Post

@mrcheeze.github.io

Entirely distracted by the fact that this fact that this post was inexplicably written as if they don't know what negative numbers are

G Elliott Morris@gelliottmorris.com

We were investigating Wedgewood for faking their data and emailed them for comment this morning, ahead of publishing the findings tomorrow. They are now trying to cover up their fraud with the "we were doing a social experiment" excuse. Full story here: blog.fiftyplusone.news/p/fiftypluso...

blog.fiftyplusone.newsFiftyPlusOne just caught a pollster faking data — and they copped to itIn response to a request for comment on a FiftyPlusOne investigation, Wedgewood Polls admitted their data was bogus

21/10/26, 12:33 am1 repost17 likes

G Elliott Morris

@gelliottmorris.com

it's explained later but they aren't negative numbers, they are IDs with dashes, according to someone at the polling company...

MrCheeze

@mrcheeze.github.io

This distribution is definitely just "random signed 32 bit integers" (random numbers between -2,147,483,648 and 2,147,483,647), which is pretty typical for computer-generated IDs, and has 53% of its values be 10 digits in base ten. Not sure why the rep called it a dash.

G Elliott Morris

@gelliottmorris.com

that may be true, we're just reporting what were told about this!

yen is building stuff

@weiyen.net

For some inexplicable reason a lot of frameworks default to using *signed* int columns for IDs, but only generate positive-valued IDs (either UUIDs which are always positive, or autoincrementing pks starting from 1)

yen is building stuff

@weiyen.net

If I saw negative-valued IDs in the wild it would be a strong smell that some data-fakery shenanigans is happening

MrCheeze

@mrcheeze.github.io

Eh not particularly, I've seen random IDs that can be positive or negative loads of times. And that was the real data, the positive-only data was the fake stuff.