Wikipedia talk:WikiProject Mathematics/Archive/2014/Feb

Intersection

This has recently been created, with the disambiguation page previously at this location moved to Intersection (disambiguation). The problem is I don't think the mathematical term is the primary topic: if anything the common usage of the word is when talking about road intersections (or listening to your sat-nav read them off to you), but probably being a common English word used in many ways and fields its best without a primary topic, as before.

At the same time the new article at Intersection doesn't seem to be on a distinct topic: it's mostly on geometric intersection, but includes some set theory and possibly other areas, leading to a very confusing introduction, some even more confusing links, and little else. The problem is the different mathematical uses have little in common, except for being different interpretations of the word in different fields. But that does not make for a good article topic.--JohnBlackburne^words_deeds 02:21, 30 January 2014 (UTC)

A road intersection is a 2-D intersection. Intersections in (Euclidean) geometry, algebraic geometry, and set theory derived from one common idea. What namely “does not make for a good article topic”, this WP:CONCEPTDAB? Okay, make the intersection (geometry) article first, and then we’ll discuss the merit of the “most general article”. I think, most people here will agree that intersection (Euclidean geometry) shall not consider differentially-geometric aspects. Imagine one wants to know what is an intersection of a line and a quadric in a projective plane. These are generally curves, but the article on curves hardly considers the question of intersections. These are submanifolds, but the reader hasn’t necessarily know this word. If s/he come to my stub, s/he will obtain some minimal idea how to approach the problem. If s/he come to the original dab, it will be a puzzle. Where to go: intersection (Euclidean geometry) (formerly “intersection point”)? It misses the line at infinity. Intersection (set theory)? S/he will not learn anything new about the problem in question. Intersection theory? The reader will get a huge charge of general nonsense. Whereas for a reader who looks for something about Euclidean geometry there is little difference between “my article” and a conventional dab page.

“Even more confusing links” – which namely? “Little else” – yes, the house is just started. I think one should say about dimensions, as well as relationship between intersection of submanifolds and the orientation structure (what is expressed with the intersection number for dim_intersection = 0, but in more general case). Incnis Mrsi (talk) 08:59, 31 January 2014 (UTC)

I agree with Incnis Mrsi that the situation was confusing. However, IMO, his solution is not the best one. In fact, in mathematics, there is only one concept of intersection, the set theoretical one. I agree that, in incidence geometry, lines and planes are not considered as sets, but they are intuitively. And, in incidence geometry, one may consider the set of the points that are incident to a line; this allows to consider the intersection of two lines as a set theoretical intersection. Therefore I suggest the following

• Rename intersection (set theory) as intersection (mathematics) (I have just noted that the latter is already a redirect to the former)
• Add to Intersection (mathematics) a section "Intersection in geometry" with template {{main|Intersection (geometry)}}
• Rename Intersection (Euclidean geometry) as Intersection (geometry) and add it a section about projective geometry (a motivation of projective geometry is to solve intersection problems)
• Add to Intersection (geometry)#See also links to Intersection theory and Intersection number
• Move back intersection (disambiguation) and replace the existing math. entries by a single link to intersection (mathematics)

D.Lazard (talk) 11:08, 31 January 2014 (UTC)

I do not agree with Daniel that “there is only one concept of intersection, the set-theoretical one”. Set-theoretically there is no difference between an intersection proper and a tangential point (note another red link), but geometrically and algebraically there is. Also look at the picture please: set-theoretically there is a set of two points, geometrically there are simply two intersections, algebraic-geometrically there is a 0-manifold consisting of two components with different signs, provided the line, the circle, and the plane all are oriented. Why not explain it in one article, indeed? Also, what is now intersection (Euclidean geometry) is not a suitable candidate for converting to intersection (geometry). It is a typical enumerative article like the current revision of rotation (mathematics) (see talk:Rotation group for further development) and, unfortunately, many other Wikipedia articles, not mathematical only, that need to be conceptual instead of enumerative. Incnis Mrsi (talk) 15:07, 31 January 2014 (UTC)

I certainly edited Intersection (mathematics) (edit | talk | history | links | watch | logs) to redirect it to intersection (I even remember how I entered {{R from extra disambig}}). Apparently there was a browser glitch and the edit wasn’t saved. BTW, the fr:Intersection (mathématiques) article is IMHO too poor to borrow something really usable from it. Incnis Mrsi (talk) 16:28, 31 January 2014 (UTC)

@Incnis Mrsi: When you write the the circle and the line of the picture have "two intersections" you are correct with respect to the non-mathematical meaning of "intersection" (road intersection), but you are not mathematically correct: the common mathematical terminology is that the circle and the line have two points of intersection, or two intersection points, or also that their intersection consists in two points. All these formulations are standard ways to talk about set intersections. Also it is clear that when the sets that are intersected have an extra structure, their intersection has also an extra structure. If I follow you argument, we should have an article for the intersection of vector spaces (the set intersection of two subspaces is a subspace), for ideals, and so on. Here, we have that the intersection of two algebraic varieties is an algebraic set, which, on your example, is not irreducible and has two components consisting of isolated points. Similarly a tangential point, aka tangent point, is a point of the (set) intersection that has a specific extra structure (the two curves or varieties or manifolds are tangent at that point). I do not see in your post any argument against merging Intersection and Intersection (set theory) into a single article called Intersection (mathematics). However, I see many reasons to use such a merger to improve both articles. D.Lazard (talk) 17:34, 31 January 2014 (UTC)

A good point about an additional structure. The only disagreement is about the precedence: I do not think the set theory should be qualified as the only formalism for intersection in mathematics. It is the standard one, certainly, but not an unique, and definitely not historically an original one (see below). Incnis Mrsi (talk) 19:28, 31 January 2014 (UTC)

(edit conflict)I agree with most of that: I think Intersection (geometry) is better than Intersection (Euclidean geometry); if that means adding some non-Euclidian geometry then do so, it's a good and natural extension of Euclidian geometry. I obviously agree with moving the DAB page back to Intersection. But I don't think it or the set theoretic use of intersection is the main mathematical use, I'd say that the geometric usage is as important. Looking at Intersection (Euclidean geometry) and Intersection (set theory) both are significant areas. So I'd change Intersection (mathematics) to redirect to the DAB page, i.e. Intersection. Apart from that any see-also links and {{main}} type links can be added as makes sense to clarify connections and help readers find articles.--JohnBlackburne^words_deeds 17:47, 31 January 2014 (UTC)

John, do not ignore my question, please. Which of my links are confusing? Of course my solution is not the best possible, but what namely did I do wrongly? Incnis Mrsi (talk) 19:28, 31 January 2014 (UTC)

I mentioned projective plane only as an easily accessible geometry that isn’t Euclidean. There are numerous other alternatives to the Euclidean space: pseudo-Euclidean spaces, for example, or just the affine geometry where words “circle” and “perpendicular” are meaningless. Incnis Mrsi (talk) 22:41, 31 January 2014 (UTC)

The primary usage of the word "intersect" in my opinion is to cut, in the geometrical sense. This is consistent with the Latin origin of the term, and the current English vernacular (as in the intersection of two streets). The set theoretic meaning if the term was not even introduced until the 20th century (or possibly the late 19th century, the OED puts it at 1909). I'm not sure what this implies for an article on the topic. Sławomir Biały (talk) 17:40, 31 January 2014 (UTC)

A bit of support from an unexpected source. But I think we have two distinct (although related) questions: the fate of the new stub (as well as of intersection (mathematics) that I failed to redirect because of a glitch), and the primary topic of the title Intersection (edit | talk | history | links | watch | logs). I do not have a highly competent opinion about the latter and IMHO it should be discussed at talk:Intersection (disambiguation) because it can possibly escalate to an RfC or otherwise attract an attention of non-mathematical disambiguators. Incnis Mrsi (talk) 19:28, 31 January 2014 (UTC)

If an RfC's needed it could be created here; RfCs can be started anywhere, including user pages. But I don't think one's needed; we're not yet reached that point. As for the fate of the current Intersection there's no need for it: Intersection (Euclidean geometry) and Intersection (set theory) are two distinct topics. If there's need to connect them that can be done using appropriate text and links in both articles, and both should be linked from the disambiguation page. But they're not both sub-topics of a more general "mathematical intersection" topic.--JohnBlackburne^words_deeds 19:58, 31 January 2014 (UTC)

John, you catch from the discussion only things convenient to you, and dodge my question about your own claim the second time. Nobody tries to refute that “Intersection (Euclidean geometry)” and “Intersection (set theory)” are distinct. The discussion deals with following problems:

1. There is no article “intersection (geometry)” (virtually all participants).
2. The “new intersection” topic can be merged with “intersection (set theory)” to “intersection (mathematics)” (D.Lazard).
3. The “intersection (Euclidean geometry)” has an inappropriate content and structure to be simply expanded to “intersection (geometry)” (Incnis Mrsi).
4. “Intersection (geometry)” is historically the primary meaning, and the set-theoretical interpretation of intersection was popularized only in 20th century (Sławomir Biały).

