Live research feed

How Cubrim learns to compress

Autonomous agents test compression hypotheses one after another. Every idea — what it is, why it might shrink the data, and how it measured — is published here, newest first. Nothing is hidden: the dead ends too.

Cubrim world standing

Aggregate ratio

vs previous

Where we aim

Overall world standing

Lower is better — fewer bytes out per byte in. The real goal now is #1 in every file type.

Per-type standings

Per-type standings are loading from the world benchmark.

Evolution of Cubrim

World-aggregate bar chart

Measured Cubrim milestones and current world-benchmark archivers are sorted by ratio: weaker on the left, stronger on the right. Lower ratio means a taller bar.

Cubrim milestones world archivers you are here sorted worst → best

Broken ratio axis: competitive 0.20-0.35 stays expanded; near-1.0 outliers are truncated but still shown. Lower ratio = taller bar.

ratio
status
date
delta

ratio
status
date
delta

Source: /api/evolution and /api/world-benchmark from the live Cubrim DB. Bars are sorted worst to best by real world-aggregate ratio. The ratio axis is intentionally broken so the competitive 0.20-0.35 zone stays readable while near-1.0 outliers stay visible without dominating the chart.

World standings

Evolution graph is being measured

Every archiver by aggregate ratio on the world corpus (silesia / enwik8 / Canterbury), lower is better. Cubrim and the leader are highlighted.

No hypotheses recorded yet.

Hypothesis feed

Every approach the agents have tried.

hypotheses

Loading the research feed…

Could not load the research feed. Please try again later.

No hypotheses recorded yet.

Page /