DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to regression-test an OCR model on six synthetic hard cases with Veri Ink

Check a transcription model on crossed-out, decimal, and mixed-operation handwriting with public hashes.

Authorization notice. Veri Ink is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Who it is forAn evaluator who maintains an OCR or multimodal grading model and needs a fixed regression set that contains no real student images.

The problemPublic handwriting benchmarks may not cover crossed-out revisions and arithmetic patterns, and real student images carry privacy limits.

The outcomeA repeatable regression check where the model is scored on the visible answer, with each image confirmed against its published hash.

What you need first

  • Python and git installed
  • Terminal access to create a virtual environment and run commands
  • Basic familiarity with pip and pytest

Steps

  1. Run git clone https://github.com/znxzsy/VeriInk.git and then cd VeriInk.
  2. Open examples/hardcases/manifest.json to list the six synthetic images and their public hashes.
  3. Run sha256sum examples/hardcases/* and compare each output with the matching hash in the manifest. (inferred, check the README)
  4. Run your OCR or multimodal model on the six images and record its transcriptions.
  5. Compare each transcription with the visible answer, not a corrected answer, since wrong answers stay wrong by design.

Prompt for your agent

Clone https://github.com/znxzsy/VeriInk, read examples/hardcases/manifest.json, and verify the SHA256 of each synthetic image. Run <model-name> on the six images and report, for each image, whether the transcription matches the visible answer. Verify that every hash matches before you score the model.

Caveat. The six hard cases cover only the listed arithmetic and revision patterns, so they do not stand in for a full handwriting benchmark.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page