your attention). I think that Popper's criterion is not a widely used definition (among scientists) of what constitutes science. I have never had a serious conversation with other scientists about science in which Popper came up. It has only come up in discussions of Philosophy (in relation to Kuhn, etc.). The word "scientific" has several common uses among modern scientists (e.g., rigorous, applied to studies, testable by experiment, applied to ideas, etc.) and it hardly ever means "falsifiable in the technical sense of Popper". I think that string theory is obviously science in the sense you pointed out earlier---done by scientists in mainstream science departments at most universities, etc, and that Popper's criterion doesn't add anything to the discussion. I for one am not arguing that string theory is not science. I think there are interesting questions about the extent to which string theory makes new predictions which may be tested in the near future---questions which don't have an "definitely no, definitely yes" answer, which the section this paragraph heads does a reasonable job of discussing. Can you be convinced to consider a paragraph which does not reference Popper, but addresses the predictability/testability issues associated with string theory in a reasonable way showing the possibilities (while acknowledging current limitations)? Wpegden (talk) 01:52, 16 December 2011 (UTC)
Thanks for that. I actually *have* had numerous conversations with other scientists about Popper. Personally I find his criterion quite useful, because I think it captures the essence of science: you test theories by trying as hard as you can to falsify them. If you fail, you have a little more confidence in that theory. You never really verify anything, the best you can say is that evidence is *consistent* with theory (so I'm not sure what you mean by "testable by experiment" other than Popper). So I can't agree with your "hardly ever", that's not been my experience at all (although of course I recognize that I myself might be the cause of that).
Regarding not mentioning Popper, it just seems rather silly not to. I think it's important to point out that string theory can be falsified. For instance, Woit says explicitly that ST cannot be falsified (and then contradicts himself in the next sentence), and I have personally encountered several people that were convinced by that, plus seen many more such assertions on the internet. So I think there's a real misconception that's been perpetuated by a few ideologues, and I think countering that mistake with facts - however self-evident or irrelevant they might seem to you - is a good idea. But once you go that far, adding a single sentence or phrase that completes the thought by pointing out Popper's criterion seems clearly indicated. It's not like there's a word limit, or this is a huge block of text. And remember, this article is not intended just for professional scientists who might not need such guidance, it's for everyone. Waleswatcher (talk) 02:51, 16 December 2011 (UTC)
Regarding the more interesting avenues, I'm in complete agreement. I would be happy to collaborate on including/improving that. There used to be a sentence following the Popper one that got deleted. I'm going to edit it back in. It leads into the following sections, which are about "positive" predictions, things that string theory predicts but few or no other theories do. See what you think. Waleswatcher (talk) 01:11, 16 December 2011 (UTC)
I think this is a big improvement, in part because I think it acknowledges the irrelevance (from the perspective of a modern scientist) of the claim of Popper falsifiability... but this is of course why I think the paragraph should be reworked to avoid discussing Popper at all. Wpegden (talk) 01:52, 16 December 2011 (UTC)
(I must admit I remain dissatisfied with the fact that the Popper sentence consists of a deduction... however obvious you think it is, I find that uncited deductions stick out in Wikipedia articles like sore thumbs, marking inappropriate homes for statements not noteworthy enough (or possibly not valid enough) to be made anywhere else. But in this case it has more serious problems with inclusion that I feel we have more common ground on)
By the way, I can see the argument for moving or merging some of that discussion with the criticism subsection. The way it's structured now is as follows: first it explains briefly why testing string theory directly is hard, then it points out that it's easy to falsify but hard to verify, then it describes some ways it might be verified, and then it goes into more detail on why it's hard to test. That's a little convoluted, and can probably be organized better. Waleswatcher (talk) 01:39, 16 December 2011 (UTC)
It's only Popper falsifiable in a trivial sense. According to this trivial sense the only way something isn't falsifiable is if it doesn't build upon any science theory at all, and conversely any bizarre theory is science if it builds on any other science theory. We should remove that sad paragraph Bhny (talk) 01:47, 16 December 2011 (UTC)
I agree but Waleswatcher's response is that this is the correct sense in which things are or are not Popper falsifiable, and your characterization is correct (see my "pink elephant theory" above). I don't see a way of reconciling this disagreement (whether or not this is correct application of Popper's criterion), except that maybe we can all agree that if this is the correct application, than it certainly makes it a less crucial concept to include in the article (since it is so far from what scientists care about on a day to day basis)??Wpegden (talk) 01:56, 16 December 2011 (UTC)
There's no such thing as "Popper falsifiable in a trivial sense". A theory is either falsifiable or not. And you cannot decide if theory A "builds on" theory B or if instead B builds on A, because the temporal order in which A and B were thought of is irrelevant to whether or not they are scientific theories. Waleswatcher (talk) 02:37, 16 December 2011 (UTC)
All theories are falsifiable by this usage, that's why it has no meaning Bhny (talk) 02:48, 16 December 2011 (UTC)
All scientific theories are falsifiable, that's precisely the point. Religion, among other things, is not. Please note that this is a very well established and discussed point, Popper is famous for a reason. Waleswatcher (talk) 02:57, 16 December 2011 (UTC)


