Page MenuHomePhabricator

diego (Diego S-T)
Senior Research Scientist

Today

  • Clear sailing ahead.

Tomorrow

  • Clear sailing ahead.

Monday

  • Clear sailing ahead.

User Details

User Since
Aug 8 2017, 10:56 AM (329 w, 4 d)
Availability
Available
LDAP User
Unknown
MediaWiki User
Diego (WMF) [ Global Accounts ]

Recent Activity

Yesterday

diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

No updates this week.

Fri, Dec 1, 4:34 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.
  • The Moderation Tools team is running tests and community discussions to implement the Automoderator project, we are in coordination with them to learn about potential areas of improvement for RR.
  • There has been some community initiatives to evaluate the quality of the RR models. In T336934 a group of rowiki editors had manually labeled a set of risky revisions. We have analyzed these results, showing reasonable good performance.
  • The ML-team is working on integrating RRLA to recent changes feed T348298. We are working on defining the best thresholds for this integration T351897 .
  • We have been working with Wikimedia Enterprise to clarify some doubts about the RRLA model T346095
Fri, Dec 1, 4:21 PM · Research (FY2023-24-Research-October-December)

Fri, Nov 24

diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..
  • I have presented the Revert Risk model Wikidata and the Annotool at the WikiProject LD4 Wikidata gathering.
  • We have started collecting new annotations on the second Wikidata labeling. The campaign is available here. @Lydia_Pintscher is helping us to find more annotators (thanks!).
Fri, Nov 24, 6:26 PM · Research (FY2023-24-Research-October-December)

Thu, Nov 23

diego added a comment to T336934: Enable communities to configure automated prevention or reversion of bad edits.

Great. Having some manual labels is always valuable.
I have done a quick check and I've seen there are few cases were the RR scores are not higher than 0.93. For example, this one:

That is very weird. I checked the code and a few of the pages identified in a newer run and did not see any mismatch. Is it possible for the score to change? I know in ores it was possible in certain conditions.

I can't think a case where this is possible but I'll have a look.

Anyhow, I've done some cleaning, and merged the datasets, and then I've computed some scores:

These scores seem to be based on the prediction, not the score returned by the algorithm, so they seem a bit useless in the context of a reverter - the community will almost certainly not accept a 53% success rate. Can you advise on why you chose these and not the score-based results, which seem better?

I've done both, you can find them on the jupyter notebook. But in summary the precision is very similar (almost identical) to ORES rowing-damagging

Thu, Nov 23, 9:06 PM · Automoderator, Epic, Moderator-Tools-Team
diego added a subtask for T314384: Develop a ML-based service to predict reverts on Wikipedia(s): T351897: Set the thresholds Revert Risk models to be used on the Recent Changes Feed (via ORES Extension).
Thu, Nov 23, 3:36 PM · Machine-Learning-Team, Research, Epic
diego added a parent task for T351897: Set the thresholds Revert Risk models to be used on the Recent Changes Feed (via ORES Extension): T314384: Develop a ML-based service to predict reverts on Wikipedia(s).
Thu, Nov 23, 3:36 PM · Research
diego set Due Date to Wed, Dec 13, 11:00 PM on T351897: Set the thresholds Revert Risk models to be used on the Recent Changes Feed (via ORES Extension).
Thu, Nov 23, 3:34 PM · Research
diego created T351897: Set the thresholds Revert Risk models to be used on the Recent Changes Feed (via ORES Extension).
Thu, Nov 23, 3:33 PM · Research

Tue, Nov 21

diego renamed T343064: Expand types of edits for Wikidata revert risk model from Expand edit types for Wikidata revert risk model to Expand types of edits for Wikidata revert risk model.
Tue, Nov 21, 6:58 PM · Research
diego updated subscribers of T346095: Investigate the tangible differences between the results from goodfaith vs revertrisk.
  1. Older revisions.

    Concerns around our understanding of the limitations of the model for older edits given the training window. If there is a user that is looking at taking a full snapshot of either our current corpus of Wikipedia, or a past version, both include revisions from a broader window of time than the training window specifically and may show “latent” bad revisions that either perform differently with the LiftWing model or are uncaught.

I am curious what you may recommend to evaluate older content that could be vandalized without us knowing due to a lack of revisions/content attention by editors.

I'm not completely sure if I'm understanding your question. What I can say is that any model would have certain time drift, that includes RR and ORES. I think the model's precision would decay if we use it for very old data, but probably it tends to a certain limit (I would assume that the same is true for ORES, and that model is probably already working close to it's boundaries). The Language Agnostic model shouldn't be difficult to run on a large old dataset, I understand that @fkaelin
and @Pablo had been working on running the model on large data, so maybe if you have an specific question to be answered, the four of us could try to design an experiment to answer that question.

