Consultations that should lead to an updating of the Wikimedia Foundation's Terms of Use will begin as early as this Tuesday, February 21 according to WMF Legal. The discussions will take place on Meta-Wiki.

The updates are necessary in order to:

• Help implement the Universal Code of Conduct
• Change the license for text to the Creative Commons BY-SA 4.0 license and
• Make changes to comply with new laws, especially with the European Digital Services Act

Other possible changes include strengthening enforcement of the requirement that paid editors must declare their employers, clients, and affiliations. – S

Wikimedia Foundation Board Member Shani Evenstein announced the results of the vote on the Wikimedia-l mailing list on 13 February 2023:

Today the results of the Universal Code of Conduct Enforcement Guidelines vote were tallied. We are pleased to report the results show that the Enforcement Guidelines are strongly supported by the community, with 76% of participants voting in support of the Enforcement Guidelines.

3,097 voters from 146 Wikimedia communities participated. Statistics for the vote are available. A more detailed summary of comments submitted during the vote will be published soon.

Next, the results and comments collected during this vote will be submitted to the Board of Trustees for their review. It is expected that the Board of Trustees review process will complete in March 2023, at which time another update will be published. – AK

The Steward elections are underway. New candidates for Stewardship are:

• User:Klein Muçi
• User:Mykola7
• User:Superpes15
• User:Turkmen
• User:Xaosflux

The Steward confirmations – an annual performance evaluation by the community that determines whether or not existing Stewards will retain their status for another year – are also currently underway.

Voting for the election and confirmation processes will remain open until 26 February 2023, 21:00 (UTC). – AK

Now you see it, now you don't – Wikipedia had hardly been blocked by Pakistan before it was unblocked.

Shehbaz Sharif, the Prime Minister of Pakistan, stepped in and convened a committee composed of the Minister for Law and Justice, the Minister for Economic Affairs and Political Affairs and the Minister for Information and Broadcasting to examine the matter.

The committee took the view that –

Wikipedia was a useful site/portal which supported dissemination of knowledge and information for the general public, students and the academia. Blocking the site in its entirety was not a suitable measure to restrict access to some objectionable contents/sacrilegious matter on it. The unintended consequences of this blanket ban, therefore, outweigh its benefits.

The government subsequently barred the Pakistan Telecommunica­tion Authority (PTA) from blocking any website without first consulting the Minis­try of Information Tech­nology and Tele­communi­cation.

Wikimedia Foundation General Counsel Stephen LaPorte said on the Wikimedia-l mailing list:

We received news yesterday that the Pakistan Telecommunications Agency was directed to restore access to Wikimedia projects, including Wikipedia, in Pakistan. Our internal traffic reports confirm that the block has been lifted and we've updated our public statement.

We're happy that the people of Pakistan can continue to use Wikipedia to access knowledge and share their experiences and culture with the world. These situations are a reminder of the importance of the work of our movement and the vital role our communities play in building the largest collection of open knowledge in history. It also underscores the need to protect people's right to access free knowledge and participate in contributing to its growth globally. Thank you for your support. We'll continue to keep you updated if there are any new developments.

– AK, R

For the media coverage of this event, see this issue's in the media.

Last issue, we reported on AI-generated articles on Wikipedia. It was a bit of fun. Find the AI-generated article! The impostor is sus!

If only it remained that way: English Wikipedia editor Rory Jaffe (rsjaffe) has found a number of them, including Draft:Cow Farts – not actual bull shit, but pretty close. Here's what he says about his discovery technique.

I've been looking for "tells" before testing [with a classifier tool that can detect AI generated text with some accuracy]. The text is more "lifeless" than human text typically is, tends to have uniform length sentences, and may have a paragraph at the end that is a summary paragraph. The text is also unlikely to have in-line references. This doesn't catch all of them but tends to be a high-likelihood way of finding them. Some of these AI-generated articles also have AI-generated references. The references are almost always fake: the AI confabulates reasonable-sounding references!

Articles or drafts tagged by Jaffe and reviewed by The Signpost were created as early as 17 December 2022 (Draft:Brisbane Lord Mayor YAC). The topics tagged by Jaffe and others range from the whimsical and neologism-ic (Draft:Twinkanic Awareness, Draft:Sharks should be saved from humans) to the plausibly- and obviously-promotional, and appear to be created by many editors, including single-purpose accounts that may be using them for promotion. Take Draft:Dachshund harness, "an essential accessory for owners of this unique breed of dog", which has a list of references at the end related to shopping for such a device. Given affiliate marketing exists, this could be promotional. Or it could be purely accidental. We don't know. Some of the rest may be deleted by the time you read this – a few examples are retained permanently at User:JPxG/LLM dungeon.

The Signpost asked Jaffe "Do you have a personal reaction to the quality of the AI generated articles? Briefly, are you for or against this method of creation?" He told us this:

Strongly against. These language generators are good at stringing together reasonable-sounding text, but:

1. Don't rely solely on what Wikipedia recognizes as reliable sources.

2. Don't have a sense of what is real and what is fake.

3. Will fabricate information to fill in gaps.

4. Cannot identify where any specific bit of "information" came from.

So the text can fail WP:RS and WP:V, yet may look very convincing.

However, they're good at helping to break "writer's block", by giving an example of how to write something. So I see having some text generated by ChatGPT would be helpful as a writing prompt, but without using any of the generated text directly—just looking at it and then writing a well-researched article similar to the prompt.

More on Jaffe's experience and conclusions on this topic can be found at the Essay in this issue.

We asked ChatGPT for a commentary as well. It said:

It's interesting to see that people are now using AI to generate articles on Wikipedia, but it's also concerning as this could lead to a proliferation of inaccurate or fake information on the platform. It's good to see that editors like Rory Jaffe are using techniques to identify AI-generated text, but it's clear that the AI-generated articles are becoming more sophisticated in their structure and references, making it harder to detect them.

It's important for Wikipedia to maintain its high standards of accuracy and reliability, so it's crucial that the platform continues to monitor and regulate the use of AI-generated content. While AI can be a valuable tool for assisting with research and writing, it should never be a substitute for human expertise and critical thinking.

– B, AC

Wikimedia Enterprise has published its first detailed financial report, complete with a summary of product updates.

Revenue in the 2022 calendar year (from subscription and professional services) totaled $3.12 million, vs. expenses of $3.18 million ($1.06 million in cost of services and $2.12 million in operating expenses), for a net loss of $60,000.

