Per today's offline discussions, we're going to work on this dashboard at the start of Q1 and narrow the scope of the initial implementation. See T428818 for more context.

• For each suggestion category/type, log LLM generated suggestions by sub-type like we do with TextMatch

In T426133#11987195, @ppelberg wrote:

In T426133#11974691, @dchen wrote:

Translations were forwarded last week to @ppelberg!

Thank you for this update, @dchen! When do you think it'd be realistic for us to receive translations back?

Resolved. Translations are all available in the spreadsheet.

In T426133#11987464, @Wellverywell wrote:

@ppelberg AFAIK Mitte has posted all the Russian translations to Translatewiki (and plans on Ukrainian too).

Amazing. Thank you, @Mitte27 and thank you, @Wellverywell!

Next steps

• @DLynch to update ticket with outcome of fixes
• @dchan to follow up w/ Reuven and communicate priority and clarify next steps

Noted and makes sense. Thank you, Ed.

Resolving; @DLynch will file a ticket to hold us accountable to making a decision about what (if anything) we want to do with the unmerged patch he and @cjming wrote at the SDS offsite.

Per what @MNeisler and I discussed offline this week (3 June 2026): at present, the effect of Suggestion Mode is being diluted because new(er) volunteers are only seeing suggestions in 27% of test group edit sessions. The remaining test edit sessions have an experience identical to those in the control group, which pulls the measured effect toward zero.

@Esanders to be doubly sure I'm understanding...

In T426133#11974691, @dchen wrote:

Translations were forwarded last week to @ppelberg!

Thank you for this update, @dchen! When do you think it'd be realistic for us to receive translations back?

In T426133#11974953, @Wellverywell wrote:

Is there some way to see the survey having more than 100 edits? Or can you at least give the list of strings? (I don't have access to the document)
Me and @Mitte27 would be happy to translate it to Russian on Translatewiki.

Wow. We'd greatly value your help, @Wellverywell and @Mitte27! Could you please let us know if you run into any issues ?

Related: T427868

@matej_suchanek + @Wellverywell + @Escargot_rouge: first and foremost, on the behalf of the entire Editing Team, I'd like to share how inspired we've been by the extent to which you all are experimenting with, extending, and as the latest comments demonstrate, identifying ways TextMatch and Edit Suggestions more broadly are breaking!

In T405185#11945641, @KStoller-WMF wrote:

@Sucheta-Salgaonkar-WMF - @Sdkb I discussed this task again as this comes up regularly as a complaint at English Wikipedia. I'm unclear how much effort a change like this would require... but I imagine this will become even more urgent as Suggestion Mode roles out and more people have access to link suggestions.

Perhaps we could consider work on this under DE1.1 next FY? @ppelberg

@KStoller-WMF: great spot. Let's talk more about this when we meet next/at the offsite?

Next step(s)

• @bmartinezcalvo to talk with Derek to understand what might explain token producing an unexpected font size

In T426687#11941166, @medelius wrote:

Yes, that's the one, @Sfaci ! I've updated the description to reflect the correct original start date.

Eeek. Great spot, @Sfaci and thank you for clarifying, @medelius !

In T415718#11909874, @Isaac wrote:

[unasked-for advice as part of my quest for better data] Do we have a more precise indicator of "made through structured editing experiences" than "≥1 Edit Suggestion was seen during the course of the edit session"? I'm assuming that means that someone clicked on the Suggestion to open up the details panel? But I wonder if we could go a bit further as I imagine folks will open up the Suggestions just out of curiosity.

@Isaac: great spot and question.

Per today's offline discussion with @bmartinezcalvo, @dchen, and @TAndic, we're going to translate the survey via MoveComms/Design Research.

Per offline