Alignment Workspace

normativity-line

frame · drafted

Question

Does the public normativity line reach a legitimacy theorem useful for corrigibility and the learning theorem its layers aim at?

Owners: @anson (GitHub A-M-Berns)

Path: normativity-line

Roots

No goal yet. This frame holds what it is about (below) and names no goal of the ranking; naming one is its owner's spelling-out.

Statement

The public normativity line, reasons-and-warrant statics, relational scorekeeping, answerability, a learning-theorem programme and traderized enforcement, reaches a legitimacy theorem useful for corrigibility and the learning theorem its layers aim at.

Source

projects/normativity/README.md: "This line tests reasons-and-warrant statics, relational scorekeeping, answerability, and the learning-theorem program."; RESEARCH_STATE.md (the checkpoint projects/normativity/legitimacy/checkpoint-2026-09-01/ as the current canonical view); projects/normativity/legitimacy/checkpoint-2026-09-01/ROADMAP.md, which asks for the "shortest path to a theorem of legitimacy that is useful for corrigibility".

Notes

The public line is maintained in large part by the repository's other maintainer; it is filed here as plans and claims with public sources, and no want is attributed to anyone. The frame's owner field names the person whose question this frame poses for the argument map. Its four layers per the checkpoint: fixed-era dynamics closed for research sequencing; diachronic legitimacy with the structural core consolidated; counterfactual non-capture open; the corrigibility and deference consumer downstream. The legitimacy half of the line is filed under the programme frame as public-legitimacy-theory and public-layer-II.

Retired by ruling F4 (2026-10-23, one decomposition per line): every root moved to the programme of normativity whose question it bears on, or to the line frame; the table of moves is in prompts/2026-10-22-map-as-canonical/REPORT.md, Follow-up of 2026-10-23. The id survives as a deprecated alias of normativity.

Author and human events

Author @smithy-verity; version 1; size L.

No human event has touched this node.

Edges

Work pointers

Ranking (the lens, not the structure)
{
 "status": "open",
 "diagnosis": null,
 "flags": [
  "superseded by normativity"
 ],
 "V": {
  "V_prior": null,
  "display": "2",
  "headline": 2,
  "ref": 2,
  "valid": 2,
  "weaker": "both"
 },
 "belief": null,
 "draft": "ai"
}

Say something about it

Each verb opens a prefilled issue; a round files what lands as the ledger event it is.

comment · challenge · estimate · want