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

~6 weeks

1,254 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.

• Top of page
• Table of Contents
• Bottom of page

AFC backlog

AfC unreviewed draft statistics as of November 18, 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)

Acceptance of Gerard Gertoux

I have an increasing feeling that this draft ought to have not been accepted, and yet I viewed it as having a better than 50% chance of survival. It may be that it is edited drastically by the community. I will not quarrel with AfD. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 16:11, 29 October 2024 (UTC)

No complaints from me, clearly this was thought about and it has multiple eyes on it now. Alpha3031 (t • c) 16:25, 29 October 2024 (UTC)

That was my intention, and I think it will have sufficient attention now. I hadn't realised there were pro and anti Gertoux factions. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 17:19, 30 October 2024 (UTC)

After much investigation and not a little editing of the accepted article I have concluded that my acceptance was in error. I have set out my rationale at Wikipedia:Articles for deletion/Gerard Gertoux and invite opinions to keep or to delete. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 16:38, 8 November 2024 (UTC)

Rarely have I seen an AfD so heavily and bizarrely defended by a creating editor! It's very hard to tell what the eventual consensus will be. I don't really care either way, though, 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 11:26, 10 November 2024 (UTC)

N Deleted at AfD. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 12:52, 16 November 2024 (UTC)

Rechecking User:SafariScribe's reviews

• SafariScribe (t · c · reviews)

Too many of User:SafariScribe's recent reviews were problematic (mainly the declines, but also accepts). This is documented at User talk:SafariScribe#List of Indian state fishes. A user whose draft was rejected then also reached out to me on my user talk page, User talk:Fram#@Fram taking up the battle vs SafariScribe. For new reviews I would propose to first see if things have improved, and not take any action now: but it would be nice if people found the time to check a number of their reviews and overturn them if necessary. Fram (talk) 15:39, 31 October 2024 (UTC)

As a technical/procedural note, SafariScribe is an NPR so they automatically have access to AFCH through that. Primefac (talk) 15:45, 31 October 2024 (UTC)

I would note that they are not autopatrolled so all their accepts are re-checked by NPP anyway. Running some quick checks and out of 1172 accepts: 62 (5.3%) have been deleted (and a spot check found many were as the submitter was found to be block evading); 152 are redirects (but my code does not show how many were accepted as a redirect vs how many redirect after); 12 (1%) currently tagged for notability; 13 (1%) tagged for multiple issues. So certainly for someone who I know works on the older submissions including those in the grey areas of notability the stats for accepts don't look out of sorts.

I agree I did not like the acceptance of List of Indian state fishes but the discussion at least shows it was not the failure to check the sources but working on the idea that sources do exist. Personally I don't like that reasoning and think if you are aware of them add them, but to be fair to SafariScribe I have come across autopatrolled editors creating articles in mainspace will zero reliable sources just using the "sources exist" excuse when challenged, and also AfD discussion that end in keep because "sources exist" but none added to the article. I don't have a quick way to sanity check declines. KylieTastic (talk) 17:27, 31 October 2024 (UTC)

It's the declines I'm more worried about, for biteyness reasons. I noticed a few weird ones from SafariScribe some time ago, but satisfied myself that they'd gotten more accurate and more helpful with responding to questions from submitters. I don't think I have much time in the next couple of days to check on any of these declines myself. -- asilvering (talk) 18:56, 31 October 2024 (UTC)

I would note that they are not autopatrolled so all their accepts are re-checked by NPP anyway. NPPs can mark their own AFC accepts as reviewed. The software only prevents their own page creations from being marked as reviewed by themselves. I haven't checked if the editor in question here is also marking their own accepts as patrolled, which is normally allowed, or if they're leaving them for other reviewers. Someone might want to check that. –Novem Linguae (talk) 02:06, 1 November 2024 (UTC)

I checked a random five of their recent accepts, and they hadn't marked any as patrolled. (I agree that it wouldn't have been wrong for them to do so – it's just worth knowing for this discussion.) jlwoodwa (talk) 02:58, 1 November 2024 (UTC)

I had actually done some spot checks already and I had already seen enough of how they worked in the past to not consider it a concern - sorry I should have mentioned. Some of their review choices may be wrong and should be challenged, but from what I have observed I believe they have been acting in good faith and they are not a bad-actor. Probably slowing somewhat would be help. Also although it's good to see the very old submissions being cleared it should not take precedence over correctness, it is fine and preferable to leave a review if your not sure. KylieTastic (talk) 09:56, 1 November 2024 (UTC)

I don't think anyone has suggested that SafariScribe is doing anything other than acting in good faith, to be clear. -- asilvering (talk) 10:03, 2 November 2024 (UTC)

I also checked yesterday half a dozen (mix of acceptances and declines; avoiding ones I had previously reviewed myself) and didn't find any issues with them. (One acceptance was a bit borderline, maybe, but no more than that.) The acceptances were already patrolled, not by SafariScribe but by uninvolved reviewers. Granted, this wasn't a large sample, esp. given how much SafariScribe gets through, and had I found problems I was prepared to keep going, but I didn't. -- DoubleGrazing (talk) 11:47, 1 November 2024 (UTC)

