Wikipedia talk:WikiProject Articles for creation

Main pageTalk pageSubmissions
Category, List, Sorting, FeedShowcaseParticipants
Apply, By subjectReviewing instructions
Help deskBacklog
drives

Welcome—discuss matters concerning this project!

AfC submissions Random submission

~8 weeks

1,730 pending submissions to update

• Are you in the right place?
  • If you want to ask a question about your draft submission, use the AfC Help desk.
  • For questions on how to use or edit Wikipedia, use the Teahouse.
  • Create an article using Article wizard or request an article at requested articles.
• Put new text under old text. Start a new topic.
• In addition to this page, you can give feedback about the AFCH helper script by creating a new ticket on GitHub.
• New to Wikipedia? Welcome! Ask questions, get answers.

AFC backlog

AfC unreviewed draft statistics as of December 09, 2024

Oldest unreviewed draft is 6 weeks old

I noticed an unusual yellow color at the top of this page, and when I went to investigate, I notice our "oldest draft" color scale had turned from red to yellow, indicating the oldest unreviewed draft is only 6 weeks old. Nice work team :) –Novem Linguae (talk) 09:39, 24 October 2024 (UTC)

Only five drafts left in Category:AfC pending submissions by age/6 weeks ago today :) Curb Safe Charmer (talk) 10:15, 24 October 2024 (UTC)

Now "5 weeks old". Thank you everyone! Ca ^{talk to me!} 13:30, 27 October 2024 (UTC)

And we're at risk of dropping < 1,000 soon, if we're not careful. Then where will we be? -- DoubleGrazing (talk) 13:40, 27 October 2024 (UTC)

In a wonderfully healthy situation 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 14:07, 27 October 2024 (UTC)

The glorious thing about this is that I believe that AFC is now working as we always wished it to work. Please let us continue to review at this broad pace. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 10:35, 28 October 2024 (UTC)

My decline of Draft:Lola bunny orel sex took us below 1000 albeit briefly. Theroadislong (talk) 17:12, 28 October 2024 (UTC)

ROFLMAO. What a thing to decline! 🤣 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 22:19, 28 October 2024 (UTC)

Crazy 🤣 Theroadislong (talk) 22:34, 28 October 2024 (UTC)

Six weeks seems to be the category that refuses to die. Curb Safe Charmer (talk) 11:58, 7 November 2024 (UTC)

Eh... people can wait a little bit for their drafts ;-) Primefac (talk) 12:43, 7 November 2024 (UTC)

I was wondering why the backlog has turned the other way (hoping it wasn't my fault as I've been doing less recently due to meat-space issues). I looked and the reviews count from the last month was over 8000 which is still high on my historic data. Turns out in August we had 172 submission per day on average (non inc deleted), but so far in November it's 251/day (with 432 on the 20th). So the reviewers are still working hard, but the submitters are working harder (I assume emboldened by having wait times in weeks rather than months). KylieTastic (talk) 19:36, 23 November 2024 (UTC)

Page Mover Moving a Sandbox to Draft Space

I have a question about AFCH reviewers who have the Page Mover privilege. If a reviewer is reviewing a user sandbox that has been tagged as submitted, standard procedure is to move the sandbox into draft space, with the appropriate title. My question is: Should the reviewer suppress redirect creation, or allow redirect creation? I became aware within the past 24 hours that different reviewers who have the page mover privilege have different practices. So, should the reviewer suppress redirect creation if they have the option (which is what Page Mover provides) to suppress redirect creation? Robert McClenon (talk) 04:31, 1 November 2024 (UTC)

Notified: Wikipedia talk:Page mover. jlwoodwa (talk) 04:46, 1 November 2024 (UTC)

Most commonly the move is within the draft space or from user sandbox/subpage to draft space, so I allow the redir.

I mainly suppress it when moving a draft that is on the actual user page; in that case I untick all the option boxes (redir, talk page, subpages).

I also suppress it when moving from the main space (or any other space from which redirs to drafts aren't allowed), but that's not what you were asking.

That's what I do. Now someone will hopefully tell us what should be done. -- DoubleGrazing (talk) 06:40, 1 November 2024 (UTC)

I think a page mover should always default to leaving a redirect. I think a page mover can only suppress the redirect if it qualifies for a CSD. In DoubleGrazing's example above, they correctly mention that you can suppress mainspace to draftspace (during draftification) since that is CSD R2. –Novem Linguae (talk) 07:20, 1 November 2024 (UTC)

When moving a draft from the actual user page to the draft space, if you don't suppress the redir it creates a mess. Anybody trying to then go to the user's user page ends up in the draft. (And the user talk page becomes the draft talk page, if you happen to move that along with the main page, which is what the default setting does.) That's why I only move the actual user page and don't allow the redir, and then manually move any WikiProject tags and other draft talk page content from the user's talk page to the draft talk page which I create. I then post a message on the user talk page telling them where I've moved the draft to, in case they can't otherwise work it out.

I don't know if this strictly complies with the page mover rules, but I'd argue it's what works best in practice, in terms of subsequent operation of the user's resultant user and user talk pages. -- DoubleGrazing (talk) 07:39, 1 November 2024 (UTC)

I don't think there is a standardised practice. My reading of policies when I first gotten the pagemover hat before becoming admin: WP:PMRC#9 allows suppression with appropriate CSD rationale. So page movers can suppress by applying CSD G7, author request rationale, since the redirect would have been created under their own usernames if not suppressed, although there is a question of WP:INVOLVED if someone wants to force the issue. Personally, I would suppress redirection if it is moving from the user's sandbox with an message be left on that editor's user talk page directing them to the draft space, because I have been pinged a couple of times before for AfDs for articles that were written over the redirect that were created in that editor's sandbox. – robertsky (talk) 09:46, 1 November 2024 (UTC)

Yup, I dislike that if you move a sandbox and leave a redirect then they use the sandbox for the next draft you are now the 'creator'. I stopped moving them years ago for this reason and still don't as a page mover due to what appears to be a grey area in the policy. Personally I think not leaving a redirect from a sandbox to avoid future confusions is best as long as long as you leave a message about the move, but I'll continue to refrain unless there is a consensus that WP:PMRC#9 + G7 is valid reasoning. KylieTastic (talk) 10:04, 1 November 2024 (UTC)

WP:G7 says: For redirects created as a result of a page move, the mover must also have been the only substantive contributor to the pages before the move. So generally they aren't eligible for G7 and probably shouldn't be supressed. C F A 💬 15:28, 1 November 2024 (UTC)

nice catch. – robertsky (talk) 01:29, 3 November 2024 (UTC)

WP:PMRC does not really allow for redirect suppression when moving a sandbox (which is what Robert is asking about), and I don't think I've ever done it. I'm not really bothered by (or care about) whether I "created" a page then expanded and actually written by someone. Exceptions will always exist, but on the whole AFC reviewers should not be suppressing the creation of a redirect when they draftify a sandbox. Primefac (talk) 11:51, 1 November 2024 (UTC)

You're right, that is the specific question Robert asked. My fault for taking this on a tangent.

Specifically on that, I don't suppress the redir either, when moving from sandbox to draft:, although I do empathise with the point made about becoming the 'creator' of subsequent drafts from the sandbox. It is a bit annoying to receive notifications (AfD, pre-G13) for 'my' drafts which have nothing to do with me, because I (feel I) have to then go and notify the actual author myself. -- DoubleGrazing (talk) 11:58, 1 November 2024 (UTC)

My practice is to leave a redirect unless a user: page at top level.

If User:Foo contains an article about Bar, I move User:Foo to Draft:Bar, do not leave a redirect, but am careful to untick SUBPAGES and Talk page.

I then tell User:Foo what I have done 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 15:36, 1 November 2024 (UTC)

@DoubleGrazing, Timtrent, and (from elsewhere) JJPMaster: I don't really see what WP:CSD it would fall under to delete move redirects from a main userpage to draftspace (and thus what basis there would be for redirect suppression per WP:PMRC). Does anyone think the following redirects are eligible for speedy deletion on that basis?

I would think that any concern about people visiting a userpage and being surprised to find they're redirected to a draft could be addressed by changing the resulting redirect to a soft redirect. Leaving no redirect behind makes it harder for logged-out editors to find a moved draft (since they only see the move and deletion logs for a page for 24 hours after the deletion or redirect suppression). SilverLocust 💬 08:34, 21 November 2024 (UTC)

@SilverLocust Thank you for the list. The pure User: page, User:Foo, as opposed to a user sandbox page, User:Foo/anything at all is deletable as an initial improper use of a user page. Customary rational is G6 (error).

Since redirects guide folk from places to paces, it is courteous to tell the editor where their work resides now.

Were this redirect to be left then every time we wish to see User:Foo we would see the work of Foo.

Your point about logged out editors is interesting. Current custom disregards that issue. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 09:01, 21 November 2024 (UTC)

If by emphasizing initial you mean that those redirects could've been speedied at the time they were moved but not now, note that {{db-error}} (in contrast to WP:R3) doesn't need to be a recent error, just an obvious error. Putting a draft in a location that is not preferred but also not disallowed – see WP:UP#What may I have in my user pages? ("Work in progress or material that you may come back to in future (usually on subpages)") – isn't what I would call an obvious error. SilverLocust 💬 09:18, 21 November 2024 (UTC)

@SilverLocust They shoudl have been deleted as part of the move by an editor wth page mover rights, or nominated for speedy deletion as part of the move by an editor without those rights. Doing it early or later is immaterial, but leaving them lying around serves to confuse. Courtesy dictates we notify the creating editor of the new locatiom 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 10:49, 21 November 2024 (UTC)

I cannot recall now why I underlined 'initial' whcih seems to be a self created nonsense! 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 10:51, 21 November 2024 (UTC)

I can't remember who told me to do what I do (suppress the redir); it probably happened when I first moved a draft from a main user page, after getting page mover rights, and created a mess. I vaguely remember asking (maybe at AN?) for help in sorting it out, and someone said next time just untick all the boxes, which made sense to me, so that's what I've done since. I don't recall anyone taking issue with this before, although I guess it's possible they just didn't come to me with their grievance.

The reason why it made/makes sense to me is, a redir is meant to be helpful in steering the user to where they want (or need, in case that's different) to go. If I want to check out User:Foo, and end up instead in an article created by Foo, I don't think the redir was helpful, because I neither wanted nor needed to see that article. (And if there are further moves, mergers, deletions, etc. involved, I might end up somewhere that has nothing at all to do with Foo.)

