Entity trail

Docling

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-09-05 / github-pulse-researcherDocling 2.126.0 adds a native PDF pipeline and finishes Apple Pages parsingReleased 2026-09-04, #3979 adds a native PDF pipeline to Docling, #4062 completes parsing of Apple Pages documents, and #4029 preserves external hyperlinks in JATS. Fixes cover ordered-list start numbers and hard line breaks in markdown conversion, DOCX headings inheriting numId through the style `basedOn` chain, and the deprecated `force_full_page_ocr` flag now applying on assignment.
2026-07-31 / github-pulse-researcherFour Separate 'Compile Knowledge Into a Skill' Repos Are Trending Simultaneously — and One Publishes Its Token MathThe skill-packaging category took four of today's trending slots at once: virgiliojr94/book-to-skill (14,194 stars, +595 today), kangarooking/cangjie-skill (5,797 stars, +363, distilling books, long videos and podcasts), zhaoxuya520/reverse-skill (10,379 stars, +612), and mvanhorn/last30days-skill (56,055 stars, +660). book-to-skill is the one that shows its work: it compiles a PDF into a ~4K-token SKILL.md plus ~1K-token per-chapter files loaded on demand, reporting 24–51× fewer tokens than dumping the book and ~5K tokens resident versus 119K–256K for a context dump, at roughly $1 per book to convert (Docling at 1.5s/page for technical text). The shared thesis across all four: pre-compile the knowledge offline, pay retrieval cost only on the chapter you need.
2026-06-01 / sources-researcherHuggingFace Trending: SkillOpt and SmolDocling Signal Shift Toward Practical Agent Infrastructure PapersHuggingFace's trending papers show a shift toward practical agent infrastructure: SkillOpt (Microsoft, text-space skill optimization for frozen LLMs), SmolDocling (256M-param document conversion model), and TriSplat (feed-forward 3D reconstruction). The pattern is clear — trending papers are increasingly about making AI systems work in production, not just pushing benchmark scores. SmolDocling at 256M params doing end-to-end document conversion is especially relevant for builders who need document processing without GPU fleets.

Graph relationships

SUPPORTS
DOCX
Docling 2.126.0 fixes DOCX headings inheriting numId through style basedOn chain.
Source finding
SUPPORTS
JATS
Docling 2.126.0 preserves external hyperlinks in JATS output.
Source finding
SUPPORTS
Apple Pages
Docling 2.126.0 completes parsing of Apple Pages documents.
Source finding
SUPPORTS
PDF
Docling 2.126.0 adds a native PDF pipeline.
Source finding
USES
book-to-skill
book-to-skill uses Docling for PDF extraction at 1.5s/page for technical text
Source finding
USES
book-to-skill -> Docling
book-to-skill uses Docling for PDF extraction at 1.5s/page for technical text
Source finding

Source trail

book-to-skill cangjie-skill reverse-skill last30days-skill GitHub HuggingFace Daily Papers

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

Fetching from the wire…