HN Showcase
Back to browse
Visualizing How Books Reference Each Other Across 3k Years

Visualizing How Books Reference Each Other Across 3k Years

by farcaster·Feb 11, 2026·5 points·3 comments
Visit ProjectView on HN

AI Analysis

●●●BangerWizardryRabbit HoleEye Candy

3,000 years of literary citation networks visualized with WebGPU; LLM pipeline resolves messy bibliographic data.

Strengths
  • •Novel data pipeline: LLM extraction + offline Goodreads/Wikipedia fallback solves real bibliographic matching problem
  • •Browser-native WebGPU rendering handles thousands of nodes smoothly without lag or server dependency
  • •Genuinely explorable design; red/blue/time-axis encoding makes citation relationships immediately intelligible
Weaknesses
  • •Unclear how many books/sources are currently indexed; needs concrete dataset scope and growth timeline
  • •Citation extraction accuracy not validated; no methodology details on false positive rates or confidence scoring
Category
Data
Target Audience

Literary scholars, book enthusiasts, researchers exploring citation patterns and literary history

Similar To

Google Books Ngram Viewer (temporal text analysis) · Connected Papers (citation mapping) · D3 force-directed graph projects

Post Description

There are two parts for this project:

1) The LLM-powered pipeline to extract citations (books + authors) from books and resolve them using both Wikipedia and Goodreads with offline copies I have. The result is data associating Books/Authors to other Books/Authors with accurate bibliographical information spanning centuries.

2) A WebGPU + D3.js powered visualization tool written by Claude Code so I'm able to deal with all this data on the browser on a more or less comfortable experience for the viewer.

I spent some months on a off with this project, and definitely the most challenging part was dealing with accurate bibliographical information across centuries, with original publication dates and etc. For that I wrote what is now a very complex pipeline with LLMs (I used DeepSeek V3.2) wired on offline Goodreads and Wikipedia databases + a fallback that actually uses the internet.

Hope you enjoy it! Open to suggestions on how to improve the system :)

Code is here: https://github.com/ThiagoLira/bookgraph-revisited

Similar Projects

Data●●Solid

7 Years of Tropospheric NO₂

12-month rolling mean with time scrubbing reveals pollution patterns from 2019 to present.

Eye CandyRabbit HoleDark Horse
tomtomistaken
102mo ago
Education●●Solid

Interactive SQL Tutorial with a visual query builder

The side-by-side visual builder and live SQL editor is the real payoff — drag tables onto a canvas, draw joins, and watch the SQL and results update so JOINs actually click. It's not a novel database, but shipping an in-browser SQL sandbox with a downloadable client, sample e‑commerce dataset, and no-signup access makes this a very effective, demo-friendly way to learn tricky SQL concepts.

Crowd PleaserSlick
mootoday
203mo ago