  1. Performance on different types of pages. You already addressed this in part, but what I mean by different page types isn’t necessarily subject-related (though cross-language data is helpful as well) but instead based on the metadata of the page.

How does the model typically perform on revisions in pages with low/high pageviews, low/high amounts of content, more/less edits, etc. This is less critical for our use-case, but we are imagining cases where a user may want to create their own filtering system based on their tolerance for risk and may want an approach that divides article approaches based on metadata.

Let us know if there are potential low-risk exercises we can collaborate on to subsect the data.

I don't have such statistics, maybe the Knowledge Integrity Observatory have some data to answer this (@Pablo ?)

  1. What to know that we do not know.

This is what I was trying to pull on with the question on use. If ORES had fallen out of style among some users and/or grown in use with others- why? If we can understand points of friction with use (Usability? Performance? Different approach needed?) it will help us integrate learnings as we design similar features (credibility signals,
etc.).

I don't think there is clear pattern here. I think the adoption/attrition of these tools is opportunistic, in the sense that ppl used them according to their needs. With no other options, ppl would use what there is available. And even with more tools available, developers would use what fits better on their workflows, or even what the have seen working in the past. Unless we have dramatic difference between models' accuracy, I don't think that differences in models' quality is something that is easy to asses for developers.
Probably the attrition is related to the (lack of) success of the tools created using ML models, and not directly to the model itself (although that model quality probably has an impact on the tool success).

Tue, Nov 21, 6:30 PM · Wikimedia Enterprise - Content Integrity, Wikimedia Enterprise
diego added a comment to T336934: Enable communities to configure automated prevention or reversion of bad edits.

Great. Having some manual labels is always valuable.
I have done a quick check and I've seen there are few cases were the RR scores are not higher than 0.93. For example, this one:

Tue, Nov 21, 6:27 PM · Automoderator, Epic, Moderator-Tools-Team

Tue, Nov 14

diego added a comment to T336934: Enable communities to configure automated prevention or reversion of bad edits.

Hi @Strainu , here Diego from the WMF Research team.

Tue, Nov 14, 12:05 AM · Automoderator, Epic, Moderator-Tools-Team

Mon, Nov 13

diego added a comment to T349410: Document and curate the learnings from executing the existing roadmap.

We would also include @cwylo !

Mon, Nov 13, 11:40 PM · Research (FY2023-24-Research-October-December)

Mon, Nov 6

diego updated subscribers of T346095: Investigate the tangible differences between the results from goodfaith vs revertrisk.

Hi, here Diego from Research. I'll take some of the questions you raised:

Mon, Nov 6, 11:15 PM · Wikimedia Enterprise - Content Integrity, Wikimedia Enterprise
diego added a comment to T348298: Add revertrisk-language-agnostic to RecentChanges filters.

<3

Mon, Nov 6, 2:20 PM · Wikipedia-Android-App-Backlog, Growth-Team, Patch-For-Review, MediaWiki-extensions-ORES, Machine-Learning-Team

Oct 31 2023

diego added a comment to T350061: [Annotool] Errors loading edits.

@MunizaA got it. Would this mean to create a another project?

Oct 31 2023, 2:46 PM · Research

Oct 30 2023

diego created T350061: [Annotool] Errors loading edits.
Oct 30 2023, 4:49 PM · Research

Oct 27 2023

diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly updates

Oct 27 2023, 8:28 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T349755: Training pipeline for Revert Risk Language Agnostic (RRLA) model.

Weekly Updates

Oct 27 2023, 8:26 PM · Knowledge-Integrity, Research

Oct 26 2023

diego added a comment to T349739: [Annotool] Include additional information on private project exports.

@diego: Please add at least one project tag to tasks, so other people can also find this task when searching via projects. Please set appropriate project tags when possible. Thanks!

Oct 26 2023, 2:58 PM · Research
diego added a comment to T349295: Determine technical approach for Automoderator edit revert component.