The Enterprise team points out that the present report for the 2022 calendar year should be considered a "beta" edition. The Wikimedia Foundation normally operates on a financial year starting in July and finishing the following June. But as January 1, 2022 marked the official start of commercial operation of the Enterprise project, this first report covers the 2022 calendar year. For future financial reports the Enterprise team intends to align with the normal financial reporting schedule of the rest of the Wikimedia Foundation. The next report will be published in late 2023.

The report adds that:

As the LLC is wholly owned by the Wikimedia Foundation, all of the financial information presented here will also be included within the Wikimedia Foundation's audited financial statements and will be in the next Wikimedia Foundation "Form 990" filing as it relates to fiscal year 2021–2022, and future years.

The Enterprise team says it is very happy with its first year in business and looks forward to growth and profitability this year:

In 2023, our second year of operations, with the addition of new customers and also new features, both revenue and expenses are expected to increase – but revenue growth is expected to outpace expenses. By comparison to other startup commercial API projects, to reach this stage within one year of operations is extremely rapid progress. The governance of these and all other commercial customer relationships is consistent with how the Wikimedia Foundation treats large corporate donations.

No information has been released on how many paying and non-paying customers Wikimedia Enterprise has at the moment. Corresponding inquiries on Meta-Wiki have been answered as follows:

As stated in the original press release, Google and the Internet Archive are indeed the first to receive paid and free access (respectively) but we have not publicized the subsequent customers (paid or free) who have signed-up to the service. ... Maintaining a public and comprehensive list of paying and free/trial customers would look like advertising/promotion of those customers, and also introduce a new privacy (and potentially security) problem: i.e. in the same way that it would be inappropriate to make a public list of "all people who have used the Wikidata Query Service this month" (for example) – it goes against our privacy culture. Nonetheless, we do intend to be making "use case" blog posts – which will describe how some users (either general categories or individual cases with their permission) are benefiting from the service in the real-world.

The Enterprise API features are designed with large commercial reusers in mind – primarily search engines and voice assistants, although education (question-and-answer modules), finance and the fast-growing AI sector represent additional market opportunities the team may explore.

But other kinds of reusers, including individual volunteer Wikimedians, can also benefit. There are several access methods to the datasets available at no cost/no registration, including a free Wikimedia Enterprise account via the project's homepage. Ongoing updates for the community can be found on the project's MediaWiki page.

The publication of the financial report was followed by a public Zoom meeting on 10 February, a recording of which is available. Click the picture on the right or go to the Wikimedia Enterprise talk page on Meta-Wiki, which also includes a list of questions discussed during the meeting and their approximate timecodes. The file description in Commons even includes an automated transcript. – AK

In response to multiple inquiries, the Wikimedia Foundation has posted a breakdown of how and when Tides Advocacy spent the $4.223 million Annual Plan Grant portion of the $8.723 million the organisation received from the WMF in the 2019–2020 financial year. – AK

• WIKIMOVE: The WIKIMOVE podcast project, hosted by Wikimedia Deutschland's Nicole Ebber and Nikki Zeuner, has published Episode 8 of its English-language podcast series. This episode's topic is "Movement Strategy" – how the strategy came about, what the envisioned future looks like, and how this relates to knowledge equity and global governance. Guests this time round are Sharon Naa Deedei Tagoe, a volunteer at the Open Foundation West Africa who joined the Wikimedia movement last year, Likambo Isaac Kangu, a South Sudanese refugee living in Uganda who is the diaspora coordinator for the User Group South Sudan in the refugee settlements in Uganda, and Ruby Damenshie-Brown, Senior Program Officer at the Open Foundation West Africa, who's been a Wikimedian since 2019. The episode is also available as a YouTube video with subtitles and as a transcript. A newsletter of the Open Foundation West Africa is available here. – AK
• This Month in GLAM: The January 2023 Newsletter is now available to read on Wikimedia Outreach.
• Ombuds Commission: The composition of the 10-member Ombuds Commission has been announced.
• AffCom liaison: The Wikimedia Foundation Board of Trustees' Community Affairs Committee elected Lorenzo Losa as an additional Affiliations Committee liaison for the Board.
• Speedy deletion criterion F10 removed: Following a Request for Comment, speedy deletion criterion F10 (Useless non-media files) was deprecated in favour of WP:PROD and marked obsolete.
• Global bans: One Japanese newbie account, after making legal threats on Japanese Wikipedia.
• Milestones: The following Wikimedia projects reached milestones this fortnight: Ladin Wikipedia reached 100,000 articles, Inari Sami Wikipedia reached 5,000 articles, Luganda Wikipedia reached 2,000 articles, and Chichewa Wikipedia reached 1,000 articles.
• Articles for Improvement: This week's Article for Improvement is Centrism. Please be bold in helping to improve this article! Next week's article (beginning 20 February 2023) will be Textbook.

An essay published on 9 February 2023 in The Journal of Holocaust Research and reported on by Haaretz and Polish daily Wyborcza, as well as San Diego Jewish World and Ynet, alleges that Wikipedia engages in "intentional distortion of the history of the Holocaust". The abstract of the essay, written by Jan Grabowski of the Department of History at the University of Ottawa and Shira Klein of the Department of History at Chapman University in Orange, California, says:

This essay uncovers the systematic, intentional distortion of Holocaust history on the English-language Wikipedia, the world’s largest encyclopedia. In the last decade, a group of committed Wikipedia editors have been promoting a skewed version of history on Wikipedia, one touted by right-wing Polish nationalists, which whitewashes the role of Polish society in the Holocaust and bolsters stereotypes about Jews. Due to this group's zealous handiwork, Wikipedia's articles on the Holocaust in Poland minimize Polish antisemitism, exaggerate the Poles' role in saving Jews, insinuate that most Jews supported Communism and conspired with Communists to betray Poles (Żydokomuna or Judeo–Bolshevism), blame Jews for their own persecution, and inflate Jewish collaboration with the Nazis. To explain how distortionist editors have succeeded in imposing this narrative, despite the efforts of opposing editors to correct it, we employ an innovative methodology. We examine 25 public-facing Wikipedia articles and nearly 300 of Wikipedia’s back pages, including talk pages, noticeboards, and arbitration cases. We complement these with interviews of editors in the field and statistical data gleaned through Wikipedia's tool suites. This essay contributes to the study of Holocaust memory, revealing the digital mechanisms by which ideological zeal, prejudice, and bias trump reason and historical accuracy. More broadly, we break new ground in the field of the digital humanities, modelling an in-depth examination of how Wikipedia editors negotiate and manufacture information for the rest of the world to consume.