As for the scenario whereby someone comes to User:Foo looking for the draft that's no longer there, I assume in the majority of cases that someone is Foo (who else would assume there's a draft at User:Foo?), and they will find a message on their talk page informing them of the draft's new location. They can also still find it in their contributions log. Somehow I don't see this as a major problem?

I'm not at all suggesting that @SilverLocust's interpretation of the policy and guidance isn't correct here, I'm sure it is. I just think better guidance is needed in this area. (Specifically, I think we should say that the main user page should not redirect anywhere, other than to the user's talk page for those who prefer that. Also, that the same page should not to be used for article content development, that should be done on a subpage or in the draft space.) -- DoubleGrazing (talk) 10:19, 21 November 2024 (UTC)

Bots/scripts that detect that a submission has not changed (much) since the last time it was submitted

Are there any bots/scripts that detect that a submission has not changed (much) since the last time it was submitted? Ideally they would be able to autoreject or at least put them on a list. It might be possible to look at the previous reason for rejection, e.g. not meeting GNG, and if no new refs are added it is highly unlikely it will pass this time. Polygnotus (talk) 15:27, 10 November 2024 (UTC)

No, and if I remember correctly we decided not to have any sort of bot that does this. Primefac (talk) 15:35, 10 November 2024 (UTC)

I think having a bot that does this would be a bad idea. One poor decline could easily lead to a series of them. -- asilvering (talk) 16:03, 10 November 2024 (UTC)

For clarity, given @Ca's comment below, my comment is about putting them on a list. (Obviously, I think an autoreject bot would be even worse.) -- asilvering (talk) 19:42, 10 November 2024 (UTC)

Yes, bad idea. Sometimes it's reasonable to resubmit without changes if the decline was incorrect or the submitter has clarified something. C F A 💬 16:06, 10 November 2024 (UTC)

How about a bot that could add a Comment to the submission to let the submitter know that the submission has not changed and that they could continue working on it? Myrealnamm's Alternate Account (talk) 16:39, 11 November 2024 (UTC)

I agree having any kind of auto-decline bot is a bad idea. However, simply putting them in a list, like this one, sounds reasonable. It would be useful for finding easy declines/accepts, provided that the reviewers check the circumstances behind the resubmission. Ca ^{talk to me!} 16:38, 10 November 2024 (UTC)

• I like the idea of a bot that can at least note the absence of material change to a resubmitted article. BD2412 T 21:58, 10 November 2024 (UTC)

  @BD2412: Let's say software detects that a submission has not changed (much) since the last time it was submitted. What should it do? Message the submitter? Stick a template on the submission? Stick it on a list similar to Wikipedia:WikiProject_Articles_for_creation/Submissions#List:_Copyvios? Notify the previous reviewer? Something else? You can choose more than one option. Polygnotus (talk) 10:54, 12 November 2024 (UTC)

  Notify the submitter and put a note on the submission to the effect that the submission was previously rejected, and that the reasons for the previous rejection should be reviewed prior to acceptance of the submission. Creating a list of little-changed re-submissions is also not a bad idea. BD2412 T 14:42, 12 November 2024 (UTC)

RfC: Should a bot be created to handle AfC submissions that haven't changed since the last time they were submitted?

Should a bot be created to handle AfC submissions that haven't changed since the last time they were submitted?

• Option 1: Yes. The bot should automatically reject decline any such submissions.
• Option 2: Yes. The bot should add such submissions to a list, similar to the list of possible copyvios.
• Option 3: Yes. The bot should notify the submitter and comment on the submission.
• Option 4: Yes. The bot should add such submissions to a list and notify the submitter and comment on the submission.
• Option 5: No.

JJP_Master (she/they) 18:55, 15 November 2024 (UTC)

Note that I changed Option 1 to decline rather than reject, as reject is a very specific term in AFC and I don't think that is what was meant here. Reject means the draft can never be resubmitted, due to violating WP:NOT or having extremely obvious and egregious non-notability. –Novem Linguae (talk) 22:07, 16 November 2024 (UTC)

---

• Oppose option 1, per the discussion above this is a very bad idea. Support option 2, this seems harmless and seems worth tracking - as long as it is made absolutely clear that being rejected previously is not a reason to reject - if the original reason was correct and still applies then it can be rejected again for that reason. Neutral on the other options, but any comment/notification must make it clear that it is informational only and not a rejection. Thryduulf (talk) 19:21, 15 November 2024 (UTC)
• Option 5. AfC reviewers make mistakes. We should not be prejudicing someone's future AfC chances based on those mistakes any more than we already do - namely, that there is already a gigantic decline message on the draft. AfC is frequently a dispiriting, demoralizing, and baffling experience for new editors, mostly one of waiting and then receiving templated replies they do not fully understand. I oppose this, and I oppose any other efforts that would further increase new editor alienation in this way. -- asilvering (talk) 19:29, 15 November 2024 (UTC)
• Option 4, but as with Thryduulf, the comment on submission should be marked as informational and a reviewer will come by to assess the submission. – robertsky (talk) 19:27, 15 November 2024 (UTC)
• Support option 2. Whether any changes have been made since the last decline is often something I look for when reviewing an article with declines, as it helps to see if the concerns from that last decline were addressed (if I feel like they are appropriate to the article as I see it), and this would be a benefit to a reviewer without being additionally "punishing" to a new editor. Reconrabbit 19:47, 15 November 2024 (UTC)
• Speaking as someone who doesn't review drafts but very occasionally comments on them, I think an {{AfC comment}}-like mention at the top would be easiest to work with, so I guess I'm at Option 3 or 4. Very dubious that a bot could reasonably handle the "(much)" in the preceding section header without unacceptable false positives and negatives, but detecting completely unchanged submissions would be both feasible and useful. —Cryptic 20:01, 15 November 2024 (UTC)

• Support Option 5 - No. Oppose Options 1, 2, 3, 4. Support based on Asilvering's comment. Opposes are my own, doubtless with others. As a reviewer I declare myself capable of checking, and I do. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 20:43, 15 November 2024 (UTC)
• Option 4 but instead of adding to a list, add to a category (preferably a hidden one). Yes, definitely notify the submitter and comment on it, but having a list may discourage the submitter if they see that their draft is listed on a list. Having a hidden category would be better (at least imho) where a parameter of Template:AFC submission can add the draft into the category. Myrealnamm (💬Let's talk · 📜My work) 20:49, 15 November 2024 (UTC)

  Though with all options, the reviewer would still do the same work... Myrealnamm (💬Let's talk · 📜My work) 20:50, 15 November 2024 (UTC)

• I suppose I wouldn't oppose a bot that automatically leaves a comment, but I don't really see the point either. Reviewers should be evaluating based on the current state of the draft — previous declines really shouldn't matter in most cases. I think this would encourage summary "no change" declines without actually looking at the content of the draft. C F A 💬 20:56, 15 November 2024 (UTC)

  You're right. It would encourage reviewers to "decline" the draft just because it hasn't changed since last review. However, thinking now, it might encourage editors to keep working on the draft because they see that "it hasn't changed since last review". If that's the case, reviewers should "wait". So perhaps after the bot leaves a comment, reviewers should wait at least a couple minute before reviewing in case the editor wants to add content? Myrealnamm (💬Let's talk · 📜My work) 21:03, 15 November 2024 (UTC)

  My position is that if they did not see being declined as reason to keep working on the draft, they are unlikely to have a positive view of an automated message telling them that the draft hasn't changed. -- asilvering (talk) 21:07, 15 November 2024 (UTC)

• No too easy to game. The simplest bot would just compare revisions. A submitter would then just have to add like a space or a few words to change it. A more complicated bot would flag changes that were too small or simple, but then that just encourages submitters to ramble. A bot can't assess the quality of a change, only editors can. CaptainEek ^{Edits Ho Cap'n!}⚓ 21:01, 15 November 2024 (UTC)
• Strongest Oppose to 1 as bad reviews do exist. Also, sometimes submitters have discussed it with the reviewer and been told to resubmit for a second opinion etc.

Weak Oppose 2, 3 & 4 as I'm not convinced a bot will accurately determine what no substantive change is and I see little value in just flagging straight re-submits

Support 5 as de-facto option left KylieTastic (talk) 21:20, 15 November 2024 (UTC)

• Option 2 or 4 especially with several disruptors (and one dynamic IP so block doesn't help) who just do drive by submissions. Frustrating to the editor to receive another decline through no fault of their own. Having them in the queue is a waste of reviewers' time though when it's a quick decline because the improvements haven't been made. I think it's less wrong decline and more no discussion about why the feedback was wrong that's the red flag. Star Mississippi 23:34, 15 November 2024 (UTC)

  I lean towards Option 5, but for those pages/editors engaged in a problematic level of drive-by submissions, I wonder whether a completely different approach might work better. For example: If you think the previous decline was correct, and you also think it's a drive-by re-nom, then move the article to the mainspace and send it straight to AFD. If it's kept, then the submitter was correct, and the previous decline was wrong. Also, it's now out of the AFC queues. However, if it's deleted, salt the page name(s) in both Draft: and mainspace for the next year (or two?), so that AFC can be done with it. Either way, it's no longer AFC's problem. WhatamIdoing (talk) 05:22, 16 November 2024 (UTC)

Strongly oppose Option 1. Frankly, trusting fellow reviewers to check how much a draft has changed since a previous decline is reasonable to do. Letting a Bot do something creates an option to game the system. We don't need that. --Johannes (Talk) (Contribs) (Articles) 00:37, 16 November 2024 (UTC)

Support Option 2, neutral on Option 4, and oppose the rest. I do not see the point in notifying submitters when they already are aware they did not make any changes. Perhaps they wanted another review. Putting unchanged drafts in a hidden list like the copyvio one seems optimal as it reduces complexity and unnecessary messages to submitters. It would make finding easy declines and disruptive drive by submissions easier to find. I also support adding a verbiage that being unchanged should not be the sole reason to decline again. Ca ^{talk to me!} 00:57, 16 November 2024 (UTC)

• Option 5 - Reviewers should be instructed, more clearly if necessary, to check whether the draft has been revised since the last decline, and to use human judgment in deciding what is enough improvement. There is no need for automated aid, which could make mistakes and could be gamed. Robert McClenon (talk) 06:10, 16 November 2024 (UTC)
• Option 2, at least, option 4, at best. Yes, reviewers make mistakes, but they make mistakes in both directions, and should also consider the guidance inherent in a previous rejection. BD2412 T 15:16, 16 November 2024 (UTC)