There are times when I've found declines from SafariScribe that I disagree with, but there's always a rationale for it and it's almost never an unwarranted "reject", which is something that would be more pressing. Declined articles ideally lead to specific improvements and from there we have better articles that can be accepted; SafariScribe is contributing to the health of the system IMO. Replying here because I concur with the last sentence ("given how much SafariScribe gets through" in particular); what I see is a fraction of what gets processed. Reconrabbit 18:16, 1 November 2024 (UTC)

SafariScribe is not autopatrolled, but they are marking their AfC accepts as patrolled. Checking the patrol log this morning, every patrol appears to be an AfC draft they accepted (e.g., Jan Koneffke, Jonathan Abrams (writer), Where's Wanda?, 3D Gaussian splatting, Zdzisław Goliński, and Paul Atanga Nji). Significa liberdade (she/her) (talk) 14:13, 2 November 2024 (UTC)

That log shows they appear to be marking the drafts as patrolled not the accepted articles. I thought when an article was moved to main-space it reset that flag is you weren't autopatrolled. KylieTastic (talk) 14:50, 2 November 2024 (UTC)

I thought so too, but apparently not? jlwoodwa (talk) 17:11, 2 November 2024 (UTC)

In Page Curator, all those appear patrolled by SafariScribe. Significa liberdade (she/her) (talk) 18:05, 2 November 2024 (UTC)

Jumping back in to add that SafariScribe marked Mary Robertson as reviewed. Given that this particular article has been a sore spot in this very discussion, I found it worth mentioning. I have unmarked it. Significa liberdade (she/her) (talk) 14:49, 4 November 2024 (UTC)

I don't really want to be piling on, and I've not done any review of other accepts so this is going to be unbalanced, but XW10508 seemed a little concerning. I've tagged it for now, but I don't think the refs are any good? Alpha3031 (t • c) 06:00, 3 November 2024 (UTC)

@Alpha3031 I don't like it either, but I'm not a WP:MEDRS expert. I've unreviewed it (it was reviewed by another NPPer) for now. -- asilvering (talk) 14:52, 3 November 2024 (UTC)

MEDRS aside, this has zero sources that count towards the GNG. I have PRODed it. Toadspike [Talk] 15:27, 3 November 2024 (UTC)

SafariScribe has been contributing to AfC for months, and he has done many AfCs. Thus, I have only seen a small fraction of his work. However, I cannot recall stumbling across AfCs in which I could see how he demonstrated a severe lack of competence; I must admit though that I have only looked into AfC declines. User:Fram, could you do us a favour and give us a list of, say, 10 recent drafts SafariScribe accepted/declined/rejected to support your "statement" (I don't want to use the word allegation) that Too many of User:SafariScribe's recent reviews were problematic? This would help getting a better understanding of the situation. Best, --Johannes (Talk) (Contribs) (Articles) 19:09, 1 November 2024 (UTC)

The discussion listed at the top has 7 examples (from one day this week), and another editor has listed 2 science articles they shouldn´t have accepted. Fram (talk) 20:09, 1 November 2024 (UTC)

If the recommendation is to slow down at AfC, I think we should look into making the same recommendation against fairly rapid relisting of discussions [1] and some questionable AfD closes (nominating an article they accepted at AfC for deletion, closing withdrawn nomination (imo a minor oversight), closing discussion they !voted in. The rest of their AfD closes look okay though; maybe these were just one-off learning moments. Toadspike [Talk] 22:13, 1 November 2024 (UTC)

AfC spot check: I have checked seven reviews, randomly choosing to do so from timestamp 2024-10-27T12:00:04Z onwards.

1. Alstom Citadis 100 is a good accept.
2. Draft:Harry Paulo is a questionable decline, as my limited access to the BNA shows that the subject might meet the GNG (see source 3, for instance) and probably meets WP:NACTOR #1, based on the reviews cited.
3. Draft:George Oliver Scott is a good decline.
4. Draft:Jeffrey Yoo Warren is a good decline based on the state of the draft, though a quick search shows that the subject is likely notable [2][3][4][5].
5. Draft:Moe Dimanche is a good decline.
6. Upsweep is a good accept, which I have now marked as patrolled (NPP).
7. Draft:Jake Van Tubbergen is probably a bad decline – the sources are probably enough to meet the GNG [6][7][8], and I haven't even checked all of them (some local news sites are blocked in Europe, probably GDPR stuff).