On 13 February 2023, Wikipedia's primary disciplinary body, the Arbitration Committee, took the unusual step of initiating a case request sua sponte in response to the essay, "invoking its jurisdiction over all matters previously heard and exercising its authority to revisit any proceeding at any time at its sole discretion." The topic area – including many of the edits and behaviours discussed by Grabowski and Klein – has been the subject of multiple arbitration proceedings before, from the 2009 Eastern European mailing list case to the 2019 Antisemitism in Poland case.

On 15 February 2023, Wyborcza (the Polish newspaper that carried Grabowski and Klein's summary of their essay) published a rebuttal by Piotr Konieczny of the Department of Media and Social Informatics at Hanyang University, one of the Wikipedians (User:Piotrus) named by Grabowski and Klein. Piotr said the essay contained many assertions of fact that were not borne out by edit histories recorded on Wikipedia, as well as instances of selective quoting. For those who don't subscribe to Wyborcza – the paper is paywalled – the text of the rebuttal is available here. A longer, English-language response by Piotr raising some of the same issues is here. Volunteer Marek, another editor named in the essay, has also published a multi-part response in English on his Substack.

Watch out for an independent review of the paper in the upcoming issue of the Signpost's monthly "Recent research" section. In the meantime, see also previous Signpost coverage of similar complaints raised in 2019. – AK

This is the premise of an article series investigative journalist Russ Baker kicked off on 6 February 2023 with a piece on his whowhatwhy.org website.

Baker is a veteran reporter who has written for top publications like The New Yorker and The Washington Post. He has tussled with the Church of Scientology. In 2005, he won the Deadline Club award for his exclusive reporting on George W. Bush's military record. Baker was among the first to cast doubt on Colin Powell's now-infamous presentation on Iraq at the United Nations – at the time a very unpopular stance – and among the first to make Americans aware of the impending genocide in Rwanda. But presently, he is concerned about Wikipedia's biographies.

Baker notes that discussions of bias on Wikipedia have generally focused on its alleged "white, American" bias as well as its alleged "leftist" bias:

But none of these critiques really get at what I'm talking about: how professional or amateur "hit men" can infiltrate Wikipedia and go after individuals and ruin them in the public eye.

Some years ago, when I began researching this, I found very little online about this phenomenon, despite the fact that I knew a fair number of individuals who had been victims of the practice. Now that I look again, I still see no sign that this problem is being addressed or even vestigially discussed.

What this means is, nobody is minding the store to make sure that we don’t end up in some type of artificial informational construct that edits the facts about powerful actors and institutions to conform to a subjective agenda instead of reality.

Baker feels that anti-establishment actors like himself are particularly likely to suffer, given that Wikipedia uses the mainstream media as its arbiter, and these media are in many ways an integral part of the establishment.

The fact is, anyone who is out there "making trouble" for the system doesn't stand a chance. Why? Because it would take a relentless, inhuman vigilance to battle those persistent and tidal forces bent on controlling the narrative … And most of us don't have the time, expertise, or energy to do that.

Also, because, for someone to make their case, they have to prove that good things have been said about them … by the establishment.

In other words, if The Washington Post likes you, then you appear in a positive light on Wikipedia. If it doesn't, then what the public sees on the platform is a person or entity it should apparently not like or trust.

In the second part (published a week later) Baker looks at his own Wikipedia biography, which he says is highly selective in a way that is unfavourable to him.

And yes, I received several scathing reviews from establishment organs, but my Wikipedia page never quoted any of the good ones I received — and from prominent people. In fact, they implied there were none. Here’s what you won’t find on Wikipedia:

• One of the most important books of the past ten years. — Gore Vidal

• An investigative gem filled with juicy revelations. — Sydney Schanberg, Pulitzer Prize winner, The New York Times

• A tour de force… Family of Secrets has made me rethink even those events I witnessed with my own eyes. — Dan Rather

• Russ Baker's work stands out for its fierce independence, fact-based reporting, and concern for what matters most to our democracy… A lot of us look to Russ to tell us what we didn't know. — Bill Moyers

• This is the book people will be mining for years to come. — David Margolick, Newsweek and Vanity Fair

There is no reason to believe these quotes aren't genuine – Schanberg, for example, joined Baker for readings of the book in question. The problem is that these are "Praise for ..." quotes from a marketing blurb rather than quotes taken from published reviews. Wikipedians would generally avoid citing marketing materials, and look for independently published reviews in the press. So, is Baker merely whining?

Well, no. Reading the fairly sympathetic Boston magazine article quoted in Baker's biography, it's hard to escape the notion that editors selected quotes to construct a narrative completely at odds with the overall tenor of the cited article. The Boston article concludes by asking, in light of important stories broken by Baker in the past, "which is more dangerous, listening to Russ Baker, or ignoring him?" – AK

This is the provocative title of an article in Germany's Der Tagesspiegel newspaper, opining that generative models like ChatGPT that create text, images and music are committing "data theft" and leaving creators "naked". The article discusses the unsung contributions of the many:

Wikipedia authors, book authors, illustrators, editors, photographers. Their work creates the raw materials that then enters an industrial process: the training data used to feed the AI.

Tech companies like Google and Amazon have used free and open internet content like the English-language Wikipedia as a quarry for years, without giving the authors or organisations a share. The paltry sums that Google and Amazon donate to the Wikimedia Foundation are dwarfed by the economic benefit these corporations derive from the online encyclopaedia.

Now, it has always been an inherent flaw of the commons idea that profit-oriented actors are as welcome to benefit from non-profit work as the general public. The "tragedy of the commons" dilemma is well known from economics. One cannot forbid Amazon to train its voice assistant Alexa with Wikipedia texts – or Wikipedia would have to jettison its foundational principles overnight.

But the relentlessness with which tech companies graze the digital commons and use it to feed their own business models raises the question under what circumstances commons will continue to be produced in the future. Who will maintain Wikipedia articles if they are used for commercialised search queries or answer modules? Who will still write books if language models glue together set pieces into third-rate novels and publishers use them to fill their portfolios?

Der Tagespiegel proposes a compensation system that gives authors an appropriate share in AI systems' profits, citing Germany's long-established VG Wort (cf. Authors' Licensing and Collecting Society) as an example. This has authors registering and then being routinely compensated with fees collected from re-users of their works, according to a complex allocation formula.

