Release 0.9.0 - #38
Merged
Merged
Conversation
The battery gains calculus -- chain-rule derivatives at a point, exact definite integrals, tangent slopes, quadratics built from their roots -- graded by mpeqs.calculus, whose two independent derivative paths must agree before any model is graded. Physics gains free fall, acceleration and kinetic energy with the formula always stated. Measured live against qwen3: 19/22 (86%). The grader itself was fixed twice by the first live run: an answer must never fail for exceeding the grader's precision, and a question that wants decimals must ask for them. mpeqs floor rises to 0.4.0, which brings the calculus module and the PySpell autograd interpreter.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PyPI's 0.8.2 predates the calculus work. Since then:
mpeqs.calculus, whose two independent derivative paths (symbolic + dual-number autograd) must agree before any model is graded. Live against qwen3: 19/22 (86%), pinned.-42.666667for-128/3was marked wrong), and a question that wants decimals must ask for them.452 tests.