When you say "There's no such thing as 'Popper falsifiable in a trivial sense'", you're conducting research in philosophy. Whether that is true or false could be the subject for philosophical debate. How about this: give us one single citation of Popper using his criterion in any situation parallel to these toy examples (where an obviously ludicrous theory is concatenated with a single falsifiable statement to produce a "scientific" theory). If there are no such examples I recommend reconsidering whether this is truly an immediate consequence of Popper's writings. Wpegden (talk) 04:23, 16 December 2011 (UTC)

Your paragraph above "Regarding not mentioning Popper..." you make it clear that you think that the statement about Popper should be here precisely because you think it is an interesting point which has been overlooked outside of Wikipedia. This is exactly the kind of statement which can't be present in an encyclopedia article without citation. I'm removing the paragraph again in light of this. Before replacing it consider the consensus appears to be building in favor of the irrelevance of the point to the article. Wpegden (talk) 04:23, 16 December 2011 (UTC)

Edit: instead of removing the paragraph, I will await the outcome of the Mediation. Wpegden (talk) 04:26, 16 December 2011 (UTC)

Mediation

I have listed here a mediation dispute on this question, I hope everyone treats it in good faith.

http://en.wikipedia.org/wiki/Wikipedia:Mediation_Cabal/Cases/16_December_2011/

8digits (talk) —Preceding undated comment added 04:15, 16 December 2011 (UTC).

Wpegden appears to have deleted the above link and the autosig, so I've added it back. Waleswatcher (talk) 20:55, 18 December 2011 (UTC)

I don't think I did, if I did so I assure you it was unintentional!! Wpegden (talk) 21:21, 18 December 2011 (UTC)

To all concerned - the mediation was declared closed by the mediator (Thehistorian10), but unfortunately with an ambiguous and self-contradictory "ruling", rather than by reaching a consensus. The other mediators at the Mediation Cabal believed the case to be so badly mishandled that they have banned Thehistorian10 from serving as a mediator. That notice is (or was) here https://en.wikipedia.org/w/index.php?title=User_talk%3AThehistorian10&action=historysubmit&diff=470485475&oldid=470482748 . There is an ongoing discussion as to re-open the mediation case elsewhere here http://en.wikipedia.org/wiki/Wikipedia_talk:Mediation_Cabal . I'm ambivalent. Waleswatcher (talk) 20:06, 9 January 2012 (UTC)

There's no doubt that case was a mess. I had no idea how Mediation cases are supposed to go but its clear from reading the guidelines after-the-fact that apart from massive general communication problems basic guidelines were ignored.
Obviously it would be best to avoid having another mediation, though. Is the paragraph at a point right now where we are basically happy with the content we've decided on? Maybe it would help to keep in mind that I consider string theory part of science (I've said this many times on this page from the very beginning) for reasons like "it is done by scientists", etc. and have no intention of defending any statements to the contrary. In part because it seems to me that there may be dispute regarding the status of string theory and Popper in the literature (among reasonable, non-crazy scientists), I think it is more appropriate to remove dubious criticisms in the article calling string theory "not science" than to work to have defenses against that criticism based on Popper falsifiability in the article. (On the other hand, I think there is essentially no dispute in the literature on whether string theory is "science".)
That said, if you are unsatisfied at where we're at now and feel another mediation is appropriate to settle it, I completely accept that given the violations of the Mediator. Wpegden (talk) 02:44, 10 January 2012 (UTC)

Contrary Source

Here is a reputable source (article written by a string theorist published in the American Journal of Physics) which takes the opposite position as the one made by the "obvious" sentence. So I think its safe to say it is not obvious and so should remain removed. Wpegden (talk) 20:26, 18 December 2011 (UTC)