After all, no one would have a street artist paint their portrait and then, after taking a digital picture of it and editing it with an AI-based Instafilter, tell the painter, without paying, "Thanks a lot, that was fun!" Respect for art is also expressed through decent payment.

(VG Wort has previously already indicated that Wikipedia would be eligible for payments under its existing system. However, in a 2011 poll the German Wikipedia community overwhelmingly voted against participating in the scheme as a website, although some individual Wikipedia editors were collecting payments separately for "their" articles, amounting to 300 Euros in one case. See previous Signpost coverage: "German Wikipedians reject author payments scheme".)

The Tagesspiegel article ends by noting that OpenAI, the developer of ChatGPT, employs thousands of clickworkers in Uganda, Kenya and India, who label potentially offensive text to help train the models (including violent or sexual text). In Kenya, where average wage is about $18 per day, these workers are paid less than $2 an hour. – AK

As discussed in this issue's news and notes, Wikipedia is back in Pakistan after a fairly brief block. The Prime Minister found that "the unintended consequences of this blanket ban outweigh its benefits", and formed a new committee to look at technical measures for selectively blocking specific objectionable content. However, back in 2015 Wikipedia switched to HTTPS, specifically to make it more difficult for ISPs and other men-in-the-middle to know what part of Wikipedia you're browsing. Numerous reports were made on the subject, including Dawn (again here), Bloomberg News, ABC News, Al Jazeera, and NPR —AC

The Washington Examiner reports that next week, the United States Supreme Court justices will decide whether to take up the longstanding case between the Wikimedia Foundation and the National Security Agency. "To this day, no public court has determined whether upstream surveillance complies with the Constitution. If the government can obtain dismissal here, it will have every incentive to make overstated or exaggerated claims of secrecy to close the courthouse doors on suits like Wikimedia's – suits seeking accountability for government overreach or abuse in the name of national security," the article's author, Bob Goodlatte, states. – AK

UPDATE: The Supreme Court denied the Wikimedia Foundation's petition on 21 February 2023, marking the end of the case. – AK

• "Major search engines to alter results with AI": Former Wikimedia CEO Katherine Maher spoke in a five-minute interview to ABC News (Australia) about the likely impact of tools like GPT on search engines and Wikipedia.
• Google Bard AI trained in part on Wikipedia: Search Engine Journal reports that Google's Bard AI is 12.5% based on English Wikipedia. Another 12.5% comes from Google's C4 Dataset ("Colossal Clean Crawled Corpus"), which apparently also includes Wikipedia as one of its main sources. The other 75% come "from the internet" but their precise origins are "murky", the article says – though the author makes some educated guesses.
• Santos is funny: especially the disgraced US parliamentarian's official web link to Wikipedia, according to the Indiana Daily Student. The link just is to the 118th United States Congress which only mentions that Santos represents New York's 3rd district. The honorable representative might also want to link here or to previous coverage in The Signpost. Where's Randy Rainbow when we need him?
• Wikipedia and its "outsize influence on judicial reasoning": Legal Futures (UK) says that the "widespread use of online source Wikipedia by senior judges could mean fake information spreading, leading to bad judgments, an update of research first revealed last year has warned".
• Political "scrubbing": In a "flashback" article published on the occasion of the appointment of Jeff Zients as the White House's new chief of staff, Fox News recaps a 2020 report by Politico about how consulting firm Saguaro Strategies had "scrubbed" politically damaging information from the Wikipedia page about him (see also "In the media" from December 28, 2020).
• Jimmy Wales comments on Online Safety Bill: IT Pro quotes comments by Jimmy Wales on the Online Safety Bill, a proposed UK law that was covered extensively in our previous issue (see Special report).
• You got something against Bigfoot?: Slate says you do, you cryptid-phobe.
• American Physical Society partnership: APS News says Wikipedia Has a Problem That Physicists Can Help Solve – a gender gap problem addressed through the Wiki Scientist Program. More about the program is at the WikiEdu blog.
• Cry foul: A "former controversial umpire" for Major League Baseball may be editing his own Wikipedia page, according to The Sporting News [1]. The Signpost can confirm that a user account has been blocked and talkpage access revoked following a legal threat on the account's talkpage.

Indian industrialist Gautam Adani has lost a lot of money over the last month. His net worth is about $67 billion less (as of 2/15/23) than it was on January 24 when Bloomberg estimated it at $119 billion and the publicly traded companies he controls have lost over $100 billion in market value. He was ranked as the third richest person in the world in late January and is now only ranked as the 24th with a net worth of $52.4 billion (as of 2/15/23). Please note that all these numbers are in billions, not millions.

What happened? On January 24 short-seller Hindenburg Research released a report titled Adani Group: How the World's 3rd Richest Man Is Pulling the Largest Con In Corporate History. The text of the report modified the claim slightly to "one of, if not the most egregious example of corporate fraud in history". It accused Adani's companies of "brazen accounting fraud, stock manipulation and money laundering ... taking place over the course of decades." The market value of the publicly-traded companies Adani controls plunged to about half of their previous levels within a few days and has mostly stayed at that level or decreased since.

Billionaires have a history of apparent undeclared paid editing on Wikipedia, including Kenneth C. Griffin (paywall), Robert T. Brockman, Robert F. Smith and several Russian oligarchs. A few near- or former billionaires including Elizabeth Holmes, Greg Lindberg, Jeffrey Epstein, and Peter Nygard have also appeared to hire people for undeclared paid editing.

This report examines Adani and his companies in much the same way we examined those other billionaires: have they used paid editing on Wikipedia to push their points of view or as an aid in their pursuit of wealth?

We remind our readers that no entirely on-Wiki investigation of a user's edits can completely identify an editor's name or employer. Even if the editor identifies themself as an employee of a company, they may be simply trying to embarrass the company, a practice known as Joe jobbing. We can, however, examine the nearly complete record of edits made to Wikipedia and identify editors that are likely to be sockpuppets, or that appear to be working together with other accounts.

In 1988 Gautam Adani founded the Adani Group trading commodities such as coal. He branched out into transportation such as seaport management and later airport management, mining, the generation and transmission of electric power, cement production, and in general, energy and infrastructure. A company report from this January gives a good overview of the group's product markets in a graphic on page 3.

G. Adani is reportedly close to India's current prime minister, Narendra Modi, and has benefited from government contracts as India's economy has grown and liberalized. Over the last decade the companies in the group have grown rapidly and Adani has acquired existing companies quickly, financed largely by debt.

