test(eval): consolidate multi-sketch + latency eval harness & results - #494
Merged
Merged
Conversation
Bundle the datasets_eval drivers, agent workloads, query sets, ground-truth, and measured results behind the merged §6 doc figures (Fig 3 per-family accuracy, Fig 7 latency CDF, multi-sketch cost/compound). Docs excluded (already merged via #491/#492/#493); this is the harness/data only. - datasets_eval/multisketch/: run_eval.py, run_perfamily.py, per-family agent configs (6 families + sampling/coldoff/wide variants), query sets, GT, RESULTS.md + accuracy_RESULTS.md, stack.sh/stack-coldoff.sh. - datasets_eval/latency/: compute_latency.py + CDF + per-query latency + RESULTS. - datasets_eval/google_cluster/run.py: --wall-clock-anchor (re-stamps replay at one wall-clock instant so warm-window queries resolve). - deploy/mvp-singlenode/scripts/queries-latency-warm.json. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This was referenced Jun 14, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bundles the
datasets_eval/harness + measured results behind the §6 doc figures already merged (#491 Pareto, #492 per-family accuracy, #493 latency CDF, plus the multi-sketch cost/compound tables).Docs excluded on purpose — the doc branches were cut off an older main and carried a stale
evaluation-plan-figures.mdrevert; this branch is the harness/data only, off current main, zerodocs/changes.Contents:
datasets_eval/multisketch/—run_eval.py,run_perfamily.py, per-family agent configs (DDSketch/KLL/CMS/CountSketch/HLL/Sum + sampling/cold-off/wide variants), query sets, ground truth,RESULTS.md+accuracy_RESULTS.md,stack.sh/stack-coldoff.sh.datasets_eval/latency/—compute_latency.py, CDF PNG, per-query latency,latency_RESULTS.md.datasets_eval/google_cluster/run.py—--wall-clock-anchor(re-stamps replay at one wall-clock instant so warm-window queries resolve — fixes the time-anchoring 'No result').deploy/mvp-singlenode/scripts/queries-latency-warm.json.Supersedes the local
feat/multisketch-eval/feat/multisketch-accuracy/feat/query-latency-cdfbranches (consolidated here).🤖 Generated with Claude Code