Your previous argument was that mentioning Popper is a bad idea because scientists don't care about it and therefore it's too uninteresting to belong in the article. As evidence, you produce an article that mentions Popper falsifiability? That source undermines your argument.
Are you now suddenly moving the goalposts and questioning that string theory is falsifiable? That is a fact that is already multiply cited, and can be cited further ad infinitum. This author - along with Woit, already discussed - apparently failed to understand that fact, and therefore comes to an incorrect conclusion regarding Popper. But the existence of this article strengthens the argument for including the phrase about Popper in the article. If you like, your citation can be mentioned as disagreeing, or can go in the criticism section. I'd oppose that - since it's manifestly wrong, just like Woit - but it's an option we can discuss.
Several sources already state explicitly that string theory is falsifiable. Multiple sources state that Popper's criterion for science is falsifiability. Still others state that Popper considered general relativity falsifiable and therefore science, and everyone (?) agrees (and in any case it's multiply cited) that string theory reduces to GR, and that if GR was falsified, so would be string theory. From there, it's a trivial synthesis to say that string theory is Popper falsifiable. There is nothing new in that. Waleswatcher (talk) 20:52, 18 December 2011 (UTC)
No, I am not changing my point or moving the goal post. As I said before, I consider the status of string theory with regards to Popper a philosphical statement, and, as such, one that should have citations from philosophy journals. I am not advocating using this citation to say that "string theory is not scientific according to Popper." I am not even using this citation to say you are wrong. I am using this citation to demonstrate the statement you are trying to make about Popper is not an obvious statement, and so constitutes original research. The relevant quote from the article is "So far string theory has failed to meet Popper’s criterion." It seems the statement is not obvious to him either, right? And I have always said that what I disagree with is that string theory is falsifiable "in the technical sense of Popper", which is what this article is speaking to. This point can still be found in our discussions of the issue. Wpegden (talk) 21:20, 18 December 2011 (UTC)
Let me put it this way. Which of the cited statements that you list do you think Emam disagrees with? Or do you think there is just something wrong with him that he comes to the opposite conclusion as the one you consider "trivial"? And how can we be sure that you are right about there being something wrong with him, without citations supporting your synthesis? Wpegden (talk) 21:27, 18 December 2011 (UTC)
There are plenty of citations that support the synthesis, that's precisely the point. There is nothing original there, it follows trivially from the cited facts presented. From reading his paper, it seems that Emam is referring to tests of the high energy predictions of string theory (since he says that technology may eventually become available). He is correct that such tests are needed to convincingly verify string theory, as is already discussed in the article. He is wrong that such tests are needed to falsify string theory, a fact that you seem to agree with. Since the latter (rather than the former) is Popper's criterion, he is also wrong about Popper. If I had to guess, I would say that he disagrees that Popper's criterion is merely falsifiability - but that is very easily established by citations which I'm happy to add if requested. Waleswatcher (talk) 22:16, 18 December 2011 (UTC)
At this point, we have had an active discussion in which you are the only person defending your viewpoint, and a mediator has suggested that the statement should be removed without citation. Is your plan to ignore the mediators suggestion and continue edit warring by replacing the uncited statement, in spite of the mediation? Wpegden (talk) 21:31, 18 December 2011 (UTC)
There is an active mediation case ongoing that has not been resolved. Only one of the two mediators has even commented, the comment is ambiguous with regard to precisely what s/he believes should be deleted, and s/he hasn't yet responded to a request for clarification. Modifying the article at this point is not in good faith, and can be interpreted as a sign that you are not interested in the outcome of the mediation case (which, I will note, was not started or requested by me). Waleswatcher (talk) 22:16, 18 December 2011 (UTC)

Mediator said today- I would like anything to do with the (alleged) falsifiability of string theory to be removed, until such a time as sources - which can be agreed on by ALL parties in this dispute - are found. That is my final word on the matter.[[10]] Bhny (talk) 17:49, 19 December 2011 (UTC)

Cites added to fulfill the mediator's request (one is new and states that Popper's criterion is falsifiability, the other two were already there, and state that string theory is falsifiable. Waleswatcher (talk) —Preceding undated comment added 18:11, 19 December 2011 (UTC).
What about the part where the moderator said sources - which can be agreed on by ALL parties in this dispute Bhny (talk) 18:21, 19 December 2011 (UTC)
So far as I know, no one has not "agreed on" (whatever that means) any of those sources. 8digits didn't seem to think highly of the Comins' source since it is an introductory text - although he had no problem citing Woit, a popular book written by a non-scientist - so I added the Distler paper, which is written by four professional researchers and published in the premier physics journal. The Distler cite is just as explicit at Comins (it says in the abstract that observations could falsify generic models of string theory). I haven't seen any objections. Waleswatcher (talk) 18:30, 19 December 2011 (UTC)
I have removed the citation, as it does not support the sentence it is attached to. The sentence it is attached to says that string theory is meets Poppers definition of a scientific theory. The citation does not even mention string theory once. You are saying that readers should read citations A, B, and C and connect the dots and realize that D holds (where D is the statement that string theory is scientific according to Popper, a statement which does not appear in any of your citations). You believe this is obvious but the consensus, including the view of the moderator, is that it is not. So the statement should go.
How in the world could it mention string theory? It was written before string theory was discovered. It says in very simple, plain English that Popper's criterion for science is falsifiability. That's obviously relevant and important to that sentence, so why did you delete it? There's another, separate issue regarding whether or not part of that statement is an "improper synthesis". If so, the appropriate action is to remove the phrase regarding Popper until a cite can be found for it. But there can be no argument that so long as the article mentions Popper's criterion, the cite you removed is relevant. Waleswatcher (talk) 19:15, 19 December 2011 (UTC)
When this conversation started there were some reasonable points raised by all sides. That ceased to be the case a long time ago. I seem to recall that when I pointed out a reputable source indicating that string theory is not scientific in the sense of Popper, you managed to assert (should I say, convince yourself?) that this strengthens your argument that the statement "string theory is scientific according to Popper" should be included in the article, without a citation. I am honestly starting to wonder if you are just trolling at this point. Certainly you are not working to achieve a reasonable consensus on the situation and improve the article.
The point that everyone in the present discussion (including the mediator) agrees to except for you is a very simple one: the statement that string theory is scientific in the sense of Popper cannot be in the article without a citation that says explicitly that string theory is scientific in the sense of Popper. I believe you understand that this is what the disagreement is, which leads me to the conclusion that you are willfully acting as if you don't so that you can ignore the consensus and view of the mediator (since you are still posting the sentence without a citation which explicitly supports the sentence). In my view, consensus is now as close as it ever will be. Walsewatcher is the exception that proves the rule. Wpegden (talk) 19:12, 19 December 2011 (UTC)
I'm sorry you feel that way. Part of the problem here is that there is no agreement among you and 8digits on what should be done. Multiple people reverted 8digit's edits prior to this starting, and you have stated positions that explicitly disagree with him/her on what should be done. From the beginning I've tried to focus the discussion on what I think we agree is the only possibly gray area - the second half of that sentence where it mentions Popper.
At this point I'm willing to propose a compromise. We can delete the second half, at least for now, but keep the first. Further, I think we should keep the cite to Popper, since it is clearly relevant as per my response above. I'll edit the article now to reflect that. I do not agree that this is (or was) an improper synthesis, I'm simply worn out under the edit war you have maintained, and I think it's better at this point to reach a consensus compromise rather than return in a while and find the article mangled even further. Please let me know if you are happy with the article as it will be in a moment. Waleswatcher (talk) 19:21, 19 December 2011 (UTC)

