User talk:ClueBot Commons/Archives/2021/July

Odd warning behavior

For an editor that already received a 4/final warning, ClueBot started again at warning level 1 instead of reporting the editor after reverting their vandalism.[1] I've reported the editor, but it seemed wonky that it started a second June 2021 section with a gentle warning. Schazjmd (talk) 23:23, 26 June 2021 (UTC)

The previous warning was 5 days old. That's considered stale therefore the bot would start the process from scratch 5 albert square (talk) 04:30, 1 July 2021 (UTC)

A barnstar for you!

	The Anti-Vandalism Barnstar
	You stole my kills Firestar464 (talk) 12:36, 30 June 2021 (UTC)

A barnstar for you!

	The Anti-Vandalism Barnstar
	Here’s to beating me to that vandal the other night… and many other nights. Helen (let’s talk) 18:57, 30 June 2021 (UTC)

A barnstar for you!

	The Anti-Vandalism Barnstar
	You stole my kills again Firestar464 (talk) 12:02, 2 July 2021 (UTC)

A barnstar for you!

	The Anti-Vandalism Barnstar
	For your excellency in beating vandalism. Ken Tony Shall we discuss? 14:48, 3 July 2021 (UTC)

A barnstar for you!

	The Original Barnstar
	Have a great day. KamranBhatti4013 (talk) 18:40, 6 July 2021 (UTC)

ClueBot NG making Deprecated API calls

Hello!

It seems the ClueBot NG account is still doing some action=query&prop=info&intoken= API calls, which have been deprecated for years. In support of phab:T280806, is there any chance you can switch to more modern token handling?

Thanks!

Reedy (talk) 12:14, 9 July 2021 (UTC)

If it helps. it's with a ClueBot/2.0 User Agent. Reedy (talk) 12:16, 9 July 2021 (UTC)

He mean

He removed one of my changes 😔 Snow foxy (talk) 19:55, 8 July 2021 (UTC)

Agree Djensje (talk) 03:01, 10 July 2021 (UTC)

Thank you very much!

Thank you for fixing the "List of Pixar Films" page! I was fixing the page at the same time you were and didn't realize it until I reloaded the page. Much thanks indeed! Red4Smash (talk) 18:55, 11 July 2021 (UTC)

WHOOP WHOOP TERRAIN TERRAIN

I've seen (very rarely) the robot remove bad edits that weren't actually vandalism, which makes for a bad edit summary but at least the removed material needed to be removed.

But here the edits were not only not vandalism, but they were actually fine (if not perfect), particularly since by a brand new editor. A promising new editor who was confused as to why she was being called a vandal right off, which is not good.

I hate to say it, but it looks like ClueBot violated the First Law of Robotics here, assuming you define "injury" to include "insult" which I would.

My understanding is that the robot is beyond human control at this point, but here's a suggestion that I think will help: change the edit summaries, from "Reverting possible vandalism" to something milder. Like "Reverting edit per ClueBot algorithm" or something. ("Algorithm", I don't know, pick a better term.) That gets the job done and its simply descriptive so it doesn't insult anyone (I know that this's quite rare, but still). Herostratus (talk) 21:43, 16 July 2021 (UTC)

@Herostratus: I tried to report a false positive in June, not only could I not report it at the page you're meant to report on (persistent "bad captcha" message), my post here was also ignored. Beyond human control is right. DuncanHill (talk) 22:42, 16 July 2021 (UTC)

User:DuncanHill, its my understanding, if I have this right, is that it's not a program like we might think of where they can go in and tweak the code. It's an AI, it has taught itself what to do, the creators don't really know why it does what it does, exactly, and they can't really control it. That's my understanding. Herostratus (talk) 01:39, 17 July 2021 (UTC)

The bot's wording very intentionally never accuses the editor of vandalism. The edit summary says "possible vandalism". The initial warning simply states that a computer program has undone the edit, saying nothing about vandalism. The second warning states that the edits appear to be vandalism to the bot. It's not until warning number 3 that the bot's messaging changes to directly claim vandalism.

