Platform
How the Epistemic Engine works.
Why claims lose their provenance, how the engine records it, and what comes next.
Service status
What is running right now.
- WebsiteNo recent check available
- Engine preview chatNo recent check available
Checked every five minutes by an independent monitor. An uptime percentage appears here once enough history exists to report one honestly.
The provenance problem
A claim gains authority every time it’s repeated, not every time it’s proven.
Claims rarely fail all at once. One paper reports a cautious result. The next cites it a little more confidently. A review restates it as established. By the time an AI system reaches it, a hedged “might” under narrow conditions is being reported as plain fact, and the original experiment is never read again. The text was real at every step; what eroded was the provenance.
How one claim escalates
- A small animal study reports a tentative result
- A later paper cites it as support
- A review describes the effect as probable
- An AI system states it as fact
Six ways a claim degrades as it travels
Hedged claims harden
Qualifiers like "may" and "in this model" drop away with each citation until nothing marks the original uncertainty.
Findings jump between species
A result established in one model organism is restated as though it were shown in humans.
Citations replace the evidence
Later work cites the review rather than the study, and the underlying data stops being read at all.
One dataset looks like many
Multiple papers drawing on a single cohort read as independent confirmations of the same effect.
Contradicting evidence detaches
Failed replications and null results are published but never linked back to the claim they bear on.
Conclusions outlive their foundation
The finding underneath is retracted or quietly corrected, and the work built on top carries on unchanged.
None of this is visible in the paper in front of you. Catching it means holding a claim’s whole history: where it came from, and everything since that has propped it up or undercut it. It means keeping that history current. That is what Veriscia builds.
Architecture
Read once. Reused by every question after.
Every paper is resolved into epistemes and reconciled into a living graph that gets deeper with each addition. The expensive reasoning happens a single time, and every query after it reads the result.
Papers enter once
Layer 1
Document layer
Raw papers, figures and citations become machine-readable objects.
Layer 2
Epistemic Engine
What each paper demonstrates is extracted as epistemes, then reconciled into one evolving graph.
Layer 3
Reasoning layer
Client agents query the graph and get structured evidence back for their own reasoning to work from.
Reused by every query
Two questions about the same claim get the same evidence.
Roadmap
Where the engine goes next.
- Preview live: neuroscience
Epistemic Engine, first generation
Traces each claim to the evidence that established it, and records its confidence, its drift, and the work that supports or contradicts it.
In development
Second-generation engine
The next version of the Epistemic Engine. We will publish what the second generation adds when it is ready for our clients.
Ongoing
Coverage of new domains
We are extending the engine into new areas of science.
Ongoing
Iterative refinement
We continue to refine how the engine extracts evidence and assesses confidence.
Changelog
What changed, by release.
v0.1.3
Maintenance. Build and deploy workflows moved to current versions, and the documentation now says plainly that production deploys only from a version tag. No change to the site you see.
v0.1.2
Maintenance. A repository formatting check no longer trips over a generated file. No change to the site you see.
v0.1.1
Preview and project-alias addresses are now marked so search engines do not index them as duplicates; veriscia.com is the only indexed copy. Unused code removed and dependencies updated.
v0.1.0
First tagged release of the public site: the homepage, the platform, access and company pages, the limited engine preview, and links to the founders’ and company profiles.
Dated entries from tagged releases only. It is short because the site is young; it grows with the product.