You did not comment on any of these 4 points in a reasonable way, only reiterate some of things you said from the beginning: one should not bother to improve or save anything of it, [because] Incnis Mrsi wrote this crap. Incnis Mrsi (talk) 22:41, 31 January 2014 (UTC)

Since there is discussion over what "intersection" truly means, mathematically, I would like to point out that most intersections can be interpreted as fiber products in an appropriate category. This is true of sets, vector spaces, ideals, schemes, and so on. But the primary meaning of "intersection" is not "a kind of fiber product", and the primary article on intersections should not introduce it as such. Ozob (talk) 02:00, 1 February 2014 (UTC)

Just a hint: Please have a look to the German WIKI on intersection = Schnitt. --Ag2gaeh (talk) 10:57, 1 February 2014 (UTC)

The German is less directly analogous, since "Schnitt" is already part of the German vernacular and literally means "cut" (as a noun, at least, as in "ein Schnitt von Rindfleisch"—"a cut of beef"), whereas in English intersection is an old loan word from Latin that would have been used exclusively in a scientific setting before its adoption into the language. This is reflected in the relative rarity of the word "intersection" in modern day-to-day English (with the exception of referring to day-to-day things that are actually geometric intersections, like streets). A better comparison for de:Schnitt would be the English disambiguation page cut. Sławomir Biały (talk) 13:41, 1 February 2014 (UTC)

Sorry, I only had the mathematical part of the German page in mind and did not think about the "intersection" of a knife and a beef. --Ag2gaeh (talk) 10:45, 2 February 2014 (UTC)

Wikipedia talk:Articles for creation/Stability of Boolean networks

Dear math experts: Here's another old abandoned Afc submission that's about to be deleted. Is this a notable topic, and should the article be kept? —Anne Delong (talk) 18:10, 30 January 2014 (UTC)

Delete it. Ozob (talk) 02:02, 31 January 2014 (UTC)

The stability of a Boolean network is one of the most important properties of the dynamics of such a network. The article gives a poorly described criterion for stability in NK models with no significant intro or background. Our Boolean network article could use more material on dynamics, but this article is unfortunately not it. I would recommend passing on this one. --Mark viking (talk) 03:02, 31 January 2014 (UTC)

If the AfC is kept, then the material can be used to supplement the existing articles. Is this reason enough to keep it for a few months?

Sorry I wasn't clear--I don't think the prose is salvageable and refs are pretty easy to find on this topic, so I don't see the utility in saving any of it. Thanks, --Mark viking (talk) 20:04, 31 January 2014 (UTC)

Thanks for taking the time to check this out. —Anne Delong (talk) 03:55, 3 February 2014 (UTC)

"Octagonal"

The usage of Octagonal (edit | talk | history | protect | delete | links | watch | logs | views) is under discussion, see talk:Octagonal -- 70.50.148.248 (talk) 07:48, 5 February 2014 (UTC)

AfC submission

Wikipedia talk:Articles for creation/K-trivial sets. Regards, FoCuSandLeArN (talk) 00:03, 4 February 2014 (UTC)

Also Wikipedia talk:Articles for creation/One-Shot Deviation Principle. Thank you, FoCuSandLeArN (talk) 01:08, 6 February 2014 (UTC)

Cyclic sieving

I've created a new, painfully stubby, article titled cyclic sieving. So work on it. Or, in other words, have fun. Michael Hardy (talk) 05:36, 6 February 2014 (UTC)

I think it would benefit greatly from one or two examples. JRSpriggs (talk) 06:19, 6 February 2014 (UTC)

So far only two articles link to it, so that's another thing to work on. Michael Hardy (talk) 20:07, 6 February 2014 (UTC)

EOM links

Spinningspark (talk · contribs · deleted contribs · logs · filter log · block user · block log) has been reverting the addition of EOM links en masse. I don't really have strong opinions about this, but I generally find the EOM to be a rather useful supplement to our own treatment of mathematical topics. At least some of the removed links are of a high quality (actually the first I noticed at Korn's inequality.) What does the project think about these edits? Should they be reverted? Sławomir Biały (talk) 16:31, 4 February 2014 (UTC)

I reverted them en masse because they had been inserted en masse. I am not particularly objecting to the site, I don't really know anything about the site one way or the other. However, the IP that has been inserting the links has been doing nothing else besides inserting them. That is spamming, regardless of the quality of the links. No justification was offered for inserting them in the edit summary, and I noted that many had been added as references without adding anything to the text. Since references are supposed to be there to support the text then that in itself looks spammy. As to their quality as external links, if editors think they are adding something that is not covered in the article then I'm fine with that, but it would be preferable that, if the material pointed to is suitable for Wikipedia, it should be added to Wikipedia and use the site as a ref instead of an EL. There are sometimes reasons material cannot be added to Wikipedia and an EL is justified on those grounds, but I'm not seeing anything here that fits in that category. SpinningSpark 16:59, 4 February 2014 (UTC)

To be sure, I don't question your reasons for removing the links, but I do think that in many cases these links are a valuable supplement to the article and that seems worth some consideration. Sławomir Biały (talk) 17:24, 4 February 2014 (UTC)

I'm fine with you just reverting me on the ones you think are useful. SpinningSpark 18:02, 4 February 2014 (UTC)

Sorry, I was the one adding all the links. My name is Camillo De Lellis and I am one of the editors of the Encyclopedia of Math, you can see my page there at User:Camillo.delellis. I noticed that several entries of the EoM are already regularly linked here at wikipedia, but the vast majority refers to entries which are rather old versions. Since I and other people have been renewing several of the pages there, I thought it was a good idea to check where they could be appropriately linked in wikipedia and I started going through mine ("En masse" might be subjective... note that from Christmas till now I anyway did not manage to link all the pages I renewed at EoM :-)). I spend a couple of hours per week with the entries at the EoM: this pretty much exhausts my alloted time for wikis and so I am not an active contributor of wikipedia. I was linking only pages which I believed appropriate and it seems to me that the pages I linked are more useful and appropriate than most of the EoM pages which are linked by other contributors (I am pretty choosy myself :-))). Some of the EoM pages do contain more material than wikipedia's corresponding pages, as for instance Function of bounded variation. Some, however, do not and I would consider EoM as a general reference work. In any case if what I was doing is considered spamming I stop right away. Sorry again, Camillo. — Preceding unsigned comment added by 188.154.99.222 (talk) 09:01, 8 February 2014 (UTC)

I'm not a fan of addition/revert em masse either way. However disagree with an overly literal application of particular line in WP:EL here, that is only adding it if it really offers information not being contained in the article yet. I rather treat it (and to degree links to MathWorld, MacTuror and PlanetMath as well) as "standard" link as long as the EL is rather small and empty. In a way similar to linking the IMDB in movie related articles. The reason for that being twofold. For short article EOM, MathWorld and MacTutor can also be considered as "general" sources/sources outside of footnotes. In such that cases a placing under references might be more appropriate, but since they are links some editors place them under EL. The other reason is simply, that I consider it as beneficial to readers to offer links to alternative encyclopedic representations of math content.--Kmhkmh (talk) 15:39, 7 February 2014 (UTC)

Actually, WP:EL is much more stringent than you portray. It does not allow EL for information that is "not contained in the article yet". Rather, it is for information that would not be in the article if it were developed to FA standard: a much more stringent requirement. Also, I believe that the community consensus on ELs is that the default position is not to include them; that is, there should be a definite good reason before they are added rather than add them automatically. However, I agree that it is sensible to consider the state of the development of the article. Good ELs in a stub or short start class article can benefit both readers and editors seeking to develop it. Well developed articles on the other hand should be a lot more choosy about including ELs. SpinningSpark 00:35, 8 February 2014 (UTC)

Yes, I'm aware of that, it is so strict to the point, that it is almost nonsensical if applied literally (always). I'd also dispute the community consensus with regard to the literal reading somewhat (after following the page for years). It is more that it has been established via "tradition" and some editors prefer an overly strict formulation (as a sharp knife in dispute and block link farms and undesirable links) but in doubt relax it in practice. In fact somewhat similar to your approach. However looking at the discussion archives and behaviour of reasonable editors in practice, I don't really see a consensus. In fact imho this guideline only works because the strict literal reading of the line you refer too is largely ignored in practice and people similar follow the nutshell description or common sense.

