Mission · Version 0.3

Knowledge that can show its work

Versioned and amendable through accepted Git history. This mission is a project statement, not evidence, policy, constitution, or a stored verdict.

em:mission:sha256:e4b4579a80a004ccb6f9b5219af7f3d6119fd4ca28cd2264e191fe098b47b268

The problem

Confidence is cheap. History is missing.

Claims arrive without their history. Ten articles confirm something that traces back to one whisper. A decade of public-health advice rests partly on an unpublished manuscript nobody can produce. A statistic everyone repeats turns out to mean something its own author never claimed.

This was always true. AI made it urgent. Writing a confident claim now costs almost nothing, so unwarranted assertions are flooding every channel we have, and the institutions built to vouch for knowledge cannot keep up.

The same machines can afford something no human ever could: checking. Fetching, tracing, and comparing are becoming cheap enough to challenge reputation-only trust.

What we are building

Store the process, then compile the reading

Encyclopedias, journals, and feeds usually foreground the conclusion. The evidence, disputes, failed replications, and revisions are harder to inspect, leaving readers with a verdict whose history is expensive to reconstruct.

Epistemedia stores the process: sources pinned to exact editions and quote-minimal spans; claims; typed relations; data lineage; unresolved records; and named policies. A page here is not the canonical source of truth. It is a reproducible projection of an accepted record under a stated policy.

No truth-like status is intrinsic to a claim. Public readings are compiled from accepted records under policies you can inspect and compare.

Evidence becomes countable

Within a bounded case, named evidence units and collapse rules answer how much evidence is present without substituting paper titles or repetition counts.

Disagreement becomes debuggable

Two readings of the same record can differ, and the policy choices producing that difference remain inspectable.

Nobody has to win the One True Page

People can share a record, run different readings, and publish each reading with a receipt.

Four cases · four failure modes

Unit tests for how knowledge goes wrong

These four failure modes are an editorial map of the first library, not a complete taxonomy and not stored evidence statuses.

Case 001Overgeneralization

Repeating a myth while correcting it makes people believe it more.

Some tested formats and contexts report backfire, but the record does not warrant a blanket rule against repeating misinformation inside corrections.

10 apparent support assertions → 4 target-comparable participant-data roots + 1 unresolved lineage → 12 counterevidence roots

Still openThe unpublished 2007 Skurnik, Yoon, and Schwarz flu-flyer manuscript remains unavailable.

Case 002False independence

Eight research agents agreed, so the answer looked independently corroborated.

Eight captured reports reused overlapping prompt, capture, source, method, and derivation lineages; report agreement alone adds no independent warrant.

8 reports → 30 URL strings → 11 source works → 7 candidate warrants → 0 independently confirmed warrant roots

Still open34 citation occurrences remain unresolved in this historical pilot, which does not estimate current or universal agent behavior.

Case 003Missing comparison class

GPT-4 scored around the 90th percentile on the bar exam.

The historical simulated score is documented; its percentile changes with the administration and comparison population.

1 historical model run · 3 official administration sensitivities · 7 rooted evidence units

Still openThree boundaries remain unresolved; the file does not establish current behavior, practicing-lawyer quality, or general legal competence.

Case 004Scope inflation

Only 7% of communication is verbal; 93% is nonverbal.

The weighting is a narrow historical cross-study proposal from experiments about inconsistent feelings and attitudes, not a universal communication law.

2 original experiments · 5 participant-data roots · 3 zero-credit propagation objects

Still openThe exact origin of the .07 coefficient remains unresolved.

What we believe

Seven operating principles

Show the work

A conclusion you cannot inspect is a rumor with good posture.

Echoes are not voices

Ten repetitions of one source are one source.

Every number has a list

No displayed total is maintained as marketing copy.

Nobody grades their own work

Contributors and authoring agents do not supply their own independent review.

The record is shared; the reading is yours

We ask readers to inspect the accepted record and the named policy, not to treat one projection as global truth.

Nothing gets lost quietly

Accepted history is append-only, so what was knowable and when remains answerable.

Fork us if we fail you

Forking is part of the constitutional amendment path, and sovereign realms may accept, reject, or reinterpret imported records.

What this is not

A shared record, not one stamped truth

Not a global fact-checker

Epistemedia publishes bounded, policy-relative evaluations. It does not stamp one universal truth label onto a claim.

Not an arbiter of truth

The shared record underneath disagreement is the product; a single final answer is not.

Not another One True Page

People who disagree can pin the same record and publish competing readings whose differences remain inspectable.

Where this goes

Agents should inspect lineage before they assert

Agents will do much of the world’s reading and research. Before an agent asserts a fact, it should be able to inspect that claim’s lineage the way a browser checks a certificate: routinely and with a visible failure state.

Communities that agree on nothing else should still be able to share evidence without inheriting each other’s conclusions.

We will know the federation is working when a sovereign realm exists that we disagree with, uses the shared protocol, pins the same record, and publishes readings we would not sign.

How to participate

Start by trying to break the record

Ten minutes

Try to break a case

Open a source span, inspect a count, and report a crack. Finding one is a contribution.

An afternoon

Run a claim through the research kit

Give the public protocol and a case-seeded brief to your coding agent. The output remains an untrusted proposal with zero evidential credit.

The long game

Run a realm

Apply your field’s standards to the shared substrate while preserving provenance and your right to disagree.

Where we actually are

Four cases. One realm. Version zero.

The repository, deterministic compiler, four reviewed cases, and public read-only research kit are implemented. The hosted API, hosted MCP service, authenticated submission queue, and second realm are not live.

Take the five-question reader check

Build receipt

Reproduce this projection

Reproducible projection
Catalog
em:catalog:sha256:175bf54963c6dd461e3f0cfa97c1bf2b8093b9b3a0729a07f1c40d7cde700542
Frontier
em:frontier:sha256:499dbbc2a7e00762b2b2ec8bd41f2e66b510ff00bcaae58ad9b2624e546ad3e7
Accepted commit
4993895ce5913e0617788272e4c221c66d8f70f6
Epistemic policy
commons-balanced-v0.1
Disclosure policy
public-noninterference-v0.1
Compiler
epistemedia/0.2.0
Content digest
4570c337c78b13bc76f4b8a48e3c8c864b83f0d0599a8e4022f9a6c1c81aa421