⬡ delegation direction · from somewhere → pointing somewhere
📐 VS Code — QC → → ☕ Claude
work done in VS Code · QC written to Claude's to-do (shape-max-match)
the commit message (the ask the narratives below are about)
feat(pmu): pin the numbers we say out loud — and gate them

HARVESTED THE MEASURED/UNMEASURED BOUNDARY INTO AN ENFORCEABLE RULE, not another doc a future
session won't read.

THE RISK: every figure we quote to an underwriter — 0.90 · 0.30 · 4.48σ · the AUC set — lived only
in PROSE, scattered across a dozen architecture docs and now several outreach docs. Nothing stopped
a future session carrying a STALE number into a room with Mike Carls, who builds frequency/severity
models for a living. ONE unsubstantiable figure contaminates every measured one beside it — which is
precisely why an unbounded precision claim is more dangerous than the 30% miss it would be deployed
to defend.

data/pmu/public-claims.json — single source of truth. Each claim carries its RE-RUN COMMAND and one
of exactly three statuses. There is no fourth:
  MEASURED   — a property of the INSTRUMENT. Provable in a lab, no world required.
               determinism · speed · separation 0.90 · out-of-universe 10/10 · SCRAMBLED-NULL FLOOR
               4.48σ (the null-hypothesis test — the number nobody quotes and an analytics leader
               respects most; lead with it AHEAD of 0.90) · paraphrase-invariance 0.30
  UNMEASURED — needs the WORLD. Each says WHY, and gives the honest sentence to say in the room.
  NULL       — we RAN it and got a negative. Our strongest credential, not our weakness.

FENCED: the DIVERGENT-SERIES walk σ is TELEMETRY, NOT RECEIPT — it comes off a wall-clock-bounded
walk, so it is machine-load dependent. (The leaf/definer recursive on-chip walk IS included; never
the analytic shortcut.) Do not quote it as a measured property.

FORBIDDEN, and now un-sayable: 'approaches infinity' · 'infinite resolution' · 'drift predicts
loss/defects' (WE MEASURED THIS AND IT IS FALSE — AUC 0.496/0.415/0.406, two of three BELOW 0.5,
i.e. inverted) · '30% miss on adversarial camouflage' (we measured PARAPHRASE, not an adversary —
nobody has red-teamed it).

GUARD: tests/pmu/public-claims-are-pinned.test.mjs. The ledger must stay well-formed; every
unmeasured claim must state why AND what to say; THE NULL RESULT MUST SURVIVE (deleting it is the
one edit that turns our strongest credential into a cover-up); and no outreach doc may ASSERT a
forbidden claim. PROVEN TO BITE: planted 'the resolution approaches infinity' into the Marsh agenda,
it turned red, reverted. 5 green.

One fix worth naming: the guard's first cut flagged our own best sentence ('we tested whether drift
predicts defects, AND IT DOES NOT') because the negation wrapped to the next line. Third time today a
line-anchored regex mis-fired on wrapped prose. It now scans a ±1-line window — read the SENTENCE,
not the line. The banned thing is the ASSERTION, never the refutation.

Originating-Terminal: 📐 architect
Relevant-Rooms: 🧪 laboratory, 🔒 vault, ☕ network
Story: The reef-densify read was right — a lesson that lives only as prose is a lesson a future session will not have. The numbers are now a gate, and the null result is protected by a test that fails if anyone ever quietly removes it.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01EssMgKix9aZmZ5dxGPqYCW