Anyway having said all I more or less agree with you distinction between smaller and larger article. However even for a large article an external link with less information can be beneficial as it potentially conveys important or some information faster than a rather large article and it might be beneficial for readers to the simply see the "authoritative" encyclopedic take on the subject. That's why I don't mind to link the EOM for instance as long as external link section is not already filled with better or more suitable links. But that's just me.--Kmhkmh (talk) 08:41, 8 February 2014 (UTC)

I would prefer not to focus on the policy for external links in general but to focus the discussion on EOM. If the consensus is that addition of links to the EOM is helpful for readers of mathematics articles, so that the links improve the encyclopaedia, then we should Ignore All Rules that prevent us from making that improvement. Deltahedron (talk) 09:03, 8 February 2014 (UTC)

I agree, above I tried to make a case for WP:IAR and explain why many editors do not follow a literal reading of the policy, that is apply WP:IAR. Personally I'd consider an EOM-Link in most cases as beneficial.--Kmhkmh (talk) 14:36, 8 February 2014 (UTC)

More on cyclic sieving

Several people have now contributed to Cyclic sieving. References and examples were added. I have now added a precise definition in a section labeled Definition.

There are still only three other articles that link to this new article. Michael Hardy (talk) 19:01, 8 February 2014 (UTC)

Displayed equations are centered?

I recently edited Talk:Transitive relation, and found that displayed equations are centered. I use MathJax, so my view may not be typical, but there could be a problem here.

$aRb\land bRc\rightarrow aRc$

Yep, it's a problem here, also. — Arthur Rubin (talk) 17:07, 7 February 2014 (UTC)

Looks like a problem with the code used to generate the MathJax code examining the code we have

<div class="MathJax_Display" role="textbox" aria-readonly="true" style="text-align: center;">
  <span class="MathJax" id="MathJax-Element-2-Frame" style=""> ...
  </span>
</div>

I've created T63051 for this issue.--Salix alba (talk): 19:35, 7 February 2014 (UTC)

How should it look like? I had a long discussion about that with one of the MathJax developers. As a result, the goal is to introduce a Displaystyle feature --Physikerwelt (talk) 11:55, 8 February 2014 (UTC)

It should respect the style defined in the wikitext. If you look at the example above its

:<math>a R b \land b R c \rightarrow a R c</math>

the maths tag is preceded by a : and WP:MARKUP#Indent text which says "Each colon at the start of a line causes the line to be indented by three more character positions." Editors will expect this rule to be applied, if the intention had been to center the equation then the {{center}} template or equivalent to be used.

There is a problem with the wikitext and you could say the above markup is a workaround for lack of proper maths support for display maths. --Salix alba (talk): 13:17, 8 February 2014 (UTC)

If you disable JavaScript in your browser, you can see that the code used to pass to MathJax is:

<dl>
<dd><span class="tex" dir="ltr">$ aRb\land bRc\rightarrow aRc $</span></dd>
</dl>

The centering decision is done within MathJax. To control the decision of MathJax the displaystyle attribute was proposed.

I think we should not start to change MathJax itself, because if we do so it will be hard to update to a new version. If there is a agreement to use the displaystyle attribute, and someone is willing to test that, we can merge that feature within a few days.--Physikerwelt (talk) 13:42, 8 February 2014 (UTC)

But things seem to have changed very recently. Possibly in the same update which caused the Texvc problem. Equations have been left aligned with MathJax until very recently, I've a screen shot from Oct 13 which shows this. --Salix alba (talk): 14:35, 8 February 2014 (UTC)

MathJax was updated from version 2.2 to version 2.3. Probably this caused the change. --Physikerwelt (talk) 15:28, 8 February 2014 (UTC)

I'm not sure where I'm supposed to report this, and moreover maybe it's just me, but an equation is still centered when "mathjax" is on.

$1+2+3+\dots =-{1 \over 12}.$

Interestingly, the problem can be fixed by adding ref:

$1+2+3+\dots =-{1 \over 12}.$

-- Taku (talk) 14:18, 9 February 2014 (UTC)

Anything you add outside the math tags, kills the centering. See Wikipedia:Village pump (technical)/Archive 136#Problems with math rendering. - DVdm (talk) 14:41, 9 February 2014 (UTC)

Wikipedia talk:Articles for creation/Ignatov's theorem

Here's another old Afc submission. It appears to have references. Is this a notable topic, and should the article be kept? —Anne Delong (talk) 18:32, 9 February 2014 (UTC)

I've rewritten the submission; it should be acceptable now. Ozob (talk) 19:31, 9 February 2014 (UTC)

With Ozob's nice rewrite, this article is ready for mainspace. --Mark viking (talk) 20:06, 9 February 2014 (UTC)

Okay, it's in mainspace now with one category and one incoming link. I put a Wikiproject Mathematics banner on the talk page, but I'm not sure if it's a stub or a start, so feel free to change that. Thanks! —Anne Delong (talk) 20:41, 9 February 2014 (UTC)

Numbering equations

Advice on whether and how to number equations is sought at User Talk:Constant314/Archive 1#Numbering equations. JohnCD (talk) 23:37, 9 February 2014 (UTC)

AfC submission

Wikipedia talk:Articles for creation/Hessian equation. Regards, FoCuSandLeArN (talk) 19:39, 10 February 2014 (UTC)

Help needed with Correlation coefficient and Transition function

Correlation coefficient and Transition function are currently disambiguation pages, and have been among the most-linked disambiguation pages for the past four months. It would be great if we could either get the incoming links to these pages fixed, or arrange them into freestanding articles. This will likely require some expert attention. Cheers! bd2412 T 04:16, 9 February 2014 (UTC)

I think Correlation coefficient would be better moved to Correlation coefficient (disambiguation), after which make Correlation coefficient into a redirect to Pearson product-moment correlation coefficient; that I think matches common usage especially outside of mathematics where it is widely used.--JohnBlackburne^words_deeds 11:35, 9 February 2014 (UTC)

I don't know anything about the field, but if that is what people generally mean when they say "Correlation coefficient", that would be the right solution. bd2412 T 02:27, 11 February 2014 (UTC)

Problem with multiline equations

The Spherical trigonometry article has several bits of LaTeX that Failed to parse, for example the displayed equation in the Spherical trigonometry#Polar triangles section. My guess is that the alignat and align environments are not being handled. I went to the Wikimedia page Help:Displaying a formula and found that the align and alignat environments seem to be supported, but also generate a Failed to parse error on the page. A bug report at the wikimedia bugzilla suggests that these environments might be supported in MathJax, but not texvc. Is this a bug that others see? Thanks, --Mark viking (talk) 23:46, 6 February 2014 (UTC)

align should work with texvc. I just looked at a place I recently edited a formula with align, Triple product#Using geometric algebra, which I'm sure was working then, and it's now broken. The parser is complaining about 'aligned' not align, so is doing some sort of substitution, but I don't know if this is something it normally does. But I'm sure this was working two weeks ago: I was only editing that section, there's only one formula, and I would have used preview when editing it. I've tested MathJax before but haven't had it enabled for several months.--JohnBlackburne^words_deeds 00:01, 7 February 2014 (UTC)

I've asked about this issue at Wikipedia:Village pump (technical)/Archive 123#Math aligned environments failing to parse. Maybe an answer will magically appear there... Melchoir (talk) 02:08, 7 February 2014 (UTC)

Thanks John, for verifying the problem, and thanks Melchoir, for submitting to the technical village pump. --Mark viking (talk) 03:29, 7 February 2014 (UTC)

There is a similar problem at Noether's theorem‎. Unfortunately, some people are trying to fix the problem by editing the source, not realizing that it is the software's interpretation of the source which is at fault. JRSpriggs (talk) 07:57, 7 February 2014 (UTC)

I ran into the problem as well, all multline formulas using \begin{align} ... \end{align} seem to be affected (see here Help:Displaying_a_formula, scroll through the page). However some special symbols seem to have a rendering issue as well (see de:Hilfe:TeX, scroll through the page)--Kmhkmh (talk) 11:38, 7 February 2014 (UTC)

As far as I can see, it seems to work again for me. -- Jitse Niesen (talk) 12:05, 7 February 2014 (UTC)

I'm having the same problem and unfortunately it's leading to people (mostly from anonymous IPs) removing important formatting. The issue with aligned formulas should have critical priority: it needs to be fixed as soon as possible. The servers were offline at some point yesterday, and I assume that this was related. Sławomir Biały (talk) 12:25, 7 February 2014 (UTC)

This remains broken for me. Seconding the urgency of this; the longer this takes, the more reverting we will have to do later. --Rhombus (talk) 13:07, 7 February 2014 (UTC)

