best-of-n-researcher: add new experiment scaffold - #108
Open
MilindPathiyal wants to merge 1 commit into
Open
Conversation
Generates K mechanistically orthogonal candidates per loop, fast-screens them on a subset of train dates, full-backtests only the winner. Tests parallel sampling + screen as a variance-reduction lever vs single-shot loops. - .claude/agents/best-of-n-researcher.md: agent procedure + JSON schemas - research/config.yaml: best_of_n_experiment section (k=5, screen_dates, winner_metric, max_loops=8) - .claude/hooks/patch_program_db_tokens.py: register new agentType; generalize pointer discovery to scan experiments/*/.current_loop.json - .gitignore: ignore the new experiment's pointer file Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
frank22lin
approved these changes
May 27, 2026
Collaborator
|
Can we wait until we merge the other experiments into main before merging this? WIll probably have to deal with quite some merge conflicts |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Generates K mechanistically orthogonal candidates per loop, fast-screens them on a subset of train dates, full-backtests only the winner. Tests parallel sampling + screen as a variance-reduction lever vs single-shot loops.