Considering this is a random sample, I am surprised by the number of reviews I disagree with (2/7 = 29%). However, haven't reviewed at AfC in a hot sec and might be rusty, so I'd appreciate if someone checked my work. All the disagreements could've been averted by more thorough source-checking on the part of SafariScribe, which seems to be the main/only issue here. Toadspike [Talk] 22:53, 1 November 2024 (UTC)

@Toadspike, agree on #7, so I've resubmitted and accepted it. #2 probably also fine but I'll leave that for someone who can check the refs. -- asilvering (talk) 16:10, 2 November 2024 (UTC)

Examples of other recent declines which seem problematic to me (showing the state of the article at the time of the decline):

• [9]
• [10]
• [11]
• [12]
• [13]

These 5 declines were all on the same day, within 32 minutes. Fram (talk) 10:03, 2 November 2024 (UTC)

• Draft:Pierre de Wet: Declined as v/bio; the draft cites 5 sources out of which one (Literator, FN 3) seems to be a quite good one; however, FN 1 and 4 are bare links, FN 5 refers to a diagram/JPEG file; FN 2 refers to Beeld. This "sourcing" situation indicates that rather than looking into the sources, the footnotes were "slapped" onto the draft's sentences. A quick comparision of the source referred to in FN 3 and the draft shows that the source was not sufficiently read. While there may be notability, the draft clearly doesn't demonstrate any in accordance with WP:NFILMMAKER.
• Draft:Eve Bernhardt: Declined as v; the draft cites three tabloid newspapers, and glamourgirlsofthesilverscreen.com. While this sourcing isn't awful, there is room for improvement. What is not okay, however, is that 50 per cent of the draft is based on hearsay due to a lack of references to any sources at all.
• Draft:Anna Lundberg: Declined as v/bio; the draft cites Metro, Express, Instagram, and Facebook, (i.e., generally unreliable sources) which make up 30 per cent of the footnotes (and I can spot 4 duplicate Footnotes by just glimpsing). I didn't check all the sources, but my 6-link sample makes me presume that the cited sources are non-notability indicating, tabloid-media like ones that either don't mention the subject, or simply mention her without discussing her.
• Draft:Sayali Salunkhe: Declined as v; the draft has 8 footnotes with references to four sources (TOI, IANS, ITAA, and Sony LIV). IANS hosts a press release, Sony LIV is a primary source, and ITAA is also a primary source. This leaves us with a single source. Large sections of this BLP are unsourced.
• Carla Guevara Laforteza: Declined as lacking sources in the Filmography and "Notable stage credits" sections. None of the sections had any references to any sources, and were subsequently shrunk due to a lack of sources (Special:Diff/1253541304/1254926670).

Fram, I must admit I fail to understand how these declines "seem problematic". Is there something I have not seen? Best, --Johannes (Talk) (Contribs) (Articles) 14:18, 2 November 2024 (UTC)

Draft:Pierre de Wet has four good sources, not one, and one (the diagram) which contains good sources, which the editor probably didn't know how to source directly. You claim "A quick comparision of the source referred to in FN 3 and the draft shows that the source was not sufficiently read.", but ref is purely used to reference "was a filmmaker in South Africa.", where the source says "Pierre de Wet is often referred to as ‘the father of the Afrikaans film industry’", which not only verifies the referenced claim, but also makes it again clear that he is really, truly notable (not that there "may" be notability). That some sources are bare links or an offline source does not in any way support your claim that the footnotes were slapped on or not sufficiently read (at least not by the creator), e.g. source 4[14] directly supports the claim made.

Draft:Eve Bernhardt: you are aware that a tabloid "format" doesn't necessarily mean tabloid "contents" surely? I have no idea why you so rudely dismiss Classic Images, which seems a perfectly legitimate (and notability-indicating) source for this type of article. It is good enough for GAs like Frank Sinatra, The Godfather or Ben-Hur (1959 film).

Draft:Anna Lundberg: are you serious? It also uses The Observer, RadioTimes, BBC, Channel4, Independent, ... We have an article purely about her from People[15], which is listed as reliable in WP:RSPN. But the decline has a big tag stating "This submission's references do not show that the subject qualifies for a Wikipedia article—that is, they do not show significant coverage (not just passing mentions) about the subject in published, reliable, secondary sources that are independent of the subject". This is just plain wrong.

Draft:Sayali Salunkhe doesn't have "one source", it has four different articles from one newspaper. And the awards source may be primary, but it is independent and an indication of notability.

Carla Guevara Laforteza: an unsourced filmography section for an otherwise adequately sourced article about a clearly notable person should never be a reason to decline a draft, it is putting way higher requirements on drafts than on other articles (no article would be draftified in the state this one was in). Accept the draft, put "refs needed" on these sections, and you have actually a decent new article and a happy new editor. Fram (talk) 15:41, 2 November 2024 (UTC)

This is why I never use AfC if I can help it. The vast majority of reviewers are terrible at reviewing and practically none follow WP:AFCPURPOSE (especially its last sentence). That entire section should honestly be scrapped if it's not going to actually be used. The section below it, WP:AFCSTANDARDS, is also pretty great, because I've seen so many of those listed non-appropriate decline reasons used as decline reasons. Heck, you just brought up the bare urls one yourself that Johannes Maximilian just erroneously used. Silverseren^C 16:07, 2 November 2024 (UTC)

@Silver seren, can I convince you to become a reviewer yourself? Even if it's just to occasionally resubmit-and-accept any problematic reviews you come across, it would be a huge help. I originally joined up to help fish out the occasional obvious pass from the backlog, myself. -- asilvering (talk) 16:21, 2 November 2024 (UTC)

I was actually planning to do so in the future (though after the end of the year, since I'm currently locked in to #1week1woman until then and it takes up the majority of my wiki time). Silverseren^C 16:34, 2 November 2024 (UTC)

I've added you to the list so that you can go ahead and give it a go if you happen to bump into something that needs mainspacing between now and then. No worries if you don't. -- asilvering (talk) 17:39, 2 November 2024 (UTC)

@Johannes Maximilian, I would agree with Fram that the first two and the last of these are problematic declines simply by reading your descriptions of them. Please try only to decline articles that would be extremely likely to be deleted at AfD, or which have problems that can't easily be fixed by normal editing. We can't expect perfection of new editors. For the other two, it sounds to me (again without looking carefully at the drafts myself) that, if declined, substantial comments should have been given so that the submitter could understand what to improve. -- asilvering (talk) 16:02, 2 November 2024 (UTC)

I would point out that Draft:Eve Bernhardt was a main-space creation that was draftified and submitted with no change so SafariScribe was just agreeing with the Broc. I must admit what always annoys me with these types of discussion is when people berate others for not accepting an article(s) then leave them languishing in draft. Anyone who reviews a draft enough to criticise another for not accepting should take the simple action to submit/accept or just move to main-space. However, as Draft:Eve Bernhardt was created in 2024 by Samuelrclaesson a sock of Dbzsamuele blocked in 2007 so I've G5ed it. KylieTastic (talk) 18:12, 2 November 2024 (UTC)

Which I have now disputed. G5 is a trash deletion policy and I have a low opinion of its use in any case that isn't connected to actual issues with the article itself. Because we're here to build an encyclopedia and G5's purpose is to harm the encyclopedia to "punish" someone who's banned, not to actually defend and improve said encyclopedia. If banned editors could actually manage to quietly make a new account and just make good articles and stop whatever behavior and actions that got them banned in the first place, then we'd all be better off for it. And this draft seems quite in my wheelhouse of what I work on. Silverseren^C 18:19, 2 November 2024 (UTC)

I actually agree and I wish/hope that your "I take responsibility" is taken as a valid argument as there have been quite a few articles I have worked on and fully checked that then got G5ed. Ideally I would like to see G5 changed to allow such challenges officially. At the moment G5 is used as punitive against the blocked editor rather than consider the value of the article or others input. If your challenge works I would definitely use myself. Another new article in main-space is always the goal.... I watch with interest. KylieTastic (talk) 18:31, 2 November 2024 (UTC)

If worked on includes substantial edits, then WP:G5 didn't apply. jlwoodwa (talk) 19:26, 2 November 2024 (UTC)

@KylieTastic if this happens to you, query it with the deleting admin, and if necessary take them to WP:DRV. That's absolutely not supposed to happen. @Silver seren, thanks for fixing that one up. I will say that in my experience G5 is not at all about punishment and is very much about defending the encyclopedia - the sockpuppet deletions I've done are usually editors who were initially blocked for things like UPE, source fabrication, etc, so G5 allows us to clean that up without wasting everyone's time. -- asilvering (talk) 14:57, 3 November 2024 (UTC)

I agree that giving submitters advice on what and how to improve is generally a good thing to do. I also reckon that giving submitters this advice is more important than working on new AfCs, especially if submitters ask for help. However, it must be said that giving this advice may be a tedious, time-consuming, yet fruitless process. AfC reviewers must learn to deal with this. --Johannes (Talk) (Contribs) (Articles) 19:47, 2 November 2024 (UTC)

Looking at some declined reviews from today (November 2):

1. Draft:Yielziey: good decline -- no footnotes, mostly links to primary sources (e.g., Spotify)
2. Draft:Assin Godstime: good decline, but weird comment to the editor: "Can we agree to accepting this, and subsequently to WP:AFD, if you think the reviewers aren't helping you". The page has been declined multiple times for failing NAUTHOR. It would likely be beneficial to have a more detailed explanation of what they must do to fix the article.
3. Draft:Michae E Burns: good decline
4. Draft:Party Bots: good decline
5. Draft:Dubdee GD: declined, but I would have marked as reject and CSD.

Significa liberdade (she/her) (talk) 14:39, 2 November 2024 (UTC)

Can we agree to accepting this, and subsequently to WP:AFD is exactly what got SafariScribe in trouble a month and a half ago at WP:Articles_for_deletion/Preston_Corbell_(2nd_nomination), which I linked above. I'm surprised to see SafariScribe still suggesting this weird process to appease AfC submitters, after being clearly told off for it. Toadspike [Talk] 20:05, 2 November 2024 (UTC)

Yup. It is a strategy that has come up several times over the last decade I've been doing this and has always got mostly negative feedback. I think there is possible merit in having a way submitters can ask for a full AfD consensus review rather than an AfC review, but it seems clear consensus is that AfC reviewers should not be suggesting this. KylieTastic (talk) 20:37, 2 November 2024 (UTC)

I think in most cases, the best process for this would likely be to inform the editor they can move the draft to the main space themselves, though it may be nominated for deletion. This applies to most editors. Significa liberdade (she/her) (talk) 21:18, 2 November 2024 (UTC)

Mary Robertson... I raised issue on this accept. Tried to discuss with this user but he never responded. I draftified the article ... they came back moved it on main space and and an IP from Italy started cleaning up. I am smelling UPE now. Hitro talk

