Lock 25-tick as default short horizon - #74
Merged
Conversation
Record the 2026-09-08 horizon sweep: t25 is the chosen short horizon for composite/harness compare; 100 ticks degrades on average; research stays floored; 50/100 force-pause re-prompt storms. Co-authored-by: Jason <jkbennitt@users.noreply.github.com>
jkbennitt
marked this pull request as ready for review
September 8, 2026 13:50
jkbennitt
commented
Sep 8, 2026
jkbennitt
left a comment
jkbennitt
left a comment
Member
Author
There was a problem hiding this comment.
LGTM — docs-only. Locks 25-tick as default short horizon from the 2026-09-08 sweep (t25 mean composite 0.816 best; t100 degrades; research still floored; pause storm at 50/100 noted). No code/CLI/matrix. All five CI SUCCESS on 22e2978 (run 34234488123). HOLD merge for CoS clear. (Own-PR approve blocked; will merge via org/integration bypass when CoS clears.)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Docs-only follow-up to #73. Records the 2026-09-08 horizon sweep and locks 25 ticks as the default short horizon for composite / harness compare. No code, deps, CLI defaults, or matrix runs. Do not merge until reviewed.
What
Updates
docs/bench-design-n-ticks.mdand the existing one-line README pointer.Horizon lock (2026-09-08)
Sweep: one cheap cell, N=3 × {10, 25, 50, 100} ticks.
Dialog_NamePlayerFactionAndSettlementdismiss counts rose sharply (t25: 0; t50: 27–40; t100: 41–80 per run). Auto-dismiss works, but longer horizons thrash.Locked sequence is unchanged: gate N=1s → variance pilot → horizon → size matrix. Horizon step now records that 25 is the chosen short horizon after this sweep.
Out of scope
No CLI/default changes. No matrix. No XAI.