eval: add two Riksbank reports to the corpus (FSR 2025:1, Betalningsrapport 2025)#137
Merged
Conversation
A Swedish, chart-dense financial-stability report (53 pages, ~28 numbered diagrams: line, stacked-bar, grouped-bar and bar+line combos). Good stress test for vector-diagram detection and Swedish-language figure interpretation. PDF is fetched by download_eval.py (gitignored), not committed. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
…he corpus Swedish payments report, 73 pages. PDF fetched by download_eval.py (gitignored). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Ztein
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds two Swedish Riksbank reports to the eval corpus manifest. Both PDFs are fetched by
examples/download_eval.py(gitignored per the corpus convention); only the manifest entries are committed.riksbank-fsr-202505riksbank-betalningsrapport-202503Both are Swedish and chart-dense — good stress tests for vector-diagram detection and Swedish-language figure interpretation.
The FSR was run through figmark on the way in: interpretation quality is high, but bar/combo charts are systematically missed by the diagram detector (Diagram 10 stacked-bar p27, Diagram 20 grouped-bar p37, Diagram 24 bar+line p41 — all dropped). Filed as a follow-up ticket.
🤖 Generated with Claude Code