Professor Aswath Damodaran of New York University, who wrote the book on stock valuation, addresses whether Adami stocks are overvalued in a February 4 post at his blog Musings on Markets. He disagrees with Hindenburg Research's conclusion that the Adani Group is a "big con", but writes that the company's close ties to political power may make the stock overvalued. "Those risks increase, if the family group companies are built around political connections, where you are one political election loss away [from] your biggest competitive advantage." But note that this sentence was omitted from his 38-minute video presentation of the blog.

So did Adani or his employees improperly edit Wikipedia? Almost certainly yes.

Due to Wikipedia's account name regulations, administrators blocked User:Adanigrouponline in May 2013, and User:Adani Group in September 2014. These were single-purpose accounts (SPAs) editing Adani related articles, including a complete rewrite of the Adani Group article which removed a conflict-of-interest notice from the top of the article. They also added a detailed list of business units, and – the paid editors' favorite section – a list of awards. But they kept a section which an unregistered user – an admitted Adani employee – had added earlier.

Adani Vision

Our vision is to be the globally admired leader in integrated infrastructure businesses with a deep commitment to nation building. We shall be known for our scale of ambition, speed of execution and quality of operation.

Adani Values

Courage

We shall embrace new ideas and businesses

Trust

We shall believe in our employees and other stakeholders

Commitment

We shall stand by our promises and adhere to high standards of business

The use of "our" and "we" in an encyclopedia article is a particular problem considering Wikipedia's policy of no ownership of articles.

The unregistered user left an edit comment of "(Revisited & updated all the content, Changes by Satyam Trivedi (Corporate Communication, Adani))" and the IP address is identified by Whois as Adani Enterprise Limited. A conflict-of-interest notice was added to the top of the article three minutes after this edit, but was soon removed by Adanigrouponline.

Other strong evidence revealed by The Signpost's investigation shows that over 40 editors who have edited Adani articles have later been blocked for undeclared paid editing (UPE) or sockpuppeting, or were blocked by checkusers, whose blocks are typically related to sockpuppeting or UPE. We'll start by reviewing the sockpuppets who edited articles on Adani family members.

The article on Gautam Adani was started in 2007 in a straightforward style by a respected editor. But by 2012 three editors who were later blocked or banned as sockpuppets or undeclared paid editors had edited the article, including User:Kkm010, who has edited three other Adani-related articles together with three other socks from the same sockfarm.

User:Similar2me is one of the leading editors of the article. They edited the article 18 times from 2018 through 2020 when they were blocked for socking. This included two large early edits that rewrote much of the article. After that they concentrated a bit on the philanthropy section, made a few reverts, removed a warning tag, and generally just updated the article. User:Liberosist666, who is suspected to be from the same sockfarm, also made an edit. Similar2me and their sockfarm also edited the articles on Pranav Adani, Gautam's nephew, and on the Adani Group, Adani Green Energy, and Adani Ports & SEZ.

User:Hatchens who only made three edits to Gautam Adani also edited the articles on Pranav Adani and Karan Adani, Gautam's son, as well as Adani Group, Adani Enterprises, Adani Green Energy, and Adani Transmission, until he was blocked in 2022 for a "general pattern (that) seems to have been to accept AfC (Articles for Creation) drafts written by other UPEs. Maybe also some direct paid edits to articles" according to Joe Roe, a widely respected editor.

User:UncleScrooze, another blocked editor who edited this article, also edited Adani Group, Adani Ports & SEZ, and Karan Adani. Other socks who edited this and other Adani-related articles include User:Bernice2019 (2 other articles) and User:Blazin777 (3 other articles).

In total 25 socks edited this article.

The article on Priti Adani, the wife of Gautam and the chairperson of the Adani Foundation, was created as a draft article on March 8, 2021, and moved to mainspace as a regular article 30 minutes later by User:Sallauddin786. They are not a blocked sockpuppet, but are a single-purpose account specializing in the Adani Foundation and Priti Adani and related articles such as Adani Transmission (which they created).

Last September a warning tag for UPE and COI editing was added to the top of the article resulting in a testy exchange on the talk page. User:Mainakchatterjee.tech was accused of UPE for adding a photo which they had uploaded to Commons to the article. Mainakchatterjee.tech owns a digital marketing service according to their user page. Both the warning tag and the accused editor remain on Wikipedia.

The only blocked socks to have edited the article are Bernice2019 and Blazin777.

The article for Karan Adani, the son of Priti and Gautam Adani, was created by an unusual roundabout process. User:Floyd1965 submitted two drafts to Articles for Creation but they were rejected in June and September 2018. User:VishalSuryavanshi89, an inexperienced editor who was suspected of paid editing, created the article as a redirect to Adani Group in the same month. User:Dirooz, another inexperienced editor, changed the redirect into a short stub article in October 2019. UncleScrooze then created it as a readable article with about 40 edits on November 29, 2019.

Last September the same warning tag was added to the top of the article resulting in the same testy exchange on the talk page as happened at the Priti Adani article after Mainakchatterjee.tech was accused of UPE for adding a photo to the article.

A total of six blocked sockpuppets including UncleScrooze, Hatchens, and Blazin777 edited the article.

The article about Pranav Adani, Gautam's nephew, was created in November 2018 by Similar2me. Two weeks later another sock, User:Venomous Sniper, who didn't seem to be representing the Adani family or firms, added a "multiple issues" tag at the top of the article, warning readers of a possible autobiography, BLP violations, and a non-encyclopedic essay-style format.

Similar2me and one of their sockpuppets, User:Danceofdeath666, made seven more edits over the following seven months. Then Hatchens, the user who was banned for abusing his position as an AFC reviewer, made a dozen edits the following year.

In 2021 a UPE warning tag was added to the top of the article with an explanation posted on the talk page by a sockpuppet investigations clerk. Similar2me and their sockfarm had been blocked. Since then the only blocked socks to have edited the article are Bernice2019 and Blazin777.

Only those six socks appear to have edited this article.

The article about Adani Group was created by a respected editor in 2006 and only had a few problems with sockpuppets before September 2010 when User:Kkm010 made five edits, followed by four edits in February 2012. But over two days in April 2013 Adanigrouponline, and the unregistered editor who claimed to work for Adani, made 19 nearly consecutive edits, rewriting the article, removing warning notices, and adding a statement of the corporate vision. In 2014 five socks edited the article, including Adanigroup.

In total about 22 socks edited this article, including Similar2me, UncleScrooze, Hatchens, User:Krishnavilasom Bhageerathan Pilla, and User:Candleabracadabra.