Option 4 preferably, but I'm okay with option 5 as well (TBH, I don't think this is a major problem in the bigger scheme of things, and the details could be tricky). Also oppose option 1, regardless of whether it was intended to say 'reject', or merely 'decline'. -- DoubleGrazing (talk) 15:29, 16 November 2024 (UTC)

PS: When I say details could be tricky, I didn't mean in a technical sense, but rather in defining what the trigger condition of "changed (much)" actually means. Size change doesn't always tell us much: only a few kb might have changed, yet the draft was completely rewritten; conversely, a large kb change could mean that the author simply deleted the earlier AfC templates. Number of sources, ditto: adding ten new rubbish sources to the earlier rubbish sources still adds up to only rubbish; whereas using the same sources but citing them correctly might have resolved the decline reason. -- DoubleGrazing (talk) 15:39, 16 November 2024 (UTC)

• Option 5. AfC reviewers sometimes make mistakes, particularly when dealing with areas that they are not familiar with. (I can't count how many drafts on academics have been rejected and told to supply GNG, and I've also seen rejections of drafts on politicians that clearly passed NPOL.) Creators should always be allowed to ask for a second opinion. Espresso Addict (talk) 18:52, 16 November 2024 (UTC)
• Option 5 Per asilvering and Espresso Addict. I would further that; reviewers often make mistakes....specifically declining articles for reasons that are not decline criteria. Also some reviewers tend to pass only unusually safe passes. North8000 (talk) 18:43, 19 November 2024 (UTC)
• Option 5 per Asilvering. If a reviewer makes a mistake (which often happens), the submitter shouldn't be even more penalized for it. Same if they just want another opinion on their draft. Chaotic Enby (talk · contribs) 18:52, 19 November 2024 (UTC)
• Option 2 or 4 per Star Mississippi. I'll add: Resubmitting an unchanged draft is a sign of a problem even if the declining reviewer had made a mistake. And it will rarely be the case that they have made a mistake given a creator who resubmits an identical draft, which very strongly correlates with the draft being poor in the first place and not deserving of acceptance.—Alalch E. 13:04, 20 November 2024 (UTC)
• Option 5 (do nothing). Like Primefac below, I'm surprised this got the RfC stage given the overwhelmingly negative reception in the original discussion, and hope the closer of this discussion will take that into account. AfC reviewers make mistakes but, more to the point, people can have good faith disagreements about the suitability of an article. If the submitter disagrees with a reviewer, they have every right to ask for a second opinion without edit warring with a bot or making pointless changes. – Joe (talk) 08:20, 25 November 2024 (UTC)
• Option 2 or 5 - Given the unevenness of reviews, authors have legitimate reasons for seeking a second, third or fourth review. ~Kvng (talk) 15:55, 30 November 2024 (UTC)

RFC discussion

Um... didn't this get fairly roundly shot down in the original discussion? Why does it need a full RFC to work out any further details? Primefac (talk) 19:41, 15 November 2024 (UTC)

I think that only Option 1 was outright rejected in the above discussion. The rest were counterproposals that seemed to have at least some support. JJP_Master (she/they) 19:48, 15 November 2024 (UTC)

Meh, RFC just seems like a lot of bureaucracy for something that didn't really have a lot of discussion and could have probably been dealt with in-house. Carry on I suppose. Primefac (talk) 19:49, 15 November 2024 (UTC)

I second your 'meh'. Why are we going through this extra layer. If it ain't broke don't fix it! 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 20:45, 15 November 2024 (UTC)

Hate to be Devil's Advocate for an RFC I've opposed, but I think we've got more, clearer answers to the question in the few hours since this RfC opened than we had in the entire earlier discussion, so there's that. And I do think AfC is pretty broke and needs some fixing. I just think this is tinkering in the wrong direction. -- asilvering (talk) 20:49, 15 November 2024 (UTC)

While we're here and talking about reviewers making mistakes, let me make my perennial plea that, if you see, this, you go ask the reviewer about it on their talk page. We all have to learn somehow! And if the reviewer is making lots of mistakes, it will be easier for any single editor to figure this out later if there's a track record of them on their talk page. By the way, for those who haven't learned this trick yet: the AFCH script will allow you to resubmit drafts as though you were the original submitter. If you think something was inappropriately declined, you can resubmit it to the queue yourself and then immediately accept it, or resubmit it and leave a comment explaining why you did so. -- asilvering (talk) 21:45, 19 November 2024 (UTC)

Or if you want to resubmit a draft on behalf of another user so they get the AfC communications rather than you, such as the Accept notification, you can use {{subst:submit|Creator's username}}. The other option is to click the Resubmit button then change the User (u=) from your name to theirs. S0091 (talk) 22:34, 19 November 2024 (UTC)

The AFCH script will do this for you automatically. -- asilvering (talk) 22:56, 19 November 2024 (UTC)

Ahh..ok, I see now. You review on an already declined draft. I had never clicked the Submit button because I assumed it worked the same way as the Resubmit button in the decline message but the AFCH script gives you options to assign the submitter. I can't tell you how many times I have resubmitted drafts using the manual methods I outline above. The more you know! :) S0091 (talk) 23:27, 19 November 2024 (UTC)

Large Language Models

I don't know about other AfC reviewers, but I've noticed an awful lot of drafts clearly written by ChatGPT or another LLM recently. I've declined every last one of them, as they always have other issues, usually with NPOV and sourcing, but I'm wondering if anyone else agrees it might be a good idea to have a specific "this article reads as though written by AI" as a specific decline reason? CoconutOctopus talk 20:53, 16 November 2024 (UTC)

There's been a lot of G11s in draftspace recently that have that look. Espresso Addict (talk) 20:57, 16 November 2024 (UTC)

I think I must have nominated about half of them! If it wasn't for them abusing Wikipedia I'd almost feel bad for how many people are clearly wasting their money on paid editors who just chuck a prompt into ChatGPT and call it a day... CoconutOctopus talk 21:02, 16 November 2024 (UTC)

It's an enormous timesink. They are not generating anything close to usable articles, far worse than the terrible English that they appear to have superceded, when at least one could generally tell whether or not the entity might conceivably be notable if rewritten. Espresso Addict (talk) 21:10, 16 November 2024 (UTC)

Totally agree with this one. I am just using the "tone" reason and then "AI generated" in the comment box. qcne (talk) 21:02, 16 November 2024 (UTC)

"Custom" as decline reason. and a comment about LLM . Next! 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 21:16, 16 November 2024 (UTC)

That absolutely works, I'm just seeing this way more than I ever see an article that I'd decline as, say, a non-notable astronomical object, or a joke submission. Not a huge deal either way, but I thought it good to get the community's feedback in case it's not just me feeling this way. CoconutOctopus talk 21:20, 16 November 2024 (UTC)

I also reject talk page comments (etc) that are from LLMs. Often they start "Thank you for reaching out" and I prove that I am a grumpy, intolerant old scrote. I do not AGF an LLM. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 22:17, 16 November 2024 (UTC)

I was going to reply with a mock ChatGPT answer but it turns out even if I try I can't write quite badly enough for it to look fake.

One thing we can all agree on is that they're a nuisance to the wiki and a complete waste of editor and reviewer time. I don't see it stopping any time soon though, sadly. CoconutOctopus talk 22:47, 16 November 2024 (UTC)

Perhaps verbiage like "This draft appears to be partially written by text-generating AI like ChatGPT. Because of this, this draft contains promotional wording, unsourced claims, opinions presented as facts, and potential misrepresentation of sources. These are all problems common in text-generating AI so you should not simply copy and paste its outputs into Wikipedia articles or drafts. Please rewrite the draft in your own words and see the instruction page Wikipedia:Large language modelss."? Ca ^{talk to me!} 01:33, 17 November 2024 (UTC)

The advantage of a specific decline for AI is that we could just hit the button and not have to write or paste in a comment. -- asilvering (talk) 02:32, 17 November 2024 (UTC)

My thoughts exactly; it might not take that much time, but if something helps save the time of reviewers when it comes to dealing with low-effort slop then I'm all for it. CoconutOctopus talk 07:32, 17 November 2024 (UTC)

Agreed. However, I think there should be some sort of warning to not decline drafts unless it is an extreme case of AI slop. For example, it took me only couple of minutes to take out the AI fluff in In Search of Bidesia. The editor was probably using it to copyedit, and AI being AI, it inserted whole lot of syncophant praise. Ca ^{talk to me!} 07:43, 17 November 2024 (UTC)

Like other pernicious activities such as copy pasting Google Translate, close paraphrasing, or creating hoaxes, it is probably quicker to delete LLM content than try to repair it. –Novem Linguae (talk) 13:57, 17 November 2024 (UTC)

I've no strong feelings about this new decline reason (helpful? yes; needed? meh), but if it does appear, we shouldn't over-encourage its use. AFAIK using LLM isn't categorically banned, so declining every LLM-generated draft purely because it's LLM-generated seems excessive, and probably against policy (or if this is indeed now policy, can someone point me to it because I've clearly missed that). -- DoubleGrazing (talk) 08:07, 17 November 2024 (UTC)

I don't think it's categorically banned, no. But a decline to have for the archetypal DraftGPT would be handy. I'm sure you know what I'm talking about - five-ish paragraphs, zero useful references, flattering tone with more adjectives than sense. -- asilvering (talk) 09:29, 17 November 2024 (UTC)

Yep. And for the slightly-less-obvious cases, it would be handy to have (eg. in the 'Reviewer tools') easy access to a detector of some sort. -- DoubleGrazing (talk) 09:43, 17 November 2024 (UTC)

Automated "detectors" are still quite unreliable. They have about 70~80% accuracy. Ca ^{talk to me!} 10:06, 17 November 2024 (UTC)

Agreed. We discussed the accuracy of AI detectors in phab:T330346 and the sentiment was they were not reliable. –Novem Linguae (talk) 13:59, 17 November 2024 (UTC)

(non-reviewer comment) Human detectors are more accurate. Slightly less than obvious cases should probably be assessed on merits. Folly Mox (talk) 15:47, 17 November 2024 (UTC)

imo if it's not so obvious a "trained" human reviewer can spot immediately, we should be assuming good faith (which here means "not trying to fill wikipedia with crap LLM output" in addition to the usual "not out to destroy the encyclopedia"). -- asilvering (talk) 18:40, 17 November 2024 (UTC)

Just as a sanity check here (like... my sanity), the issue is that LLM drafts are promotional and/or improperly sourced, yes? If that's the case, why not just decline as NPOV and/or unsourced? If the fact it was made via LLM isn't the reason for the decline itself, why not just decline using what we have? Primefac (talk) 13:11, 17 November 2024 (UTC)

