Title: OCR & extraction accuracy benchmark · Issue #2 · docsgraph/docsgraph-eval · GitHub
Open Graph Title: OCR & extraction accuracy benchmark · Issue #2 · docsgraph/docsgraph-eval
X Title: OCR & extraction accuracy benchmark · Issue #2 · docsgraph/docsgraph-eval
Description: Description We need to know whether OCR and field/clause extraction are actually accurate, not just that they run without erroring. Proposed Solution Build a labeled dataset of sample documents with ground-truth text/fields, and a benchm...
Open Graph Description: Description We need to know whether OCR and field/clause extraction are actually accurate, not just that they run without erroring. Proposed Solution Build a labeled dataset of sample documents wit...
X Description: Description We need to know whether OCR and field/clause extraction are actually accurate, not just that they run without erroring. Proposed Solution Build a labeled dataset of sample documents wit...
Opengraph URL: https://github.com/docsgraph/docsgraph-eval/issues/2
X: @github
Domain: github.com
{"@context":"https://schema.org","@type":"DiscussionForumPosting","headline":"OCR & extraction accuracy benchmark","articleBody":"## Description\n\nWe need to know whether OCR and field/clause extraction are actually accurate, not just that they run without erroring.\n\n## Proposed Solution\n\nBuild a labeled dataset of sample documents with ground-truth text/fields, and a benchmark that scores OCR and extraction output against it.\n\n## Acceptance Criteria\n\n- [ ] Labeled dataset of sample documents with ground truth exists\n- [ ] Benchmark scores OCR text accuracy against ground truth\n- [ ] Benchmark scores field/clause extraction accuracy against ground truth\n- [ ] Results are reproducible and comparable across runs","author":{"url":"https://github.com/MaximilianRau04","@type":"Person","name":"MaximilianRau04"},"datePublished":"2026-07-28T17:35:55Z","url":"https://github.com/docsgraph/docsgraph-eval/issues/2"}
| react-profiling | 0 |
| react-import-map | react,react-dom,react-dom/client,react-dom/profiling,react-is,react/compiler-runtime,react/jsx-dev-runtime,react/jsx-runtime,scheduler@b8488ee2c322 |
| route-pattern | /_view_fragments/issues/show/:user_id/:repository/:id/issue_layout(.:format) |
| route-controller | voltron_issues_fragments |
| route-action | issue_layout |
| fetch-nonce | v2:90d56f79-61d5-de80-3402-d46392db82e4 |
| current-catalog-service-hash | 81bb79d38c15960b92d99bca9288a9108c7a47b18f2423d0f6438c5b7bcd2114 |
| request-id | D7E4:EA06E:3BA9AB9:4BCDDB0:6B01EA3F |
| html-safe-nonce | 3aac4498c9e9fbcd27ba8fbae99e7a0eaebe09a94daece5550dca491d0148eab |
| visitor-payload | eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJEN0U0OkVBMDZFOjNCQTlBQjk6NEJDRERCMDo2QjAxRUEzRiIsInZpc2l0b3JfaWQiOiI0MjkzMjQ3MzU2NjY2NzY3OTM1IiwicmVnaW9uX2VkZ2UiOiJpYWQiLCJyZWdpb25fcmVuZGVyIjoiaWFkIn0= |
| visitor-hmac | bd7e6bc734cbe67f96cf20c1f9f079f089da8078edbb2e85abd5901c7c0cd3f0 |
| hovercard-subject-tag | issue:5001387092 |
| github-keyboard-shortcuts | repository,issues,copilot |
| google-site-verification | Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I |
| octolytics-url | https://collector.github.com/github/collect |
| analytics-location | / |
| fb:app_id | 1401488693436528 |
| apple-itunes-app | app-id=1477376905, app-argument=https://github.com/_view_fragments/issues/show/docsgraph/docsgraph-eval/2/issue_layout |
| twitter:image | https://opengraph.githubassets.com/d0bccfe35125b4ee4b87da51116130cff27e09dc1661dcb2f1bf1dcd8602ebc5/docsgraph/docsgraph-eval/issues/2 |
| twitter:card | summary_large_image |
| og:image | https://opengraph.githubassets.com/d0bccfe35125b4ee4b87da51116130cff27e09dc1661dcb2f1bf1dcd8602ebc5/docsgraph/docsgraph-eval/issues/2 |
| og:image:alt | Description We need to know whether OCR and field/clause extraction are actually accurate, not just that they run without erroring. Proposed Solution Build a labeled dataset of sample documents wit... |
| og:image:width | 1200 |
| og:image:height | 600 |
| og:site_name | GitHub |
| og:type | object |
| og:author:username | MaximilianRau04 |
| hostname | github.com |
| expected-hostname | github.com |
| None | 87e774ee7c6b3bee0490394e4d3e57ec9dbc956f74b87ea685dc8996c1676456 |
| turbo-cache-control | no-preview |
| go-import | github.com/docsgraph/docsgraph-eval git https://github.com/docsgraph/docsgraph-eval.git |
| octolytics-dimension-user_id | 307759105 |
| octolytics-dimension-user_login | docsgraph |
| octolytics-dimension-repository_id | 1309172084 |
| octolytics-dimension-repository_nwo | docsgraph/docsgraph-eval |
| octolytics-dimension-repository_public | true |
| octolytics-dimension-repository_is_fork | false |
| octolytics-dimension-repository_network_root_id | 1309172084 |
| octolytics-dimension-repository_network_root_nwo | docsgraph/docsgraph-eval |
| turbo-body-classes | logged-out env-production page-responsive |
| disable-turbo | false |
| browser-stats-url | https://api.github.com/_private/browser/stats |
| browser-errors-url | https://api.github.com/_private/browser/errors |
| release | 423dbb54c5e7bfecc838eb387c1435eb3d0e760d |
| ui-target | full |
| theme-color | #1e2327 |
| color-scheme | light dark |
| react-app-name | issues |
Links:
Viewport: width=device-width