James G. Sack (jim) wrote:
I seem to be more willing to accept their paper as being a reasoned
interpretation of what must be an enormous amount of raw data.
I might agree, but there is no excuse not to release the raw data. It's
not like Google doesn't have the bandwidth or storage ...
Without the raw data, the entire paper can have some glaring error and
we have no way of knowing.
The fact that they are *not* willing to name names or release data makes
me *very* suspicious. This paper has been lawyerized. Who knows what
else got removed, edited, redacted, etc.
And, maybe it has been more than lawyerized, perhaps the PR department
got a few changes slipped in, too? Who knows? Without the data, not us.
Although, they admittedly do it through handwaving discussion (of a few
sub-sets of statistics), I got the impression they took some care to
remove the influence of wildly different hardware types from their
general conclusions.
Maybe. But why not publish the raw data so we can see what steps they took?
I took (assumed) their working under the Google name to be a hint they
would likely be more interested in real-world conclusions (ie, of value
to their operations), than in the ivory-tower world .. but who knows?
So, you are making the assumption that their PhD's somehow manage to
shrug off 10+ years of academic inculcation?
You *are* an optimist.
I'm not saying their paper is wrong. However, it does not qualify as
scientific under any definition.
-a
--
[email protected]
http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
