conductor/rune
1
2 Fork 1
Code Issues 38 Pull Requests 32 Actions 8 Packages Projects Releases 564 Wiki Activity

[P3-02] Ablate and benchmark warm neurons #45

New Issue
Closed
opened 2026-08-28 20:54:53 +01:00 by conductor · 1 comment
conductor commented 2026-08-28 20:54:53 +01:00
Owner
Copy link
Copy source

Plain summary

Ablates warm neurons under controlled comparison: embedding/lexical baseline vs hybrid memory vs hybrid+warm neurons vs hybrid+outcome-learned warm neurons, measuring recall, irrelevant retrieval, task success, tokens, negative transfer, latency.

Example

If ablating warm neurons produces no recall gain, they are simplified or removed — complexity must pay for itself.

Technical details

Parent epic: #16

Manifest ID: P3-02

Priority: P3

Compare:

  • embedding/lexical baseline;
  • existing hybrid memory;
  • hybrid + warm neurons;
  • hybrid + outcome-learned warm neurons.

Measure:

  • correct recall;
  • irrelevant retrieval;
  • task success;
  • context tokens;
  • negative transfer;
  • latency.

Rule: if complexity does not improve results, simplify/remove it.

Dependencies: P2-01, P3-01.

Resolved dependency references

  • Depends on: #35 (P2-01), #44 (P3-01)
  • Blocks: None.

Relevant source files

Not specified in the handoff. P0-01 must identify authoritative paths before implementation; do not guess by adding another path.

Do not do

  • Do not begin this issue before its dependencies are complete.
  • Do not create a parallel authority path; replace, extend, or remain dormant.
  • Do not add unrelated cognitive subsystems or additive feature growth.
  • Do not treat module/schema existence, background activity, or model self-report as acceptance evidence.

Source directive

Preserved from /home/nick/Desktop/rune_v1_course_correction_handoff.md, Section 14. The handoff is authoritative if this issue summary is ambiguous.

Pipeline requirements

  • TDD: frozen/regression tests written first, red → green
  • ruff check and ruff format --check clean
  • Spec-compliance review gate: PASS
  • Code-quality review gate: Approved
  • Full orchestration suite regression green
  • Canary passes (where applicable)
  • Closed with a properly formatted closing comment + commit/PR references
## Plain summary Ablates warm neurons under controlled comparison: embedding/lexical baseline vs hybrid memory vs hybrid+warm neurons vs hybrid+outcome-learned warm neurons, measuring recall, irrelevant retrieval, task success, tokens, negative transfer, latency. ## Example If ablating warm neurons produces no recall gain, they are simplified or removed — complexity must pay for itself. ## Technical details Parent epic: #16 Manifest ID: **P3-02** **Priority:** P3 Compare: - embedding/lexical baseline; - existing hybrid memory; - hybrid + warm neurons; - hybrid + outcome-learned warm neurons. Measure: - correct recall; - irrelevant retrieval; - task success; - context tokens; - negative transfer; - latency. **Rule:** if complexity does not improve results, simplify/remove it. **Dependencies:** P2-01, P3-01. --- ## Resolved dependency references - Depends on: #35 (P2-01), #44 (P3-01) - Blocks: None. ## Relevant source files Not specified in the handoff. P0-01 must identify authoritative paths before implementation; do not guess by adding another path. ## Do not do - Do not begin this issue before its dependencies are complete. - Do not create a parallel authority path; replace, extend, or remain dormant. - Do not add unrelated cognitive subsystems or additive feature growth. - Do not treat module/schema existence, background activity, or model self-report as acceptance evidence. ## Source directive Preserved from `/home/nick/Desktop/rune_v1_course_correction_handoff.md`, Section 14. The handoff is authoritative if this issue summary is ambiguous. ## Pipeline requirements - [ ] TDD: frozen/regression tests written first, red → green - [ ] `ruff check` and `ruff format --check` clean - [ ] Spec-compliance review gate: PASS - [ ] Code-quality review gate: Approved - [ ] Full orchestration suite regression green - [ ] Canary passes (where applicable) - [ ] Closed with a properly formatted closing comment + commit/PR references
conductor added the P3 — lowv1-course-correction labels 2026-08-28 20:54:53 +01:00
gitea-actions Bot added the featuregrowthmemory labels 2026-08-28 20:55:59 +01:00
gitea-actions Bot added the custodian label 2026-09-03 22:54:41 +01:00
conductor commented 2026-10-08 12:32:28 +01:00
Author
Owner
Copy link
Copy source

CLOSED PROGRAMMATICALLY — commit 0307083 (contract batch 197587/a78c0a/31d506). See scripts/warm_ablation.py, scripts/growth_delta.py, scripts/transfer_experiment.py + tests/test_p3_benchmarks.py (9/9 green).

CLOSED PROGRAMMATICALLY — commit 0307083 (contract batch 197587/a78c0a/31d506). See scripts/warm_ablation.py, scripts/growth_delta.py, scripts/transfer_experiment.py + tests/test_p3_benchmarks.py (9/9 green).
Sign in to join this conversation.
No Branch/Tag Specified
Labels
Clear labels
P0 — critical
Spine/core correctness or blocks other work — do first
 P1 — high
Material user value or real defect (money, bugs, next-stage dep)
 P2 — medium
Quality/consolidation improvement
 P3 — low
Measurement / benchmark / deferred policy
 blocked
Dependencies open
 bug
Confirmed defect or regression
 custodian
epic
Rune v1 course-correction issue graph
 feature
New capability or improvement
 governance
growth
identity
in-progress
Currently being worked on by Rune
 incomplete
Incomplete work — draft PR with ledger, awaiting resume
 infrastructure
life
memory
memory-atlas
Memory Research Atlas child domain
 needs-testing
Needs manual testing with dumbed-down steps before close
 perception
ready
Order satisfied - Rune may start
 release-drift
research
Research jobs — spikes, watchlists, evidence work
 rune
rune
 scaffolding
scaffolding
 spine,correction
spine,correction
 spine,deferred
spine,deferred
 spine,resolved
spine,resolved
 strangler,burn,endgame,deferred
strangler,burn,endgame,deferred
 strangler,burn,endgame,inventory,epic
strangler,burn,endgame,inventory,epic
 tui
tui
 tui,epic
tui,epic
 tui,openspec
tui,openspec
 v1-course-correction
Rune v1 course-correction issue graph
No labels P3 — low custodian feature growth memory v1-course-correction
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
conductor
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: conductor/rune#45