Docs
Documentation for agents and the people who review their work
Run the public verifier directly or through local MCP, teach an agent when to call it, and interpret the returned evidence using the same versioned documentation.
Product development since limited Release 1
Since limited Release 1, nomue development has expanded candidate calculation range, improved completion of difficult calculations, clarified what was checked, and added historical-result handling.
Development update: integrated candidates and completed internal milestones are not a new hosted release or an expansion of public verifier support.
Available now
Verify a supported Release 1 Record locally
Anyone can install the public @licklider/nomue-verifier package from npm and run nomue verify locally to check a conforming Release 1 Record for independent two-group continuous outcomes under the two-sided Welch two-sample t procedure. It recomputes the covered numerical quantities and returns a machine-readable report of the scoped checks without calling a nomue server after installation.
Release 1 publishes source code together with public fixtures, a signed source archive, checksums, a snapshot manifest, detached signatures, and the public release key.
Choose the path you need
Run
Verify a nomue Record
Install @licklider/nomue-verifier 0.2.1-rc.1 from npm for the independent two-group continuous outcomes profile under the two-sided Welch two-sample t procedure.
Connect
Run the local MCP release candidate
The exact @licklider/nomue-verifier-mcp@0.2.0-rc.1 release candidate is public on npm and in the official MCP Registry as nomue Record Verifier. It exposes the method-neutral verify_nomue_record tool over local stdio; the current supported scientific scope remains Release 1 Welch Record verification. It delegates to @licklider/nomue-verifier@0.2.1-rc.1 and has passing package-path CI across Linux, macOS, and Windows. It requires no account, API key, environment variable, or Licklider-hosted service. The first npx launch may download npm dependencies; after installation, verification runs locally. This release candidate supports stdio only: it is not a hosted HTTP endpoint and does not add paired-t, Wilcoxon, Mann–Whitney, method selection, raw-sample calculation, or an overall scientific verdict.
Call
Teach an agent when to verify
Use the when-to-use rules, stop triggers, decision vocabulary, and machine-readable examples. A statistical method name is not a verification contract. A useful guarantee also depends on the comparison family, error criterion, assumptions, sidedness, balance conditions, and exact procedure variant.
Interpret
Understand the returned result
Keep pass, fail, clarification, refusal, unsupported scope, and operational failure distinct.
Product access: Approved recipients can submit data and required scientific declarations for a supported Welch calculation, or submit a claimed result with structured evidence for checking, through authenticated MCP and HTTP. The service returns scoped outcomes, reasons, evidence, and next actions.
Use the npm-published Release 1 verifier, the local stdio MCP server, the Protocol, and their machine-readable documentation today. The agent-facing Welch capability is now available in limited Release 1 to approved recipients through authenticated MCP and HTTP interfaces; public self-registration is not available. The hosted capability does not yet emit public Records for replay through the local verifier. Limited-release announcement
Release 2 candidate: The Release 2 paired-t candidate now has an independently reviewed formal decision-readiness packet. It assembles the D1–D6 decision ledger, numerical and execution evidence, structural candidates, review dispositions, Release 1 safeguards, and the required coupled landing order. The Steward decisions, authoritative issuance, support activation, and release remain open.
Release 3 proposal: Release 3 public discussion is open on independent groups and multiple comparisons. The proposal makes design, comparison families, result meaning, and error-control questions explicit across 49 catalogued procedures. Its evidence scope is limited to supplied originals; method adoption and numerical support remain separate decisions. Public discussion and scope
Release 4 proposal: Release 4 public discussion is open for a balanced two-by-two fixed-factor proposal. Its unissued numerical, report and controlled-execution candidate has reached independently reviewed final readiness, without establishing Protocol support. A separate amendment discussion covers strict binary64 comparison and completed indeterminate results; it changes neither the current verifier nor the original RFC clock. Public discussion and scope
Release 5 proposal: Release 5 public discussion is open on a common evidence view for declared study design and selection timing across analysis families. The proposal covers versioned mappings, timing declarations, explicit limits on what a passing check means, and a shared report view. All three candidate families require separately accepted successors; no new verification capability is available. Public discussion and scope
Documentation
What a verification call is
A shared model for asking a separate capability to check one bounded part of AI-assisted research.
Conceptual guide for selecting a verification capability
Verify a Release 1 nomue Record
When and how to use the public local verifier for the exact Release 1 Public Draft support target.
Public npm release candidate — @licklider/nomue-verifier 0.2.1-rc.1
Use nomue Record verification over MCP
Install the public local stdio server, decide when its method-neutral Record tool applies, and replay the current Release 1 Welch result with the independent verifier.
Public local MCP release candidate — @licklider/nomue-verifier-mcp 0.2.0-rc.1
nomue CLI reference
The exact public command surface shipped by @licklider/nomue-verifier 0.2.1-rc.1, including current help and version boundaries.
Public CLI reference — release candidate 0.2.1-rc.1
Decision vocabulary
Keep execution, clarification, unsupported scope, refusal, failed checks, and unasserted scientific validity separate.
Public explanatory vocabulary — upstream semantics remain authoritative
Examples for agents and implementers
Runnable verifier examples and selection examples showing execute, clarify, unsupported, and bounded interpretation behavior.
Public examples — executable examples use the Release 1 verifier fixtures
Current capability and boundaries
What can be used now, what comes next, how the platform expands, and how to interpret a successful result.
Current public capability map — September 17, 2026
For agents
Every documentation page has a clean Markdown version. The indexes stay short so an agent can discover the relevant page and fetch only the detail it needs. Normalized examples are also available as JSON.