It tells submitters that they should not trust LLM content blindly. They may have not checked the draft for NPOV or tone issues because they thought LLMs were infallible. Ca ^{talk to me!} 13:20, 17 November 2024 (UTC)

Agreeing with this. (I am also of the opinion that LLM generated articles should be outright banned, but I may not be in the majority there, and besides, it'd be a hell of a thing to try and enforce) CoconutOctopus talk 13:56, 17 November 2024 (UTC)

I'm also on the stricter side than current consensus. Lazy editors who trust software too much without proofreading and correcting its output are likely to create more problems down the road if not firmly dissuaded, and we should be openly unwelcoming to that behaviour. Also it's deeply unfair to write a prompt for an automated process to compose an article, then ask a human to spend more effort reviewing it than you spent thinking about it. Folly Mox (talk) 15:47, 17 November 2024 (UTC)

I think a specific "we see what you did there, and we don't like it" is helpful in this particular case, for two main reasons. One, most people using LLMs, obviously, have no idea how bad they are at doing the thing they want them to do, and a specific decline message could tell them that. Two, we don't actually want someone to waste their time trying to clean up and find sources for their garbage DraftGPT, do we? Personally, I'd prefer they just started over. -- asilvering (talk) 18:39, 17 November 2024 (UTC)

For a laugh I asked Chat GPT: "Please create a warning for a wikipedia editor who uses a Large Language model to generate articles, making sure that the understand that it is not appropriate. Then create a second wring against using LLMs in wikipedia talk page responses and conversations"

It replied:

Warning 1

Using Large Language Models to Generate Wikipedia Articles

Subject: Warning: Inappropriate Use of LLMs for Article Creation

Hello,

It has come to our attention that you have been using a Large Language Model (LLM) to generate Wikipedia articles. While LLMs can be helpful tools for research and drafting, their outputs often lack the rigor, neutrality, and verifiability required for Wikipedia content.

As per Wikipedia’s content policies, all articles must adhere to:

• Verifiability: Information must be supported by reliable, published sources.

• Neutral Point of View (NPOV): Content must be unbiased and factual.

• No Original Research: Contributions must be based on published information, not generated content.

LLMs often produce content that:

1. Lacks verifiable sources.

2. Introduces subtle bias or inaccuracies.

3. Contains synthesized information that may not reflect reliable sources.

This behavior undermines Wikipedia’s integrity and is considered inappropriate. If you continue using LLMs for article generation, further action may be taken, including editing restrictions or account sanctions.

Please ensure your contributions are original, well-researched, and comply with Wikipedia’s guidelines moving forward.

Thank you for your cooperation.

Warning 2

Using Large Language Models in Wikipedia Talk Page Responses

Subject: Warning: Inappropriate Use of LLMs on Talk Pages

Hello,

It has been observed that you may be using a Large Language Model (LLM) to generate responses on Wikipedia talk pages. While LLMs are capable of producing coherent text, their use in discussions is discouraged because:

1. Lack of Accountability: Wikipedia is built on collaborative, human input, and responses from LLMs lack personal accountability and intentionality.

2. Potential for Inaccuracy: LLM-generated responses may include subtle inaccuracies or misinformation.

3. Disruption of Collaboration: Talk pages are intended for genuine human dialogue and decision-making about article content.

Please refrain from using LLMs in talk page discussions. Instead, engage authentically with your own thoughts and words. If you need assistance in contributing effectively, refer to Wikipedia’s policies or seek help from experienced editors.

Continued misuse of LLMs may result in restrictions on your account or contributions.

Thank you for understanding the importance of maintaining human collaboration and integrity on Wikipedia. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 21:36, 17 November 2024 (UTC)

Warning 2 is a trainwreck, but warning 1 isn't half bad, honestly. -- asilvering (talk) 21:43, 17 November 2024 (UTC)

It was therefore "half worthwhile" 🤡 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 21:56, 17 November 2024 (UTC)

For the record, I have found LLMs to be an extremely useful tool for taking a set of statements from sources and constructing them into a good start at a coherent and encyclopedic presentation of that content. Of course, content that is entirely generated by an LLM without using provided sources is going to be problematic, but we should not throw out the use of the tool as a tool in itself. BD2412 T 21:52, 17 November 2024 (UTC)

While I agree with the point that LLMs aren't banned and that "generated by LLM" by itself isn't a decline reason, it could be very handy to have a way to decline a draft for showing the problems usually associated with LLM content (promotional tone issues, generic speculative statements, "conclusion-like" paragraphs, essay-like wording trying to emphasize the subject's place in a broader context, etc.)

These drafts are sadly way too typical to not have a specific decline reason. If the person used, say, ChatGPT, without knowing its limitations and what should be done to use AI-generated content constructively, then a generic "this article has tone issues" will be far less helpful than a "here is what you can do to improve raw LLM content". Chaotic Enby (talk · contribs) 23:02, 17 November 2024 (UTC)

Did you see that there's this template: Template:AI-generated? Any use? Curb Safe Charmer (talk) 10:32, 18 November 2024 (UTC)

Useful as a template especially when doing NPP, but I was thinking more of a decline reason (I'm loathe to put a template on a draft article as I'd like to think they wouldn't need any once published). CoconutOctopus talk 10:56, 18 November 2024 (UTC)

This isn't strictly related, but someone might wanna see this for a good laugh. '''[[User:CanonNi]]''' (talk • contribs) 10:21, 20 November 2024 (UTC)

🙂 —Alalch E. 12:43, 20 November 2024 (UTC)

Draft decline text (LLM)

Working on a draft decline message, would be happy to have feedback on it!

Your draft shows signs of having been generated by a large language model, such as ChatGPT. While the use of large language models isn't disallowed, their outputs usually have multiple issues that prevent them from meeting our guidelines on writing articles. These include:

• Promotional tone, editorializing and other words to watch
• Generic, speculative statements extrapolated from similar subjects
• Essay-like writing

Furthermore, it is your responsibility to accurately verify LLM-generated content, as it will often contain hallucinations and fictious references.

Chaotic Enby (talk · contribs) 17:30, 18 November 2024 (UTC)

Looks good to me - I'd maybe have something in there saying to please rewrite in your own words, just in case it isn't clear enough that they should be doing that. CoconutOctopus talk 17:35, 18 November 2024 (UTC)

Thanks! Before the last line, we could add You should ideally rewrite the generated content in your own words to avoid these issues. maybe? Chaotic Enby (talk · contribs) 17:40, 18 November 2024 (UTC)

I think that makes sense, yeah! Thanks very much for writing this up. CoconutOctopus talk 17:52, 18 November 2024 (UTC)

Just splitting this off into its own section for further discussion and possible approval/consensus. Primefac (talk) 18:01, 18 November 2024 (UTC)

I disagree. An encyclopedia demonstrates what is believed to be established knowledge; this requires finding, reading, assessing, and analysing sources prior to writing a Wikipedia article. Encouraging editors not to learn this principle is anything but useful to this project. Content generated by LLMs is mostly useless for Wikipedia because LLMs are not knowledgeable. They excel at composing text that is sufficiently convincing to the average ignorant person if that text does not require any sort of factual accuarcy. For Wikipedia, compelling but erroneous content is extremely dangerous. Telling someone, who has already demonstrated a failure to understand what Wikipedia is, to rewrite unsensible LLM text is hopefully ignored by that addressee. Best, --Johannes (Talk) (Contribs) (Articles) 18:35, 18 November 2024 (UTC)

Just to clarify, this would be in conjunction to the final sentence that currently reads Furthermore, it is your responsibility to accurately verify LLM-generated content, as it will often contain hallucinations and fictious references.
While it could be worded a bit more strongly, I believe this already tells editors that they should be verifying the factual accuracy of LLM-generated content, especially regarding sources. Chaotic Enby (talk · contribs) 18:38, 18 November 2024 (UTC)

Do we expect editors having to use LLMs to comprehend this? I'm drifting off course here, but I'm not sure whether you are aware that, to a certain group of people, using LLMs appears like a splendid way to circumvent the necessity to learn English. --Johannes (Talk) (Contribs) (Articles) 18:51, 18 November 2024 (UTC)

That is indeed a pretty good point. Maybe we could replace these two sentences by:

You should research and write content by yourself, and not trust what AI models write for you, as it is often made up. It is your responsibility to fully verify LLM-generated content that you introduce on Wikipedia, as it will often contain hallucinations and fictious references.

I've tried to make the bolded part and its surroundings use less technical terms to be more accessible for potential LLM-using editors. Chaotic Enby (talk · contribs) 19:10, 18 November 2024 (UTC)

Consider deleting "While the use of large language models isn't disallowed". Even if it isn't technically disallowed, I think this sentence plants a seed in editor's heads that LLM use is OK, and giving this advice to a new editor is probably not a good idea. Consider also deleting the last sentence, "Furthermore, it is your responsibility to accurately verify LLM-generated content, as it will often contain hallucinations and fictious references.", for the same reason. This makes it sound like it's OK to have LLMs write articles as long as you double check their output. Which is not good advice at all. The basis of new articles should be reading and summarizing reliable sources, not asking ChatGPT to hallucinate an article.

Might as well add a new sentence to the end, too. Something like "Please address these issues. The best way to address these issues is usually to read reliable sources and summarize them, instead of using a large language model.".

So to summarize, I'd like to propose these modifications:

Your draft shows signs of having been generated by a large language model, such as ChatGPT. Their outputs usually have multiple issues that prevent them from meeting our guidelines on writing articles. These include:

• Promotional tone, editorializing and other words to watch
• Generic, speculative statements extrapolated from similar subjects
• Essay-like writing

Please address these issues. The best way to address these issues is usually to read reliable sources and summarize them, instead of using a large language model.