I discovered that it has to do with the maths preferences; MathJax works fine (at least for me) while PNG gives problems. It is still not fixed; sorry for falsely suggesting it is working again. The relevant bug seems to be bugzilla:60997 bugzilla:61012. -- Jitse Niesen (talk) 13:27, 7 February 2014 (UTC)

Problem still present. Isn't there a way to post a warning about this issue? Just to avoid people editing all sorts of math articles, escalating problems. This section in this talk page isn't all that easily found, even when looked for:) This is a serious issue after all. I think it should be posted somewhere central that it's known and is a server-side problem. --Loudandras (talk) 19:21, 7 February 2014 (UTC)

Personally, I think all articles in the List of mathematics articles should be semi protected, and an edit notice added saying that Wikipedia's implementation of LaTeX is broken, until it is fixed. I doubt that I would be able to convince WP:RFPP that this is an appropriate course of action, but even after one day I think this is going to require related changes patrolling of the List of mathematics articles by someone with tool server access (which afaik means Jitse). More than a day will be an unmitigated disaster. Sławomir Biały (talk) 19:30, 7 February 2014 (UTC)

I'm afraid a bunch of physics-related articles will be affected as well (Maxwell's equations for instance have already been 'fixed'). Not that removing the 'align' environments causes disaster, but these formulae would still look better in the original version. This could really get messy. --Loudandras (talk) 22:37, 7 February 2014 (UTC)

I've been finding the server very slow to respond today when I edit articles with mathematical equations in them, to the point where it sometimes times out without saving my changes (that is, it is a back end issue rather than a front end issue). Perhaps this is related? —David Eppstein (talk) 01:08, 8 February 2014 (UTC)

I was getting timeout/too many people accessing the page errors just looking at Noether's theorem and Help:Displaying a formula. Maybe the latter was unusually busy with the problems but not the former. And anyway WP handles pages becoming suddenly very busy for all sorts of reasons without problems usually. So it seems very likely it was the rendering problems on those pages, causing it somehow to timeout.--JohnBlackburne^words_deeds 04:02, 8 February 2014 (UTC)

Wikid77 (talk · contribs) and I have reverted each other a couple of times at Integral and Spherical trigonometry regarding this issue. Other editors may want to express an opinion. Ozob (talk) 06:08, 8 February 2014 (UTC)

As I expressed at the VP I back you completely on this: the articles aren't broken so no need to 'fix' them.--JohnBlackburne^words_deeds 06:29, 8 February 2014 (UTC)

Ultimately we need to do the right thing for the readers! That includes today's readers and future readers, after the software bug is fixed (and we don't know when that will happen).

It would be a reasonable compromise to "fix" high-traffic articles and list the edits on this talk page. Then, after the bug is fixed, it will be easy to revert the edits. Melchoir (talk) 07:06, 8 February 2014 (UTC)

Yes, but please wait a little bit if someone succeeds in turning amsmath support back on in texvc. Btw., the better replacement of align is {array}{rl}, {array}{rlrl} etc.--LutzL (talk) 11:48, 8 February 2014 (UTC)

I wrote a hotfix for that. It's waiting to be reviewed. After the problem should diaper. --Physikerwelt (talk) 11:48, 8 February 2014 (UTC)

Thank you! Ozob (talk) 15:30, 8 February 2014 (UTC)

Thanks for addressing this bug! Is there some way we can help write an automated test so that for instance breakages like this are caught in Jenkins before being deployed? --Mark viking (talk) 17:43, 8 February 2014 (UTC)

Sorry again for breaking the rendering. It was really only my fault. Prior to the change, the user input was checked (i.e. whitelisting to a secure subset of all possible TeX commands) for the PNG rendering mode only and not for MathJax and Source rendering modes. This caused a potentially security problem, i.e. given the fact that we wanted to render MathJax at the server side. I opened a bug in May 2013 and wrote and fixed it with the in the first attempt to release Math2.0 in October 2013. Since nobody wanted to review this, I broke down the change (that changed a lot of things (see list below) to several small commits. While breaking down the commits I made the mistake to put the required change for the texvc renderer to another commit than the security checking for MathJax. Since still nobody from WMF side wanted to do code review for that, I recruited new code reviewers for the math extension. In the end the change that does the security check for MathJax was merged and the changes to the PNG rendering mode were not merged. As a result the PNG rendering mode did the security checking twice. Unfortunately the output of the checked output is insecure, e.g. align is transformed to aligned which is not whitelisted. So that's the whole story.

For the testing, I think it would help if someone would vote for the bug concerning the test coverage. --Physikerwelt (talk) 21:49, 8 February 2014 (UTC)

As far as I can tell, "voting" on Bugzilla is ignored. Whatamidoing (WMF) (talk) 19:41, 10 February 2014 (UTC)

See also bugzilla:34490. Helder 13:32, 11 February 2014 (UTC)

The fix has been deployed now, and looking at a few pages it does seem fixed, though I had to purge one page to see it working.--JohnBlackburne^words_deeds 21:21, 8 February 2014 (UTC)

For those who don't know, you can purge the server cache with ?action=purge. Melchoir (talk) 21:26, 8 February 2014 (UTC)

You can also enable it in a menu in your gadgets preferences, 'Appearance' section, perhaps temporarily if you're checking and cleaning these up.--JohnBlackburne^words_deeds 21:55, 8 February 2014 (UTC)

Decoupling (mathematical analysis)

I think this article is a hoax. There is no source, the definition does not make sense, and the so-called "super-trowel", allegedly "one of the most used tools in the analysis of general equilibrium" fails to show up at ZMATH. Can anyone shed any light on it? Deltahedron (talk) 17:36, 11 February 2014 (UTC)

The speedy deletion tag was removed. I've prodded the article. Ozob (talk) 14:49, 12 February 2014 (UTC)

Not directly related, but there's obviously some editorial work needed in the articles decoupling and decoupling (disambiguation). --JBL (talk) 18:55, 11 February 2014 (UTC)

There's now discussion ongoing at Talk:Decoupling (disambiguation) and Talk:Decoupling (mathematical analysis). --JBL (talk) 17:15, 12 February 2014 (UTC)

Suborder into order?

Should the new article titled multiplicative suborder get merged into multiplicative order? Michael Hardy (talk) 20:34, 12 February 2014 (UTC)

It is difficult to imagine the article multiplicative suborder ever growing beyond a basic definition. --JBL (talk) 22:07, 12 February 2014 (UTC)

Summation

A properly sourced example of (Abel) summation by Euler was deleted by User:Slawekb here and here. Now that User:Incnis Mrsi joined the discussion, a tempered opinion would be welcome. Tkuvho (talk) 16:46, 10 February 2014 (UTC)

It should be noted that the material that User:Slawekb deleted was more of the -1/12 material that is so common. Perhaps the best solution would be to mention that Euler and others have done this summation, but that it is only useful or meaningful in very specialized circumstances, and then mention the fact that news reports in 2013 made too much of a big deal about this. Brirush (talk) 16:05, 12 February 2014 (UTC)

I have no problem mentioning this in the appropriate article 1+2+3+..., but in the main summation article it's undue weight and quite misleading without providing adequate context. In that article, it's rather a stretch to think that Ramanujan summation or zeta functional regularization or renormalization are in any way appropriate for a general article on the subject of summation. Sławomir Biały (talk) 18:59, 12 February 2014 (UTC)

Yes, User:DLazard pointed out that this article is only about finite summations anyways Brirush (talk) 19:05, 12 February 2014 (UTC).

As User:Melchoir pointed out at talk, it turns out that it is far from clear that Euler actually performed the 1+2+3+... summation, though of course 1-2+3-... is sourced. As far as the article Summation goes, I see no reason why it should not have a more advanced subsection dealing with infinite summations (ones that can be sourced, that is). Tkuvho (talk) 14:33, 13 February 2014 (UTC)

Summary style is appropriate in that case. The main article is series (mathematics). Also, please no coat racking to give divergent series more prominence than they deserve. Sławomir Biały (talk) 15:12, 13 February 2014 (UTC)

Not sure what "coat racking" is (coat rack does not help) but if you have a suggested wording please mention it at talk. Tkuvho (talk) 15:17, 13 February 2014 (UTC)

WP:COATRACK. Sławomir Biały (talk) 15:22, 13 February 2014 (UTC)

OK, thanks. I guess you've been around WP longer than me :-) Frankly I don't see why discussion of the paradoxes of infinite summation would obscure the topic of the summation page. Many mathematics pages have subsections containing far more advanced topics. Tkuvho (talk) 15:51, 13 February 2014 (UTC)

A more appropriate article for discussing such paradoxes would be the article on divergent series. This article is briefly summarized with appropriate weight in the series (mathematics) article. It's hard to see how emphasizing edge cases in the summation article would conform to WP:WEIGHT. Sławomir Biały (talk) 18:02, 13 February 2014 (UTC)

{{val2}}

Template:Val2 (edit | talk | history | links | watch | logs) has been nominated for deletion -- 70.50.151.11 (talk) 05:24, 15 February 2014 (UTC)

How to display math with the next release

Hi, I feel sorry about the problems with the current version of the Math extension.

