Polish RoadAffordanceLab research portfolio - #2
Closed
drxadqz wants to merge 2 commits into
Closed
Conversation
Owner
Author
|
Superseded by the merged bilingual portfolio in #3. Closing this draft to keep the public repository history focused. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
Why
The previous repository contained strong result evidence and checkpoint provenance, but its first page did not communicate the research question, architecture, engineering depth or reproducibility story quickly enough. It also lacked CI that could prevent the README figures from drifting away from machine-readable results.
The new landing page is designed for two readers: a recruiter can understand the project in under a minute, while an ML engineer can continue into exact configs, checkpoints, metrics and code.
Scientific boundary
The page reports the frozen standalone S7 checkpoint result (90.632% Top-1, 88.920% Macro-F1 on 49,500 images) as verified internal evidence. It explicitly does not claim a new public SOTA. Active ARCQ/TACT experiments remain excluded until their validation protocol is completed and frozen.
Validation
python -m compileall -q src scripts train.py validate.py test.pypython train.py --helppython validate.py --helppython test.py --helppython scripts/verify_release.pypython scripts/generate_readme_assets.py --checkgit diff --checkAll checks passed locally on Python 3.11.