What you are doing Waleswatcher, is making a mockery of the mediation process. You have till the 6 January to provide evidence of this claim of yours. Note I do not like the references you have picked to support the other two sentences, can you please add more to show the mediator. 8digits (talk) —Preceding undated comment added 01:36, 21 December 2011 (UTC).

Sorry, but - what?? YOU'RE the one who edited the page while the mediation was still ongoing - mediation that YOU requested. You asked that it be respected, but then YOU went ahead and edited the page before the mediation was anywhere close to concluded (closely followed by Wpegden and Bhny, who did the same). Not only that, you barely participated on the mediation page. Now you accuse me of making a "mockery" of it? Talk about hypocrisy.
What we ought to do is restore the page to as it was before this process started, since it is still ongoing. Would you like me to do that, 8digits?
As for the references, you've made it clear that no matter what I add you will never be satisfied. You've lost all credibility in this. At least Wpegden is honestly trying to improve the article. I have no idea what you're trying to do to it. Waleswatcher (talk) 06:44, 21 December 2011 (UTC)
Please try me, add a few more references which you did say you would do.

8digits (talk) —Preceding undated comment added 11:10, 21 December 2011 (UTC).

Please Waleswatcher, can you list some references to support your case, the ones you are using now are a combination of beginners book or rticles that have only minor associations with your claims. 8digits (talk) 01:56, 23 December 2011 (UTC) 8digits (talk)

The Comins reference is a physics textbook written by professional (astro)physicists. It says explicitly that string theory is falsifiable for precisely the reasons stated in the article (plus some more). The Distler reference is an article written by four professional researchers, published in the premier peer-reviewed physics journal, and has at least 18 citations in other research articles. The Distler cite is just as explicit at Comins - it says in the abstract and in the text that certain observations would falsify generic models of string theory, full stop. The title is "Falsifying Models of New Physics via WW Scattering". How exactly you manage to twist that as having only a "minor association" with "my" claims I have no idea - the word "falsify" is in the title, and string theory is mentioned in the abstract, and the topic is precisely how to falsify it using quantum mechanics and unitarity. The third reference is to an article by Popper, who is widely considered to be an authority on Popper. So no, I'm afraid I cannot fulfill your request to add higher quality references, because these are already of the highest possible quality. Waleswatcher (talk) 04:56, 23 December 2011 (UTC)
One more comment on that. A while back when the primary citation for this was Comins (and Polchinski, but never mind), 8digits objected to it on the grounds that it was an introductory textbook. So, I added Distler, which is as far from a intro textbook as you can get... and 8digits still objects. I can only conclude that s/he simply won't be satisfied no matter what references are added.
I'll also point out that 8digits has repeatedly added uncited claims to the article, and for a while insisted vehemently that Popper thought quantum mechanics was unfalsifiable. But when challenged, s/he simply shifted ground (since that's of course not the case, Popper was very familiar with QM and its predictions). So it seems to be part of a pattern. Waleswatcher (talk) 05:50, 23 December 2011 (UTC)

You have no reference to support your view that to falsify string theory, it would suffice to falsify quantum mechanics.

