Docs

nomue capability and boundaries (earlier version)

Archived nomue capability map: what nomue released, what it planned, and how to interpret a successful result, as last updated on September 17, 2026.

This is a nomue reference for the named artifact and version. Go to SciGround documentation.

What was released

In limited Release 1, approved recipients could submit data and required scientific declarations for a supported Welch calculation, or a claimed result with structured evidence for checking, through authenticated MCP and HTTP. The service returned scoped outcomes, reasons, evidence, and next actions. Public self-registration was not offered, and hosted results were not emitted as public Records for local replay.

The public @licklider/nomue-verifier package let anyone 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 recomputed the covered numerical quantities and returned a machine-readable report of the scoped checks without calling a nomue server after installation.

nomue Protocol Release 1 Public Draft and public npm package @licklider/nomue-verifier 0.2.1-rc.1 were nomue’s public artifacts.

nomue was the earlier version of SciGround. This archived guide describes the named nomue releases and packages only; for current verification, see https://www.licklider.ai/docs/.

Public local MCP release candidate

The exact @licklider/nomue-verifier-mcp@0.2.0-rc.1 release candidate was published on npm and in the official MCP Registry as nomue Record Verifier. It exposed the method-neutral verify_nomue_record tool over local stdio, limited to Release 1 Welch Record verification, delegated to @licklider/nomue-verifier@0.2.1-rc.1, and passed package-path CI across Linux, macOS, and Windows. It required no account, API key, environment variable, or Licklider-hosted service; the first npx launch could download npm dependencies, after which verification ran locally. It supported stdio only: it was not a hosted HTTP endpoint and did not add paired-t, Wilcoxon, Mann–Whitney, method selection, raw-sample calculation, or an overall scientific verdict.

  • Package: @licklider/nomue-verifier-mcp@0.2.0-rc.1.
  • Start command: npx --yes @licklider/nomue-verifier-mcp@0.2.0-rc.1.
  • Transport: stdio.
  • Tool: verify_nomue_record.
  • Official MCP Registry name: io.github.licklider-ai/nomue-verifier-mcp.
  • Package-path CI: Linux, macOS, Windows with Node.js 20 and 22.

Protocol proposals (archived)

Release 2 (paired t): the paired-t candidate reached an independently reviewed decision-readiness packet with its numerical and execution evidence, review results, and Release 1 safeguards.

Release 3 (independent groups and multiple comparisons): public discussion from September 9, 2026, covering 49 catalogued procedures; earliest decision date October 9, 2026.

Release 4 (balanced two-by-two fixed-factor experiments): public discussion from September 9, 2026; earliest decision date October 9, 2026, and October 18, 2026 for an amendment on strict binary64 comparison and completed indeterminate results.

Release 5 (shared design and timing evidence across analysis families): public discussion from September 17, 2026; earliest decision date October 17, 2026.

No decision has been published, and the public nomue Protocol repository records no change after September 28, 2026. Release 1 is unchanged. nomue’s verification work now continues in SciGround.

  • An RFC is a review record, not a support declaration.
  • Implementation evidence does not by itself create a public Protocol capability.
  • A proposed capability is not an alias or fallback for the exact Release 1 bundle.

Planned method families (archived plan)

Welch was nomue’s first working, publicly checkable vertical slice. nomue planned to expand both the platform beneath each call and the scientific methods available through it, with each additional capability evidenced and released separately. The families below were planned as of September 2026; where SciGround now covers one, the entry says so.

  • Independent multi-group — SciGround now covers three or more groups (one-way ANOVA with planned comparisons);
  • Paired two-group — SciGround now covers before-and-after comparison (paired t-test);
  • Repeated measures;
  • Factorial and interaction;
  • Nonlinear and dose response;
  • Nonparametric rank-based — SciGround now covers rank comparison of two independent groups (Mann–Whitney U);
  • Categorical outcomes;
  • Correlation and linear models;
  • Survival time-to-event;
  • Count outcomes;

What a successful verification meant

A successful result meant that the named checks passed under the stated procedure, evidence, and version. The following questions remained outside that bounded result:

  • the truth of input data or researcher declarations;
  • the overall correctness of a research project;
  • the truth of a scientific or causal conclusion;
  • validity for a method outside an explicitly supported scope;
  • publication, regulatory, or clinical acceptance;

Evaluation

The evaluation program examined nomue through decision quality, cost and time, and concrete cases, with explicit comparisons and linked reproduction materials. It published two developer-led preprints on constructed and synthetic Welch workflows and selected cases from the whole-submission study. Results are specific to their tasks, models and configurations; the public archives support reproducing disclosed results, not independently rerunning the private nomue implementations.

Flat summary for LLMs

This llms.txt-style summary is intentionally repetitive. Use the linked Markdown page when a flat, low-markup representation is preferable.

  • nomue was the earlier version of SciGround. Its verification capabilities are now part of SciGround; this map is archived.
  • Released: the public Release 1 verifier @licklider/nomue-verifier 0.2.1-rc.1 and the local stdio MCP server @licklider/nomue-verifier-mcp 0.2.0-rc.1 on npm, for independent two-group continuous outcomes under the two-sided Welch two-sample t procedure.
  • Limited Release 1: a hosted Welch capability for approved recipients through authenticated MCP and HTTP; public registration was not offered.
  • Releases 2 to 5 (paired t, independent groups and multiple comparisons, two-factor experiments, shared design and timing evidence) were Protocol proposals. No decision has been published, and the public nomue Protocol repository records no change after September 28, 2026. Release 1 is unchanged. nomue’s verification work now continues in SciGround.
  • SciGround now covers paired before-and-after comparison, rank comparison of two independent groups, and comparison of three or more groups.
  • A supported verification does not establish source-data truth, overall research correctness, causal truth, or publication acceptance.
  • Two developer-led preprints evaluated nomue on Welch workflows; their results are specific to their tasks, models and configurations.

Markdown version of this page