Hi @HitroMilanese:, sorry if I chime in, I just wanted to point out that I do not personally know Mary Robertson and I have most certainly not been asked (let alone paid) to write this page. Her Psychiatry at a Glance was one of my textbooks at university and I simply enjoy her work. Since she was a professor at UCL and an expert on Tourette, I assumed she met Wikipedia's notability criteria, but of course I might be wrong. I wrote the draft a few hours ago and was surprised to discover it had already been published when I checked half am hour ago, I thought it would take weeks. Since more sources were required, I simply addeded them.87.4.47.249 (talk) 23:44, 3 November 2024 (UTC)

An emeritus prof at UCL is extremely likely to be notable. -- asilvering (talk) 23:57, 3 November 2024 (UTC)

Let us accept them because they are "An emeritus prof at UCL" and they are "extremely likely to be notable".... Hitro talk 00:36, 4 November 2024 (UTC)

@HitroMilanese, that had already been draftified once. You can't draftify it a second time. Please move it back. If you think it should not exist, nominate it at AfD. -- asilvering (talk) 00:58, 4 November 2024 (UTC)

@Asilvering

Let me check the policies and guidelines once more. Hitro talk 01:05, 4 November 2024 (UTC)

@HitroMilanese: See WP:DRAFTOBJECT. jlwoodwa (talk) 01:08, 4 November 2024 (UTC)

I raised COI/UPE issue, I guess WP:DRAFTOBJECT does not apply to my case. Does it? Hitro talk 01:21, 4 November 2024 (UTC)

Just like a disputed PROD, there are no exceptions other than the standard exception for rolling back vandalism, which does not apply here. This should only go back to draft as the result of an AfD. -- asilvering (talk) 01:24, 4 November 2024 (UTC)

WP:DRAFTOBJECT does say excluding editors with a conflict of interest, but my interpretation is that it wouldn't apply here anyway. jlwoodwa (talk) 01:27, 4 November 2024 (UTC)

Not unless Hiro wants to accuse SafariScribe of having a COI. Which, well, that wouldn't be my choice. -- asilvering (talk) 01:33, 4 November 2024 (UTC)

@Asilvering Can you accept this draft in current condition? Hitro talk 01:31, 4 November 2024 (UTC)

I'm not going to accept the draft. I'm asking you to revert your out-of-process draftification. -- asilvering (talk) 01:33, 4 November 2024 (UTC)

@Asilvering You can revert it. [[WP:BOLD|Be Bold]]. Hitro talk 01:38, 4 November 2024 (UTC)

I'm sure asilvering knows how to move pages. You are being encouraged to self-revert, which (as described at that link) is a way to show good faith after realizing that you've erred. jlwoodwa (talk) 01:43, 4 November 2024 (UTC)

@Jlwoodwa You concluded that I have erred. Does this draft belong to main space? Give me Yes or No answer. Hitro talk 01:48, 4 November 2024 (UTC)

That is irrelevant. Where it does not belong, at present, is draftspace, and it should not have been returned there. If you think it does not belong in mainspace either, you may nominate it for AfD. -- asilvering (talk) 01:49, 4 November 2024 (UTC)

That is what SafariScribe promotes. Deal at AfDs. Hitro talk 01:51, 4 November 2024 (UTC)

What SafariScribe did was "accept a draft and then immediately nominate it for deletion", which is discouraged because you should only accept drafts that you think belong in mainspace. What you should do is "revert your improper draftification", which does not mean you think it belongs in mainspace. jlwoodwa (talk) 02:00, 4 November 2024 (UTC)

@Asilvering You want me to revert? you want me to move this article at main space? Hitro talk 01:54, 4 November 2024 (UTC)

@HitroMilanese: You should have never moved the page back to the draft space given WP:DRAFTOBJECT. As such, you should move it back to main space to recognize your error. Significa liberdade (she/her) (talk) 01:56, 4 November 2024 (UTC)

I am accepting my error. I may have erred. Should I move this draft to main space? Even in this condition? Yes or No will suffice. Hitro talk 02:00, 4 November 2024 (UTC)

Yes. -- asilvering (talk) 02:03, 4 November 2024 (UTC)

Thank you. -- asilvering (talk) 02:10, 4 November 2024 (UTC)

I did. But bad decision with your admin hat on. Hitro talk 02:11, 4 November 2024 (UTC)

@HitroMilanese You broke the rules. Asilvering telling you to stop breaking the rules is hardly an unexpected outcome. Whatever happened to "Oh, sorry, I misunderstood when I could move something back to draftspace. I'll fix that, and open up a COI thread"?