What??? That's the entire point of the Distler paper. That's what it is about. (It's also stated in the Comins reference - and every text on string theory spends a major part of its material explaining how to quantize the string.) I'm sorry, but it seems very clear from your comments and questions that you are not approaching this in good faith. I'm going to stop responding to your comments from now on, unless someone else supports them or shares your concerns. Waleswatcher (talk) 02:29, 25 December 2011 (UTC)

For your statement to falsify string theory, it would suffice to falsify fundamental Lorentz invariance, you quote this article http://arxiv.org/PS_cache/hep-ph/pdf/0604/0604255v4.pdf which part exactly of this article supports this view. Also which part of this article supports your view that all string theory models are falsifiable, it is your quote and reference.

Discovering the Universe: From the Stars to the Planets [Paperback] Neil F. Comins (Author), William J. Kaufmann (Author) 5.0 out of 5 stars

Discovering the Universe: From the Stars to the Planets engages students with an inquiry-based exploration of the universe and the scientific process. Developed with a “big picture” approach, the text first explains how the stars, the galaxies, and the entire universe formed, and then discusses planets and other components of our solar system. Students follow this natural conceptual progression within a proven learning method designed to address misconceptions and build a deep understanding of science and the world around us.

Really this is your reference that to falsify string theory, it would suffice to falsify general relativity? Also which part of this book supports your view that all string theory models are falsifiable, again it is your quote and reference.

Already done on this page. You ignored it. Now you're asking me to give quotes again? No. It's page 519, or just scroll up. As for GR, the fact that string theory reduces to GR is in Polchinski, GSW, BBS, and every other text on string theory. It's the reason people care about string theory in the first place. These are truly basic facts about string theory. They're elsewhere in this wiki article, even. Do you want me to reference our own article? Waleswatcher (talk) 12:55, 25 December 2011 (UTC)

Page numbers and quotes would be appreciated for this book. 8digits (talk) 14:18, 24 December 2011 (UTC) 8digits (talk)

Did you read this part of the conclusion of the article you quoted with the word *could* emphasis added "Theories which *could* violate the bound include those which violate Lorentz invariance [21], or unitarity [22]."

This article in other words is saying *could* not necessarily that it will.

So? It seems you've still failed to understand the basics of this discussion. Yes, some Lorentz or unitarity violating theories might NOT violate that bound. But any theory that DOES violate the bound is necessarily Lorentz or unitarity violating. In other words, data that shows the bound is violated FALSIFIES any theory that is Lorentz invariant and unitary, such as string theory. Waleswatcher (talk) 04:50, 27 December 2011 (UTC)

There are some other interesting quotes from the article too which I will quote in full so you cannot accuse me of cherry picking.

"Indeed, if the scale of quantum gravity is as high as the Planck scale, it becomes interesting to ask the question as to whether or not the theory is, even in principle, falsifiable. One possibility is that the mathematical structure leads to unique low energy predictions. However, in the case of string theory, recent progress seems to indicate that this is not a likely scenario. Another possibility is that there are low energy, non-Planck suppressed, consequences of some underlying symmetries. Symmetries link the UV and the infrared (IR) by distinguishing between universality classes. However, string theory does not seem to have any problems generating the low energy symmetries manifested at energies presently explored. Indeed, given the enormous number of string vacua it may be that string theory can accommodate whatever new physics is found at the TeV scale by the Large Hadron Collider (LHC).

Thus it seems that decoupling may have the effect of rendering string theory unfalsifiable."

I see you chose to stop your quote right at that point, which is exactly cherry picking since the next sentence begins "However" and goes on to explain precisely how to falsify it (which is, after all, the subject of the article). Transparent sophistry like that simply undermines your position even further, 8digits. Anyone can read the article for themselves, it's available free on the net. It says string theory can be falsified, that's the whole point. Waleswatcher (talk) 04:50, 27 December 2011 (UTC)

I do not think this article supports your case good enough, to be used the way it is.

Now let me get on to our logic.

This is what is written in the article.

"all string theory models are quantum mechanical, Lorentz invariant,[36] unitary, and contain Einstein's General Relativity as a low energy limit.[37] Therefore, to falsify[38] string theory, it would suffice to falsify quantum mechanics, fundamental Lorentz invariance,[39] or general relativity.[40] Hence, all string theory models are falsifiable."

Let me reword it and make the following statements.

"all GR theory models contains Newton's Physics at ..... Therefore, to falsify GR, it would suffice to falsify Newton's Physics. Hence, all GR theory models are falsifiable."

I do not think the logic is good enough. 8digits (talk) 13:40, 26 December 2011 (UTC) 8digits (talk)

What? Are you trying to say that GR is falsifiable because it contains Newton's theory as a limit? If so, you're right (and that further supports the points made in the article). If not, I have no idea what you're trying to say. Waleswatcher (talk) 04:50, 27 December 2011 (UTC)
These are evasions not answers.