–Novem Linguae (talk) 22:44, 18 November 2024 (UTC)

Thanks, that is indeed much better advice. Small detail, there is some repetition in Please address these issues. The best way to address these issues is.... Would The best way to do it is... work instead? Chaotic Enby (talk · contribs) 23:06, 18 November 2024 (UTC)

Feel free to put my version in a sandbox somewhere, link it here, and start modifying. I think we're at the point where folks being able to boldly edit the message and iterate on it would be helpful. –Novem Linguae (talk) 23:33, 18 November 2024 (UTC)

I put it at the top of Template:AfC submission/comments/sandbox, and I'll put the transcluded version below. Chaotic Enby (talk · contribs) 00:00, 19 November 2024 (UTC)

I've added a line on non-existant references, since IMO it's a pretty major issue with LLM writing. CoconutOctopus talk 07:56, 19 November 2024 (UTC)

For me the elephant in the room is copyright. Who owns the copyright of an LLM generated piece of text, (etc). 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 09:31, 19 November 2024 (UTC)

I thought they were public domain? Ca ^{talk to me!} 11:06, 19 November 2024 (UTC)

That part is still being heavily debated by legal scholars, although for now LLM output is considered to be public domain. Chaotic Enby (talk · contribs) 11:25, 19 November 2024 (UTC)

That is an interesting point you make. I reckon that we must think out of the box – do we know which legal system applies to content on Wikipedia? The principle of a copyright is something usually found in Angloamerican legal systems, while other legal systems may have other principles. In Germany, for example, copyright (Vervielfältigungsrecht) is part (a proper subset) of the creator's right (Urheberrecht). In the latter, it is defined that Werke im Sinne dieses Gesetzes sind nur persönliche geistige Schöpfungen, i.e., only works created by persons can be subjected to a creator's right, and, therefore, copyright can only exist if a work was created by a person. In other words, text created by an LLM may be deemed being below the threshold of originality, i.e., not "copyrightable" if the person who used the LLM is German. Best, --Johannes (Talk) (Contribs) (Articles) 12:07, 19 November 2024 (UTC)

For this subthread, see m:Wikilegal/Copyright Analysis of ChatGPT. (TL;DR: inconclusive.) Folly Mox (talk) 11:22, 20 November 2024 (UTC)

I've reworded it a bit, as "hallucinated references" would be redundant with "non-existent references". The existence of hallucinations in the content (and not only the references) deserves a mention. Chaotic Enby (talk · contribs) 11:27, 19 November 2024 (UTC)

I would also note LLM's tendency to produce very vague claims without citing statistics or specific examples. I would also add a wikilink to the help page WP:Large language models. Ca ^{talk to me!} 11:59, 19 November 2024 (UTC)

For your first point, that's what the "generic, speculative statements" point was about, although I invite you to reword it if you feel there's a better way to convey the idea. Agree with linking WP:LLM, I figure it can replace the article link at "large language model". Chaotic Enby (talk · contribs) 12:13, 19 November 2024 (UTC)

I added "Vague" to the second bullet point and added a note about copyright. I think having a link to both mainspace article for those unfamiliar with the term and the WIkipedia help page is the best solution. Ca ^{talk to me!} 07:37, 20 November 2024 (UTC)

Slightly reworded it, I think it's good! Chaotic Enby (talk · contribs) 09:32, 20 November 2024 (UTC)

Looks good to go to me at least! CoconutOctopus talk 10:50, 20 November 2024 (UTC)

Current draft text

Your draft shows signs of having been generated by a large language model, such as ChatGPT. Their outputs usually have multiple issues that prevent them from meeting our guidelines on writing articles. These include:

• Promotional tone, editorializing and other words to watch
• Vague, generic, and speculative statements extrapolated from similar subjects
• Essay-like writing
• Hallucinations (plausible-sounding, but false information) and non-existent references
• Close paraphrasing
  

Please address these issues. The best way to do it is usually to read reliable sources and summarize them, instead of using a large language model. See our help page on large language models.

@Ca @Johannes Maximilian @Timtrent @Novem Linguae @Primefac @CanonNi @Curb Safe Charmer @BD2412 @Timtrent @Asilvering @Folly Mox @DoubleGrazing @Qcne @Espresso Addict, what are your thoughts on this final version? (pinging everyone else who participated in the discussion, please tell me if I forgot someone!) Chaotic Enby (talk · contribs) 11:09, 20 November 2024 (UTC)

I am happy with this. It is not too bloated while capturing many issues in LLM writing. Ca ^{talk to me!} 11:18, 20 November 2024 (UTC)

(responding to ping)  Works for me Folly Mox (talk) 11:25, 20 November 2024 (UTC)

Support. --Johannes (Talk) (Contribs) (Articles) 11:29, 20 November 2024 (UTC)

Support. qcne (talk) 11:45, 20 November 2024 (UTC)

Y Looking good! -- DoubleGrazing (talk) 11:50, 20 November 2024 (UTC)

Support '''[[User:CanonNi]]''' (talk • contribs) 11:57, 20 November 2024 (UTC)

Support, obviously! CoconutOctopus talk 12:23, 20 November 2024 (UTC)

Support, nice work. Curb Safe Charmer (talk) 12:43, 20 November 2024 (UTC)

Support.—Alalch E. 12:46, 20 November 2024 (UTC)

Support. I am good with this as is. BD2412 T 14:31, 20 November 2024 (UTC)

Looks fine to me. Personally I'd advise editors to insert line-by-line citations as they go along, particularly for BLPs, but that might be too much for the average newbie. Espresso Addict (talk) 15:17, 20 November 2024 (UTC)

SUpport. Any small refinements will happen over time. This version is wholly suitable. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 16:55, 20 November 2024 (UTC)

Given the clear consensus, I went ahead and made the edit request at Template talk:AfC submission. Chaotic Enby (talk · contribs) 17:05, 20 November 2024 (UTC)

Looks good - though can we get a link to WP:BACKWARDS in there? -- asilvering (talk) 17:09, 20 November 2024 (UTC)

Makes sense, I don't think it will be a big deal for anyone if you add it. Maybe as a piped link, The best way to do it is usually to read reliable sources and summarize them? Chaotic Enby (talk · contribs) 17:17, 20 November 2024 (UTC)

I couldn't think of anywhere to put it in there that wouldn't be too "hidey", but I think I've got it now: The best way is to start over by reading reliable sources and summarizing them... -- asilvering (talk) 17:28, 20 November 2024 (UTC)

Even better! Chaotic Enby (talk · contribs) 17:29, 20 November 2024 (UTC)

Marketing Buzzspeak

Just to illustrate how it may be difficult to recognize the output of a Large Language Model, I will point out that within the year 2024 I had a brief discussion with another reviewer about a draft which they thought had been written by a large language model, and I said that I thought it read like it was written by a technical marketeer and contained marketing buzzspeak. In my career as an information technology engineer, I sometimes saw prose that was designed to dazzle or confuse the reader, and did not convey useful information. It had been written by humans, before the invention of large language models. A large language model that contains marketing buzzspeak may be imitating a human, and may even have been trained using marketing buzzspeak . For a reviewer, there is not much difference between bad human writing and bad computer writing that may be imitating bad human writing. Sometimes a page that appears to have been written by AI was written by a human. So if you are not sure if a draft was written by AI, maybe it should be declined either as 'adv' or as 'npov', or rejected as contrary to the purpose of Wikipedia because Wikipedia is not for advertising. Robert McClenon (talk) 17:41, 22 November 2024 (UTC)

Rechecking reviews by new reviewer

Hi all, Royiswariii has recently started reviewing AfC drafts and has been making some incorrect declines. I've checked everything from Nov 14-18, and found enough mistakes that I think their whole record so far should be cross-checked by other reviewers. There's only about 80 left, so this shouldn't be too hard for us to get through. Reminder as always to keep things constructive. -- asilvering (talk) 22:42, 19 November 2024 (UTC)

Note that they are still on the list at WP:AFCP, so it looks like we're in the "see how bad it is" phase rather than the "they already lost the perm and now we need to cleanup" phase.

Asilvering, want to provide some diffs of problems you've found so far? I see you posted a paragraph on their user talk talking about some of the problems. But they will probably need more detail to properly calibrate, and we'll probably need more detail to properly judge if this is a situation where we should consider more action or if this can be a learning experience for them. –Novem Linguae (talk) 07:27, 20 November 2024 (UTC)

"Learning experience" is my aim here. -- asilvering (talk) 17:02, 20 November 2024 (UTC)

Hello, Asilvering! Please note that i am a probability participants here in AfC for 3-6 months and they will check wether will retain me or not. Also, I will defend myself that November 14-18 that "whole record" are all mistakes. I am based on the review guide and if I am mistaken, another reviewer can correct me if I am doing wrong or not, i am open to all feedbacks because I am PROBABILITY participants here. But, I will disagree that all records are wrong because some articles that I declined it's either wrong format of encyclopedic tone, not English written or no citations or failed in WP:GNG. Royiswariii Talk! 09:15, 20 November 2024 (UTC)

Just to clarify, formatting issues alone should not be a reason to decline a draft. Chaotic Enby (talk · contribs) 09:24, 20 November 2024 (UTC)

yes, that's my fault and i fix it. Royiswariii Talk! 09:28, 20 November 2024 (UTC)

I'm aware you're on the probationary reviewer list. I didn't say your whole record was mistakes - just that I found enough mistakes in Nov 14-18 that the rest of the record should be checked. We don't want people giving up on their drafts because they received an incorrect decline. Please do keep reviewing, and incorporating any feedback you get as we recheck things. -- asilvering (talk) 17:07, 20 November 2024 (UTC)

I've now gone through the rest, nothing left to do here. -- asilvering (talk) 13:22, 21 November 2024 (UTC)

AFCSW bug?

I came across this edit, where the user resubmitted a rejected draft. It doesn't look copy-pasted, the template is filled-in properly and the edit summary looks normal. A bug, maybe? '''[[User:CanonNi]]''' (talk • contribs) 07:43, 20 November 2024 (UTC)

It's not really a bug; the submit wizard doesn't check if a draft has been rejected. They presumably clicked the "Submit for review" button on the {{draft article}} template and submitted it normally. C F A 14:13, 20 November 2024 (UTC)

That makes sense. A check seems like a good idea though. '''[[User:CanonNi]]''' (talk • contribs) 14:17, 20 November 2024 (UTC)

cc SD0001 –Novem Linguae (talk) 11:56, 21 November 2024 (UTC)

"Xxps" listed at Redirects for discussion

The redirect Xxps has been listed at redirects for discussion to determine whether its use and function meets the redirect guidelines. Readers of this page are welcome to comment on this redirect at Wikipedia:Redirects for discussion/Log/2024 November 20 § Xxps until a consensus is reached. 65.92.246.77 (talk) 18:31, 20 November 2024 (UTC)

Draft:Payer Ahmed

Hello again -- Could someone take another look at this one, now declined twice; the subject is claiming to be vice chancellor of a university, which might well meet WP:PROF. The creator has just tried to create it on the talk page in mainspace, so I suspect they are not understanding the process. Cheers, Espresso Addict (talk) 22:45, 21 November 2024 (UTC)

I think only the very top administrative position meets WP:NPROF#C6. I don't think "Second Vice-Chancellor" qualifies. Normally I'd say move it to mainspace per WP:DRAFTOBJECT, but they are an IP so are not allowed to make articles directly in mainspace, so I do not think they're supposed to bypass the AFC process. –Novem Linguae (talk) 23:26, 21 November 2024 (UTC)

If you look at the university article the chancellor position is held by the president of Bangladesh, so I think vice-chancellor would count as the top position here. The "second" is simply because he is the 2nd person to hold it. Espresso Addict (talk) 23:33, 21 November 2024 (UTC)

Two of the three references will not open for me at the moment. The one that does isa mare courtesy anouncement. I can't make up my mind if there was a first VC and now he is the second, on whose departure a third will be appointed. An intervening comment suggests. succession!

