Detect syndication from text, not just from configured ownership

Connor's observation: two outlets running the same story can be caught by
comparing the text, without anyone having to know who owns whom.

Corroboration is now origin_count(), a union-find where two items share an
origin if EITHER they are in the same bucket, OR their text is near-identical
(normalised title match, or cosine >= 0.97). The rules are complementary:
buckets are same-owner/different-text (NYT filing five distinct AfD pieces),
text matching is different-owner/same-text (a local station reprinting wire).

On real data it fires exactly where it should: the vote-by-mail cluster
collapses 2 buckets -> 1 origin, catching the States Newsroom syndication
automatically -- the case previously fixed by hand in config -- and a
Smithsonian story collapses 3 -> 2, catching WCPO reprinting wire, which no
static bucket can express since WCPO is genuinely independent on local stories.
The eight Renoir-heist reports, each independently written, correctly stay at 8.
Across 91 multi-item clusters: 174 buckets -> 163 true origins.

Note this is the one place a lexical comparison is right. Clustering fails on
lexical methods because paraphrases share no wording, which is why the SimHash
stage was measured and deleted -- but syndicated copy is literally the same
bytes.

First formulation was wrong and the data caught it: summing syndication groups
and solo buckets produced 3 origins for a 2-bucket cluster. Syndication may only
ever reduce corroboration, which the union-find guarantees and a test asserts.

profile/config.toml

@@ -40,6 +40,12 @@ dim = 384
 threshold = 0.82
 window_hours = 48
 
+# Above this cosine, two items from DIFFERENT newsrooms are treated as the same
+# syndicated copy rather than independent corroboration. Deliberately high:
+# eight outlets each writing their own Renoir-heist headline stayed separate,
+# while a local station reprinting a wire dispatch collapsed correctly.
+syndication_threshold = 0.97
+
 [scoring]
 # Compare blocks by z-score WITHIN each block, never by raw cosine: cosine
 # magnitude is not comparable across blocks, and a plain max let one block win