spec(reasoning): wire the Assay into ReasoningReceipt (run-level epistemic posture)#199
Merged
Conversation
Add optional ReasoningReceipt.assay — the reserved receipt landing spot for the epistemic Assay (PR #198 follow-on). Run-level, render-time summary that references its run's ReasoningAssay records by URN (assayRefs, so verdicts stay independently re-projectable) and surfaces overallState, weakest-link binding, verifier calibrationRef, per-state counts, and projectedAt. A cache, never authoritative over the assays. EventEnvelope needs no structural change: each assay's authority axis already mirrors EventEnvelope.actor/integrity by reference. Backward-compatible (optional field). validate-reasoning-examples green.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Follow-on to #198 (the Epistemic Assay). Adds the optional
ReasoningReceipt.assayblock — the receipt landing spot the Assay design reserved for binding + verifier calibration.Why
#198 shipped
ReasoningAssay(per-claim, 5-axis) andAssayStandard(verifier calibration). A run's receipt had no way to carry the epistemic posture of the claims produced in it. This wires that in.How
schemas/ReasoningReceipt.json— new optionalassayobject:assayRefs— URNs of the run'sReasoningAssayrecords (referenced, not embedded, so each verdict stays independently re-projectable when anAssayStandardimproves)overallState— theok/sad/badprojection for the run's overall answer (weakest-link readout)binding— weakest evidence binding across the run (a singlepost-hocclaim pulls the run topost-hoc)calibrationRef— theAssayStandardthe overall verdict rests oncounts— per-state tally;projectedAt— when the summary was projectedexamples/reasoning_receipt.json— references the existingsuperconscious-demo-okassay (samerunRef), self-consistentokposture.Design fidelity
EventEnvelopeneeds no structural change: each assay'sauthorityaxis already mirrorsEventEnvelope.actor/integrityby reference, so authenticity is corroborated from the envelope, not asserted by content.assayis optional andReasoningReceiptisadditionalProperties: true, so all existing receipts remain valid.Validation
make validate-reasoning-examplesgreen — 13/13 checks, includingreasoning_receipt.jsonagainst the updated schema and projection-soundness on all three assay fixtures.🤖 Generated with Claude Code