DocHop-QA: Towards Multi-Hop Reasoning over Multimodal Document Collections
arxiv.org·18h
📇Dublin Core
Claude Code's 19 cent Parser
blogger.com·9h
🔧Binary Parsers
Appreciating Libxslt (2005)
xml.com·12h·
Discuss: Hacker News
🔀XSLT
Linux Foundation says yes to NoSQL via DocumentDB
theregister.com·1h
🔓Open Source Software
Automated Semantic Disambiguation via Multi-Modal Knowledge Graph Fusion
dev.to·1d·
Discuss: DEV
✓Automated Theorem Proving
Show HN: DataCompose – Prevent downstream data failures with composite functions
datacompose.io·2h·
Discuss: Hacker News
✅Format Validation
Karl Voit: Why Markdown Is A Disaster
irreal.org·6h
📝Concrete Syntax
Show HN: I Built a XSLT Blog Framework
vgr.land·1d·
Discuss: Hacker News
🔀XSLT
Facts, Arguments, Theses: Building AI Knowledge Retrieval on Meaning, Not Slices
nsavage.substack.com·2d·
Discuss: Substack
📄Text Chunking
7 Steps to Mastering No Code Automation with n8n for Data Professionals
kdnuggets.com·10h
🌊Stream Processing
Exhaustive Generation of Pattern-Avoiding s-Words
arxiv.org·18h
💾Binary Linguistics
Some recent project milestones
markjgsmith.com·1d
🔌Interface Evolution
From Unstructured Data to RAG-Ready With Docling
thenewstack.io·4d
🤖Archive Automation
Why Semantic Layers Matter—and How to Build One with DuckDB
ssp.sh·1d
🗄️Database Internals
URL Context
ai.google.dev·36m·
Discuss: Hacker News
🔗Hypermedia APIs
Fine-Tuning and Deploying GPT Models Using Hugging Face Transformers
blog.jetbrains.com·11h
🤖Grammar Induction
Sharing Is Scaring: Why Is Cloud File-Sharing Hard?
blog.brownplt.org·5h·
Discuss: Lobsters, Hacker News
💧Liquid Types
Format as a Prior: Quantifying and Analyzing Bias in LLMs for Heterogeneous Data
arxiv.org·18h
🧠Machine Learning
Context Engineering: Bringing Engineering Discipline to Prompts—Part 3
oreilly.com·11h
🔄Archival Workflows
Legal Doublet (Wikipedia)
en.wikipedia.org·23h·
Discuss: Hacker News
📜Text Collation