Krishnavilasom Bhageerathan Pilla created the article on Adani Enterprises in 2021 from a redirect by using the Articles for Creation process. They dominated the editing of the article in the amount of text contributed and the number of edits.

Four blocked socks edited this article, including a sock of Khaliwarriors, Hatchens, and Krishnavilasom Bhageerathan Pilla.

The article Adani Transmission was created by Sallaudinn786 (who is not blocked) on November 27, 2020, with four edits from the blocked sock User:Amkgp and two edits from Hatchens following on the 27th. The article was seldom edited and stayed essentially the same length, until January 26, 2023.

The only blocked socks who edited this article were Amkgp and Hatchens.

User:Globaltrends.LK created the Adani Green Energy article in March 2020. They were soon asked if they were a paid editor, and were soft-blocked for a violation of user name regulations.

Four blocked socks – User:Mirror1010, a sock of Similar2me, Hatchens, Amkgp, and User:Cyberfan195 – worked on this seldom edited article.

This article was created in 2006 and was dominated by unblocked SPA User:Vineethxavier from 2009 through 2012 with their 161 edits.

Six blocked socks – User:Lancelot1818, a sock of Similar2me, Hatchens, Amkgp, Kaliwarriors, UncleScrooze, and Cyberfan195 – edited this article.

Gautam Adani and the Adani Group of companies were recently accused by a short-seller of a very serious "con", involving accounting fraud, stock price manipulation and money laundering. As a result G. Adani has lost about $67 billion in net worth. Did he and his employees also try to "con" Wikipedia readers with non-neutral PR versions of related Wikipedia articles?

Almost certainly they did. Over 40 later banned or blocked sockpuppets or undeclared paid editors created or revised nine related articles on the Adani family and family businesses. Many of them edited several of the articles and added non-neutral material or puffery. A declared paid editor, using a company IP address, completely rewrote the Adani Group article. Others removed warnings about conflict-of-interest editing. Some created articles by unusual methods that circumvented Wikipedia's quality control systems.

Perhaps the most concerning finding is that Hatchens, an Articles for Creation reviewer, was banned for abusing his position and possibly corruptly approving several Adani articles. He edited seven of the nine articles examined here.

This interaction with ChatGPT was recorded on January 29, 2023

Author: Are any Wikipedia articles written by ChatGPT?

ChatGPT: No, ChatGPT is not capable of writing articles on Wikipedia. It can only generate text based on the input it receives and its training data.

Author: What should I do with a Wikipedia article someone wrote using ChatGPT?

ChatGPT: Articles generated by language models like ChatGPT are not suitable for use on Wikipedia as they are not written by humans and lack context and accuracy. If you have come across such an article on Wikipedia, you should report it to the Wikipedia community for review and potential removal, as Wikipedia has strict policies regarding the sources and reliability of the information on the platform.

Near the end of January, I ran across some odd-sounding articles in draftspace. All the articles had the same structure and layout, even though they were about different things. The articles also had impeccable English, though the author's comments did not. Suspecting something was up, I found an artificial intelligence (AI) article detector that then pronounced all these articles machine generated with greater than 99.9% confidence. Not knowing what to do, I went to the calm environ of the Administrators' noticeboard for incidents. That discussion is worth reading, as it shows a bunch of knowledgable Wikipedians struggling and debating how to deal with these articles. Were they hoaxes? Copyright violations? Good for publication? How does generated text fit within Wikipedia's requirements for articles?

As it turns out, an effort was already underway to develop a policy regarding articles written by ChatGPT and its relatives: Wikipedia:Large language models. There, and in its associated talk page, you can see the reasoning related to these articles. In short, AI-generated text is not reliably correct, may not have a neutral point of view, needs verification, can occasionally violate copyright, and can downright lie. This is all in its inherent nature. It is fed information from a large corpus of text, much of which would not meet Wikipedia's sourcing and neutrality criteria, and it synthesizes its output without regard as to whether the text maps to a real source. To quote the ChatGPT general FAQ: "These models were trained on vast amounts of data from the internet written by humans, including conversations, so the responses it provides may sound human-like. It is important to keep in mind that this is a direct result of the system's design (i.e. maximizing the similarity between outputs and the dataset the models were trained on) and that such outputs may be inaccurate, untruthful, and otherwise misleading at times."

I then started going through recent drafts and new articles looking for text reminiscent of the text I had seen in the first articles I identified. It didn't take long to find more. The current limiting factor is that I don't have the tools for rapidly reviewing Drafts as I do for new articles as a new page patroller, and I don't have the resources (including time and patience) needed to do this consistently and daily.

I've put the {{AI-generated}} template on those articles and had not one author disagree with the finding. You can search for the template with hastemplate:AI-generated in the Wikipedia search box. Expand the search to Drafts to see the drafts so marked. About sixty articles have been tagged. Several of the previously tagged articles have either been deleted or de-tagged once the generated text was replaced with real text, but many remain. You can then read those remaining examples and get a feel for AI-generated articles.

Editor's note: If you are reading this in the future and none of these are available, some representative drafts have been retained more permanently at User:JPxG/LLM dungeon.

I have been conservative in identifying articles: only testing articles that had a similar appearance and using > 99% assurance that it was machine-generated. I am sure I've missed many more articles. I was looking for typical phrases like "in conclusion" starting the last paragraph, use of the article's title repetitively without abbreviation or variation, and consistent sentence and paragraph length. A more sophisticated AI user would use better prompts to the AI software and produce harder-to-detect output; the ones I've found typically were produced by asking ChatGPT something like "Write a Wikipedia article about XXXX."

I test for articles typically using https://openai-openai-detector.hf.space/, though other sites exist, including https://detector.dng.ai/, https://gptzero.me/, https://platform.openai.com/ai-text-classifier, and https://contentatscale.ai/ai-content-detector/. Before testing, I remove headings, inline references, and other text and markup that appears to have been added after text generation, as those can confuse the analyzer.

Is this a real problem? I believe it is. Many of the articles sound reasonable but may have serious errors. The conversation at the administrators' noticeboard includes an analysis of a generated article on geckos. The article contains a lot of specific plausible-sounding information (e.g., size range), much of which is wrong.

ChatGPT will even provide references if requested, but those references are synthesized from its input text and, while sounding correct, usually do not point to real articles. For example, when I asked it for references on an article ChatGPT wrote for me on Sabethes cyaneus (a mosquito), one of the references was "Sabethes cyaneus" (Encyclopedia of Life): https://eol.org/pages/133674. That page does exist, but is for Clavaria flavopurpurea, a fungus. Another reference it provided also had a link, but the link pointed to an article about a mink, and the reference itself was fictional.

