cdt-defined-for-learner
and · drafted
Statement
At a recorded point, interventional supposition on the act equals conditioning on it if and only if the act is independent of its graph-parents under the state, so the CDT/EDT contest has no content there (Theorem 3 of the CDT-in-the-learning-setting note, four clauses).
Source
projects/deference/faf-cleanroom-2026-10-02/packages/dp-causal-consist/dp-causal-consist-report.md: thm3_i to thm3_iv over FAF's FactorizesOverDAG. Source: projects/deference/faf-cleanroom-2026-10-02/sources/decision-problems/directions/defining-cdt-in-the-learning-setting.md and projects/deference/faf-cleanroom-2026-10-02/sources/decision-problems/wiki/learning-cdt-renderings.md.
Notes
A done result bearing on the predictor half of the counterfactuals plan: where the act is independent of its parents the two referents coincide. The package is flagged on its ledger only and three core targets are absent; the notes' hypothesis of clause (iii) is to be rewritten to joint independence, and the ledger repair is not filed.
Bridge card
Connected to no informal claim yet: held by no frame.
Declaration thm3_i (record cdt-defined-for-learner.record)
The declaration's interventional and conditional suppositions are the note's CDT and EDT renderings at a recorded point, so its biconditional is Theorem 3(i) as the note states it.
Hypotheses, read:
- recorded-point-dag-setting definitional: The decision point is recorded and the state factorizes over a temporal DAG in which the act has the named parents.
Completeness (cdt-defined-for-learner.complete): No hypothesis beyond the recorded point and the DAG factorization is needed for Theorem 3's clauses.
Author and human events
Author @smithy-verity; version 1; size M.
No human event has touched this node.
Edges
Above
- part of updateless-dt-programme
- root (shared-claim) of updateless-dt-programme
Children
- part: cdt-defined-for-learner.record leaf/record
- part: cdt-defined-for-learner.bridge leaf/bridge
- part: recorded-point-dag-setting leaf/hypothesis
- part: cdt-defined-for-learner.complete leaf/completeness
Ranking (the lens, not the structure)
{
"status": "open",
"diagnosis": null,
"flags": [
"AI number"
],
"V": {
"V_prior": null,
"display": "2",
"headline": 2,
"ref": 2,
"valid": 2,
"weaker": "both"
},
"belief": null,
"draft": "ai",
"root": {
"status": "open",
"Pr": {
"hi": "1/1",
"lo": "5187/320000",
"mid": "365001/640000"
},
"value": null,
"cost": "132/1",
"margin": "no established leaves"
}
}Say something about it
Each verb opens a prefilled issue; a round files what lands as the ledger event it is.