My goal was to move from the current version to a completely new version of the Math-extension aka Math 2.0 in one step. Unfortunately, this does work with the code review system used at MediaWiki, since it was a lot code and nobody was willing to do a code review for that. So I started to integrate the changes via continuous integration. That means all features from the list below are going to be integrated step by step. I turned out that this is not a good idea as well.

Since the new features interact with each other, it happened that parts were merged whereas other parts are still waiting for the code review. For example in the case of the broken align environments the adjustments to the PNG mode were in another feature as the general security improvement that was merged. A hotfix for that is waiting to get merged to the Wikipedia live version https://gerrit.wikimedia.org/r/#/c/112057/ I really want to get feedback for the planned changes and asked over and again on the Mediawiki mailing list. But I did not get much feedback. So I’d be more than happy if someone would like to help testing the changes before they break things in production environments. See http://www.formulasearchengine.com/review for a guide that I wrote to attract people for that task.

The discussions above show that I might find someone in this portal… If not… sorry for the spamming.

Changes of Math 2.0

• MathML support with SVG fallback (pending)
• Distinction between inline and display-style
  • http://math-test2.instance-proxy.wmflabs.org/wiki/Displaystyle (pending)
• MathJax now available independent of the rendering mode (pending)
• Debug functionality (pending)
• independent of the file-system (pending)
• backwards compatible, without dependencies to it (pending)
• removes dependencies to math specific core functions
  • getMathOptions() (merged)
  • armourMath (pending)
• Asynchronous generation of Math images (to be discussed)
• upgrade to MathJax 2.3, use the unpacked version and remove unusued files (merged)
• use MediaWiki's resource loader for Javascript files (merged)
• improve the way MathJax is configured (merged)
• make math fonts available as Web fonts for native MathML (pending)
• The MathML/SVG output is used as a preview while MathJax is processing (pending)
• new table (mathoid) enables quick migration from Math1.0 to Math 2.0 (no schema change for math table required) (pending)
• SVG generation is done by using MathJax on the server-side. (pending)
• Link to idividual equations
  • ID feature request of Gabriel Wicke http://math-test2.instance-proxy.wmflabs.org/wiki/IDs#eq.20-sim

See a live demo http://math-test2.instance-proxy.wmflabs.org/wiki/Fourier_series.

It would help us to help you to be a little clearer about what you are trying to do (as an overview), why you are trying to do it, how you are doing it, what the results should look like, when it is proposed to happen and what you want our help with. For example, the paragraphs PS31,...,PS61 make no sense to me. Deltahedron (talk) 12:27, 8 February 2014 (UTC)

Oh, and it would be nice to know how it happened that the very first that people at this project, such as myself, heard about all this was when it broke mathematics rendering. Earlier involvement would have been helpful. Deltahedron (talk) 12:29, 8 February 2014 (UTC)

This isn't really my area expertise, but the bug makes me wonder whether there is any regression testing done before such software or configuration changes go live. I mean just a regression test against a single project side such as Help:Displaying_a_formula presumably would have revealed problems as the current one.--Kmhkmh (talk) 12:42, 8 February 2014 (UTC)

That's a good idea. I'll add the test (I had already implemented that before.). The hard thing will be to get a code review for the test. --Physikerwelt (talk) 13:09, 8 February 2014 (UTC)

I created a bug about the type of the tests. --Physikerwelt (talk) 14:09, 8 February 2014 (UTC)

When I started to work on the Math extension of MediaWiki (about one year ago) the connection to the page Wikipedia_talk:WikiProject_Mathematics mathematics was not obvious to me. I just found that page today, while googling for a bug report at bugzilla. And I really appreciate the feedback.

I'm basically looking for some people who want to discuss about how the display of math can be improved in the future and to test the implemented features. I feel sorry about the mistakes I made in the past, but I think it's better to look forward rather than to complain about the past. I'll update the Roadmap that I started more than a year ago. And come back to this project page again after completing this task. --Physikerwelt (talk) 13:05, 8 February 2014 (UTC)

Its good to see the move towards making MathJax as the default. I'm quite happy to do some testing, and contribute to BugZilla, but only as an end user and not at the git/code review level (just because I know very little about it). If test version is released on one of the test wikis I'll happily look at that.

That's great to hear. We have to find a way how this testing can be done. The current worflow is that after the code-review the change gets merged to all live versions of Wikipedia. Maybe we can set up a common test environment (like described in the http://www.formulasearchengine.com/review). To validate the functional correctness of the change before doing the formal code review. (Manny aspects of code review are related to whitespaces and typos in comments and commit messages.). I'll think about that.--Physikerwelt (talk) 15:27, 8 February 2014 (UTC)

I've tried using http://math-test2.instance-proxy.wmflabs.org/wiki/Fourier_series but I can't log in so can only see it in SVG. I tried following the the log in instructions on the main page and 'There is no user by the name "MathJaX".'.--Salix alba (talk): 13:49, 8 February 2014 (UTC)

Thank you. You found the first error. The unser name is MathJax. I corrected that on the main page. --Physikerwelt (talk) 15:27, 8 February 2014 (UTC)

Cool, I can login now. The first obvious error is failing to parse some equations with 'Entity nbsp' not defined. Seem spaces inside \text( and ) get translated to   somewhere along the line.

I'm not really sure how things are different to what is on en.--Salix alba (talk): 16:19, 8 February 2014 (UTC)

I tried without logging in and search doesn't work: I got An error has occurred while searching: Error fetching URL: couldn't connect to host

At my first random page, Lundquist_number the subscripts and superscripts don't work: they just give spaces. Deltahedron (talk) 17:10, 8 February 2014 (UTC)

The same problem with sub/superscripts when I log in as MathJax. Typing into the box provokes a series of errors in the console at the foot of the page but the search then works. Rendering of letters in italic (text) and roman (display) seems inconsistent. Deltahedron (talk) 07:56, 9 February 2014 (UTC)

By the way, it would help us to help you if we knew where you want this sort of problem reported -- is there a centralised location for collecting comments and questions -- surely this subsection isn't it? Is there a list of known problems that don't need to be reported again? Is there a list of changes or proposed changes that you particularly want tested? Is there a list of things you've changed but which you're quite sure can't possibly affect the user experience? Is there a roadmap for future development and a schedule of proposed work? Where is all this information collated and made visible to other editors? Deltahedron (talk) 09:41, 9 February 2014 (UTC)

@Deltahedron: I'm open for proposal how to organize feedback and mange the todos. Yesterday I went throguh bugzilla there were 85 bug reports. Now there are 71. (Some of them were really old and already fixed.) I updated the bug List at the Roadmap. From what I see there are two option for the organization of the project. Either to user that roadmap page and maybe some subpages or to use Bugzilla. I saw some green and red buttons on Wikipedia buttons where user can give feedback. Maybe they could be useful to get a quick overview, which features are most wanted. I'll clean the math-2 test server and remove the experimental features that are connected to my PhD thesis about Formulasearch and are not supposed to be used at Wikipedia in the short term. PS: My prototype use case, to find the Jensen's_inequality by searching for $\langle {\frac {1}{x}}\rangle \geq {\frac {1}{\langle x\rangle }}$, is not reachable in the near feature, due to a lack of semantic information in formulae. --Physikerwelt (talk) 10:18, 9 February 2014 (UTC)

Perhaps it would help to create a page www.mediawiki.org/wiki/Extension:Math/Feedback and advertising it here, be appropriate for comments and discussion on such things as the roadmap at www.mediawiki.org/wiki/Extension:Math/Roadmap and experiments and experiences at math-test2.instance-proxy.wmflabs.org. Then advertise it widely, with a permanent link at places like WP:WPM and with a mention in the current debates at Wikipedia:Village pump (technical). Deltahedron (talk) 11:42, 9 February 2014 (UTC)

@Deltahedron: Great idea. First I'll start with the automated tests. If someone could start to create such a page in the meantime that would be great. Furthermore, there are a lot of open bugs left. I think there are still some missing in the overview page. In the end we have to come up with an orderd list of features that we break down into planned releases in the end. --Physikerwelt (talk) 12:21, 9 February 2014 (UTC)

