Add AlphaEvolve B.1. math problem - First order autocorrelation inequality#75
Open
vicruz99 wants to merge 110 commits intoSakanaAI:mainfrom
Open
Conversation
fix: Fix database summary when patch_name metadata is missing
Fix packaging so pip install ships full shinka module tree
… of expected 2 (end and start) markers
fix `apply_full.py` when the patch has incomplete markers
Doc explaining how to add suport for a local LLM and embedding model
…rust Add rust to supported languages
docs: change repo name on the onboarding doc
add google gemini embeding model
Enhance docs, robustify wrap_eval, Visualization w/o API key
Public migrate: async evolution stack + tooling cleanup
…dded variant for open_evolve implementation and test_time_discover implementation
…ms for first autocorrelation inequality problem to the appropiate folders
…rrelation inequality
feat: add wrap_eval multiprocessing and Julia evolution example
…shinka/example/alpha_evolve_math_problems/first_autocorr_ineq
Contributor
Author
|
I am not sure why Claude Code Review is failing... Error: Action failed with error: Could not fetch an OIDC token. Did you remember to add |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR contains an implementation of the problem detailed in Annex B.1 of the AlphaEvolve paper.
Because the original AlphaEvolve codebase is not publicly available, this implementation was adapted from open-source implementations to work within ShinkaEvolve.
All credits go to the authors of the original code. The files in this repository were adapted for ShinkaEvolve from the following sources:
Verification Code: Adapted from the Test-time-discover repository [2].
Initial Programs: Two variations are included, alongside their respective configuration files.
Variation 1: Sourced from Test-time-discover [2] repository.
Variation 2: Sourced from OpenEvolve (originally implemented by Codeevolve). See the source file and algorithmicsuperintelligence/openevolve#302.
Two initial programs were included to be evolved.
I tested these examples with Shinka using GPT-oss-120b in a medium buget. The results didn't surpass SOTA, but the tests weren't extensive.
A README is included with more details on these tests and on how to use this example.
I am planning on adding more examples, using a similar structure.