experiment log
Live CortexAgent Hippocampus Prefix Validation — 2026-06-27
- File
2026-06-27_use_agent_prefix_validation.md- Size
- 2.7 KB
- SHA-256
8467f8c754565bf6…
Primary source. This is the verbatim Oczy document. The analytical field notes on the research page interpret and summarize these sources.
Live CortexAgent Hippocampus Prefix Validation — 2026-06-27
Question
Does the live CortexAgent.use_hippocampus_prefix path actually generate a
useful ReservedPosition during articulate() and produce exact-token recall
in a real multi-fact turn?
Method
Added --use-agent-prefix to src/oczy/experiments/multi_fact_stressor.py.
When this flag is set:
- The stressor enables
agent.config.use_hippocampus_prefix = True. _recall_fact()now passesrecall_query=querytoagent.articulate(), so the agent has a query to drive hippocampal replay.- The stressor wraps
agent.set_reserved_position()to capture the source of anyReservedPositionthe live agent sets (becausearticulate()clears it infinally).
Ran real-driver scalar and hybrid with --auto-consolidate --hybrid-cap 0 --use-agent-prefix --length 512.
Results
| mode | prefix_source | recall_a | recall_b | co_recall | consolidation_strength |
|---|---|---|---|---|---|
| scalar | hippocampus | 1 | 1 | 1/1 | 10.0 |
| hybrid | hippocampus | 1 | 1 | 1/1 | 35.99 |
Both configurations reach exact-token co_recall via a prefix generated by the
live CortexAgent, not by the stressor wrapper.
Interpretation
- The closed loop works end-to-end:
- perceive long turn → hippocampus stores high-surprise traces
- consolidate → traces remain available
- articulate with recall_query → agent replays relevant traces
- derive ReservedPosition from replay → apply as reserved-position prefix
- exact-token recall achieved.
- The stressor wrapper's own
_derive_prefix_from_hippocampusis no longer required when--use-agent-prefixis active; the agent handles it. - Scalar and hybrid are indistinguishable at this probe resolution.
Limitations
- Hippocampus keyword extraction still relies on query tokens and content words; it has not been tested on out-of-vocabulary or paraphrased queries.
--use-agent-prefixis a stressor flag; production use requires enablingCortexAgentConfig.use_hippocampus_prefixdirectly.- No comparison was made to the hand-coded prefix path in the same run, but
earlier runs show it also reaches
co_recall=1/1.
Next steps
- Remove or deprecate the stressor-only
--auto-prefixnow that--use-agent-prefixvalidates the agent path. - Generalize keyword extraction with explicit expected targets from a knowledge store.
- Measure IdentityHypernetwork adapter effects on the same probe.
Artifacts
src/oczy/experiments/multi_fact_stressor.pysrc/oczy/experiments/tests/test_multi_fact_stressor.py
Commits
e580526— Add--use-agent-prefix.ab1134a— Update SUMMARY.md with run #98 result.
Run
Run #98: benchmark code_qa_accuracy=1.0, fast suite 310 passed.