Is there a general agreement that the roadmap would be a good central point for discussions. Just because it's somehow pointless to set up a site if nobody comments... Like it sometimes happens at the mailing lists http://wikimedia.7.x6.nabble.com/template/NamlServlet.jtp?macro=user_nodes&user=365222 --Physikerwelt (talk) 12:42, 10 February 2014 (UTC)

Physikerwelt, I just want to thank you for your work. I tried to do some work many years ago and I did not get much feedback from the developers then (it was all run less professionally then). Don't feel too bad about the align issue and don't give up. -- Jitse Niesen (talk) 17:14, 8 February 2014 (UTC)

• I noticed the article Fermi–Pasta–Ulam problem has a messed up display, and when I looked at Help:Displaying a formula to see how to fix it, that is messed up too--I came here for help and see that others here have noticed the same thing. Is it possible to revert to the old version of the software for now, and debug the new code on a test server before deploying it to production? I believe the WMF does have some test servers available for this type of thing. Thanks. 70.36.142.114 (talk) 17:19, 8 February 2014 (UTC)

There is a fix for the bug that waits for review. I try to find someone who has the power to merge it.--Physikerwelt (talk) 18:23, 8 February 2014 (UTC)

@Physikerwelt: Is the following a valid summary of the current situation? As a security measure, and to get the same output regardless of method, you broke out the translation/normalization/macro-expansion part of texvc as texvccheck. The normalized output of texvccheck is then used as input for all the other output methods. This should have worked transparently except for the old misguided decision to name the multiline sub-environment "align" instead of "aligned". Misguided since if one considers the "math" tags as forming an outer math environment, everything inside "math" tags should be a sub-environment. And so the translation of texvccheck produces output "aligned" for input "align", which is correct for latex and mathjax, but not recognized by another texvc run (idempotence) to generate the png images, since texvc does not recognize "aligned" or "alignedat" as input environments. Is your fix making texvc accept them?--LutzL (talk) 18:44, 8 February 2014 (UTC)--Edit--LutzL (talk) 19:14, 8 February 2014 (UTC)

No to the last question, I see from the patch diffs that the second texvc run is given the original, untransformed tex input.--LutzL (talk) 19:20, 8 February 2014 (UTC)

That's correct. texvccheck is a subset of texvc... originally I wanted to call it texvc-light... but this name was not accepted. To explain it in a mathematical way. We call $s$ the securtity check and $l$ the latex conversion that texvccheck for input $x$ mans $s(x)$. Appling texvc to $x$ means $l(s(x))$. The bug was that both, texvccheck and texvc were applied to $x$ and $l(s^{2}(x))$ was displayed. $s$ is not idempotent which means that $\exists x:s^{2}(x)\neq s(x)$. For example let's assumme that $x_{1}$ contains a an align command than $s(x_{1})\neq s(s(x_{1}))$ since align is transformed to aligned which is not whitelisted. --Physikerwelt (talk) 22:14, 8 February 2014 (UTC)

The fix seems to have been deployed; I'm not seeing any problems. Ozob (talk) 22:34, 8 February 2014 (UTC)

I agree, the problems I was seeing with the align and alignat environments look to be fixed. Thanks again, Physikerwelt for getting on this and and getting the hotfix in! --Mark viking (talk) 23:06, 8 February 2014 (UTC)

• Fermi-Pasta-Ulam problem works ok now, but Integral of the secant function shows a lot of messed up equations. 70.36.142.114 (talk) 05:47, 13 February 2014 (UTC)

Performance problems

Are the current performance problems also due to the upgrade? In several wikipedias previewing or editing articles with formulas takes very long at the moment. Articles with many formulas (such as List of mathematical symbols) even get a "504 Gateway Time-out" when you just try to preview them. Best wishes, --Quartl (talk) 06:32, 9 February 2014 (UTC)

Yes. I thought this was caused by the broken rasteriser but it still seems very slow despite that being fixed. I just tried loading Seven-dimensional cross product then unnecessarily purging it to force it to redo everything. Here (from the page source) is the timing information on the purge:

NewPP limit report
Parsed by mw1173
CPU time usage: 1.452 seconds
Real time usage: 26.816 seconds
Preprocessor visited node count: 3564/1000000
Preprocessor generated node count: 10682/1500000
Post‐expand include size: 50621/2048000 bytes
Template argument size: 3857/2048000 bytes
Highest expansion depth: 11/40
Expensive parser function count: 1/500
Lua time usage: 0.091s
Lua memory usage: 2.49 MB

26.8 seconds. And is isn't especially long or template heavy. The one thing it does have is a high density of formulae.--JohnBlackburne^words_deeds 06:45, 9 February 2014 (UTC)

I tried looking at List of mathematical symbols and that took a lot longer, though it did eventually load.

NewPP limit report
Parsed by mw1079
CPU time usage: 13.505 seconds
Real time usage: 308.243 seconds
Preprocessor visited node count: 11927/1000000
Preprocessor generated node count: 37075/1500000
Post‐expand include size: 217037/2048000 bytes
Template argument size: 90026/2048000 bytes
Highest expansion depth: 15/40
Expensive parser function count: 3/500
Lua time usage: 0.084s
Lua memory usage: 2.76 MB

This was only the first time accessing it. Reloading the page took a second. Obviously purging or editing would force it to redraw and so would take a similarly long time.--JohnBlackburne^words_deeds 07:05, 9 February 2014 (UTC)

I'm quite sure that this issue is connected to the new security feature. I followed the guideline, "you can not trust database entries" and check the user input text every time it's send to the rendering engine, even before the database lookup checks if the entry is already in the database. In local experiments this had almost no impact on the performance. Obviously the situation is different in production. I proposed to opt-out this new security feature via $wgMathDisableTexFilter = true on the bug report.--Physikerwelt (talk) 09:50, 9 February 2014 (UTC)

Out of interest, in what sense was this a "security feature"? Is there a specific security issue here or is this just belt-and-braces? Deltahedron (talk) 10:03, 9 February 2014 (UTC)

No there is no known urgend concrete threat, that can be caused by entering potentially dangerous input between <math> and </math>. But without this feature the possible input depends on the rendering mode, and we rely on the build in security of renderer i.e. MathJax or LaTeXML. Furthermore texvccheck provides a well defined set of allowed input, which could be discussed and modified in the future. However, I think that the drawbacks of slower editing are not compensated by the benefits of the well-defined and secure input independent of the rendering engine. --Physikerwelt (talk) 10:39, 9 February 2014 (UTC)

Any news on this? I just timed Seven-dimensional cross product and the article still takes close to 30 seconds to preview or purge. Best wishes, --Quartl (talk) 19:40, 12 February 2014 (UTC)

• FIXED. See: #Performance of cache fixed 15 Feb 2014. -Wikid77 08:39, 15 February 2014 (UTC)

Is this really fixed? I'm seeing long loading times for math pages again, simply viewing a page. E.g. Clifford algebra gives me the following:

NewPP limit report
Parsed by mw1076
CPU time usage: 1.236 seconds
Real time usage: 26.291 seconds
[...]

Exterior algebra gives.

NewPP limit report
Parsed by mw1046
CPU time usage: 1.548 seconds
Real time usage: 30.305 seconds
[...]

And this is not previewing or purging, just viewing (though subsequent views are fine). The pages were last edited on the 7th and 8th of this month so were presumably viewed and cached then, and even if they required recaching since the patch they're viewed over 100 times a day each on average. How are they still slow four days later?

Performance of cache fixed 15 Feb 2014

By 00:02 15 February 2014, fix deployed (https://gerrit.wikimedia.org/r/113481) by User:Aaron_Schulz as update so math-tags run faster, than during 8–14 Feb 2014. I have confirmed the math-tag cache speed as double (2.4x), similar now to Simple WP, so new equations edit-preview 2.4x faster than before (124 math-tags in 38 seconds, formerly 92 sec.) and then will re-display from cache within 3 seconds. -Wikid77 08:39, 15 February 2014 (UTC)

List of mathematical symbols as TeX codes

There is a new article called List of mathematical symbols as TeX codes. I haev commented at Talk:List of mathematical symbols as TeX codes and put a factual-accuracy-dispute tag at the top of the article. So some work is needed. Michael Hardy (talk) 17:33, 14 February 2014 (UTC)

Why not include TeX commands (and for that matter HTML codes and Unicode code points) as separate columns in List of mathematical symbols (as I did in de:Liste mathematischer Symbole)? Best wishes, --Quartl (talk) 18:13, 14 February 2014 (UTC)

My thoughts as well. There seems to be no clear reason for having what is just a copy paste of List of mathematical symbols with nowiki tags thrown in. Sławomir Biały (talk) 18:57, 14 February 2014 (UTC)

I have nominated the page for speedy deletion as an A10, "recently created article that duplicates an existing topic". Ozob (talk) 20:35, 16 February 2014 (UTC)

user Wachipichay

I noticed that the user Wachipichay is making many edits to mathematics pages. It seems the purpose of all edits is to include references to a mathematician called István Mező. As far as I can tell, these are typically very recent minor results that have no place in an encyclopedia. Perhaps someone who reads this can have a look at his edits and clean up as needed. I apologize if this is the wrong forum, I am not active on Wikipedia and have no idea how these things work. 129.16.126.117 (talk) 08:43, 18 February 2014 (UTC)

At least, not all edits; Gamma function#Raabe's formula is not. But most of them are. Boris Tsirelson (talk) 09:36, 18 February 2014 (UTC)

FYI: Wachipichay (talk · contribs · deleted contribs · logs · filter log · block user · block log) Sławomir Biały (talk) 12:50, 18 February 2014 (UTC)

Euler's identity?

