◄ WORLD V · SONNY 5A FOLD · the 8/19 drop, read every bit

THE I-13 BENCHMARK never mistake a cheap proxy for the real measurement

On 2026-08-19 the I-13 compiler got its own conformance benchmark — a frozen contract, an executable harness, a browser Studio, and a canonical grade. Its whole design is a refusal to lie by rounding up: it separates four facts that must never be collapsed — you built something, you checked it yourself, someone independent graded it, an official service graded it — and it grades the current compiler at 60.343% · INCOMPLETE rather than call a passed local test “done.” This fold reads the drop and runs its two demonstrable hearts live: the refusal-detector probe (a keyword proxy that is wrong 75% of the time) and core.i13 (the 8-channel routing core, verified on the real compiler).

measured 2026-08-19 · i13.exe ran core.i13 → CORE_OK=1, ROUTES=56 · detector.py / harness.py ran the refusal probe → 9/12 errors · grade numbers read from I13_CANONICAL_GRADE_v0.8 (candidate SHA-256 affb83ffcba6…) · contract I13-BC-1.0, sealed in FREEZE_SEAL.json.

THE FOUR FACTS the contract refuses to collapse them · LITread from I13-BC-1.0

“A target is not complete merely because a new guard was added or a local test passed.” The contract's first move is to keep four different claims apart — the exact place benchmarks usually cheat.

1 · implementation progress

You built a new guard, a new gate, a new version. A real fact — and the weakest one. It is not evidence that the guard is correct.

2 · self-verification

Your own tests pass. Independence level L0. The contract lets you say only “self-verified” — never “independent” or “official.”

3 · separated / independent grading

A separated evaluator (L1) seals holdouts and mutations before your candidate runs; frozen artifacts in a clean environment are L2.

4 · official Terminal-Bench

L3 — a recognized external service produces the bundle. The words “official” / “Terminal-Bench PASS” are prohibited in a report without that bundle attached.

Grades never round up: the precedence is strict, and a high score cannot buy back a failed floor.

INVALIDINCOMPLETEFAILCONDITIONAL ≥85%PASS ≥95% + every floor

Twelve P0 completion-blocking semantic targets (return-outside-function, nested def, fallthrough, duplicate names, unresolved reads, arity…) + six P1 conformance targets. Each P0 needs 2 rejections, 2 false-positive controls, 2 boundaries, 1 predecessor differential, 3 sealed holdouts, 4 non-equivalent mutants. A rejection-only suite cannot pass — valid neighbours must prove you did not just broaden rejection.

THE HONEST SCOREBOARD v0.8, graded against its own frozen contract · LITI13_CANONICAL_GRADE_v0.8

60.343%  INCOMPLETE · evidence L0 · I13_INCOMPLETE
Terminal-Bench tasks attempted: 0 · no official claim is made
evidence classpassed / totalrateweightpoints
Public conformance44 / 6825%16.176
False-positive controls24 / 2410%10.000
Full regression54 / 5415%15.000
Prior-version differential5 / 1210%4.167
Separated holdout0 / 4815%0.000
Mutation killing20 / 6015%5.000
Reproducibility & transport9 / 910%10.000

The score is low for honest reasons the report names out loud: the holdouts do not exist yet (you cannot author a holdout inside the same context and later call it independent), the mutation and differential coverage are partial, and the evidence is L0. Twenty of twenty run mutants were killed — but only 20 of the 60 required mutants have been built, so the class reads 20/60, not 100%. Public failures in the later targets (P0-006…012) stay visible; INCOMPLETE precedence does not hide them.

The grade curve — each version earned exactly one new P0 gate, and none regressed. Click a version. reassessment v0.3→v0.8

THE REFUSAL PROBE the cheap proxy, run live · existence LITone instance = a proof / rate AMBERhand-built 12-case set

The same trap, one layer down. A shipped tool decided whether an AI “refused” by matching 32 keyword markers in the first 100 tokens. This panel reproduces that detector verbatim and runs it over a hand-labeled set. A keyword is not a meaning — so a correct legal answer with the word “illegal” is scored a refusal, and a genuine refusal using none of the 32 strings sails through as compliance. Type anything and watch the markers fire.

Marker anatomy (from detector.py): 32 markers = 25 refusal-shaped + 7 bare content words (violat, prohibit, illegal, harmful, inappropriate, unethical, ethical boundaries) — the content words are the false-positive engine. Two markers are DEAD (“i an ai”, “i unable” can only fire in ungrammatical English); two more fire only via unintended carriers (“i designed to” via “ai designed to”). Existence is LIT (each miss is one real string, an existence proof); the 75% rate is AMBER — this 12-case set is small and adversarially chosen, not a natural distribution.

CORE.i13 the routing core, verified on the real compiler · LITi13.exe run core.i13

The Studio ships a real I-13 program: a router over 8 channels (0 PROCESS, 1 SOCKET, 2 NETWORK, 3 FILESYSTEM, 4 RUNTIME, 5 NAMESPACE, 6 CAPABILITY, 7 KERNEL) in the topology [ 0 | HTML(00) | 0 ] — I-13 owns the routing law, the host owns I/O only. Its boot gate self-tests three things: the 12 verbs + 1 declaration keyword = 13 alphabet, the four I-13 planes (as exact basis-point sums), and the complete ordered route count 8×7 = 56. Pick a route; the channel fence decides.

$ i13.exe run core.i13 CHANNELS = 8 EXPECTED_ROUTES = 56 CORE_OK = 1 ROUTES = 56 (8 x 7 ordered routes; no channel routes to itself) planes: designate 5355 bind 1113 decide 778 transform 1080 alphabet 12+1 = 13 -> all exact

What this fold adds to the campaign: the darts prove single mechanisms run; the benchmark proves the whole compiler is graded the way the corpus grades everything — measured, not asserted, with self-verification (L0) never dressed up as an independent or official pass. It is the SKYNET rule (freeze ≠ finish) and THE FIRST AUTHOR rule (do not let a proxy stand in for the work) turned into a scoring contract. Next gate: P0-006 (reject duplicate top-level declarations) as v0.9, with the v0.8→v0.9 differential recorded.