I think Ahmed passes as the top functioning official, though not necessarily as a professor. It is on the correct side of the borderline for us to accept. However two highly experiences reviewers have a different opinion.

Pinging @Jamiebuba and KylieTastic: for your current thinking? 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 23:38, 21 November 2024 (UTC)

@Timtrent Initially my analysis of "Second Vice Chancellor" was that its a position below the "Vice Chancellor" itself like a deputy vice chancellor or an assisting vice chancellor like some countries would have, but checking some references the subject does meet WP:NPROF. An additional secondary source would do for now. Jamiebuba (talk) 05:52, 22 November 2024 (UTC)

According to Chandpur Science and Technology University#List of vice-chancellors, "second" is chronological here, so he was the second ever vice-chancellor. According to my notes, I still don't think vice-anything passes WP:NPROF#C6. I think only university presidents pass C6. –Novem Linguae (talk) 09:10, 22 November 2024 (UTC)

I would assume (but don't know) that Bangladesh follows the British system, where V-C is the de facto head of the uni, with the actual Chancellor being a ceremonial role for publicity/lobbying etc. purposes. -- DoubleGrazing (talk) 09:46, 22 November 2024 (UTC)

When I reviewed with the single source this the caption translated as "has been appointed as the new vice chancellor of Jagannath University mathematics department". So that suggested just a departmental appointment. I think I missed the later text google translates as "has been appointed as Vice Chancellor of Chandpur University of Science and Technology". I had also missed the part of WP:PROF #6 "or vice-chancellor in countries where this is the top academic post" - that is an oddity I had not come across before. There is also the muddying of the water in that part with having "may be satisfied" and "significant accredited college or university". (Takes a moment to miss DGG who was the goto for these). I also note that https://www.cstu.ac.bd/ lists him as Vice Chancellor on the front page and with the additional sources I have accepted per PROF#4. KylieTastic (talk) 09:47, 22 November 2024 (UTC)

or vice-chancellor in countries where this is the top academic post is a good find and seems to be a clear C6 pass then. Thanks for spotting that. –Novem Linguae (talk) 10:27, 22 November 2024 (UTC)

This has now been Accepted. Thank you all, and thank you @KylieTastic for performing the acceptance. It's good when folk agree. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 10:56, 22 November 2024 (UTC)

Thanks everyone! For the record, vice-chancellor is the usual top position in UK universities, and some places where the UK system has been adopted. The deputy position, where it exists, is often referred to as "pro-vice-chancellor", but that would not of itself confer notability. Cheers, Espresso Addict (talk) 23:45, 22 November 2024 (UTC)

Wikipedia:Articles_for_creation/Redirects/Reviewing_instructions#Other types of submissions

As for Wikipedia:Articles_for_creation/Redirects/Reviewing_instructions#Other types of submissions:

• Is it on-topic for information about non-redirects to be discussed on a page whose title includes "Redirects"?
• This appears to exist, but is rare
• Should we add the instructions about AFC drafts to {{afd footer}} (WP:AFDHOWTO), which currently only mentions using the talk page?

76.71.3.150 (talk) 00:21, 22 November 2024 (UTC)

Xx network draft article

https://en.m.wikipedia.org/wiki/Draft:Xx_network

Hi, can anyone help me understand why my draft article was rejected. At first a reviewer told me I needed more sources and now after weeks of waiting another reviewer is telling me I have too many sources. Also they pretend my sources are low quality sources. Can anyone explain how Wired, Bloomberg, Wall Street Journal and Cointelegraph articles can be qualified as low quality? I spent much time and effort on this article so I would really like to have some more precise guidance to help me modify it for acceptance. Thanks in advance. Jstrob (talk) 17:35, 23 November 2024 (UTC)

@Jstrob, your reviewers are correct: you have too many low-quality sources. Please check your sources against WP:RSP and avoid WP:CITEKILL. -- asilvering (talk) 23:33, 23 November 2024 (UTC)

Ok thank you I will go through all my sources and eliminate all that could be lower quality. Jstrob (talk) 03:52, 25 November 2024 (UTC)

Draft:Slim Jxmmi

I would appreciate if another reviewer could look at this draft. The title Slim Jxmmi was an article from April 2017 to July 2017. In July 2017 it was nominated for deletion, and then was redirected to Rae Sremmurd by the closer. The redirect was then restored as an article five times, and then the redirect was locked in May 2018. I reviewed a draft in January 2024 and declined it as not establishing enough additional information to overcome the presumption of non-notability from the AFD. That draft was deleted as G13 in July 2024, so I can't compare this draft to the one that I declined. I can compare a draft to the redirected version, because the redirected version is in the history. The draft has added a considerable amount of information, but I am not sure that it is enough more information to overcome the presumption of non-notability, or to justify requesting unprotection of the redirect. Thank you. Robert McClenon (talk) 22:04, 23 November 2024 (UTC)

@Robert McClenon I think we're far enough away from the 2017 AfD that it ought to get another shot at it. -- asilvering (talk) 23:31, 23 November 2024 (UTC)

Is using Template:WikiProject Articles for creation needed for redirects?

Recently, I requested @Eejit43 to add a feature in his script for reviewing redirects to turn off the talk page creation after accepting a redirect. Currently, if a redirect is accepted, it also creates the talk page (eg. Talk:Chevrolet C/K (4th generation)) with the template {{WikiProject Articles for creation}}. Based on the Reviewing instructions, creation of talk page is listed under Additional tasks.

Is it required or just optional? Most of the redirects in the wiki do not even have a talk page, so wondering if that is needed here as well. ~/Bunnypranav:<ping> 12:17, 26 November 2024 (UTC)

@Bunnypranav I believe your request just creates busywork. If it isn;t broken there is no need to fix it. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 12:29, 26 November 2024 (UTC)

Why create the page if it has barely any views or importance. I know it's a script, but isn't that busywork? ~/Bunnypranav:<ping> 12:34, 26 November 2024 (UTC)

It's a tracking metric, which can be useful. Since the script is already doing the job, it is not busywork to have it do an extra edit. Primefac (talk) 12:36, 26 November 2024 (UTC)

Semi-RfC: Add mention of search engine indexing delay in TM:AfC accept

Should the following warning be added to {{AfC accept}}?

Your article may not be indexed on search engines for up to 3 months until your article is reviewed.

(previous discussion) Ca ^{talk to me!} 01:09, 27 November 2024 (UTC)

Anytime I see someone asking about appearing on a search engine I suspect COI/promotion issues. In several cases it actually gets the article moved back to draft, deleted or edited for POV. The trouble with trying to answer follow up questions is you can just move onto a new question or rephrasing. I would think many who see that notice would just ask what it means as they thought it had been reviewed and accepted but now says it still needs to be reviewed. Trying to explain AfC reviews vs NPP patrols in a short sentence to new editors is not likely to work. KylieTastic (talk) 11:18, 27 November 2024 (UTC)

I am not sure I was convinced enough during the previous discussion to change my on-the-fence position, in that it might be useful, but really all we are doing is punting the ball into badgering NPPs. Based on the previous conversation, it looks to have been asked only a half-dozen or dozen times in the last five years, so the potential confusion of "why are they telling me this?" seems more of an issue than the handful of people who just must have their article appear in Google now. Primefac (talk) 19:01, 27 November 2024 (UTC)

I specifically avoided mention of NPP in my proposed text per this feedback. When I made my first article, I was excited my work is showing up on Google(because very few actually uses Wikipedia's search). Ca ^{talk to me!} 22:43, 27 November 2024 (UTC)

If including I would probably drop the until your article is reviewed bit as well and just say it might not appear in search engines like google until 3 months have passed. There's a very small chance of confusion ("but hasn't my article already been reviewed?") and it's not that informative if we don't mention NPP. Alpha3031 (t • c) 04:08, 28 November 2024 (UTC)

• I think it is a question that is asked infrequently enough that we don't need to add to the instruction creep to deal with it. And I agree that the question remains useful as a sort of self-tattle... CaptainEek ^{Edits Ho Cap'n!}⚓ 01:07, 28 November 2024 (UTC)

  As one of the most frequent NPP reviewers, I agree with this entirely. There's no need to confuse users, and if users are already aware of it, well, it means you might want to keep an eye on them while still doing your best to assume good faith. Hey man im josh (talk) 13:27, 28 November 2024 (UTC)

Question

Is this wikiproject also for articles that exist in other languages but not wikipedia? For example i am planning to translate the chinese article on the PLANMC 7th Marine Brigade when i have time Thehistorianisaac (talk) 05:47, 27 November 2024 (UTC)

Hi @Thehistorianisaac: if you're asking whether you can translate an article into English and rather than publishing it directly, put the draft through AfC review, then yes, by all means; we see quite a lot of those. -- DoubleGrazing (talk) 06:08, 27 November 2024 (UTC)

Thanks! Thehistorianisaac (talk) 07:31, 27 November 2024 (UTC)

May I ask if my draft is a translated version of an existing article in another language, do i need to go through any extra procedures? Thehistorianisaac (talk) 02:06, 29 November 2024 (UTC)

Yes. Please indicate that it's a translation in the first edit summary, for copyright reasons. You can also add a {{Translated from}} to the talk page. More details at WP:CWW. Thank you for asking :) –Novem Linguae (talk) 02:30, 29 November 2024 (UTC)

Thanks for the information Thehistorianisaac (talk) 02:32, 29 November 2024 (UTC)

Welcome template

Tracked in github.com
Issue #386

Howdy folks. I'm about to approve a patch for AFCH that will give you the option to add {{Welcome draft}} to user talk pages when declining and rejecting. In the patch, the check box for this feature is ticked by default but untickable on a per-draft basis. Does this sound OK? Or would folks like this to default to unticked? Thanks. –Novem Linguae (talk) 07:35, 27 November 2024 (UTC)

I don't like on by default as I like to choose different welcomes depending - most notably for non-English submissions. From discussions on Twinkle in the past a lot of people do not like to be told to use particular welcomes. In particular I have seen many, including me, who do not like welcomes that encourage coming to the leavers talk page.