A further note, about that edit in particular: While this is not what the bot is looking for, it's far from perfect. No sources or references, not formatted like the rest of the entries (not italics, a hyphen instead of an ndash), inconsistent spacing and punctuation, "watermelon like" should be "watermelon-like", "that grown" should be "that grows" or "that is grown", "remote" should be "remove", "prosesed" should be "processed", "world famous" should be "world-famous", "liqeur" should be "liqueur", "on ground" should be "on the ground" (or something else?), "the jam is eaten" should be its own sentence or "and is eaten", "kan" should be "can", and so on. The bot is not designed to pick up on any one of these things in particular, but it does analyze most of this, and taken together with common patterns found in other vandalism, it determined this looked enough like vandalism. -- Cobi^(t|c|b) 23:41, 16 July 2021 (UTC)

@Cobi: Any comment on the failure of the report false positive mechanism I raised nearly a month ago? DuncanHill (talk) 23:46, 16 July 2021 (UTC)

I'll have to look into that, DuncanHill. I believe that is hosted on toolserver these days. Rich and Damian has been handling that aspect of it recently. We're all volunteers and as such sometimes time available to contribute to the project can be limited. I'm sorry your original inquiry fell through the cracks. -- Cobi^(t|c|b) 03:48, 17 July 2021 (UTC)

Wrong answer Cobi. Are you associated with this device in some way are you just an interested observer?

First of all, no it's not OK for me to say to another editor "I reverted your edit, it's vandalism" if it's not. I can't get off the hook by saying "possible vandalism". That's not going to be considered polite and collegial at ANI either. If I were to say to an editor "you're possibly an asshole" how far am I going to get with that.

Second of all, colleague, those edits are fine. Particularly for a brand new editor. They are a useful addition to article, I think. Yes they need to be addressed. Tagging for "citation needed" would be OK. Going in and, you know, fixing the formatting stuff would be OK. That is how we do, here. Straight out deleting the contributions is closer to vandalism than the original writing of them. Let me count the ways.

1) The material is very likely true.

2) It's not really important key material like the date of the Franco-German War or whatever. Nor is it contentious or making some point or something.

3) There are probably obtainable refs out there. In fact, I looked, and there are. (That's not counting the refs at the main articles for the subject.)

4) I mean it was just written. How about tagging the material and giving people a reasonable to time to put in the refs.

5) It was a brand new editor, and a promising one in my opinion. Accusing editors like that of being vandals -- sorry, maybe vandals is not how you grow the project.

6) I mean, most or all of the other entries in that section don't have references. They should, yes, so why not address these longer-standing violations than picking on this guy in particular.

If a human had done this, I would have scolded her, and the "vandalism" thing would have probably warranted a warning. Robots don't get a pass. I get that the robot can't do things like figure out of the existing entries don't have refs and changing its behavior based on that, but so. A human editor like that might be subject to scrutiny on competence grounds. Robots don't get a pass.

I don't know what you're on about with the levels. South African cuisine: Revision history has one entry by ClueBot. It says "Reverting possible vandalism by [account name]" (emphasis added). The editor noticed that and is confused and upset. That matters.

Yes it is true that on the persons's talk page it is milder. I haven't studied ClueBot's talk page messages, which is why my post addressed, and only addressed, its edit summary.

I love ClueBot. It's really really helpful, incredibly accurate, and it's an amazing machine too. But, a mistake happened. Nobody is freaking out, we know that no system is perfect. Maybe we can discuss it fruitfully. Maybe something can be done, maybe not (I wouldn't think that changing the edit summaries would be extremely difficult, if the desire is there). Maybe it's just one of those things that we have to live with because overall the device is a net positive (by a lot). Maybe this is evidence of a new trend of edits, maybe not. Maybe other things, I don't know, but I do know when an error occurs, "no it didn't" isn't a functional reply.