8digits (talk) 13:27, 27 December 2011 (UTC) 8digits (talk)


Waleswatcher, the GR example should convince you that your viewpoint is incorrect. Popper wrote specifically about General relativity as an example of a theory meeting his notion of "scientific". He believed that GR was falsifiable because of new predictions it made which could be tested (i.e., light curving around the sun), and not because of its Newton-laws limit. That Popper never made a claim about a theory such as GR being falsifiable based on predictions made by previously established theories should convince any fair-minded observer that this is a leap of logic which is not "trivial" or "obvious" (and, in fact, probably not a valid application of Popper's criterion at all). Wpegden (talk) 18:03, 29 December 2011 (UTC)
Thanks for your comment, but I don't agree. I think that Popper would have agreed with me that the fact that GR reduces to Newton suffices to guarantee its status as a scientific theory. If you read his criteria for what constitutes science, which are very simple, concise, and written in plain English, that's clear. Popper was trying to distinguish between theories like GR and "theories" like Marxism and astrology. There would have been no doubt in his mind regarding the scientific status of GR, regardless of whether the technology at the time was adequate to conclusively rule it in or out compared to Newton.
Of course GR also makes predictions that contradict Newton, and testing those predictions (and thereby falsifying either GR or Newton) was obviously crucial for it to replace Newton as the dominant theory of gravity. Popper quite rightly focussed on those tests, the first of which occurred in 1919 when Popper was young. This article, after mentioning that string theory is obviously scientific by Popper's standard (as well as any other I've ever heard of), should certainly go on to point out that string theory does in fact suffer from the difficulty that it's hard to test with experiments that distinguish it from other putative theories of quantum gravity. Waleswatcher (talk) 19:15, 29 December 2011 (UTC)
I don't think this really a reasonable perspective. If Popper considered "including a falsifiable theory" as a way that a theory could be falsifiable, there would be at least one example of him applying his criterion in his way. The most reasonable explanation for him never having done so, is that he didn't consider this a valid application of his criterion. Wpegden (talk) 21:49, 29 December 2011 (UTC)
Quite possibly he DID apply it that way: I haven't searched, and neither had anyone else to my knowledge. But quite possibly not, because from what I've read Popper thought it was obvious that theories like this in physics were scientific. I don't think there would be any question in his mind about string theory, because it clearly meets the criterion he carefully laid out, just as GR and special relativity did. Popper was very aware of the hierarchical nature of physical theory - he commented how Newton superseded Kepler, then SR took the place of Newton, and GR took the place of SR. In each case each theory included the former as a special case. All were obviously falsifiable, both because they included the previous theory and because they made new predictions. String theory is no different. Waleswatcher (talk) 23:22, 29 December 2011 (UTC)
You say "from what I've read Popper thought it was obvious..." . So then there's a simple resolution to this dispute after all... tell us where you've read these things!!! Wpegden (talk) 01:39, 30 December 2011 (UTC)
The link that's in the article now is concise, that's the best place to start. If you want more detail, read The Logic of Scientific Discovery, online here http://www.cosmopolitanuniversity.ac/library/LogicofScientificDiscoveryPopper1959.pdf Browsing through it again, I found several relevant passages. p.66 "We can put this more briefly by saying: a theory is falsifiable if the class of its potential falsifiers is not empty." It follows trivially that if theory A contains (the predictions of) theory B, and if the class of potential falsifiers of B is non-empty, then A is falsifiable. On page 106 Popper considers a toy model where one has a set of theories, some of wich are "dependent theories" in the sense of the title of this section of the talk page. Popper considered all the theories to be falsifiable - it's just that some are more easily falsifiable than others (that section is about degrees of falsification). Finally, you might read section 3 (page 9). Popper outlines four lines on which to test theories: 1) logical consistency, 2) establishing whether or not it's a scientific theory, 3) determining whether the theory would be a scientific advance if it survives, and 4) testing it with experiment. It is only in 4) that the issue of new predictions comes up. Step 2) (whether the theory is scientific) is independent of data and experimental technology, it's a question about the theory as an abstract, stand-alone construct (deciding if a theory is scientific is what he calls the problem of demarkation). His answer? Scientific=falsifiable=at least one prediction that could be falsified. That's it. It's very simple, and string theory obviously meets this criterion. Waleswatcher (talk) 14:33, 30 December 2011 (UTC)
Aha. I thought you meant you had a secondary source on this. Popper's work itself can easily argued both directions... this is why you are doing original research. For example, he makes it clear in section 3 that he only envisions people trying to falsify new theories by trying to falsify predictions made not by pre-established theories. This calls into question whether new theories without new predictions should be considered scientific. To take a simple example: Freudian psychoanalysis could easily be argued to be predicated on the assumption that everyone has a brain. This is clearly a falsifiable, but also a trivial and "preestablished" statement. And Popper certainly didn't Freudian psychoanalysis to be falsifiable. In general, you have this problem, that with your logic, one could make an argument that almost anything is falsifiable (including, say, Christianity, if we consider it to predict that all new people are not messiahs, which implies they have human parents, which is a falsifiable statement, since if its false we can find babies appearing out of nowhere.) In general, I have trouble imagining a common nonscientific world-view that I couldn't argue is falsifiable using this kind of logic. The example on 106 doesn't help your case, since each theory considered introduces new falsifiable predictions above its dependent theories. My problem is: I know of no evidence that Popper thought his criterion could validly be applied in this trivial way, and 2) if he thought so, I think he would have pointed it out, or some person in the world other than you would have noticed this and written something about it. So far, you appear to be the only person in the world I can find who thinks this is clearly a valid application of Poppers criterion. And thats the point. Even if you are right (which I don't believe) it can't be in Wikipedia when it is the only place the statement is being made.Wpegden (talk) 03:05, 1 January 2012 (UTC)