"untickable on a per-draft basis" - Yes you need to be able to override on a case-by-case basis, but also there would need to be a config (preferences) setting to change the default behavior for a user. I don't mind if the default out of the box is on, but people need to be able to turn off depending on workflow.

As the script is available to many by default I would guess many 'reviewers' do not pay attention to this page so any change will probably get feedback only when live. KylieTastic (talk) 10:06, 27 November 2024 (UTC)

so any change will probably get feedback only when live. Known in some circles as the "scream test". Change something and see if people scream. A staple of software engineering :) –Novem Linguae (talk) 10:55, 27 November 2024 (UTC)

I would rather the box be un-ticked by default (i.e. opt-in) as I rarely even leave the Teahouse message if the user already has a talk page (and especially if the draft has already been declined). Primefac (talk) 19:03, 27 November 2024 (UTC)

Draft:Rosamond Jacob

Could someone please take a look at this draft to advise on what to do about it? It is a copy of Rosamond Jacob and has already been declined as such. The question is not whether to accept it, since it has already been declined, but whether it should be redirected to the article (the obvious action), or whether it should be deleted because of copying without attribution. The draft appears to be the work of an editor who has done nothing but copy the article. My first thought is to blank it and redirect it to the article, which I have done hundreds of times, but I want another opinion. Thank you. Robert McClenon (talk) 17:53, 27 November 2024 (UTC)

@Robert McClenon My view is to redirect and also assist the copyist to understand the rules. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 18:23, 27 November 2024 (UTC)

It is not a copy, large amounts/most of it are different. Some new editors think if they are making a fundamental rewrite that AfC is the way to go. Although this is not just expansion as they also drop valid content. Why not just leave it, blanking and redirecting could just confuse them and I fail to see the purpose unless someone keeps resubmitting and is not-listening. KylieTastic (talk) 18:24, 27 November 2024 (UTC)

That was a better analysis than mine. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 18:29, 27 November 2024 (UTC)

Thank you, User:KylieTastic and User:Timtrent. If this is a substantial rewrite, then I agree that the draft itself should be left alone, but the originator has misunderstood how AFC works, and should be advised to discuss their changes at Talk:Rosamond Jacob with normal editing. Robert McClenon (talk) 18:56, 27 November 2024 (UTC)

I think that we need an essay giving advice to editors who try to use AFC to revise an existing article. In this case, we have a new contributor to Wikipedia who should be encouraged to edit, and is making a reasonable effort to contribute, but has taken a reasonable wrong turn. I have given advice to the editor, who should be encouraged. Robert McClenon (talk) 19:07, 27 November 2024 (UTC)

Does it need a whole essay, or three well crafted paragraphs, do you think, Robert McClenon? I'd read three paras before I'd read an essay. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 19:23, 27 November 2024 (UTC)

I'd go further: Does it need three paras? Maybe an extra sentence or two on the 'exists' decline if some think more clarity is required. What needs to be said other than maybe something like: "AfC is not for article change approval. If you want input before making changes discus on the article talk page where you can link to a draft as a proposal if desired". Which is another reason not to blank a draft, submitters should be able to use a draft as a proposal for big changes. KylieTastic (talk) 19:36, 27 November 2024 (UTC)

I mean, I'm kind of a fan of three sentences... Primefac (talk) 19:38, 27 November 2024 (UTC)

Please précis my thoughts to what ends up being agreed, if anything! 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 19:41, 27 November 2024 (UTC)

Or KylieTastic's. Or both! 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 19:43, 27 November 2024 (UTC)

It may not, but I've drafted a shirt piece. It's below the line here. Please edit mercilessly, or ignore, or do whatever makes sense. Itls always easier to start with something than to write from scratch.

----

Hi **username**. I want to thank you for starting work to edit the content of **article**, and I would like to save you some time and effort.. You may not know that the article it able to be edited by anyone at all. Yes, you are able to edit it. And you really should.

There are some things you need to know first. You may know them already.

• References, citations, for facts you add are essential
• Removing cited facts is frowned upon even if the fact is incorrect, provided that the citation supports the ‘incorrect fact’. Yes, this sounds odd! Wikipedia is happy to have two, cited, contradictory facts in the same article, though the prose must draw a distinction, but never a conclusion
• If someone disagrees with your edit, they may remove it, or edit it. If you disagree with them then please start a discussion on the article’s talk page. Whatever you do don’t go into battle on behalf of your edit.

Taking a copy, and working on the copy in Draft space or in your user sandbox might feel reasonable, but Wikipedia does not work that way. Every edit here is attributed to the edit who made it. Youy might think that copying your draft of what you are sure is am improved article should be copied and pasted over the existing one, but this loses the attribution of the edits. Please don’t do that, because it causes a lot of work for other people. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 19:39, 27 November 2024 (UTC)

A Misunderstanding by a Submitter

This is just a case to let reviewers know that, no matter how clear you think your advice was, there will be weird ways that it can be misunderstood in good faith by an inexperienced submitter. I just reviewed a draft BLP that had been declined once. It had no references. It had previously been declined as 'v' and as 'bio'. It had two unreliable sources. I looked at the history and saw an edit summary, "I took out the sources". That was clearly a good-faith action, but was a mistake, making it worse than before. I declined it as 'v' and 'ilc', and advised the originator to ask for advice at the Teahouse before resubmitting. There are good-faith errors that inexperienced editors can make that a reviewer cannot anticipate in advance. Robert McClenon (talk) 05:33, 28 November 2024 (UTC)

Yes Robert, misunderstanding must always come. Even when I was new to Wikipedia, only God knows how I was ignorant to people's ideas. Infact I would do as advised in good faith, but it won't clearly define what the editor is asking of me. The better way is to help in whichever way we could. For example I would barely decline a draft because it is promotional, when I know that my "small experienced editing" could take it to mainspace. Thank you for reminding us about this very thing some of us have forgotten or ignored in the name of "we must always go down for a newbie". We can't hide the truth that everybody deserves explanation, we often see our words [reviwers] twisted everyday. People don't know that reviewers sacrifice alot and others wouldn't care for a reviewer rather a new editor's wish to either quit or continue editing WP. No matter what goes on, love and kindness are always helpful to all. Safari Scribe^{Edits! Talk!} 05:52, 28 November 2024 (UTC)

Active sock alert

Please do not continue to create redirects for mass anime and comic/graphic novel redirect requests. These are all being requested by banned user Wikipedia:Sockpuppet investigations/TotalTruthTeller24 and should be reported at Wikipedia:Sockpuppet investigations/TotalTruthTeller24 .-- Ponyo^{bons mots} 18:43, 29 November 2024 (UTC)

@SafariScribe:, please be aware of this pattern. You have proxy created hundreds of these redirects over the last couple of days.-- Ponyo^{bons mots} 18:49, 29 November 2024 (UTC)

Ok, thanks. I only accept plausible redirects. Safari Scribe^{Edits! Talk!} 03:10, 30 November 2024 (UTC)

Ok. I accept non-anime and non-comic/graphic novel and disambiguation redirect requests, and i only accept plausible redirects. Thanks. Ampil ^{(Ταικ • Cοnτribυτιοns)} 03:20, 30 November 2024 (UTC)

Frankly I'm pretty pissed at myself. I know their patterns and habits, yet I was oblivious from what was right before my eyes. Hey man im josh (talk) 19:21, 30 November 2024 (UTC)

Etiquette

Hi. I'm an occasional AfC reviewer myself (too occasional—I keep losing access!), but not at the moment, and in any case it would still be an ethical conundrum. Viz, can I move a restored G13 draft (that I requested) into articlespace or should it be reviewed at AfC first? I assume so, to maintain proprieties, but it's never arisen for me before (and admittedly may not again!). Cheers, SerialNumber54129 17:29, 30 November 2024 (UTC)

The only time you need to go through AfC is if you have a conflict of interest (or if you aren't autoconfirmed). Otherwise you're free to skip the extra review and move it to mainspace yourself. C F A 17:41, 30 November 2024 (UTC)

If it were a draft you wrote, I'd say make sure to move it rather than approving it with the helper script. In general one should not use the helper script on one's own drafts.

For a g13 that you are rescuing, I don't see any conflicts of interest here. You are simply using your experience to decide that someone else's draft is worth rescuing.

You are a new pages patroller, so as long as that perm doesn't expire, you will remain an AFC reviewer. The two are linked. –Novem Linguae (talk) 19:14, 30 November 2024 (UTC)

Thanks CFA and thanks Novem Linguae; I'll move it now. Novem, re. the NPP, I see what you mean, but I assumed the AfC was different because I used to see the AFC script in the twinkle drop down tab, but it's not there anymore? SerialNumber54129 19:17, 30 November 2024 (UTC)

I think the AFC script link is in the "More" menu (Vector 2010) or "Tools" menu (Vector 2022) rather than the Twinkle menu. It also requires that the "AFC Helper Script" be turned on in Special:Preferences -> Gadgets. Hope that helps :) –Novem Linguae (talk) 19:53, 30 November 2024 (UTC)

It wasn't activated in preferences... *facepalm* In fact, nothing was. Except of course the 'Rollback confirmation' which hardly ever seems to work!  :) Thanks for the help, yes! SerialNumber54129 20:09, 30 November 2024 (UTC)

Third Opinion on Draft: Revival (Zach Bryan song)

I am requesting a third opinion (not a yThird Opinion} on Draft: Revival (Zach Bryan song). A reviewer has said that it should either be redirected to Elisabeth (Zach Bryan album) or merged to it. My opinion is that it should either be declined or accepted. I disagree with redirection because the redirect already exists. It seems that some reviewers don't notikl,ce the Warning at the bottom of the yellow Review Waiting panel. I disagree with merging because, in looking at the album article, I see that there is no detailed information about songs, so that merging would change the format of the album article. Can someone please review this draft, with regard to whether it should be accepted as a standalone article on the song? Robert McClenon (talk) 07:00, 1 December 2024 (UTC)

I have gone ahead and accepted the draft. Safari Scribe^{Edits! Talk!} 09:24, 1 December 2024 (UTC)

Thank you, User:SafariScribe - I thought that it might pass musical notability, but thought that another opinion was in order after what looked like a well-meant but mistaken comment. Robert McClenon (talk) 05:43, 2 December 2024 (UTC)

Warning That Title Already Exists

The above section is an example of something I sometimes see, which is that a draft is being reviewed, and the title of the draft already exists in article space, and there is a previous review that apparently indicates that the reviewer didn't pay attention to the Warning in the bottom of the yellow Review Waiting panel. For instance, an article may already exist, but the reviewer may have declined the draft for notability, rather than as 'exists'. These reviews in which the reviewer appears not to have seen the warning have one of two explanations. Either the reviewers don't notice the Warning, in which case maybe our instructions for reviewers should say that if there is a warning, look at what it says, or perhaps some reviewers don't get that warning. Is there a skin problem, so that some skins display the warning in extra-small text that can be ignored, or is there a stupid option that suppresses display of the warning? Does one of the script experts know whether there is a reason why some reviewers don't see the warning? Robert McClenon (talk) 07:00, 1 December 2024 (UTC)

Template:AfC submission/tools seems to be working properly, and it's just transcluded into {{AfC submission/pending}}. I suspect those who do not notice a pending draft is a duplicate do not look at the bottom of the submission template. I could always make it bigger and louder, but I tried doing that with Category:AfC submissions declined as copyright violations and it doesn't work half the time either. Primefac (talk) 23:23, 1 December 2024 (UTC)

Master log?