...or we could play the "I'm a more experienced editor than you" card. Yeah, that'll help. GreenLipstickLesbian (talk) 02:19, 4 November 2024 (UTC)

It wasn't like that at all. Mistakes happen. Are you saying you're not prone to making errors? Anyone can make mistakes. I don’t understand what you’re trying to say. Asilvering can respond to me directly, Hitro talk 02:25, 4 November 2024 (UTC)

@GreenLipstickLesbian

Can you reformulate what you were trying to say so that I may understand and respond to you properly? Hitro talk 02:37, 4 November 2024 (UTC)

I very deliberately kept that hat off. -- asilvering (talk) 02:21, 4 November 2024 (UTC)

I feel you did not. Hitro talk 02:27, 4 November 2024 (UTC)

@Asilvering Technically, I don’t understand what you expect me to do. Do you want me to move this draft to back to the main space, even though I know it doesn’t belong there, especially considering that the reviewer is already under scrutiny? Hitro talk 01:45, 4 November 2024 (UTC)

Please see jlwoodwa's comment above. -- asilvering (talk) 01:47, 4 November 2024 (UTC)

@Asilvering Responded already. Hitro talk 01:48, 4 November 2024 (UTC)

If the editor has plausibly denied having a COI, then (unless WP:COIN finds otherwise) you should probably not assume that they have a COI. jlwoodwa (talk) 01:25, 4 November 2024 (UTC)

@Jlwoodwa The draft is waiting for review. Can you accept it in current condition? Hitro talk 01:32, 4 November 2024 (UTC)

No, HitroMilanese. Jlwoodwa should not accept the draft. You should move revert your inappropriate draftification. Significa liberdade (she/her) (talk) 02:02, 4 November 2024 (UTC)

@Significa liberdade I did. I don't understand how it helps the project. Hitro talk 02:09, 4 November 2024 (UTC)

HitroMilanese: We have specific guidelines and policies for a reason. Sometimes, you may disagree with a policy, but that doesn't mean you don't have to abide by them. Significa liberdade (she/her) (talk) 02:16, 4 November 2024 (UTC)

I know and respect guidelines that is why I survived here on Wikipedia for 18 years. 14 years before you made your first edit. Hitro talk 02:18, 4 November 2024 (UTC)

WP:DRAFTOBJECT Significa liberdade (she/her) (talk) 01:08, 4 November 2024 (UTC)

How did you land here? This was first time I discussing something here. I never pinged you. Hitro talk 01:02, 4 November 2024 (UTC)

Apologies for being a PITA, but WP:DRAFTOBJECT is part of an essay and is not a policy or a guideline, no matter how some people treat it. Redraftifying an article is perfectly acceptable in some cases, e.g. when a terrible article on a notable subject is put into the mainspace again by the creator without making an effort to make even the most basic improvements. Please stop treating it is a policy or even a guideline. Fram (talk) 08:06, 4 November 2024 (UTC)

It appears that I was coerced into moving the draft back to the main space by two inexperienced admins who were attempting to enforce an essay, mistakenly believing it to be policy or guideline. One of them called it an "out of process redraftification". @Asilvering that is why I said, "Bad decision with your admin hats on". Hitro talk 10:07, 4 November 2024 (UTC)

Holy cow, can we chill with the accusations? I am not an admin, but it is clear to me that civility (which is a policy) has flown out the window here. Toadspike [Talk] 10:11, 4 November 2024 (UTC)

I do not understand why you are pointing towards civility. However, I apologise if it came across as uncivil in any way. Hitro talk 10:32, 4 November 2024 (UTC)

Fram: Would you say redraftifying was an appropriate decision in the case at hand (Mary Robertson)? Significa liberdade (she/her) (talk) 14:43, 4 November 2024 (UTC)

Not for notability/sourcing/quality of writing, no (things could be improved of course, but clearly good enough for the mainspace). I have no opinion whether there was any evidence of COI, which might be a good enough reason to redraftify if so. Fram (talk) 14:55, 4 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)

Increased Archival rate at Redirects creation

The list of requests at Wikipedia:Articles for creation/Redirects is growing at an outstanding rate. While we all have done a job to never create a backlog there, the slow archival process has made it tough to go to the newer requests. I know that we can just use the End key, but is there a need to keep the requests for such a long time? I think the archival rate can be increased, changing it to 15 or 10 days. Thoughts? ~/Bunnypranav:<ping> 11:29, 1 November 2024 (UTC)

The archive period is 7 days, based on Special:Diff/1253421658; I don't really think that should be shortened. We could maybe do something similar to WP:BOTREQ and speed up the archival process if {{AfC-c}} is used on a request, shortening it to maybe 3 days (i.e. "immediate archiving"). Rcsprinter123 would be the one to ask about implementing that sort of change, though. Primefac (talk) 11:59, 1 November 2024 (UTC)

According to User talk:RscprinterBot#Task 8 frequency, it is on demand, I have posted a message about this there. ~/Bunnypranav:<ping> 12:08, 1 November 2024 (UTC)

Figured I was missing something. On-demand is fine by me, but I do agree not letting it get to 200+ threads is ideal. Primefac (talk) 12:18, 1 November 2024 (UTC)

Hi guys. The automatic threshold for a closed thread to be archived is 24 hours. I have been away during the week which is why threads built up on this occasion, but they are cleared with a single bot edit. Rcsprinter123 (discourse) 13:10, 2 November 2024 (UTC)

Thanks for that. Primefac (talk) 15:39, 3 November 2024 (UTC)

Submission

The following discussion is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.

