Use the labels: seed signatures from them, and take them back

The labels have been arriving and sitting there. Now the shadow run
acts on all three kinds.

A report is advertising pointed at where detection found nothing, so
it becomes a signature in its own right -- that being the whole gap
the library exists to close, since the scan accounts for about 38% of
what the feeds imply is there.

A mark saying a break is right adds no audio, because the break is
harvested anyway. What it adds is that a person vouched for it.

A mark saying a break is wrong does two things. It stops that audio
being harvested, and it takes back any signature already held that
matches it. That second half is the one that matters: a signature
built from programme would cut the programme in every episode carrying
it, until somebody noticed. So his "no" removes it outright rather
than lowering a score.

Being pointed at outranks partners and occasions both. Those are ways
of inferring what a stretch of audio is; he was there. A confirmed
signature is trusted at once and stays confirmed -- he does not
un-hear it next week.

A report whose end was never corrected is trimmed to its first fifteen
seconds. An uncorrected end is wherever the 25-second jump landed
rather than where the advertising stopped, so its tail may be
programme -- and one ad unit is already far more audio than a landmark
fingerprint needs to be distinctive.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018AwnALZL6bD4VBtATDVv3B

1 files changed, 23 insertions, 0 deletions

diff --git a/docs/superpowers/plans/2026-10-20-corrections-and-signature-library.md b/docs/superpowers/plans/2026-10-20-corrections-and-signature-library.md
index 687a293..289ffc8 100644
--- a/docs/superpowers/plans/2026-10-20-corrections-and-signature-library.md
+++ b/docs/superpowers/plans/2026-10-20-corrections-and-signature-library.md
@@ -206,6 +206,29 @@ on the wrong side of a kill.
 
 Gated on `audioFromServer`, as the design note required.
 
+**The labels are used now — 2026-10-27.** The shadow run reads them and acts on three things.
+
+A **report** is advertising the listener pointed at where detection found nothing, so it is
+harvested as a signature in its own right. That is the gap the library exists to close: the scan
+accounts for roughly 38% of what the feeds imply, and a report is a finger on a piece of the rest.
+
+A **mark saying a break is right** does not add audio — the break is harvested anyway — so what
+it adds is that a person vouched for it.
+
+A **mark saying a break is wrong** does two things, and both matter. It stops that audio being
+harvested, and it takes back any signature already held that matches it. A signature built from
+programme would cut the programme in every episode carrying it until somebody noticed, which is
+the worst failure this system has; his "no" removes it rather than lowering a score.
+
+**Being pointed at outranks everything else.** Detection and the occasion count are both ways of
+*inferring* what a stretch of audio is. He was there. So a confirmed signature is trusted at
+once, and the confirmation is never unset — he does not un-hear it next week.
+
+**A report with a guessed end is trimmed to its first 15 seconds.** An uncorrected end is
+wherever the jump landed, not where the advertising stopped, so its tail may be programme. One ad
+unit is far more audio than a landmark fingerprint needs and is the part most certainly
+advertising.
+
 ### 3. The index spike — DONE 2026-10-24. **It passes.**
 
 **Do this before anything else in the library, because it decides whether the library is