Popper's work cannot be argued in either direction. It's crystal clear, he was very good at that and very careful. In the part of section 3 I think you're referring to he's not discussion demarkation (determining whether a theory is scientific), he's discussing comparing the theory against alternatives. As for your Freudian example, Popper would agree that if you add/include "everyone has a brain" in the theory that might make it falsifiable (depending on precisely what you mean by "everyone"), but - by the criteria he explains later - only to a very small degree. Indeed, that simply points up the issue that we've discussed already, that Popper discusses, and that's already in the article - you need relatively unique predictions that get verified to start having real confidence that the theory is correct. But that's a separate issue from whether the theory is science, both according to Popper and logically. Waleswatcher (talk) 15:20, 2 January 2012 (UTC)
Wow. So, let me get this straight: you think we should have the statement that "Freudian pyschoanalysis is scientific according to Popper" in the article on Freudian psychoanalysis? I could set it up exactly the same way as you are defending here, but with brains instead of general relativity. Why should this be here if that should not be there? We could go around and add these little paragraphs to hundreds of articles: Christianity, ESP (also depends on brains), astrology (depends on basic astronomical facts like the rising of the sun), phrenology (depends on everyone having a head), etc. Wpegden (talk) 21:34, 3 January 2012 (UTC)
You're not arguing in any sort of serious way anymore - you're just trying to knock down strawmen. Putting words in my mouth and then attacking them doesn't get us anywhere.
If you're actually in earnest, the difference is that "everyone has a brain" is not really part of Freudian analysis - it's a fact about anatomy or biology, not psychology. The fact that string theory is quantum and general relativistic, on the other hand, is the essential, fundamental feature of the theory. It's why string theory is interesting. It's the single most important thing about it. And, on top, it's a precise, highly falsifiable prediction that emerges in a very non-obvious and unexpected way. The two are not at all comparable. Waleswatcher (talk) 22:19, 3 January 2012 (UTC)
You're missing my point. My point is that we agree more than you think; we both think the trivial logic A is B, B is C, so A is C cannot justify calling something "scientific according to Popper" in a Wikipedia article. Rather, you think all of these other things matter for your sense of whether or not its appropriate (the other things being: its "why string theory is interesting", its "the single most important thing about it", and, especially, "it emerges in a very non-obvious and unexpected way", etc.). This demonstrates why the the trivial logic in the Wikipedia article is unacceptable. The point is that whether it something is scientific according to Popper (or, for the sake of agreement, lets say, whether this is a meaningful/interesting statement, unlike the corresponding statements for Christianity, etc.) is not as trivial as the language you are defending makes it sound. The fact that all of these factors go into your viewpoint of whether it is disingenuous to call something "Popper Scientific" illustrates why Wikipedia cannot be the home for a 3 sentence deduction representing the only place in the world where String Theory is "shown" to be so. Wpegden (talk) 14:22, 4 January 2012 (UTC)
We're just going around in circles. The facts are these: string theory is interesting primarily because it's a quantum theory of gravity, it's falsifiable (multiple cites) because it reduces to GR, is Lorentz invariant and quantum (multiple cites) and because it makes unique new predictions (cites), professional researchers think those facts are interesting enough to write papers and books about, Popper says that all falsifiable theories are scientific (multiple cites), therefore it's a trivial synthesis to state that string theory is science according to Popper. Waleswatcher (talk) 12:45, 5 January 2012 (UTC)
Wow, this still? Let me try to boil this down: String theory is not "shown" to be scientific in any particular place because it's status as a scientific theory is not seriously questioned in the scientific community (its correctness, on the other hand, is). If it were not science, there would not be O(1000) or more papers published in peer reviewed physics journals like Physical Review, MIT's course on string theory would be classified as math or something else instead of physics, and so on. Its quite easy to agree that ordinarily the claim that a given scientific theory is, in fact, science would not be noteworthy, but its obvious why this case is an exception: because there is a widely-selling popular-level physics book, as well as one of the most trafficked physics blogs on the internet, claiming otherwise. Im not opposed to having this book, as well as Smolin's, included in the article; since they surely have some significance (though not much in the way of rigorous content bearing on the scientific question itself). However, as long as the claim that string theory is not science is being presented, the article also deserves an explicit recitation of Popper's criterion, as well as the rigorously derivable properties of string theory that show unambiguously that it fits that criterion.
I noticed earlier that the phrase "de facto untestable" was criticized. Let me say that this was my phrase, and I basically chose it as a compromise with whatever was in there before – I dont remember exactly what the previous language was that I replaced, but it seemed too clearly wrong to stand. I choose this language because it does represent a claim about string theory that is not rigorous, and thus may take on varying shades of truth, depending on what a more detailed study of the landscape of phenomenologically viable solutions yields. That string theory is testable and that it is science according to Popper's criterion are empirical facts. That it may not be feasible to test in practice is more subtle, and thats what that language I chose was hoping to convey. I dont agree that string theory is de-facto untestable (or at least I think its too early to claim that), but this is at least a claim that is not rigorously ruled out, and I think it accurately captures what many of the more skeptical physicists think, yet it is distinct from the wrong statements that string theory fails to be science. isocliff__ 06:02, 6 January 2012 (UTC) — Preceding unsigned comment added by Isocliff (talk • contribs)
Isocliff, the dispute currently is not whether string theory is science. Personally, I consider string theory within the realm of science, for reasons like "it is done by science departments". Indeed, I think this issue is clear in the article. The first line is, after all: "String theory is an active research framework in particle physics..." No one is saying its Math or English.
Instead, the issue is that there is a paragraph which states as fact that string theory is "falsifiable". This is not an undisputed statement in the literature. (In fact, my estimation is that the majority of sources call it "unfalsifiable", but it is difficult to make judgements of these kinds). In any case, I have provided several high quality references on the mediation page stating that string theory is not falsifiable. As these are all recent citations, it doesn't matter what you or I personally believe. Wikipedia can't be picking winners and losers among the available citations, regardless how rigorous a case you feel you can make for one side or another. The only option is to state that the issue is in dispute and give both sides, with citations. Wpegden (talk) 21:06, 6 January 2012 (UTC)

Poppers demanded that to be scientific all statements had to be falisfied, let us again check what is written in the article.

"all string theory models are quantum mechanical, Lorentz invariant,[36] unitary, and contain Einstein's General Relativity as a low energy limit.[37] Therefore, to falsify[38] string theory, it would suffice to falsify quantum mechanics, fundamental Lorentz invariance,[39] or general relativity.[40] Hence, all string theory models are falsifiable."

Popper stated that (A) "Tomorrow it will rain" is a scientific statement because it can be falsified.

He also stated that "Tomorrow it will not rain" is a scientific statement again because it can be falsified let us call it (B)

I could make the following statement call it (C) "Tomorrow it will rain" or "Tomorrow it will not rain". This statement Popper stated was not scientific as it was not falsifiable.

Yet if I put your logic I get the following.

"all (C) statement contains (A) and (B). Therefore, to falsify (C), it would suffice to falsify (A) or (B). Hence, all (C) is falsifiable."

Clearly this statement is wrong. 8digits (talk) 09:46, 2 January 2012 (UTC) 8digits (talk)

You're desperately grasping at straws now. You've replaced "or" with "and" in the hopes no one notices. Your theory (C) is not falsifiable, because "tomorrow it will rain OR tomorrow it will not rain" contains all possibilities. But the theory "tomorrow it will rain AND tomorrow it will not rain" is very falsifiable - in fact it's automatically falsified since those two statements directly contradict each other. But even if they didn't, with AND in between falsifying either statement falsifies the theory. That's the case with string theory. String theory is unitary AND reduces to GR AND Lorentz invariant, so falsifying any of those properties falsifies string theory. Waleswatcher (talk) 15:11, 2 January 2012 (UTC)
Here is your exact words....

Therefore, to falsify[38] string theory, it would suffice to falsify quantum mechanics, fundamental Lorentz invariance,[39] or general relativity.[40]

I simply replaced in this statement "string theory" with (C) "quantum mechanics" with (A) I could have put something in "fundamental Lorentz invariance" but choice not too "general relativity" with (B)


The OR comes from you. There is no AND. 8digits (talk) 13:17, 3 January 2012 (UTC) 8digits (talk)

I can't understand what you're asking, sorry. Try again. ST is quantum mechanical AND general relativistic AND ... Therefore falsifying any of those falsifies string theory - that's really basic logic. The "example" you gave was a theory that was (A) OR (B), not (A) AND (B). Waleswatcher (talk) 22:04, 3 January 2012 (UTC)

Read the next line please which I quoted in my previous post.

By the way string theory is certainly much more then "quantum mechanical AND general relativistic AND ... " but that is another error.

8digits (talk) 03:50, 4 January 2012 (UTC) 8digits (talk)

I have no idea what you're talking about. You're not making sense. Waleswatcher (talk) 04:54, 4 January 2012 (UTC)

What is not clear to you. 8digits (talk) 13:56, 4 January 2012 (UTC) 8digits (talk)

  1. ^ J. Polchinski, String Theory, Cambridge University Press, Cambridge, UK (1998)
  2. ^ N. Comins, W. Kaufmann, Discovering the Universe: From the Stars to the Planets, W.H. Freeman & Co., p. 357 (2008)
Retrieved from "https://en.wikipedia.org/w/index.php?title=Talk:String_theory/Archive_4&oldid=1137208099"