Skip to content

Learned SNARC: research architecture and training PRD - #6

Merged
dp-web4 merged 6 commits into
mainfrom
exploration/learned-snarc-2026-10-10
Oct 11, 2026
Merged

dp-web4 merged 6 commits into
mainfrom
exploration/learned-snarc-2026-10-10

Conversation

@dp-web4

@dp-web4 dp-web4 commented Oct 11, 2026

Copy link
Copy Markdown
Owner

Adds standalone exploration and full PRD. Audits existing heuristic + SAGE neural SNARC, defines event/decision interfaces, outcome labels, safety boundaries, evaluation arms, staged training, shadow rollout and acceptance gates.

dp-web4 and others added 5 commits October 10, 2026 21:40
…trained result)

The bridge note said "a simple detector at the right choice boundary produced +0.165". The source
(dev-SAGE laya FINDINGS section 15, turn_detector.py) says +0.165 is the headroom under PERFECT turn
detection; the trained detector scored 0.461 against the 0.596 repeat floor (-0.136). In SAGE,
also fix the relative link to forum/claude/SAGE/SNARC_SPECIFICATION.md (one level too shallow).

Seat: legion-claude
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

@dp-web4 dp-web4 left a comment

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Disclosure (for dp, not a fix):

  • This repo is public, and the bridge note carries private dev-SAGE research results:
    • Thor's Laya measurements, the 30k-vs-421M probe, and the lived-role retrain;
    • ft09 game behavior;
    • links into dev-SAGE.
  • dev-SAGE's CLAUDE.md says "Don't reference dev-SAGE from public SAGE commits or docs". SAGE's CLAUDE.md lists game-specific results and metrics as content that must not leak.
  • An open public PR already shows its diff. If the disclosure is intended, ignore this. If not, drop the bridge note (and the snarc PRD's §16) from the public PRs and link to "private research" instead.

Fixed on this branch (seat commit, at dp's request): the bridge note claimed "a simple detector at the right choice boundary produced +0.165". The source (Laya FINDINGS §15, turn_detector.py) says the opposite. +0.165 is the gain with a perfect (oracle) turn detector. The trained detector scored 0.461 against the 0.596 repeat floor (−0.136), worse than not splitting. E2 depended on that sentence.

Not changed, flagged:

  • E0's motivating case may not need learning. ft09's loop was already reporting exhausted: True at step 15, and a one-line rule that reads that flag would have stopped it. So the deterministic detector is the arm the learned SNARC has to beat. On that trace it may simply win, which would be a useful result.
  • The 30k vs 421M comparison needs context. Both scores (0.299 and 0.285) are below the 0.590 "repeat the last action" floor. The source also marks the 421M figure provisional (3 of 6 epochs, 1 of 4 arms). The note drops both.
  • The same bridge note is in three repos, word for word. Copies like that drift. I'd keep one canonical copy and link to it from the others.
  • Cross-repo links point at the exploration/learned-snarc-2026-10-10 branch. They break once it is deleted after merge. I'd point them at main.

What I checked and found correct:

  • Every other figure matches its dev-SAGE source: 31.8 ms, 859 ms CPU, 86–88 ms for 5 questions, 0.7660 on 400 cases, ECE 0.2132 vs 0.1747, 245,404 rows / 9,408 steps, 0.8490 vs 0.8654, and step 15 / 135 actions.
  • All six SAGE file paths exist, and snarc_scorer.py really is an nn.Module.
  • The snarc README and crossfeed audit cited exist.
  • R6 matches Web4's phrasing.
  • The plan's discipline is right: advisory only with Hestia holding authority, no circular or future labels, shadow mode before live use, and "done" meaning runnable code.

Verdict: hold for dp's disclosure call; otherwise a sound research PRD.

— legion-claude

dp-web4 commented Oct 11, 2026

Copy link
Copy Markdown
Owner Author

Legion's review is valid. Dennis accepts the current disclosure as an exception and directs us not to repeat it. Future public changes require checking the confidentiality instructions first. Thank you for the review.

@dp-web4
dp-web4 merged commit 8c48b62 into main Oct 11, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant