Seven declarative stages: quality margin unmet; tokens rose in three runs
The prompts here state what must be true, not how to build it. Across three repeat runs, the z3-checked algebra arm scored level with or below No docs and never reached the threshold. It used more tokens than No docs in every run.
Results at a glance
| Run | Arm | Average score | Stages compared | Tokens | Time | Python CC |
|---|---|---|---|---|---|---|
| E020 run 1 | No docs | 0.322 (best in run) | 6 of 7 | 31.21M (best in run) | 1:39:38 | 5.63 (best in run) |
| Algebraic docs + z3 | 0.292 (−0.030) | 36.36M (+17%) | 1:38:00 (−2%) (best in run) | 7.64 | ||
| E020 run 2 | No docs | 0.355 (best in run) | 6 of 7 | 22.03M (best in run) | 1:23:43 | 5.71 (best in run) |
| Algebraic docs + z3 | 0.273 (−0.082) | 26.57M (+21%) | 1:21:00 (−3%) (best in run) | 6.48 | ||
| E026 | No docs | 0.303 | 6 of 7 | 24.43M (best in run) | 1:37:05 | 6.61 |
| Algebraic docs + z3 | 0.308 (+0.005) (best in run) | 28.14M (+15%) | 1:34:16 (−3%) (best in run) | 6.09 (best in run) |
Scores average the stages every arm of the run scored: the stages compared. Tokens and time are each run’s builder totals over every stage it worked. Brackets compare with No docs. Highlighted values mark the highest quality score and lowest recorded tokens, time, and Python CC within each run; ties share the highlight. This does not mean the success rule passed. Python CC means the recorded mean cyclomatic complexity of the Python code’s functions, classes, and methods at the stage immediately before Rust conversion.
What changed in this condition
The agent grows the application from an empty repository over seven stages of declarative prompts: each states only what must be true when the stage ends. The last stage converts it to Rust. This condition has no Prose docs arm.
Control
No docs
No design method and no starting design. Before coding, it writes its own method, then its designs.
Hypothesis arm
Algebraic docs + z3
Algebraic docs, with each charter and proof also as a z3 file, and z3 installed. It must check its algebra with z3 before writing code, and every proof must pass when a stage ends.
Runs: 3 (E020 run 1, E020 run 2, E026), repeats of one setup.
Builder model: gpt-6-sol · medium
Agent harness: codex-cli. Judge: claude-opus-5-5-high.
Stage evidence
Not supported. Each part of the rule must hold in every run.
Stages:
initial-buildtelemetry-addparity-substrateprocess-ontologycheck-no-writeconcurrent-submissionsrust-conversion
| Run | Arm | Met | 1 | 2 | 3 | 4 | 5 | 6 | 7 |
|---|---|---|---|---|---|---|---|---|---|
✗ Algebraic docs + z3 must score at least 0.1 above No docs in every graded stage, in every run: not met | |||||||||
| E020 run 1 | Algebraic docs + z3 | 0 of 6 | −0.04 | −0.06 | −0.02 | −0.04 | 0.00 | −0.02 | No docs failed |
| E020 run 2 | Algebraic docs + z3 | 0 of 6 | −0.11 | −0.10 | −0.03 | −0.07 | −0.11 | −0.07 | both failed |
| E026 | Algebraic docs + z3 | 0 of 6 | +0.09 | 0.00 | 0.00 | 0.00 | 0.00 | −0.06 | both failed |
Each cell is the arm’s score minus the other arm’s at that stage. ✓ marks a stage that meets that part of the rule; Met counts them, of the stages with a value. “failed” means that arm’s grade failed at that stage, so the stage has no score.
Noise. Between runs that repeat the same setup, the same arm’s score at the same stage moved by a median of 0.05 and at most 0.11, over 12 comparisons; 2 moved by 0.10 or more, the rule’s threshold.
Details
The prediction, set before the runs
The test card names the arms as follows: control is No docs, algebraic is Algebraic docs + z3; total_tokens is tokens and elapsed_s is time.
Prediction. The algebraic arm’s quality score exceeds the semantic arm’s by at least 0.1.
Falsifier. The algebraic arm’s quality score is no higher than the semantic arm’s. A positive difference below 0.1 is inconclusive.
Measured: Each arm’s judged score at each stage. Quality Δ is the arm’s score minus No docs. A stage meets the quality target at +0.1 or above. Every counted check must pass in every run. A planned comparison with Prose docs could not be measured because that arm did not run.
z3
| Run | Arm | Last stage | Proof goals | Proved | Disproved | Undecided | Stages the agent ran z3 |
|---|---|---|---|---|---|---|---|
| E020 run 1 | Algebraic docs + z3 | 7 | 139 | 139 | 0 | 0 | 5 of 7 |
| E020 run 2 | Algebraic docs + z3 | 7 | 142 | 142 | 0 | 0 | 7 of 7 |
| E026 | Algebraic docs + z3 | 7 | 159 | 155 | 4 | 0 | 5 of 7 |
After each stage, the system runs z3 on the proof goals in the design’s z3 files and counts those it proves, disproves or leaves undecided. The counts are from the last stage that has them; — means none were recorded. The last column counts stages in which the agent itself ran z3. In E026, some goals were still disproved at the last stage.
Runs
E020 run 1 — gpt-6-sol · medium
Run ID: run-20260923T235842Z-4979eeee
Started: 2026-09-23
Harness status: failed
The No docs arm’s grade failed at stage 7 (rust-conversion): cargo test failed. Every earlier stage was graded.
E020 run 2 — gpt-6-sol · medium
Run ID: run-20260924T031833Z-a6b163d1
Started: 2026-09-24
Harness status: failed
The Algebraic docs + z3 arm’s grade failed at stage 7 (rust-conversion): cargo test failed. The No docs arm’s grade failed at stage 7 (rust-conversion): cargo test failed. Every earlier stage was graded.
E026 — gpt-6-sol · medium
Run ID: run-20260924T033220Z-8386576e
Started: 2026-09-24
Harness status: failed
The Algebraic docs + z3 arm’s grade failed at stage 7 (rust-conversion): cargo test failed. The No docs arm’s grade failed at stage 7 (rust-conversion): cargo test failed. Every earlier stage was graded.
The harness marks a run failed when any arm’s grade fails. That stage has no score for that arm; the run’s other stages still count.
Source data
View condition E020-E026 in G001.json. The run IDs above identify the counted runs. See Data and methods for the export method and limits.