@jsn.sherman this might be of your interest: T338792

Oct 26 2023, 2:40 PM · MediaWiki-Platform-Team (Radar), Moderator-Tools-Team (Kanban), Spike, Automoderator

Oct 25 2023

diego added a subtask for T314384: Develop a ML-based service to predict reverts on Wikipedia(s): T349755: Training pipeline for Revert Risk Language Agnostic (RRLA) model.
Oct 25 2023, 7:56 PM · Machine-Learning-Team, Research, Epic
diego added a parent task for T349755: Training pipeline for Revert Risk Language Agnostic (RRLA) model: T314384: Develop a ML-based service to predict reverts on Wikipedia(s).
Oct 25 2023, 7:56 PM · Knowledge-Integrity, Research
diego created T349755: Training pipeline for Revert Risk Language Agnostic (RRLA) model.
Oct 25 2023, 7:55 PM · Knowledge-Integrity, Research
diego added a subtask for T344016: Improvements to Annotool: T349739: [Annotool] Include additional information on private project exports.
Oct 25 2023, 4:39 PM · Research
diego added a parent task for T349739: [Annotool] Include additional information on private project exports: T344016: Improvements to Annotool.
Oct 25 2023, 4:39 PM · Research
diego created T349739: [Annotool] Include additional information on private project exports.
Oct 25 2023, 4:38 PM · Research
diego added a project to T341820: Evaluate and improve the Revert Risk model for Wikidata.: Epic.
Oct 25 2023, 4:35 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T348666: Add randomization to the revision order showed in Annotool.

This feature is working correctly. From my perspective this task can be marked solved.

Oct 25 2023, 4:34 PM · Research
diego updated the task description for T344016: Improvements to Annotool.
Oct 25 2023, 4:33 PM · Research

Oct 24 2023

diego created T349649: Update links for Research Team meetings to enable "Join by phone" from outside of USA.
Oct 24 2023, 4:20 PM · Research, Research-management
diego added a comment to T219903: Keep research.wikimedia.org landing page updated.

looks good. Thanks.

Oct 24 2023, 1:53 PM · periodic-update, Research

Oct 23 2023

diego updated the task description for T341820: Evaluate and improve the Revert Risk model for Wikidata..
Oct 23 2023, 8:57 PM · Research (FY2023-24-Research-October-December)

Oct 17 2023

diego added a comment to T219903: Keep research.wikimedia.org landing page updated.

Hi @DDeSouza, please add the following papers:

Oct 17 2023, 2:35 PM · periodic-update, Research

Oct 11 2023

diego triaged T348666: Add randomization to the revision order showed in Annotool as High priority.
Oct 11 2023, 3:24 PM · Research
diego added a subtask for T344016: Improvements to Annotool: T348666: Add randomization to the revision order showed in Annotool.
Oct 11 2023, 3:21 PM · Research
diego added a parent task for T348666: Add randomization to the revision order showed in Annotool: T344016: Improvements to Annotool.
Oct 11 2023, 3:21 PM · Research
diego created T348666: Add randomization to the revision order showed in Annotool.
Oct 11 2023, 3:21 PM · Research

Oct 10 2023

diego added a comment to T340427: Check home/HDFS leftovers of paramd.

Hi! The standard archival process works good. Thanks!

Oct 10 2023, 12:15 AM · Data-Platform-SRE

Oct 6 2023

diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Oct 6 2023, 8:07 PM · Research (FY2023-24-Research-October-December)
diego updated subscribers of T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Oct 6 2023, 8:05 PM · Research (FY2023-24-Research-October-December)

Oct 5 2023

diego added a comment to T347136: Review Revert Risk reports from WME.

In the last 50 hours, we haven't seen any "Unsupported lang" issue.
Thanks for fixing this.

Oct 5 2023, 3:44 PM · Machine-Learning-Team, Research
diego updated the task description for T348264: Review WWW'24 Sumbission .
Oct 5 2023, 3:26 PM · Research-outreach
diego created T348264: Review WWW'24 Sumbission .
Oct 5 2023, 3:25 PM · Research-outreach

Sep 27 2023

diego added a comment to T347330: Expand language support for Revert Risk Model.

Let's the updated csv for now. Later Iets to coordinate with @fkaelin to periodically update these values, both RRLA and Article quality models.

Sep 27 2023, 2:17 AM · Machine-Learning-Team, Research

Sep 15 2023

diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Sep 15 2023, 10:23 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Sep 15 2023, 10:18 PM · Research (FY2023-24-Research-October-December)

Sep 12 2023

diego added a comment to T344016: Improvements to Annotool.

@MunizaA , could we please add an action to finish a project? By finish I mean to keep the project data, but stop showing in the front-end.

Sep 12 2023, 6:05 PM · Research
diego updated the task description for T344016: Improvements to Annotool.
Sep 12 2023, 6:04 PM · Research
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Sure, the data is public (we just remove the labeler username). As I mentioned in the previous comment the amount of data is pretty low, but you can find it here.