---

Hi There! I Was Wondering Why @Theroadislong Declined My Submission On My First Article. Can You Explain Why? CharlieSimpson27112014 (talk) 22:32, 3 November 2024 (UTC)

Please ask at the AFC help desk. This page is for discussion about the operation of the AFC process. 331dot (talk) 22:58, 3 November 2024 (UTC)

Better yet, ask Theroadislong on their user talk page. 331dot (talk) 22:59, 3 November 2024 (UTC)

The discussion above is closed. Please do not modify it. Subsequent comments should be made on the appropriate discussion page. No further edits should be made to this discussion.

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)

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)

Propose Split

Please join the discussion at Template talk:Improper AfC redirect or category request#Propose Split? regarding splitting that template. Thanks, Myrealnamm (💬Let's talk · 📜My work) 20:51, 15 November 2024 (UTC)

Phantom!

Please will one of the more Sherlock Holmes folk amongst us find and sort out the phantom draft suggested to be in Category:Pending AfC submissions in userspace by Category:Pending AfC submissions? The latter suggests that one is present. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 18:10, 11 November 2024 (UTC)

I confirm I also see a phantom draft. qcne (talk) 18:20, 11 November 2024 (UTC)

From experience it is likely to be a stray hidden template related to AFC, or an AFC comment. It is unlikely to be particularly obvious. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 19:02, 11 November 2024 (UTC)

Was hoping this meant a Phantom of the Opera themed AfC when I saw the section header on my watchlist :P CaptainEek ^{Edits Ho Cap'n!}⚓ 19:04, 11 November 2024 (UTC)

Sing, my angel of music... --DoubleGrazing (talk) 19:17, 11 November 2024 (UTC)

I think it is more like Ruddigore 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 19:20, 11 November 2024 (UTC)

I think counting pages in categories is expensive, so the counts aren't always recalculated every time they change. I think they can become inaccurate. I think a WP:NULLEDIT to one of the pages currently in the category might force a recalculation, although I am not 100% sure. –Novem Linguae (talk) 19:29, 11 November 2024 (UTC)

I suspect it to be a real article causing the issue, potentially a user sandbox. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 22:33, 11 November 2024 (UTC)

Tried the null edit. No difference, I'm afraid. Nor with a real edit prior to review. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 10:13, 12 November 2024 (UTC)

This is a bug that has been around for a while, every now and then a category count goes wrong by 1 (or I've only ever seen if off by one). If you see this database query the count is set against the table not generated on demand. Looking at the code it appears that the category page that the purge calls the category refresh as long as the count is less than 5000. However, doing a purge does not fix the issue, so another bug somewhere. There does appear to be a maintenance function cleanupEmptyCategories.php that would fix. KylieTastic (talk) 13:13, 12 November 2024 (UTC)

ok not a bug in the refresh code but a problem with duff data. A query of category links returns page 78323717 at the moment, but page_id 78323717 is not in the pages table. So the purge/refresh counts the categorylinks which while this phantom record exists will always be +1. We can see the categorylink was updated 2024-11-09 T22:23:45, the page has no revisions in the 78323717 (so deleted), so I looked in archive (which I didn't realise we could see) and the page title was User:SeeznTvUZ/sandbox which was deleted by Rsjaffe 22:23, 9 November 2024. see this quarry for how I found this.

So it's a bug in the way categorylinks are managed, maybe it was a race-condition, but one possible way to fix would be to undelete (assuming it keeps the old page_id) then do a purge or remove the AfC submission and then re-delete. KylieTastic (talk) 14:00, 12 November 2024 (UTC)

Would someone with the necessary rights please try this?

@KylieTastic Somehow I knew it would be you who got the drains up on this. Awesome job. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 15:22, 12 November 2024 (UTC)

Yeah, we had this issue with the copyvios (G12) category for a while, especially since it was deletion-prone. I couldn't for the life of me remember the cause, so thanks to Kylie. I'll take a look and see if I can sort out some un/re/deletions to clear things up. Primefac (talk) 17:03, 12 November 2024 (UTC)

Whiiiich is now  Done. Primefac (talk) 17:05, 12 November 2024 (UTC)

"Who ya gonna call? Ghostbusters!!" 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 17:11, 12 November 2024 (UTC)

I got nerd sniped and spent a couple hours on this today. I couldn't reproduce this, but discovered there's an extension called mw:Extension:CategoryTree that is involved, and the code that generates the category counts is in the PHP back end of this extension. @KylieTastic, may want to consider filing a bug report and tagging it CategoryTree. –Novem Linguae (talk) 23:49, 16 November 2024 (UTC)

Had to look that one up as it was new to me. Why do you think that is involved as it appears to just be a viewer and has no way to effect the data stored in categorylinks as far as I can see? As the extension page says: "extension provides a dynamic view" like this for the Category:Pending AfC submissions sub cats. KylieTastic (talk) 11:15, 17 November 2024 (UTC)

If that extension is not installed, the category counts don't display. So that extension is involved and I'd recommend tagging it in the Phab ticket. As for where the root cause code is, the buggy SQL code / cache code / algorithm / DeferredUpdate / job could be located in either the extension or MediaWiki core, depending on if the extension calls some code in MediaWiki core or just uses its own code. –Novem Linguae (talk) 13:49, 17 November 2024 (UTC)

Editors not qualified, but using AFC templates

Please see Special:Contributions/ArifVlog782 where you will see at 0902UTC today they faux-accepted a draft using the AFC acceptance template. I have asked them on ther talk page about this. I have also asked the previous reviewer who declined the draft to check the "acceptance".

