Repository navigation
Benchmark Jev with and without DSPy across repeated searches and calibration - #28
Merged
Merged
Conversation
…earches and disjoint calibration
… fresh prompt searches manual
…alization regressions and restart bounded live study
…prevent automatic repeat charges
…y, calibration ablations and graph/workflow comparison reports
…nterpretation; execute complete paired benchmark pipeline
This was referenced Sep 18, 2026
CompleteDotTech
added
reproducibility
CompleteDotTech
marked this pull request as ready for review
September 28, 2026 19:31
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Scope
This first branch of the DSPy benchmark stack adds the frozen v2 protocol, primary search and calibration harnesses, independent audit code, and focused tests. It preserves the historical live captures for the downstream offline audit and publication in #29 and #30.
The first primary run 35342763186 had four failed entity jobs, so it did not establish full coverage. The completion run 35345560822 supplied the missing captures. Its hosted analysis then failed on a numerical near-tie; #29 repairs the independent analysis using those existing bytes. Together the preserved captures support eight formulations and 40 actual DSPy searches (five per formulation). No new model calls were made in this remediation.
All new workflows are manual-only; paid inference jobs in this branch have an unsatisfied authorization condition. The separate #32 comparison package, manual workflows, optimizer inventory, and #33 structural study remain integrated.
Full measured results and durable raw journals arrive in #30. The original frozen research inventory remains unchanged.