Epistemic confidence Phase A — honest confidence scoring#8
Merged
msitarzewski merged 1 commit intomainfrom Feb 18, 2026
Merged
Conversation
Confidence now reflects inherent uncertainty of the question domain, not just challenge quality. Rigor (renamed from old confidence) measures challenge genuineness [0.5–1.0]; confidence = min(domain_cap, rigor) where domain caps are factual=0.95, technical=0.90, creative=0.85, judgment=0.80, strategic=0.70. Adds calibration module (ECE metric), duh calibration CLI, GET /api/calibration endpoint, and calibration dashboard in web UI. Full-stack propagation of rigor field across ORM, handlers, CLI, API, WebSocket, MCP, and frontend (47 source files + 5 memory-bank files). 1586 Python + 126 Vitest = 1712 tests passing. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Confidence now reflects inherent uncertainty of the question domain, not just challenge quality. Rigor (renamed from old confidence) measures challenge genuineness [0.5–1.0]; confidence = min(domain_cap, rigor) where domain caps are factual=0.95, technical=0.90, creative=0.85, judgment=0.80, strategic=0.70. Adds calibration module (ECE metric), duh calibration CLI, GET /api/calibration endpoint, and calibration dashboard in web UI. Full-stack propagation of rigor field across ORM, handlers, CLI, API, WebSocket, MCP, and frontend (47 source files + 5 memory-bank files). 1586 Python + 126 Vitest = 1712 tests passing.