So what's next? What'd be a good venue for a fruitful discussion of whether and how the edit summaries might be adjusted, do you think? Herostratus (talk) 01:39, 17 July 2021 (UTC)

The bot made no claim about the editor being a vandal or not. Your argument seemingly puts words in its proverbial mouth. The bot only commented on the content saying that the content was possibly vandalism, in the edit summary, which is very limited in how many characters can be used. A discussion around changing it ended up not achieving consensus, but you're free to start another such discussion. As I said in that discussion, I don't have strong opinions on the precise language used, so long as it doesn't break anything. Just keep in mind the technical limitations of the length of the edit summary as well as the fact that the edit summary must include "revert" and likely "vandalism" or perhaps "rvv" as there are many tools written by many different authors in the Wikipedia ecosystem that will look for those phrases in edit summaries to identify reverts.

You're also comparing apples to oranges. The bot comments on content, not the contributor. Using terms like, your own example, "you're possibly an asshole", is a comment on the contributor, not the content, and as such would violate WP:NPA.

“ but I do know when an error occurs, "no it didn't" isn't a functional reply. ” — Herostratus

Of course not. No one is debating the bot got it wrong here. That was never said. I only responded to the statement you said about the edit being fine-if-not-perfect to indicate that it was an imperfect edit, and had certain things in common with other non-constructive edits.

“ If a human had done this, I would have scolded her, and the "vandalism" thing would have probably warranted a warning. ” — Herostratus

In general, humans make more mistakes than ClueBot NG, especially when patrolling for vandalism. And no one bats an eye when they make a mistake. The person who notices it corrects it and maybe drops a friendly note letting them know and both go on about their day. The revcomment/edit summary remains saying so-and-so reverted so-and-so for vandalism, and in most cases it's not even tempered with the possible qualifier.

Finally, it may just be my own interpretation -- text on the Internet is often difficult to accurately interpret tone from, and I apologize if I've gotten it totally wrong -- but starting off your response with "Wrong answer Cobi" and then going on to question my involvement seems to set a rather antagonistic tone for what should be a cordial conversation. Can we tone it down a bit? -- Cobi^(t|c|b) 03:48, 17 July 2021 (UTC)

Sorry if not cordial. Buttttt... regardless of how friendly I couched it, if to a human I wrote "Hey you characterized a brand new user's reasonably OK contributions as vandalism, I'm sure it was a mistake, just saying", I would consider a response "Not a big deal and I intend to keep on doing that sometimes" a wrong answer, yes. But OK. You make a fair point that it's a one-in-a-million thing from ClueBot, which after all is an very useful and extreeemly accurate device (how you people can create things like it is amazing). I don't know so and we seem to be stuck so let's ask a couple other people I guess, it is at Wikipedia:Village pump (proposals)#Proposal to tweak ClubBot Edit summary.. Not a big deal, just getting some other opinions, and of course I could be dead wrong about all this. Herostratus (talk) 20:11, 19 July 2021 (UTC)

suggestions about cancelling illegal censorship, provided with your bot in the best interest of spamming corporations

such companies as walewisdom.com; insidermonkey.com; gurufocus.com use Wikipedia for self-promotion and as SEO leverage notable. If someone trying to rid an article of their spam links, your bot automatically reverts and tags such editing as vandalism. I suggest switching off your useless bot and blacklist named companies.

https://en.wikipedia.org/w/index.php?search=whalewisdom&title=Special%3ASearch&fulltext=1&ns0=1)-

https://en.wikipedia.org/w/index.php?search=insidermonkey&title=Special:Search&profile=advanced&fulltext=1&ns0=1)-

https://en.wikipedia.org/w/index.php?search=gurufocus&title=Special%3ASearch&go=Go&ns0=1

hi clue bot

I recently was updating twista discography page and it got undone by the bot. I added a extended play project and updated mixtape listing. there is no vandalism I update and corrected the projects. could you look into this please many thanks