Seal Phase 4AM whole-brain plastic interface audit without learning claim
This commit is contained in:
@@ -0,0 +1,13 @@
|
||||
# Phase 4AM — whole-brain plastic interface
|
||||
|
||||
Status: `PASS-EXACT-WHOLEBRAIN-PLASTIC-INTERFACE-NOT-LEARNING`.
|
||||
|
||||
All 144 zero-overlay runs reproduce sealed AK D18 exactly. All 120 fixed-overlay primary runs and 24 repeats are retained.
|
||||
The fixed overlay is the original float32 25% floor, added through the declared float64 SI bridge. No training occurred.
|
||||
|
||||
- novel_to_aj/matched_energy: KC event changes 30/30; MBON event changes 30/30; mask_recipient_MBON event changes 30/30; DAN event changes 30/30; MBON_downstream event changes 30/30; descending event changes 30/30; motor event changes 30/30.
|
||||
- novel_to_aj/physiological: KC event changes 30/30; MBON event changes 30/30; mask_recipient_MBON event changes 30/30; DAN event changes 30/30; MBON_downstream event changes 30/30; descending event changes 30/30; motor event changes 30/30.
|
||||
- seed_validation/matched_energy: KC event changes 30/30; MBON event changes 30/30; mask_recipient_MBON event changes 30/30; DAN event changes 30/30; MBON_downstream event changes 30/30; descending event changes 30/30; motor event changes 30/30.
|
||||
- seed_validation/physiological: KC event changes 30/30; MBON event changes 30/30; mask_recipient_MBON event changes 30/30; DAN event changes 30/30; MBON_downstream event changes 30/30; descending event changes 30/30; motor event changes 30/30.
|
||||
|
||||
Old artifacts and five deterministic-v2 references pass integrity/regression. This does not complete the learning goal.
|
||||
Reference in New Issue
Block a user