Projects

Models, data infrastructure and tools I have built, most of them open source.

2026

SciEmbed

Embedding model for scientific documents, trained with the sentences in which papers cite each other as contrastive signal. ModernBERT-base with up to 8K context; six checkpoints released under MIT.

Up to ~30M training pairs on 4×H200, SciRepEval 66.85 (EMNLP 2026)

PyTorch, ModernBERT, Contrastive learning, DuckDB

Code Models Paper Write-up

2026

Science Data Lake

Locally deployable infrastructure that joins eight scholarly databases (Semantic Scholar, OpenAlex, Crossref and others) into one SQL interface, with embedding-based alignment of 4,516 topics to 13 ontologies.

293M papers, ~960 GB of Parquet behind 153 DuckDB views

Python, DuckDB, Parquet, Embeddings

Code Dataset Paper Write-up

2026

Offprint

Native macOS app that converts PDFs to Markdown and JSON on the device: reading order across columns, tables as tables, maths as LaTeX. Decides per page whether to trust the text layer or run OCR.

Runs a 0.9B OCR model locally in 1.25 GB at 4-bit

Swift, SwiftUI, MLX, Apple Vision

Code Write-up

2024

AI Concept List

Curated, weighted list of AI concepts, seeded from textbook indices and the Computer Science Ontology, extended with keyphrases from PapersWithCode and filtered with a classifier against OpenAlex abstracts.

10,797 concepts (DRUID 2024)

Python, YAKE, Neo4j, PostgreSQL, Logistic regression

Code Dataset Write-up

2023

PubCrawl

Tool for downloading scientific papers at scale and converting the PDFs to text in parallel, as the data layer for the first PhD experiments.

Python, multiprocessing

Code Write-up