Repository navigation
Time only real updates in compare_prequential's p95 latency - #18
Merged
Merged
Conversation
Masked-out batches were timed as zero-cost updates, so with a sparse observe_mask p95_update_ms collapsed toward zero (0.006 ms vs 0.76 ms with 2% of labels observed) and select(max_update_ms=...) could accept configurations that miss the budget. The delayed-label path already timed only real updates; the batch path now matches it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011pXaJ5DLex7BrdUyfTqjL4
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
In
compare_prequential's batch path, batches with no observed labels (underobserve_mask) were timed as zero-cost updates, draggingp95_update_mstoward zero, soselect(max_update_ms=...)could accept configurations that miss the budget. Now only batches that actually callupdateare timed, matching the delayed-label path.Proof it fixes the bug
test_update_latency_ignores_masked_batches(2 ms updater, 1 of 40 labels observed, both paths): the batch case fails onmainand passes here.p95_update_ms:Proof of no regressions
mainand this branch. 0 differences in any non-timing field (Brier, log loss, calibration error, AUC, per-batch and cumulative scores, squared errors, state and serialized sizes).ruff,ruff format,pyright,pydoclintclean; CI green.🤖 Generated with Claude Code
https://claude.ai/code/session_011pXaJ5DLex7BrdUyfTqjL4