[e2e] was double blind, now reproduceable results

[Joe Touch]

David P. Reed wrote:


>>> If the issue is prevarication, anonymizing protects the prevaricator.
>>
>>
>> If there exists an anonymization that doesn't kill the experiment, 
>> sure. But that presumes:
>>         a) such anonymization exists for that experiment
>>         b) the data source is comfortable with the anonymization
>>
>> Neither necessarily applies.
> 
> Prevaricators (liars and fraudsters) are not normally considered good 
> actor(YMMV!).   Hence I don't understand why you brought up data source 
> comfort as a relevant presumption.   The prevaricator is protected in 
> his bad actions whatever the data source's comfort.
> 
> I will use the simpler word liar in the future to prevent such confusion.

Liars cannot lie about an experiment you run - this is how SETI at home 
protects its results database. It computes something that users can't 
forge to make sure the results - and thus how much individuals 
contribute - aren't faked.

I.e., if my experiment on your fraudulent data is consistent with the 
anonymized data, I can't tell that you're a liar. Hopefully that's not 
the general case, though.

Joe
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 254 bytes
Desc: OpenPGP digital signature
Url : http://www.postel.org/pipermail/end2end-interest/attachments/20040526/3cd35659/signature.bin