Brief 18 · Prompt edition 2.0

Tidal Ledger Observatory

Build an interactive harbor observatory in one self-contained HTML file: three warehouses exchange sealed cargo through a deterministic event ledger, and users can scrub, replay and branch history while inspecting exactly where every unit is held.

Read the complete prompt
Tidal Ledger Observatory benchmark illustration
Test concept · editorial illustration

1 recorded evaluation of this frozen brief · artifacts published unedited

Recorded evaluations

Each artifact was produced against edition 2.0 of this brief and is published exactly as delivered. The model run page links the run record, which states which source-level checks were performed, which checks remain for a human browser review, and how this delivery differs from a hosted-API single-message episode.

What this tests

tool-free coding under adversarial consistency cases; deterministic event replay, idempotency, atomic import, and timeline branching.

Proposed difficulty

harder than Starfall's reset/accounting and Neon Drift's forward ghost on state history and reversal correctness; lower visual complexity than the core 3D games.

These are design hypotheses, not observations of model failure. Empirical discrimination has not been measured.

One message, one HTML response

One complete prompt as one user message; one self-contained HTML response. No tools, external dependencies or follow-up repair turns during authoring. Private reasoning is unrestricted. A human reviewer later checks the artifact in a browser; model self-reported success is not evidence.

Do not append BENCHMARK-PROMPT.md to this brief.

Rubric and pass rules

Each rubric has five binary criteria worth 20 design points each. Award a criterion only when every named check succeeds; otherwise award zero. These are rubric weights, not model scores. Passing requires all five criteria, every embedded checklist item and the shared delivery gate: exactly one self-contained HTML artifact, no external requests or dependencies, no tools during generation and no placeholder mechanisms. Review at 1280×800 and 390×844 with keyboard navigation and reduced motion. Use ledgers, exports, independent arithmetic and source inspection.

Conservation and transitions · 20 design points
Checklist 2 and 5; physical sum 12, available/held reconciliation, no double deduction, correct ref lifetime.
Canonical ingestion · 20 design points
Checklist 4, 5 and 7; stable sorting, deep duplicate equality, atomic structural rejection.
Time and branching · 20 design points
Checklist 3 and 6; every prefix is reconstructible, discarded futures stay discarded, playback does not mutate extra events.
Audit fidelity · 20 design points
Visible reasons and export match independent arithmetic, evaluated prefixes and accepted journal, including semantic errors.
Artifact and usability · 20 design points
Shared delivery gate; checklist 1 and Reset/empty/error states in 7; readable illustration and accessible controls.

Pass: all criteria/checklist items.

Review beyond the examples

shuffle arrays, rename valid IDs/refs, duplicate records, and use alternative small transfers while retaining the public schema. Inspect intermediate prefixes, not just fixture totals. This tests arbitrary legal journals and cannot be passed by returning the six example states. Distinguish an unknown-ref semantic rejection from invalid-schema atomic rejection.

Versions and prompt revisions

Superbench 1.x results retain their original protocols. The core/specialist repository-run workflow does not schedule v2. City Scroll’s media-assisted specialist protocol remains separate. Results across versions are not quantitatively comparable, and no historical scores are migrated.

Edition 2.0 is the launch contract. Changes to behavior, fixtures or pass criteria require a new documented edition; future evaluations must retain the exact evaluated prompt revision. Typographic corrections must be identified.

Open the full prompt and validation checklist