arXave GitHub
Dignew Haultoday StockpileWIPhistory Detailshow it works

arXiv drops hundreds of papers a night. Say what you care about, and this page ranks the whole night against it.

  1. 1 Haul the stones Fetch tonight's papers.
  2. 2 Filter Say what interests you.
  3. 3 Assay Keep the pay dirt.

Runs in this tab. Text you score is embedded, not stored. Small print.

1. Haul the stones

Fetch tonight's arXiv announcement: new papers and cross-lists, the same set the listing page shows. The train below groups them, one wagon per cluster.

arXiv categories
The train
drag a stone · drag the rock to pan · scroll to zoom · click to pin, then hover to compare
2. Filter

A word, a phrase, a sentence, or papers you already like.

Catalogue ready-made setups

Replaces the rows below. Edit any row afterwards; an edited phrase is yours.

Mine setups you saved
More

A claim is one dig setup. Edits save themselves. Clear empties the touchstones, cores and gate; hauled stones stay put.


Touchstones free text, one per row

Core samples papers you already like

A DOI or arXiv ID per row, or upload a .bib. Abstracts come from OpenAlex.


The rush WIP crowd attention
Scirate scites signal unavailable —
3. Assay
Feature cells
0 0.55
Grade
0 0.45
Coupling map

What is sent. Your touchstones, core samples and weights stay in this tab and survive a reload. The one thing that leaves is text you want scored: the pick runs on a server, so that text is sent there to be embedded, and is not stored.

The shared cache. Published text (arXiv abstracts, core-sample abstracts, preset touchstones) also goes into a shared vector cache, keyed by a hash, so nobody pays to cut the same phrase twice. A touchstone you type yourself never enters that cache, because reads on it are public and a hash of a short phrase is one dictionary away from the phrase.

Your own pick or relay. Set window.ARXAVE_EMBED to any OpenAI-shaped /v1/embeddings (LM Studio, Ollama, a paid endpoint) and text is embedded there instead, with the shared cache skipped. Set window.ARXAVE_RELAY the same way for the arXiv fetch. Or fork it (source).

Touchstone length. One word and a paragraph are not directly comparable, since longer text is more specific. The per-row weights are the mitigation.

What is real today. Scouting arXiv, embedding abstracts, and ranking on touchstone similarity with live re-blending. The rush (Scirate) sits behind a Cloudflare challenge and stays inactive.

The idea · Contribute · Source

By Jan A. Krzywda and collaborators.

Wash a night of arXiv and keep the few papers worth a careful look.