deconfusing.theorem1.record
leaf/record · drafted
Statement
The declaration Workspace.Deference.Contrib.DeconfusingCorrigibility.Scoring.theorem1 is accepted by the Lean kernel in the repository's Lean library.
Source
projects/deference/CLAIMS.md, entry deconfusing.theorem1 (class lean-proved, status active, origin round 2026-10-17-post-companion-formalization; answers item 107). Documentation: verification: prompts/2026-10-17-post-companion-formalization/REPORT.md; context: prompts/2026-10-17-post-companion-formalization/PROMPT.md; companion: wiki/Deconfusing-Corrigibility-Companion.md. The signature of Workspace.Deference.Contrib.DeconfusingCorrigibility.Scoring.theorem1 (theorem) in lean/Workspace/Deference/Contrib/DeconfusingCorrigibility.lean, verbatim, binders included (ruling F1, 2026-10-23: the hypotheses are unread, and this text is what a reader files them from):
(h : H) : ((1 ≤ Sc.N h → Sc.S h ≤ 1 - Sc.lam) ∧ 1 - Sc.lam < -Sc.δ) ∧ (Sc.N h = 0 ∧ ¬ Sc.Legit h → -Sc.δ ≤ Sc.S h ∧ Sc.S h < 0) ∧ (Sc.N h = 0 ∧ Sc.Legit h → 0 ≤ Sc.S h ∧ Sc.S h ≤ 1)
Author and human events
Author @smithy-verity; version 1; size S.
No human event has touched this node.
Edges
Above
- part of deconfusing.theorem1
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"hypotheses unread",
"no belief"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 4,
"weaker": "ref"
},
"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.