I think this is a prime example of a mathematics page which needs to communicate with a general readership [1]. I have posted some strictly editorial concerns on the talk page which I think deserve some response. Thank you in advance, 109.157.83.88 (talk) 11:46, 13 February 2014 (UTC) [previously 109.158.185.136 and 81.147.165.192]

• I have tried to address (in this edit) some of the issues I've encountered as a layperson coming to this page. The more general disambiguation problem in the page header (and at List of things named after Leonhard Euler) imo remains. While fully recognizing that we're all volunteers and that nobody is obliged to make any particular contribution I find it hard not to express some disappointment that my appeals for feedback appear not to have elicited any response (so far) either here or on the article talk page. 86.173.146.3 (talk) 14:14, 18 February 2014 (UTC)

Probably you have gotten no response (until today) for the following reasons:

(1) The number of people confused by the issue troubling you is well approximated by 0.

(2) The source of your confusion is your not very good source, which draws distinctions that mathematicians do not (either in the formal or informal setting).

You can see my more detailed comments on the talk page of the article in question. --JBL (talk) 20:10, 18 February 2014 (UTC)

(1) Your forcefully worded statement "The number of people confused by the issue troubling you is well approximated by 0" implies that the present Wikipedia editor does not belong to the set of people? (I do request you to be civil to your fellow gf Wikipedian.)

(2) I will certainly reply on the article talk page. As a general principle I think it is courteous in such circumstances to source your assertions. (My understanding is that Wikipedia does not contemplate argument from authority.)
86.173.146.3 (talk) 21:25, 18 February 2014 (UTC)

Eigenvalues and eigenvectors - Illustration

What am I missing? The rationale for depicting vectors as "line segments" floating on a stretchy background rather than as unique elements of a vector space is eluding me, including that these are "an elementary concept in vector spaces" not even needing to be mentioned in that article, and intuition can be relied upon for underlying concepts in WP. —Quondum 02:41, 20 February 2014 (UTC)

Popular pages tool update

As of January, the popular pages tool has moved from the Toolserver to Wikimedia Tool Labs. The code has changed significantly from the Toolserver version, but users should notice few differences. Please take a moment to look over your project's list for any anomalies, such as pages that you expect to see that are missing or pages that seem to have more views than expected. Note that unlike other tools, this tool aggregates all views from redirects, which means it will typically have higher numbers. (For January 2014 specifically, 35 hours of data is missing from the WMF data, which was approximated from other dates. For most articles, this should yield a more accurate number. However, a few articles, like ones featured on the Main Page, may be off).

Web tools, to replace the ones at tools:~alexz/pop, will become available over the next few weeks at toollabs:popularpages. All of the historical data (back to July 2009 for some projects) has been copied over. The tool to view historical data is currently partially available (assessment data and a few projects may not be available at the moment). The tool to add new projects to the bot's list is also available now (editing the configuration of current projects coming soon). Unlike the previous tool, all changes will be effective immediately. OAuth is used to authenticate users, allowing only regular users to make changes to prevent abuse. A visible history of configuration additions and changes is coming soon. Once tools become fully available, their toolserver versions will redirect to Labs.

If you have any questions, want to report any bugs, or there are any features you would like to see that aren't currently available on the Toolserver tools, see the updated FAQ or contact me on my talk page. Mr.Z-bot (talk) (for Mr.Z-man) 05:15, 23 February 2014 (UTC)

List of unsolved problems in Cryptography

FYI, List of unsolved problems in Cryptography (edit | talk | history | protect | delete | links | watch | logs | views) has been nominated for deletion. -- 70.50.151.11 (talk) 10:28, 23 February 2014 (UTC)

Global analysis?

We have no article titled global analysis. Michael Hardy (talk) 20:08, 23 February 2014 (UTC)

That was my thought exactly too. I don't feel qualified to create the article myself, but this is such a terrible oversight. -- Taku (talk) 20:22, 23 February 2014 (UTC)

Is this the only omission from the top-level MSC categories, as listed here? Deltahedron (talk) 20:47, 23 February 2014 (UTC)

Judging from Mathematics Subject Classification, the two red links are Expansion (approximation theory) and Mechanics of deformable solids. I think we have the latter covered in articles such as Deformation (mechanics) and Elasticity (physics). I don't know about the former. We have articles like Taylor expansion, Perturbative expansion and Asymptotic expansion, but I don't see offhand a general article on the subject. --Mark viking (talk) 00:28, 24 February 2014 (UTC)

I just created a short stub for the topic. Contributions welcome. --Mark viking (talk) 21:13, 23 February 2014 (UTC)

Requested articles/Mathematics/Logic‎

The subpage Wikipedia:Requested articles/Mathematics/Logic‎ is not picked up by the bot that maintains Wikipedia:WikiProject Mathematics/Current activity and so new entries there are not flagged up. Is it possible to get that changed? And is there any special necessity to maintain this separation anyway? Deltahedron (talk) 07:37, 24 February 2014 (UTC)

I think what probably is useful is to keep the organization into mathematical logic, and subfields. I would be fine with having an L2 heading of "Mathematical logic" in the main page, with the subfields as L3 headings, and get rid of the subpage altogether. (There are probably several other fields that could benefit from such a structure as well.) --Trovatore (talk) 15:42, 24 February 2014 (UTC)

Upright versus italic d

I am in a dispute with Bub250 (talk · contribs) on Fundamental theorem of calculus. The issue is whether a roman or italic letter d should be used for differentials. Formerly, the article used italic d, as in:

$\int f(x)\,dx.$

Bub250 changed these to roman, as in:

$\int f(x)\,\mathrm {d} x.$

I firmly believe that this is wrong, regardless of the interpretation of d, and accordingly I reverted him. He reverted me, citing the IUPAP Red Book and ISO 80000-2 standards. We have both hit WP:3RR, and neither of us seems to be budging, so I think it would be helpful to have some outside input.

In the past, the community has applied WP:RETAIN to the question of upright versus italic d. That may still be the consensus, but since it has been a while since we had this discussion it may be worth reopening the issue. Ozob (talk) 18:23, 23 February 2014 (UTC)

Might I suggest the following process that each of you might follow:

• Stop editing that article immediately
• Find a (different) redlink in Wikipedia:Requested articles/Mathematics
• Write a substantial article on that topic
• Either

• Come back here and explain why your preferred choice improves the encyclopaedia from the point of view of the reader

or (better)

• Laugh ruefully, realise how extremely unimportant this issue really was, and put it all behind you.

Deltahedron (talk) 19:00, 23 February 2014 (UTC)

I have reverted the last edit of this user and left a warning on his talk page with references to MOS:MATH and our previous discussion here. D.Lazard (talk) 19:06, 23 February 2014 (UTC)

The consensus here in the many times this has come up before is that the italic d is by far the one more commonly used in sources, and that we should stick to that convention. Sławomir Biały (talk) 21:09, 23 February 2014 (UTC)

I should note that "upright d" is mathematically incorrect. (I know some students use them, but the usage is incorrect.) The reason is simple: "dx" means the diffenrial or the exterior derivative of x. Here, d is a function (from the space of functions to the space of one-forms). One can write d(x), but since d is linear, one can drop parathesis; like one writes Tx instead if T(x). Whenever you see the "upright d", the order is to eliminate them. -- Taku (talk) 03:25, 25 February 2014 (UTC)

I agree that upright d is mathematically incorrect, but I disagree that dx exclusively refers to an exterior derivative. It can also refer to a measure. In some sense this is more fundamental, because integrals of differential forms are ultimately defined by integrating in coordinate patches, and the integrals in coordinate patches are defined in terms of a measure. In a measure-theoretic context, for a function f, df is the Lebesgue–Stieltjes measure associated with f; in a sense this is the pullback of Lebesgue measure of R. Since d is still an operator on functions, it is still correct to italicize it and incorrect to romanize it. For measures like Lebesgue or Hausdorff measures which are defined directly (not as a Lebesgue–Stieltjes measure), the d is simply notation, but consistency seems to demand that it still be italic.

