HUD fidelity self-assessment (mean of 12 categories)

An honest self-assessment against a demanding reference. It has not met its gate.

HUD fidelity self-assessment (mean of 12 categories)

Then 3.71 score (0–10) 30 Jul 2026 Now 2.43 score (0–10) 20 Sept 2026 worse

  • measured or observed

acceptance gate above 9.0

Show the numbers
HUD fidelity self-assessment (mean of 12 categories)
Date Value Evidence Revision Samples Note
30 Jul 2026 3.71 score (0–10) OBSERVED 58ca5e6aa 12 The HUD is graded against a deliberately harsh 9.0-per-category bar; independent rescoring lowered the score, and the gate is not yet met.
31 Jul 2026 4.83 score (0–10) OBSERVED fe0246c46 12 The HUD is graded against a deliberately harsh 9.0-per-category bar; independent rescoring lowered the score, and the gate is not yet met.
3 Aug 2026 2.94 score (0–10) OBSERVED c9ad1b641 12 The HUD is graded against a deliberately harsh 9.0-per-category bar; independent rescoring lowered the score, and the gate is not yet met.
7 Aug 2026 3.34 score (0–10) OBSERVED ad616aed1 12 The HUD is graded against a deliberately harsh 9.0-per-category bar; independent rescoring lowered the score, and the gate is not yet met.
20 Sept 2026 2.43 score (0–10) OBSERVED 2ea210950 12 The HUD is graded against a deliberately harsh 9.0-per-category bar; independent rescoring lowered the score, and the gate is not yet met.

An honest self-assessment against a demanding reference. It has not met its gate.

Test: Mean of twelve design/fidelity categories (cinematic hierarchy, density, originality, data truth, 3D depth, motion, etc.), scored 0–10; release gate requires every category strictly above 9.0.

Protocol

Test definition

Mean of twelve design/fidelity categories (cinematic hierarchy, density, originality, data truth, 3D depth, motion, etc.), scored 0–10; release gate requires every category strictly above 9.0.

Limits

Limitations

  • Reviewer-scored, not an instrument reading. By 2026-08-08 all twelve had been rescored by twelve independent read-only reviewers; gate not met (minimum category 1.42). Revision is the commit that wrote BUILD_STATE.

Log

Recorded values

Date Value Evidence Samples Source
30 July 2026 3.71 score (0–10) OBSERVED 12 docs/ledger/BUILD_STATE.json (hud_twelve_scores_mean) @ 58ca5e6aa
31 July 2026 4.83 score (0–10) OBSERVED 12 docs/ledger/BUILD_STATE.json (hud_twelve_scores_mean) @ fe0246c46
3 August 2026 2.94 score (0–10) OBSERVED 12 docs/ledger/BUILD_STATE.json (hud_twelve_scores_mean) @ c9ad1b641
7 August 2026 3.34 score (0–10) OBSERVED 12 docs/ledger/BUILD_STATE.json (hud_twelve_scores_mean) @ ad616aed1
20 September 2026 2.43 score (0–10) OBSERVED 12 docs/ledger/BUILD_STATE.json (hud_twelve_scores_mean) @ 2ea210950

Source paths refer to the private JARVIS repository and runtime records. They are listed for audit and are not published.