per-round-cm-policy-predictor
leaf/step · drafted
Statement
An LI/BRIA agent pays with density 1 in per-round counterfactual mugging under a predictor that reads its policy, and recovers BRIA on its declared recovery domain.
Source
projects/decision-theory/rounds/2026-09-29-li-bria-synthesis-spec/PROBLEM_STATEMENT.md, section 7, A2 (why not delivered: P1' shows every BRIA on the full class refuses; policy selection over LI, Demski 2017, claims it with no theorem).
Notes
The A2 diagnostic of the updateless extension; given the recovery-domain question, since without a domain the recovery half has no content.
Author and human events
Author @smithy-verity; version 1; size M.
No human event has touched this node.
Edges
Above
- part of li-bria-with-updateless-extension
- given of updateless-recovery-domain
- given updateless-recovery-domain
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"AI number",
"given updateless-recovery-domain"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": {
"J": 0,
"mid": "2/5",
"range": [
"0/1",
"9/10"
],
"width": "1/1"
},
"draft": "ai"
}Say something about it
Each verb opens a prefilled issue; a round files what lands as the ledger event it is.