Runs share the same frozen target and prompt within each test, with disclosed provider-specific stacks. Costs are recorded estimates as labelled in each ledger, not subscription invoices.
Targets
Turbofan Engine
Model coverage
Qwen 3.8 Flash · Max
DeepSeek V4.1 Flash · Max
GLM 5.3 Flash · Max
Gemini 3.8 Flash · High
GPT-6 Astra · Max
Claude Opus 5.5 · Max
Claude Sonnet 5.5 · Max
GPT-6.1 Sol · Max
Evidence available
8 campaign-evidence records
Prompt hash was not published
Exact prompt file path was not published
Still missing
No released Builder project, harness package, or skill download.
Prompt hash was not published with this campaign evidence.
Exact prompt file path was not published with this test.
Published target is fixture package CAD-001 version 1.0.1. TASK.md SHA-256 fdf63d66a86c4784685bd68f022cc65c0090acc7df52f0cc5ad50e23ea8de118 identifies the fixture file, not a per-run prompt receipt. No library download is published for that fixture.
Repeat-run reliability evidence is not established.
Public receipts
8 measured run ledgers
Open any row for its recorded workflow cost, timing, token usage, stack disclosure, artifact integrity, and explicit evidence gaps.
A path is shown only when the published record includes the prompt hash that identifies it. Campaign evidence and projections keep the hash gap visible.
Prompt identity not recorded
Prompt hash was not published.
Exact prompt file path was not published.
Separate records
Related records with unknown prompt provenance
These published records stay separate from the prompt receipts above. Unknown provenance is why they are listed here.
No separate unattached records are published for this collection.