[EPIC][CORE-C] World-model query + symbolic attention: epistemic recall, provenance, identity, bounded TAPS projections, and source dependence #35
Labels
No labels
accessibility
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
question
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
nsaspy/symbolic-memory#35
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Parent: #11
Refines: #7 #10
Research: prolog-rlm#400 #403
Goal
Implement the durable query/attention surface that turns a huge semantic ledger into small, dependency-complete, provenance-bearing answers without flattening truth, relevance, identity, or coverage.
Own:
Prolog-RLM retains reasoning/profile semantics and Retrieval Expert policy. This epic provides durable indexed evidence and projection mechanics.
Hard invariants
Acceptance
After restart, query facts/rules/time/defaults/conflicts/procedures/constraints with exact source/provenance, reverse an incorrect identity link, produce a bounded dependency-complete projection, and run known-symbolic queries with providers disabled.