Is there a log of AfC-everything – submissions regardless of whether they've been reviewed or are pending, reviews regardless of the outcome and the reviewer, the whole shooting match? And if so, is this log searchable, if I wanted to know, say, whether anyone has submitted a draft with a particular word in the title (or better yet, title or content)? -- DoubleGrazing (talk) 13:43, 2 December 2024 (UTC)

The short answer is, as far as I am aware, no. We have categories for every page submitted that is still undeleted (part of the reason why we put AFC tags on the talk pages) and we have {{AfC statistics}}, but nothing like a database report of everything. Primefac (talk) 15:15, 2 December 2024 (UTC)

I believe @The Earwig's bot (which updates the {{AfC statistics}}) maintains a (private?) database on toolforge which has more details than what is saved to the template, though even that may not contain everything. – SD0001 (talk) 20:03, 2 December 2024 (UTC)

No but you can use the categories as Primefac says such as searching incategory:Pending_AfC_submissions, incategory:Declined_AfC_submissions or incategory:Draft_AfC_submissions in the draft and user spaces but that wont show you the deleted or accepted. While the Accepted articles talk pages are mainly in Category:Accepted AfC submissions I'm not aware of any "talkpageincategory:" search facility so it does not help. You can also search all three cats with insource:/\{\{AfC submission\, but since that is most drafts often just searching draft space is easier as it also won;t catch the oddities such as {{AfC_submission}} with an underscore. KylieTastic (talk) 15:47, 2 December 2024 (UTC)

Could also use Petscan to combine cats and title searches in various namespaces. Primefac (talk) 16:52, 2 December 2024 (UTC)

While there's no "talkpageincategory:", there does exist "inproject:", added 11 days ago (phab:T378868). – SD0001 (talk) 20:11, 2 December 2024 (UTC)

oh! nice! Good work SD0001 KylieTastic (talk) 20:14, 2 December 2024 (UTC)

On the hunt for socks? If the "content" you're looking for is an unusual URL, https://spamcheck.toolforge.org/ will do you. -- asilvering (talk) 22:28, 2 December 2024 (UTC)

If you ask a more specific question, we can probably craft a WP:QUERY for you. For example, "any page currently in draftspace containing the word Bob". –Novem Linguae (talk) 23:12, 2 December 2024 (UTC)

Draft:Razorpay

I need some help with this review. I'm having a hard time establishing whether the sources make this subject notable. TheTechie@enwiki (she/they | talk) 04:24, 3 December 2024 (UTC)

@TheTechie  Declined, with a full rationale. Some might, but I sample checked a significant number and each, chosen as randomly as I was able, failed as a reference.

Good call asking for other eyes. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 05:55, 5 December 2024 (UTC)

Help desk new question page

I often see the same editor asking multiple questions @ the help desk and they are often told not too by others, sometimes in a bitty way. I wondered why so may did this and I think the reason is the userpage decline template links to Wikipedia:WikiProject Articles for creation/Help desk/New question with the draft title filled in but it seems non-obvious, for new editors, how to get from this page to the help desk without posting a new question. Should we add a something like "If you have already asked a question about this draft recently please continue that discussion at the help desk here" to the top? KylieTastic (talk) 14:49, 3 December 2024 (UTC)

Ah, that could indeed explain this. (I always assumed it was because users didn't realise it's a threaded forum, and not a chat stream etc.) That seems a good suggestion; worth a try.

And one of my new year's resolutions will be to make an effort to be less "bitty" to those opening multiple threads, now that I know why they do it. -- DoubleGrazing (talk) 15:02, 3 December 2024 (UTC)

I'm not sure I fully understand what's happening here, could someone provide a diff/example of this happening? Primefac (talk) 20:19, 3 December 2024 (UTC)

Some editors keep opening new questions on the help desk rather than continuing with one that's ongoing, often one after another. So I'm proposing that these may be the editor coming back to the help desk from the link on the decline on the users talk page. That goes to a page like this and I'm saying that it encourages asking a new question everytime and many would not see or understand using the breadcrumb link to the help desk at the top. KylieTastic (talk) 09:45, 5 December 2024 (UTC)

Why don't we adopt the pragmatic solution of not worrying, and answering questions as they arise, but tidying up sweetly prior to answering?

Unless, of course, someone writes a gadget so we can highlight threads to merge, and we do that? 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 09:52, 5 December 2024 (UTC)

I have ignored for years but after seeing it again a couple of times recently I engaged brain to wonder why it was happening. Updating the gadget to work out if there is an active question is a nice ideal solution but too much work for the problem. Is it not better to tell editors they can continue a discussion rather than open a new question rather than give give them an interface that encourages it then tell them they are wrong. Just adding a simple explanatory sentence and link seemed like a quick, simple easy solution..... KylieTastic (talk) 10:13, 5 December 2024 (UTC)

Ah, I see, something like this. I see two (maybe three) options here. First, we change nothing and politely merge/combine duplicate sections. Second, we make the decline link a direct link to the HD and hope that editors use the "Ask a new question" link at the top if they have a question (which, if I recall, did not work, and the whole reason we have the script in the first place). Third, we could add an additional line as proposed, saying that existing questions will be answered without a new question not needing to be filed. Primefac (talk) 13:13, 5 December 2024 (UTC)

Yes that is the sort of thing that happens most, but I failed to find a diff for one of the cases of more than 2 or the sometimes bitty remarks not do do it. Not that I hang about the HelpDesk much. On the current page GwnftLight and Sukdev Mahapatra also had two back to back posts. KylieTastic (talk) 13:23, 5 December 2024 (UTC)

I added a variant of that text to the top - feel free to copyedit. – SD0001 (talk) 13:45, 7 December 2024 (UTC)

Oops. It seems the script replaces it altogether. Will need a script update as well. – SD0001 (talk) 13:47, 7 December 2024 (UTC)

 Fixed – SD0001 (talk) 15:33, 7 December 2024 (UTC)

Thanks SD0001 KylieTastic (talk) 15:35, 7 December 2024 (UTC)

J-1 visa vs J-1 visa

I declined Draft:Internship_and_Trainee_J-1_Visa_Programs as a duplicate of J-1 visa, however, on my Talk page the editor is (I think) indicating they are different topics and I should re-review the draft. To be honest, I don't entirely understand. Given my lack of understanding, would someone else mind taking a second look at both the editor's comment to me and the draft and, if appropriate, remedying any error I've made? I may be missing something. Thanks. Chetsford (talk) 15:49, 3 December 2024 (UTC)

It looks like this might be one of the subcategories of the J-1 visa? Primefac (talk) 20:21, 3 December 2024 (UTC)

Yeah, I was going to say the same. Mind you, it's been years since I've dealt with any US visa issues, so could be some newfangled stuff I don't know about. In any case, don't see why different flavours of J-1 (or even J-class) would require separate articles? -- DoubleGrazing (talk) 20:40, 3 December 2024 (UTC)

The draft does get rather far into the weeds of the specifics of that visa type. The article is pretty long as it is, though, so a full merge might not make sense. Primefac (talk) 20:42, 3 December 2024 (UTC)

Draft:Barron Trump

I am reviewing Draft:Barron Trump, and I have two mostly unrelated questions. The first is about reviewing a draft when the title in article space is a locked redirect. This is a question that I have asked before, but the answer has not always been entirely clear, and I would rather ask again than not ask and make a mistake. The title is a locked redirect because there was a previous AFD (the third AFD) and the consensus was to redirect and salt. Am I correct that I should compare the draft against the deleted version in the history, and consider whether there has been enough of a change so that it is reasonable to consider making a request to Requests for Unprotection? If so, my thought at this time is that it is not much of a change, and the submitter has not met the burden of overcoming the consensus of the AFD, but I will review it one more time. Are there any particular rules that I should follow when reviewing a draft where the title is a locked redirect due to an AFD? Robert McClenon (talk) 20:42, 3 December 2024 (UTC)

Short answer: yes. If the draft isn't significantly different, then it's not worth accepting. Primefac (talk) 20:46, 3 December 2024 (UTC)

I declined the draft. This is a case of notability is not inherited. Robert McClenon (talk) 05:17, 4 December 2024 (UTC)

Mostly Constructive Edit with Vandalism

The second question has to do with one of the edits to the draft. The edit appears to have been mostly constructive, but it introduced sneaky vandalism to an item in the infobox. I have reverted the vandalism and warned the editor. Should I be satisfied with assuming that the other edits were constructive, or should I revert the entire edit? I would have reverted the entire edit, except that there had been a subsequent edit that appeared to be constructive. What should be done if one discovers that an edit was mostly constructive but made a destructive change? Robert McClenon (talk) 20:42, 3 December 2024 (UTC)

If there's a mix, and it's not obvious what was good and what was bad, I'll revert the whole thing. That's just my philosophy, but I'm not going to untangle a complex edit if "vandalism" is part of it. Primefac (talk) 20:46, 3 December 2024 (UTC)

Yes. The only reason that I didn't revert the whole thing is that there had been another edit after it. It now appears that the change may have been a sloppy error rather than vandalism. The editor changed the height of the subject from 2 m to 2 cm. 2 m is 6 ft 7 in, which is what the subject's height has been reported as. The two possible explanations are both implausible, either that it was sneaky vandalism or that it was an error, so assume good faith applies. So I think that the draft is now correct. If the subject becomes individually notable in the future, his height is likely to be 201 cm or 202 cm. Robert McClenon (talk) 05:15, 4 December 2024 (UTC)

drafts are too long

Please see discussion: link. -- Gryllida (talk, e-mail) 00:58, 9 December 2024 (UTC)