Sep 12 2023, 5:55 PM · Research (FY2023-24-Research-October-December)

Sep 8 2023

diego added a comment to T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Sep 8 2023, 8:01 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Sep 8 2023, 8:00 PM · Research (FY2023-24-Research-October-December)

Sep 1 2023

diego added a comment to T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weeky Updates

Sep 1 2023, 7:19 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Sep 1 2023, 7:16 PM · Research (FY2023-24-Research-October-December)

Aug 25 2023

diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Aug 25 2023, 11:46 AM · Research (FY2023-24-Research-October-December)
diego added a comment to T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Aug 25 2023, 11:43 AM · Research (FY2023-24-Research-October-December)

Aug 22 2023

diego updated the task description for T344016: Improvements to Annotool.
Aug 22 2023, 4:53 PM · Research
diego added a comment to T344537: Fast Vandalism Detection .

Revert Risk Language Agnostic should do the work, the inference time goes below 200ms.

Aug 22 2023, 4:35 PM · Machine-Learning-Team

Aug 21 2023

diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Hi @emwille! Sure I'll be happy to present, I'll send you an email to coordinate. Thanks!

Aug 21 2023, 4:31 PM · Research (FY2023-24-Research-October-December)
diego updated subscribers of T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Aug 21 2023, 11:14 AM · Research (FY2023-24-Research-October-December)
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Aug 21 2023, 11:10 AM · Research (FY2023-24-Research-October-December)
diego updated the task description for T341820: Evaluate and improve the Revert Risk model for Wikidata..
Aug 21 2023, 11:08 AM · Research (FY2023-24-Research-October-December)

Aug 15 2023

diego updated the task description for T344016: Improvements to Annotool.
Aug 15 2023, 5:58 PM · Research
diego added a comment to T344016: Improvements to Annotool.

Thanks for the input. In order to make the annotations as much useful as possible for training the algorithm, it would be good to have labels that are not too specific, and can generalize as much as possible. Do you think that something like: "long-term vandalism" or "hijacked item" could be a good name for the phenomena that you are describing ?

Aug 15 2023, 5:56 PM · Research
diego closed T290008: Autocomplete is very slow (unusable) in Newpyter as Resolved.
Aug 15 2023, 5:40 PM · Data-Platform-SRE, Data-Engineering-Jupyter, Data-Engineering
diego added a comment to T290008: Autocomplete is very slow (unusable) in Newpyter .

@BTullis , yes, this has been solved in the current environment, thanks!

Aug 15 2023, 5:40 PM · Data-Platform-SRE, Data-Engineering-Jupyter, Data-Engineering

Aug 11 2023

diego added a comment to T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Aug 11 2023, 4:21 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Aug 11 2023, 4:17 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T340427: Check home/HDFS leftovers of paramd.

Would you like me to move this in bulk to a new directory within your home, such as: /home/dsaez/paramd-archive

This sounds good and enough!

Aug 11 2023, 4:10 PM · Data-Platform-SRE
diego updated the task description for T344016: Improvements to Annotool.
Aug 11 2023, 5:59 AM · Research
diego added a comment to T344016: Improvements to Annotool.

In the description you list "Remove list of languages". Instead of removing the drop-down box, can it not instead be made functional, i.e. only display tasks in the chosen language? For example, I'm only proficient in English, so it is likely better for me to focus on tasks in English, rather than additionally displaying Spanish, German, etc. Being able to choose which language these training tasks are from would be useful.

Aug 11 2023, 5:59 AM · Research

Aug 10 2023

diego added a parent task for T343973: Fix relative links for Qids in Annotool: T344016: Improvements to Annotool.
Aug 10 2023, 7:38 PM · Research
diego added a subtask for T344016: Improvements to Annotool: T343973: Fix relative links for Qids in Annotool.
Aug 10 2023, 7:38 PM · Research
diego added a subtask for T341820: Evaluate and improve the Revert Risk model for Wikidata.: T344016: Improvements to Annotool.
Aug 10 2023, 7:37 PM · Research (FY2023-24-Research-October-December)
diego added a parent task for T344016: Improvements to Annotool: T341820: Evaluate and improve the Revert Risk model for Wikidata..
Aug 10 2023, 7:37 PM · Research
diego added a comment to T343973: Fix relative links for Qids in Annotool.

Thanks @wolfgang8741 I'm adding this here T344016

Aug 10 2023, 7:37 PM · Research
diego updated the task description for T344016: Improvements to Annotool.
Aug 10 2023, 7:37 PM · Research
diego updated the task description for T341820: Evaluate and improve the Revert Risk model for Wikidata..
Aug 10 2023, 7:31 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Hi all, here Diego from WMF Research.

