xberg · Issues· 16 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #1696
bug: a text layer that decodes to the wrong characters is not detected
bugP0Updated Sep 19, 2026 - #1699
bug: PyPI 1.2.5 contains only macOS wheels after the publish job failed
bugUpdated Sep 19, 2026 - #1694
bug: the quality score and the OCR aggregate disagree on the confidence floor
bugUpdated Sep 19, 2026 - #1676
bug: candle-paddleocr-vl emits LaTeX markup and CJK glyphs for a handwritten signature scribble
bugP2Updated Sep 19, 2026 - #1675
bug: candle-glm-ocr duplicates characters inside long hyphenated identifiers
bugP1Updated Sep 19, 2026 - #1674
bug: candle-deepseek-ocr returns a quarter of the page text, invents a table on a signature block, and has no default model id
bugP1Updated Sep 19, 2026 - #1669
bug: quality_score stays 1.0 on OCR runs with low aggregate confidence and hundreds of noise warnings
bugP0Updated Sep 19, 2026 - #1667
bug: PDF: a text layer that decodes to shifted glyph codes passes the OCR quality gate with quality_score 1.0
bugP0Updated Sep 19, 2026 - #1668
bug: PDF: the document structure of long mixed native-and-scanned PDFs holds only paragraph nodes, no headings, tables or page breaks
bugP0Updated Sep 19, 2026 - #1663
bug: DOCX: list items are emitted as paragraph nodes in the document structure
bugP0Updated Sep 19, 2026 - #1567
chore(lint): pay down the size and complexity baseline
help wantedgood first issueUpdated Sep 6, 2026 - #1407
feat: Publish conda/pixi packages so native deps like libheif resolve
enhancementhelp wantedgood first issuedependenciesUpdated Aug 28, 2026