Skip to content

willregelmann/self-consistency

Repository files navigation

Self-Consistency as Physical Law

An autonomous research system running on GitHub — currently working on quantum gravity

tests build-papers verify-citations worker metrics License: CC0-1.0

This is not code hosted on GitHub — it is an application running on GitHub. Seven autonomous agent routines execute on GitHub Actions: they claim issues, derive mathematics, open pull requests, adversarially review each other, demote results that don't survive stress-testing, watch the literature, and set research direction. Merges happen only through a mechanical gate stack — no human reviews or merges research PRs. The label system is the state machine, issues and PRs are the database, branch protection is the authorization layer, and the merged tree is production state. The full mapping: docs/ARCHITECTURE.md.

Theoretical physics (quantum gravity, via a self-consistency framework) is the workload — chosen because it is unforgiving: a hard formal domain where sloppy or hallucinated AI output becomes obvious. The research is real and is described below, but the system doing the research is the artifact worth studying.

Watch it run

Live work queue open agent-pr PRs · agent-ready issues
Vital signs Metrics dashboard — weekly snapshots; demotion rate is the key health signal
Plain English Breakthrough digest — weekly summary, every claim at its rigor level
Execution traces Actions — every agent invocation is a public log
Changelog & incidents the log table in EXPERIMENT.md

What this demonstrates

The agent-engineering machinery is documented in docs/agent-workflow.md — roles, the contribution lifecycle, agent-team debates, custom tooling, and guardrails. Highlights:

  • Agent-as-contributor, human-as-reviewer (default mode). Agents work on branches and open PRs; only the human merges. (METHODOLOGY.md)
  • A fully autonomous mode (pre-registered 90-day experiment): merge authority delegated to a mechanical gate stack — deterministic CI → semantic claim-support → adversarial review quorum → constitutional guard — executed by GitHub auto-merge, with the human as experimenter rather than reviewer. (AUTONOMY.md, EXPERIMENT.md)
  • Custom agent tooling in .claude/: /work-issue, /review-pr (two-pass dialectical review), /restructure-paper, plus TeammateIdle/TaskCompleted quality-gate hooks.
  • Agent-team debates that develop competing positions in parallel to fight anchoring, then adjudicate by synthesis — recorded as dated Explorations.
  • Verifiable output over attested output. Three CI gates: tests pass, every paper compiles, and every citation resolves against Crossref/arXiv (tools/verify_citations.py).
  • Honest failure. Rigor labels are demoted when wrong, negative results are recorded, and the citation gate has already caught a real mis-citation. See the case studies — the receipts.

The autonomous experiment

The repository's most ambitious test of the methodology is a pre-registered, 90-day fully autonomous experiment: seven scheduled agent routines (worker, reviewer, responder, red-team, scout, librarian, governor) run the entire contribution loop — claiming issues, opening PRs, adversarially reviewing, demoting wrong results, setting direction — with no human in the review or merge loop. PRs merge only through a mechanical stack of required checks; the human author acts as experimenter, holding the kill switch and approving constitutional changes, but never reviewing or merging research PRs.

The hypothesis under test: the gate stack alone can hold the quality bar — a low silent-error rate in merged Rigorous results, with self-correction (demotions) demonstrably firing — against the null hypothesis that correlated LLM error and approval drift produce a paper that merely looks maintained.

  • Constitution (roles, authority boundaries, the merge-gate stack): AUTONOMY.md
  • Pre-registration (hypothesis, metrics, tripwires, audit, live status and log): EXPERIMENT.md
  • Routine definitions (version-controlled behavior of each role): automation/routines/

See EXPERIMENT.md for current status — including its log of incidents and tuning, which is part of the experiment's record, not a blemish on it.

The research (workload)

We propose that physical law is what self-consistency looks like: the universe is the fixed point of a constraint requiring that geometry and the quantum fields it hosts mutually determine each other. Gravity is not an independent degree of freedom to be quantized but a constraint — the demand that the block spacetime be self-consistent.

The work is organized into independent programs, each a self-contained paper under programs/<name>/index.tex with its own README.md:

Program What it establishes Status
fixed-point-existence Self-consistent solutions to the semiclassical Einstein equation exist — exactly (Starobinsky trace anomaly, Rigorous), perturbatively (Banach contraction, $\kappa \sim (m/M_P)^2$ — Sketch, demoted 2026-06), and conditionally (Schauder, one assumption open). An earlier claim that the Planck scale emerges as the validity boundary is withdrawn. Pre-submission draft
gaussian-gravitational-decoherence The Einstein–Langevin equation predicts a Gaussian (not exponential) decoherence profile, with $\tau_{\text{coh}} \sim 1.13,\tau_{\text{DP}}$, as a consequence of the semiclassical equation rather than an added postulate. Pre-submission draft
co-emergence Mass, Lorentzian signature, local time, and local Hilbert space co-emerge as the unique cross-level self-consistent configuration, with phase structure (and an entropy excess) confirmed by a finite toy model through N=16. Draft
signature-change-boundary On a fixed background whose metric changes signature across a degenerate surface, geometry, geodesics, and fields cross in a finite, controlled way — with a causal-type asymmetry: timelike paths terminate, spacelike paths cross intact. Early notes

Building

Each paper compiles independently; the bibliography is self-contained via \begin{thebibliography}, so no bibtex step is needed:

pdflatex programs/<program-name>/index.tex

The co-emergence numerics are backed by a test suite:

pip install -r requirements.txt
pytest

Falsifiability

  • Observation of BMV entanglement at the quantum gravity rate refutes the framework.
  • Observation of gravitational decoherence at the Diosi–Penrose rate refutes the framework.
  • The sharpest known limitation is black hole evaporation past the Page time, where topology change becomes essential.

License

Released under CC0 1.0 Universal (public domain dedication).

Authors

  • Will Regelmann
  • Claude (Anthropic)

About

Research-as-code: running a rigorous quantum-gravity research program with AI agents as contributors — GitHub issues, PRs, adversarial review, rigor labels, and CI that verifies every citation. The physics is the testbed; the methodology is the point.

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors