examples/itq_pipeline.cpp: anisotropic-data onboarding example - #8
Merged
Conversation
A second self-checking example covering the ITQ workflow end to end: synthesize decaying-spectrum data, train a rotation (2k subsample, 10 iterations - seconds, not minutes, by design: examples run on contributor machines and CI), persist/reload it with validation, build raw and rotated indexes over the same floats, and measure both against exact float32 ground truth. The example gates its own claims: rotated codes must beat raw codes (measured here: 0.340 -> 0.420 recall@10), and exact re-ranking over the rotated index must work with the ORIGINAL, unrotated floats - the cosine-preservation property that makes rotation-only ITQ practical. Wired into examples/Makefile, CMake (EDGEVECTOR_BUILD_EXAMPLES), and the CI quickstart job via both build paths. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017ULiWeodALX2ZQiLKvTw25
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Second self-checking example: the full ITQ workflow (train → persist → rotated index → recall comparison vs raw codes against float32 truth → exact re-rank with unrotated floats). Gates its own claims; runs in ~13 s; wired into make, CMake, and CI.
🤖 Generated with Claude Code
https://claude.ai/code/session_017ULiWeodALX2ZQiLKvTw25