Aug 10 2023, 7:31 PM · Research (FY2023-24-Research-October-December)
diego created T344016: Improvements to Annotool.
Aug 10 2023, 7:29 PM · Research

Aug 4 2023

diego updated subscribers of T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.
  • Weekly Updates**
Aug 4 2023, 10:31 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Aug 4 2023, 10:26 PM · Research (FY2023-24-Research-October-December)
diego added a parent task for T343419: Move Wikidata tools to Lift Wing: T341820: Evaluate and improve the Revert Risk model for Wikidata..
Aug 4 2023, 10:18 PM · Wikidata.org, Wikidata Dev Team, User-ItamarWMDE, Item Quality Evaluator, Machine-Learning-Team, Wikidata
diego added a subtask for T341820: Evaluate and improve the Revert Risk model for Wikidata.: T343419: Move Wikidata tools to Lift Wing.
Aug 4 2023, 10:18 PM · Research (FY2023-24-Research-October-December)
diego renamed T341820: Evaluate and improve the Revert Risk model for Wikidata. from .Evaluate and improve the Revert Risk model for Wikidata. to Evaluate and improve the Revert Risk model for Wikidata..
Aug 4 2023, 10:16 PM · Research (FY2023-24-Research-October-December)
diego updated subscribers of T341820: Evaluate and improve the Revert Risk model for Wikidata..
Aug 4 2023, 10:16 PM · Research (FY2023-24-Research-October-December)
diego added a comment to T343419: Move Wikidata tools to Lift Wing.

Also the experimental model is available through the Knowledge Integrity package.

Aug 4 2023, 5:12 PM · Wikidata.org, Wikidata Dev Team, User-ItamarWMDE, Item Quality Evaluator, Machine-Learning-Team, Wikidata
diego added a comment to T343419: Move Wikidata tools to Lift Wing.

And if you want to help with the evaluation, please go to this site: https://annotool.toolforge.org/ and help us to annotate data :)

Aug 4 2023, 3:26 PM · Wikidata.org, Wikidata Dev Team, User-ItamarWMDE, Item Quality Evaluator, Machine-Learning-Team, Wikidata
diego added a comment to T343419: Move Wikidata tools to Lift Wing.

@elukey Research team's plan for the RevertRisk Wikidata model is to evaluate it in Q1, and then improve and deploy it in Q2.

Aug 4 2023, 2:30 PM · Wikidata.org, Wikidata Dev Team, User-ItamarWMDE, Item Quality Evaluator, Machine-Learning-Team, Wikidata

Jul 28 2023

diego updated subscribers of T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Jul 28 2023, 9:38 AM · Research (FY2023-24-Research-October-December)
diego added a comment to T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Jul 28 2023, 9:31 AM · Research (FY2023-24-Research-October-December)

Jul 21 2023

diego updated the task description for T341820: Evaluate and improve the Revert Risk model for Wikidata..
Jul 21 2023, 9:57 AM · Research (FY2023-24-Research-October-December)
diego updated subscribers of T341820: Evaluate and improve the Revert Risk model for Wikidata..

Weekly Updates

Jul 21 2023, 9:56 AM · Research (FY2023-24-Research-October-December)
diego renamed T341820: Evaluate and improve the Revert Risk model for Wikidata. from Explore alternatives for Revert Risk model improvements for Wikidata to .Evaluate and improve the Revert Risk model for Wikidata..
Jul 21 2023, 9:53 AM · Research (FY2023-24-Research-October-December)
diego added a comment to T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.

Weekly Updates

Jul 21 2023, 9:44 AM · Research (FY2023-24-Research-October-December)
diego updated the task description for T341819: Explore alternatives for Revert Risk model improvements for Wikipedia.
Jul 21 2023, 9:36 AM · Research (FY2023-24-Research-October-December)

Jul 13 2023

diego added a comment to T340822: Revert Risk multi-lingual model performance and reliability may need a review.

Few things:

Jul 13 2023, 4:55 PM · Machine-Learning-Team

Jul 11 2023

diego added a comment to T340427: Check home/HDFS leftovers of paramd.

I have access to most of the data, I can wait a couple of weeks to get the full dump.

Jul 11 2023, 2:20 PM · Data-Platform-SRE
diego added a comment to T340427: Check home/HDFS leftovers of paramd.

Hi @MoritzMuehlenhoff ,
Yes, please I'll need a copy of all the data both on the stat machines and HDFS

Jul 11 2023, 11:56 AM · Data-Platform-SRE
diego closed T288333: Understanding the spread of disinformation on Wikipedia as Resolved.
Jul 11 2023, 7:51 AM · Research