That is beside the point. It should either be in mainspace or should not

Is there a technical way of preventing (what I see as) abuse of these templates by non qualified editors. This one has only 167 edits in their edit log on this project 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 09:25, 12 November 2024 (UTC)

Convenient link https://en.wikipedia.org/enwiki/w/index.php?title=User_talk:DareshMohan&diff=prev&oldid=1256937209 Polygnotus (talk) 10:59, 12 November 2024 (UTC)

The short answer is no. Primefac (talk) 13:12, 12 November 2024 (UTC)

Were we to wish for it, if this technically a reach too far, or is it technically possible without undue effort? 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 15:19, 12 November 2024 (UTC)

I think it would be technically possible to use an edit filter to prevent this (at least for non-EC editors), though I haven't looked into the regex for it. C F A 💬 16:25, 12 November 2024 (UTC)

The initial situation has led us to Wikipedia:Sockpuppet investigations/DareshMohan. 🇺🇦 Fiddle^Timtrent Faddle^Talk to me 🇺🇦 15:24, 12 November 2024 (UTC)

Now merged to Wikipedia:Sockpuppet investigations/Rydex64. Polygnotus (talk) 20:53, 13 November 2024 (UTC)

Source Assessment Tables

This isn't really about AFC, but about a process that AFC reviewers are often involved in, and that is the creation of source assessment tables that are used in AFD. I had created a source assessment table in an AFD, and another editor observed that I had created it by hand, and suggested that I use a template for the purpose. I replied that I only appeared to have created it by hand, because I use the Excel2Wiki tool [16], which converts a spreadsheet to a Wiki table. There are at least two ways to create a cleanly formatted source assessment table. I have been using the Excel conversion tool for years and will continue to do so, and other editors have been using templates for years and will continue to do so. Robert McClenon (talk) 15:14, 13 November 2024 (UTC)

Thanks for the heads-up, I wasn't aware of this tool.

...and that now makes me wonder how many other great tools there are that I must be missing out on! -- DoubleGrazing (talk) 15:18, 13 November 2024 (UTC)

I did this one recently. I used Template:Source assess table generated using the associated script. However, you have to paste all the URLs from the article into the form that the script displays, or directly into the generated table as I did, which is time-consuming especially if there are a lot of sources. It would be great if someone could produce a v2 of the script that automatically extracts the URLs from the sources and pre-populates the table with metadata from each source and a hyperlink. Curb Safe Charmer (talk) 15:53, 13 November 2024 (UTC)

There's also Template:ORGCRIT assess table for assessing against NCORP. Curb Safe Charmer (talk) 15:59, 13 November 2024 (UTC)

Generally I think it would be great if we used these more often, particularly on drafts that have been hanging around for weeks or months because they are in the 'too difficult' pile. These often have a lot of sources to assess, and it is inefficient for successive reviewers to go through all the sources when the earlier reviewers could ideally have marked the ones that definitely did not contribute to notability, and then we could build up the table as a team effort / relay, and focus on the sources that are borderline. Curb Safe Charmer (talk) 16:05, 13 November 2024 (UTC)

Agreed, that would be a good idea. Someone could check particular types of source, like ones behind a paywall that they have access to. Others, non-English ones in a language they read. And so on. No one reviewer might want to check all the sources, but between a few of them they could cover the lot. Just (!) need to figure out a way to keep track of the citations so that when they change, the source table updates accordingly. -- DoubleGrazing (talk) 16:11, 13 November 2024 (UTC)

@Curb Safe Charmer: I have combining User:Polygnotus/Scripts/SourceTable with the Source assess table on my todolist. Polygnotus (talk) 20:25, 13 November 2024 (UTC)

♥ Curb Safe Charmer (talk) 21:13, 13 November 2024 (UTC)

I will note that the Excel to Wiki table is not specifically intended for use by reviewers, because it is meant for construction of tables for use in articles. Its use for assessing notability is a side benefit. For that reason, I have confidence that it has been thoroughly debugged. But any reviewer should be encouraged to use whatever tools they are familiar with. Robert McClenon (talk) 04:21, 16 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)

ANI thread on AI-generated drafts

• Wikipedia:Administrators' noticeboard/Incidents § AI-generated articles by Tatar Russian

There are eight articles by the editor that was accepted. They should be re-checked for hoaxes and fake references. They are milhist articles with a lot of Cyrillic sources. Ca ^{talk to me!} 11:35, 20 November 2024 (UTC)

Wikiproject AI cleanup was also notified. Ca ^{talk to me!} 11:37, 20 November 2024 (UTC)

Blocked as sock and all articles and drafts deleted. KylieTastic (talk) 15:51, 20 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)

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)