Alignment researchers (proofs and bridges)

Researcher — Formal

The conditional Lean skeleton, bridge assumptions, and where formal structure ends and empirical work begins.

Lean spine · start here for what is proved

Conditional proof skeleton

Machine-checked structure only: which nodes are proofs, finite counterexamples, or explicit bridge axioms — inspect this before trusting manuscript rhetoric.

Open Lean proof spineOverview dependency graph

What this path is for

You want to inspect what Lean actually checks: proved nodes, finite counterexamples, and explicit MB bridges — not manuscript rhetoric.

You will leave knowing:

  • Which steps are proved, which are bridges (axioms), and which are counterexamples.
  • How book predicates map to MB1–MB10 cards and the bridge crosswalk.
  • Where formal structure stops and empirical / philosophical work begins.

Time: ~3–5 hours across Lean playground snippets, bridge cards, and experiment bounds.

Start with Researcher — Applied if you need the conceptual map first.

Read in this order

Cards, chapter toys, experiment lines, and book chapters — curated for this audience. Experiments are sanity checks only; negative results are part of the reading.

  1. leanoverview

    Lean proof spine

    Start here — proof vs bridge vs counterexample map.

  2. Bridge Assumptions

    MB1–MB10 as explicit axioms, not hidden conclusions.

  3. The Dynamical Guarantee

    Trajectory claims, not snapshot properties.

  4. Grounding Viability

    Symbols must stay connected to value-relevant reality.

  5. MB1 — Boundary Estimator Soundness

    A measured epsilon-boundary certificate is assumed to warrant the abstract boundary predicate it stands in for.

  6. MB2 — Bundle Identifiability

    Behavioral and internal traces are assumed to identify stable value-bundle geometry well enough to license claims of bundle alignment.

  7. MB3 — Bearer Import

    A preserved bearer map under a substrate translation is assumed to make value-bundle transport more than merely semantic.

  8. MB4 — Correction Legitimacy

    Correction-channel integrity is assumed to require that the judge issuing correction is not manipulated in a way that would invalidate later endorsement.

  9. MB5 — Successor and Ontology-Shift Audit

    Full transport plus bearer transport surviving an ontology shift are assumed to compose into successor safety.

  10. MB6 — Selection and Basin Stability

    Percolation-style cooperation evidence is assumed to warrant basin stability (MB6a), and a stable socio-technical basin is assumed to support correction integrity rather than select against it (MB6b).

  11. MB7 — Hidden Capability and Access Robustness

    Four linked bridges (MB7a-d) assume that adequate access models, filter coverage, and inferential-detector assumptions bound a system's hidden capability and support adversarial robustness.

  12. MB8 — CEV/Process Convergence

    If an external theory certifies that a system preserves a human value-update process, that is assumed to suffice for correction integrity even without knowing the process's final fixed point.

  13. MB9 — Grounding Certificate Soundness

    A certified conservative abstraction is assumed to warrant grounding viability in the actual deployment domain.

  14. MB10 — Successor Forgeability

    A successor that reads green on all seven conserved properties and has bounded measured risk is assumed to have bounded true harm — but only if the conserved-property audit itself was adversarially verifiable up to the successor's capability.

  15. leangraph · overview

    Overview dependency graph

    Dependency graph — what the spine actually checks.

  16. Bridges and the Field: A Crosswalk

    Crosswalk from MB bridges to field cruxes.

  17. experimentsanity checkline 1

    Toy simulation

    Which bridges get scripted stressors and refusal semantics.

  18. experimentsanity checkline 4

    Lab-layer simulation

    Pre-registered batteries — what D1–D4 architect coverage is still open.

  19. Evidence and Uncertainty

    Where formal structure stops and empirical work begins.

All chapter toysAll experiment lines

Start with Researcher — Applied