There is also the interpretation of dx as an infinitesimal (in the sense of Newton, Leibniz, and so on). Here the d is again an operator, so again it should be italicized. Ozob (talk) 05:34, 25 February 2014 (UTC)

This is a perennial problem. In things like differential topology the upright will always be used but in straightforward calculus learnt for hundreds of years the italic is used. I don't think we can decide that one form should be used everywhere, it depends on the circumstances. Dmcq (talk) 16:21, 25 February 2014 (UTC)

I think we should generally stick to what most sources in the relevant subject use. It bothers me that the argument for using an upright d almost always refers exclusively to a (paywalled) ISO standard, as if that should somehow trump every other mathematical style guideline. Sławomir Biały (talk) 16:39, 25 February 2014 (UTC)

This should be in WP:MOSMATH; I've been told that the upright d should be used in integrals, but it's often too difficult to implement. I don't have any elementary textbooks to determine the current usage in print. — Arthur Rubin (talk) 20:13, 26 February 2014 (UTC)

It is in the section WP:MOSMATH#Choice of type style, where both roman and italic forms of the differential are claimed to be correct. --Mark viking (talk) 22:23, 26 February 2014 (UTC)

AfC submission no 2

Wikipedia talk:Articles for creation/Multivariate metamodelling of mathematical models. FoCuSandLeArN (talk) 15:47, 26 February 2014 (UTC)

This seems like original research to me. At least there appears to be no identifiable reference that supports the topic of the article as a whole. But this is far outside my area of knowledge, so YMMV. Sławomir Biały (talk) 17:46, 26 February 2014 (UTC)

We already have an article on this general topic using the more familiar name of surrogate model. This AfC article seems like a perhaps unintentional POV fork of surrogate model; it spends most of the prose extolling the advantages of using such a model, but doesn't acknowledge that almost all systems requiring a surrogate model are multivariable in nature. Right now, I cannot see how this fork is notable--most of the refs are primary refs about examples of surrogate models rather than discussing the subject directly. Note that the article metamodeling is about metamodels in software design, which is a different concept than that presented here. --Mark viking (talk) 19:16, 26 February 2014 (UTC)

I concur with this evaluation. Also, there is the whole book dealing with the subject, The simulation metamodel. I would suggest the author to rework/expand "surrogate model" page, rather than write a separate essay, as well as browse wikipedia for the subject/keywords, to draw the connections, make cross-links. I don't know how communication in AFC is carried out (the afc page does not have a talk page: it is a talk page itself). I will point the user in his talk page to this discussion. Staszek Lem (talk) 23:07, 26 February 2014 (UTC)

K(n,n) equation

Anybody here acquainted with the K(n,n) equation? -- Crowsnest (talk) 07:02, 26 February 2014 (UTC)

It's a variant of the KdV equation used for studying compactons, a variety of soliton with compact support. See for instance, [2]. --Mark viking (talk) 01:11, 27 February 2014 (UTC)

Miss-matched <sub> and <sup> tags

I've been doing a scan of wikipedia articles for miss-matched <sub> and <sup> tags. Things like e<sup>x</sub>. Anyway there are a fair number of maths articles (357) with such problems. You can see a list at User:Salix alba/subsup. For the most part the normal renderer works fine and manages to correct the problem, however the Visual editor makes different assumptions so things look a bit odd. If anyone fancies fixing a few of these that would be great.--Salix alba (talk): 08:08, 26 February 2014 (UTC)

I fixed Dirac equation and Zero sharp which are on my watch list. I could not find the error in Mass in special relativity. JRSpriggs (talk) 10:03, 26 February 2014 (UTC)

Found it. — HHHIPPO 10:23, 26 February 2014 (UTC)

To help spots these things I written a bit of javascript which displays lines with errors. To use add the line

importScript('User:Salix alba/SubSup.js');

to your Special:MyPage/skin.js. This will add an entry 'SubSup' to your toolbox. Clicking on that link will open a window showing the lines where the tags don't match.--Salix alba (talk): 13:30, 26 February 2014 (UTC)

There's enough of them so a general mismatched tags check and fix should be stuck into some robot and standard checks somewhere. Dmcq (talk) 14:03, 26 February 2014 (UTC)

I fixed several more articles and your tool was a very great help. However, it sometimes indicated that there was no problem in one of the articles even though that article was on your list and the revision history indicated that no one had previously fixed it. JRSpriggs (talk) 08:40, 27 February 2014 (UTC)

There is now a discussion at Wikipedia talk:WikiProject Check Wikipedia#Mismatched sub and sup tags. Sees like a check for these may be added to some bots, AWB etc. My list is a bit dated being generated from dumps rather than live versions. There are some cases like <sup id="foo">ref</sup> correct markup which get listed in the dumps but the javascript tool does not report.--Salix alba (talk): 10:06, 27 February 2014 (UTC)

Total free access to Royal Society History of Science journals for 2 days on March 4th and 5th !!!

As Wikipedian in Residence at the Royal Society, the National Academy for the sciences of the UK, I am pleased to say that the two Royal Society History of Science journals will be fully accessible for free for 2 days on March 4th and 5th. This is in conjunction with the Women in Science Edit-a-thon on 4 March, slightly in advance of International Women's Day, on Saturday March 8th. The event is fully booked, but online participation is very welcome, and suggestions for articles relevant to the theme of "Women in Science" that need work, and topics that need coverage.

The journals will have full and free online access to all from 1am (GMT/UTC) on 4th March 2014 until 11pm (GMT/UTC) on 5th March 2014. Normally they are only free online for issues between 1 and 10 years old. They are:

• Notes and Records: the Royal Society journal of the history of science
• Biographical Memoirs of the Fellows of the Royal Society

The RS position is a "pilot" excercise, running between January and early July 2014. Please let me know on my talk page or the project page if you want to get involved or have suggestions. There will be further public events, as well as many for the RS's diverse audiences in the scientific community; these will be advertised first to the RS's emailing lists and Twitter feeds.

I am keen to get feedback on my personal Conflict of Interest statement for the position, and want to work out a general one for Royal Society staff in consultation with the community. Wiki at Royal Society John (talk) 12:17, 28 February 2014 (UTC)

Fibred category -> Fibered category

I've started a requested move at Fibred category. Participations are very welcome. -- Taku (talk) 12:55, 28 February 2014 (UTC)

Four-paragraph leads -- a WP:RfC on the matter

Hello, everyone. There is a WP:RfC on whether or not the leads of articles should generally be no longer than four paragraphs (refer to WP:Manual of Style/Lead section for the current guideline). As this will affect Wikipedia on a wide scale, including WikiProjects that often deal with article formatting, if the proposed change is implemented, I invite you to the discussion; see here: Wikipedia talk:Manual of Style/Lead section#RFC on four paragraph lead. Flyer22 (talk) 15:09, 28 February 2014 (UTC)

Help needed with eight links to Index (mathematics)

Index (mathematics) is a disambiguation redirect, and happens to be one of the last links needing to be cleared for the February 2014 list of most linked disambigs. The seven pages linking to this title are:

1. Distortion synthesis
2. Differential geometry of surfaces
3. Timeline of numerals and arithmetic
4. Timeline of mathematics
5. Wall-crossing
6. Fritz John conditions
7. Residual feed intake

If someone with the requisite knowledge could go correct the link to Index (mathematics) in these seven pages, that would be most appreciated. Cheers! bd2412 T 15:48, 25 February 2014 (UTC)

All done - thanks! bd2412 T 23:35, 25 February 2014 (UTC)

To editor BD2412: Unfortunately, the correction was erroneous in the articles 2 and 5, linking to indexed family instead of winding number. I have corrected these. In the 7th article, I do not know what is a "resource allocation theory index", but the link to indexed family is certainly wrong. The link to winding number in the first article seems also dubious. D.Lazard (talk) 12:18, 28 February 2014 (UTC)

I assume someone from this project applied those fixes after I posted this request - so to the extent that fixes were erroneous, that is a matter to take up with whichever editor made that edit. bd2412 T 13:12, 28 February 2014 (UTC)

Article 1 and 7 are not mathematics articles. Thus I have replaced the controversial wikilinks by {{clarify}} templates. Now, all are done. D.Lazard (talk) 16:16, 28 February 2014 (UTC)