There are efforts to improve these programs, and I am sure that eventually they will be successful. Currently, however, those efforts fall well short. One such effort, "Elicit" (elicit.org), only searches research papers and summarizes them. I asked Elicit "What are the characteristics of Sabethes cyaneus?" It summarized one reference as "Sabethes cyaneus is a species of frog."

These false but plausible answers are an inherent property of the current models and is called "hallucination".

Even once these programs improve, there will still be significant concerns limiting the direct use of generated text, such as:

1. Did the program only use sources acceptable to Wikipedia?
2. Is the information up to date?
3. Can the program identify correct references? (One of the biggest hurdles, as the inherent nature of current models is that the output is not linked to a specific source.)
4. Will the program avoid hallucinating?

However, programs like ChatGPT are great for generating ideas for articles and helping to "mock up" a good article, if the user takes a sophisticated view of the output, using it more for inspiration than for a source of truth. The proposed policy Wikipedia:Large language models has additional information on how these programs can be used to improve Wikipedia.

Nine featured lists were promoted this period.

List of awards and nominations received by Zayn Malik, nominated by Harushiga

English singer Zayn Malik has garnered numerous awards and nominations throughout his career, which began in 2010 through the formation of the boy band One Direction. Malik received two Pop Awards at the BMI London Awards for co-writing the band's songs "Story of My Life" and "Night Changes". He left the group in 2015 and signed a solo record deal with RCA Records. He began his solo career in 2016, which led to many more successes.

List of lilioid families, nominated by Dank

The lilioid monocots are a group of 33 interrelated families of flowering plants. They generally have tepals (indistinguishable petals and sepals) similar to those on the true lilies (Lilium). Like other monocots, they usually have a single embryonic leaf (cotyledon) in their seeds, leaves with parallel veins, scattered vascular systems, flower parts in multiples of three, and roots that can develop in more than one place along the stems.

List of Los Angeles Chargers starting quarterbacks, nominated by Harper J. Cole

The Los Angeles Chargers are an American football franchise who play in the National Football League (NFL). They began play in Los Angeles in 1960 as charter members of the American Football League (AFL), switched cities to San Diego the following season, and returned to Los Angeles in 2017. The AFL was formed as rivals to the established NFL, though the leagues would later merge, with all AFL teams including the Chargers officially joining the NFL in 1970.

List of World Heritage Sites in Sri Lanka, nominated by Tone

We've talked about World Heritage sites a lot, because a lot of work has gone into them, largely thanks to Tone. As of 2022^[update], Sri Lanka has eight sites on the list. The first three sites, the Ancient City of Polonnaruwa, the Ancient City of Sigiriya, and the Sacred City of Anuradhapura, were listed in 1982. The most recent site, the Central Highlands of Sri Lanka, was listed in 2010. The Central Highlands and the Sinharaja Forest Reserve are natural sites, the other six are cultural. In addition, Sri Lanka has three sites on its tentative list.

List of Hot R&B Sides number ones of 1959, nominated by ChrisTheDude

Another of our series on the Billboard record charts, featuring the most popular music in various genres for each year.

Paul Rudd on screen and stage, nominated by Lady Lotus

Paul Rudd is an American actor, comedian, writer, and producer. His career began in 1992 when he played a recurring role in the television series Sisters until 1995. In 1995, he made his film debut opposite Alicia Silverstone in the cult film Clueless, and starred as Tommy Doyle in Halloween: The Curse of Michael Myers. Rudd has frequently collaborated with filmmaker Judd Apatow in such comedy films as Anchorman: The Legend of Ron Burgundy (2004), The 40-Year-Old Virgin (2005), Knocked Up (2007), Forgetting Sarah Marshall (2008), This Is 40 (2012), and Anchorman 2: The Legend Continues (2013). Since 2015, he has played Scott Lang / Ant-Man in the Marvel Cinematic Universe, appearing in Ant-Man (2015), Captain America: Civil War (2016), Ant-Man and the Wasp (2018), and Avengers: Endgame (2019). He has also starred in the supernatural comedy film Ghostbusters: Afterlife (2021).

List of lamiid families, nominated by Dank

The lamiids are a group of about 40 interrelated families of flowering plants. They include about 40,000 species, representing one-seventh of the total diversity of flowering plants, and about half of all asterid species. Like most asterids, they tend to have petals that are fused with each other and with the bases of the stamens, and just one integument (covering) around the embryo sac. In lamiids, the fusion of the petals tends to occur late in their development, and the bases of the petals are usually beneath the ovaries.

List of bibliographies of works on Catullus, nominated by Umimmak

Gaius Valerius Catullus (c. 84 – c. 54 BCE) was a Latin poet and a leading figure of the Neoterics. Catullus and his poetry, comprising 113 poems, have been the subjects of many books and papers in classical studies and other fields, including literary criticism, gender studies, and cultural studies; there are many critical editions, commentaries, translations and student guides of his poetry as well. Even in 1890, Max Bonnet wrote that Catullus was "inundated" with academic publications concerning his life and works.

List of National Football League annual receptions leaders, nominated by Newtothisedit

In American football, passing, along with running (also referred to as rushing), is one of the two main methods of advancing the ball down the field. Passes are typically attempted by the quarterback, but any offensive player can attempt a pass provided they are behind the line of scrimmage. To qualify as a passing play, the ball must have initially moved forward after leaving the hands of the passer; if the ball initially moved laterally or backwards, the play would instead be considered a running play.

• These lists exclude the Wikipedia main page, non-article pages (such as redlinks), and anomalous entries (such as DDoS attacks or likely automated views). Since mobile view data became available to the Report in October 2014, we exclude articles that have almost no mobile views (5–6% or less) or almost all mobile views (94–95% or more) because they are very likely to be automated views based on our experience and research of the issue. Please feel free to discuss any removal on the Top 25 Report talk page if you wish.

Going to do this one in reverse from how we normally do it, because, frankly, there wasn't that much going on five years ago, and a whole lot to say about fifteen years ago.

Citizendium, Larry Sanger's first attempt at a Wikipedia rival (he would go on to make many more), was doing fairly well at the time, but mismanagement would eventually kill its momentum. Meanwhile, in the wake of various incidents that caused chaos, it was made impossible to delete the Main Page of Wikipedia. Don't test this out. Seriously, don't. Though you might get a special barnstar if you do:

		The Destroyer of the Wiki Barnstar
		OH MY GOD WHAT DID YOU DO THERE'S MONKEYS AND FISH EVERYWHERE SOMEONE HELP

Finally, on a more serious note, this was also the point where controversy over Wikipedia hosting images of Muhammad reignited. There had been some controversy in 2006 when the Jyllands-Posten Muhammad cartoons controversy hit the main page, but this was the start of demands that all such cartoons be removed. In this issue's Cobwebs, we finally publish an article from 2010 about the point where we lost the moral high ground on such issues.

Lovers of regular Signpost segment the Traffic Report will find its presumptive origins in a Special Report in the 4 February 2013 issue that analysed some of the interesting trends and spikes. The film Star Trek[:] [I/i]nto Darkness caused pretty much the expected amount of controversy as to how it should be capitalised. A list of Wikipedia hoaxes provides all the fun reading one would expect.

Looking in more detail, portals were still a big deal back then; they're fairly moribund now: Featured portals would close in 2017, and there was an attempted purge in in roughly 2019. Why? It's hard to say. Perhaps as Wikipedia's search tools improved, portals ceased to be a key way to find articles; perhaps it has to do with the general decline of WikiProjects. Portal:Opera is still doing great as a way to show off content in WikiProject Opera, but there's certainly a lot fewer WikiProjects than we once had. I still remember when, if you wanted help on basically any subject, you'd just find the relevant WikiProject and ask them.

We'd be remiss not to include this wonderful illustration by Jon Robson from the Humour section:

We also had a short (but pretty decent) interview with The Rambling Man, who, at least at the time, was Wikipedia's top contributor of Featured Lists. A sample:

As covered in last week's Signpost, the Acehnese Wikipedia has erupted in controversy over images of Muhammad hosted on Commons.

This is by no means a new debate. In 2006, the article on the Jyllands-Posten Muhammad cartoons controversy was featured on the main page, and caused significant controversy for including the cartoons. In 2008, a petition to delete images of Muhammad circulated. However, as long-standing policy stated, like Wikipedia itself, our image host, Wikimedia Commons, is not censored. That it could cause offense was not sufficient to remove an image.

Amongst those advocating for this view was Jimbo Wales. cited his free speech advocacy, and stated that "we can not deviate from our goals to accommodate [those governments who would force Wikipedia to be censored]."

However, the current petition comes after we have lost some of the moral authority we once had.

Jimbo Wales, out of fear of a media attack, led by Fox News, about allegations of pornography on Wikipedia, instituted a massive deletion of content from Commons, including many examples of artwork by notable artists. For example, the artwork to the right, by Franz von Bayros, was personally deleted by Jimbo, who even edit warred to keep it deleted. On being challenged about this deletion, Wales wrote:

He also deleted several works by major artists, for example, File:Félicien_Rops_-_Sainte-Thérèse.png by Félicien Rops, and numerous line art illustrations used to illustrate articles on sexual content.

Only long after these deletions were done did he state his reasons:

It wasn't even effective: Fox News shortly thereafter posted an article attacking Wikipedia.

If Wikipedia is going to sacrifice its moral high ground and neutrality – for saying that things offensive to Fox News are worth mass deletion sprees including historic artwork, but that the complaints of Muslims are not, is highly non-neutral – we should not sell ourselves cheap. We recently did, and only the effective loss of all Jimbo Wales' powers over his actions leaves us any moral high ground at all. This petition is much harder to deal with, as we have shown that, yes, we will give into pressure – but only if it comes from our mainstream Western culture.

Back by popular demand: this little ditty, taken from Wikipedia:Songs about Wikipedia/The RfA Candidate's Song, was recorded with considerable panache and musicianship back in 2006 – which means there's probably a whole new generation of editors who've never heard it. Enjoy! Lyrics below.

I am the very model of a modern Wikipedian:

I've knowledge of Greek drama, both comedic and tragedian;

I know historic battlefields from Ancient Rome to World War Two,

and neutral is the mode in which I always keep my point of view!

I'm very well acquainted, too, with Polynese ethnology.

I understand Samoan lore and Mā-ori mythology.

From mountain peaks of Suriname to passes of the Great Divide,

I see to it that everything is quite correctly wikified!

He sees to it that everything is quite correctly wikified!

He sees to it that everything is quite correctly wikified!

He sees to it that everything is quite correctly wiki-wikified!

Some people think my entries are little more than trivia —

that episode of Barney or that woodwind of Bolivia —

and yet, in matters great and small, high and low and median,

I am the very model of a modern Wikipedian.

In short, in matters great and small, high and low and median,

He is the very model of a modern Wikipedian!

I SIGN all of my comments; and give summaries for each edit;

I never BITE; I never POINT; I follow wiki etiquette;

I assume good faith when wiki-flamed, and wear a thickened wiki-skin.

For I am the very model of a proper wiki-citizen:

I'm often found at village pumps discussing rules and policy,

and judging notability while over at the AfD,

In matters wiki-sophic, I'm no exopede inclusionist,

but an incremento-eventuo-darwikian-delusionist!

an incremento-eventuo-darwikian-delusionist!

an incremento-eventuo-darwikian-delusionist!

an incremento-eventuo-darwikian-delusion-usionist!

I am the very model of a modern Wikipedian.

I wrote this wiki-parody to ease some wiki-tedium.

When dealing with my colleagues I'm a friendly wiki-editor,

but the sight of trollishness makes me a vandal-stalking predator;

When dealing with his colleagues he's a friendly wiki-editor,

but when provoked he can become a vandal-stalking predator!

Reverts and warnings I have made while on the recent change patrol,

I play some cat-and-mouse with them, but now I want to block-a-mole,

and so at last I must become a wiki admin-candidate:

since I'm my only fan, I have no choice but to self-nominate.

As prep for this I've learned about all bans and blocks and redirects,

now I can tell you anything on SEMIs and full page protects,

and when you hear all that I know of Wikipede sysop-ery,

you’ll say no better candidate has ever sought the moppery

you’ll say no better candidate has ever sought the moppery.

you’ll say no better candidate has ever sought the moppery.

you’ll say no better candidate has ever sought the moppa-moppery.

Now the adminship, as Jimbo says, is really no big deal at all:

many fail and so might I (my role in portal talk's been small).

But still in matters great and small, high and low and median

I am the very model of a modern Wikipedian.

In fact, in matters great and small, high and low and median,

He is the very model of a modern Wikipedian!