◎ COMPETENCE SHAPE — the leaf walk, encircled
the shape the off-lane % describes — each cluster ringed in its own colour, numbered, located on the 144-anchor lattice
each region is where the leaf walk — the recursive definer-of-definer walk on the chip — lit reality outside the declared intent lane. Named, ranged and read below deterministically, with zero model in the loop — recompute the identical bytes yourself: npx thetacog-mcp attest-demo
1drift · ShortLex A3,C ▸ C1,B3 B2.Tactics.Deal × A3.Strategy.Fund → ~comms-email · email comms newsletter telegram · 21 red blocks
ask: "'30% miss on adversarial camouflage' (we measured PARAPHRASE, not an adversary —" · landed off that lane · drift
2bleed · ShortLex C1,A1 ▸ C3,C3 C2.Operations.Loop × B2.Tactics.Deal → ~comms-email · email comms newsletter telegram · 14 amber blocks
ask: "HARVESTED THE MEASURED/UNMEASURED BOUNDARY INTO AN ENFORCEABLE RULE, not another" · landed off that lane · bleed
3drift · ShortLex A3,C1 ▸ C1,C3 B2.Tactics.Deal × C2.Operations.Loop → ~infra-hooks · hook pre-commit post-commit launchd · 11 red blocks
fired from the code, not the ask · lane not declared · drift
4in-lane · ShortLex B,A1 ▸ A1,A3 C.Operations × A2.Strategy.Goal → comms-newsletter · newsletter audience resend broadcast · 8 green blocks
ask: "One fix worth naming: the guard's first cut flagged our own best sentence ('we t" · held the declared lane
5in-lane · ShortLex A,C1 ▸ C,C3 B.Tactics × C2.Operations.Loop → pmu-walk · walk ballistic recursive on-chip · 7 green blocks
held the declared lane · not singled out by the ask
6bleed · ShortLex C,B2 ▸ A2,C2 A1.Strategy.Law × C1.Operations.Grid → ~book · book chapter tesseract manuscript · 7 amber blocks
fired from the code, not the ask · lane not declared · bleed
7bleed · ShortLex C1,A ▸ C3,C C2.Operations.Loop × B.Tactics → ~comms-email · email comms newsletter telegram · 6 amber blocks
fired from the code, not the ask · lane not declared · bleed
8in-lane · ShortLex A,A ▸ A1,B C.Operations × B.Tactics → ~patent-ip · patent uspto inventor provisional · 5 green blocks
ask: "THE RISK: every figure we quote to an underwriter" · held the declared lane
9bleed · ShortLex A1,C ▸ A2,A3 A2.Strategy.Goal × A2.Strategy.Goal → ~comms-email · email comms newsletter telegram · 5 amber blocks
ask: "ONE unsubstantiable figure contaminates every measured one beside it" · landed off that lane · bleed
10drift · ShortLex B1,A ▸ B3,B B2.Tactics.Deal × B.Tactics → ~comms-email · email comms newsletter telegram · 5 red blocks
fired from the code, not the ask · lane not declared · drift
11bleed · ShortLex A1,A ▸ A3,B A2.Strategy.Goal × B.Tactics → ~comms-email · email comms newsletter telegram · 4 amber blocks
fired from the code, not the ask · lane not declared · bleed
12in-lane · ShortLex A,B1 ▸ B,B2 B.Tactics × B2.Tactics.Deal → symbol-grounding · symbol referent denotation groundedness · 3 green blocks
held the declared lane · not singled out by the ask
13in-lane · ShortLex A1,B ▸ A3,C A2.Strategy.Goal × C.Operations → ~comms-email · email comms newsletter telegram · 3 green blocks
held the declared lane · not singled out by the ask
14in-lane · ShortLex A1,C1 ▸ A1,C3 A1.Strategy.Law × C2.Operations.Loop → ~book · book chapter tesseract manuscript · 3 green blocks
held the declared lane · not singled out by the ask
15in-lane · ShortLex C2,A ▸ C3,B C3.Operations.Flow × B.Tactics → ~comms-email · email comms newsletter telegram · 3 green blocks
held the declared lane · not singled out by the ask
16in-lane · ShortLex C2,A1 ▸ C3,A1 C3.Operations.Flow × A1.Strategy.Law → ~comms-email · email comms newsletter telegram · 2 green blocks
held the declared lane · not singled out by the ask
17bleed · ShortLex A,B2 ▸ A,B3 A.Strategy × B3.Tactics.Signal → tesseract · tesseract axis latent focused · 2 amber blocks
fired from the code, not the ask · lane not declared · bleed
18bleed · ShortLex A,A A.Strategy × A.Strategy → ai-regulation · regulation governance compliance article · 1 amber block
fired from the code, not the ask · lane not declared · bleed
19bleed · ShortLex A,A1 A.Strategy × A1.Strategy.Law → payments · stripe webhook payment checkout · 1 amber block
fired from the code, not the ask · lane not declared · bleed
20bleed · ShortLex A,A3 A.Strategy × A3.Strategy.Fund → voice-prompt · voice tts say mp3 · 1 amber block
fired from the code, not the ask · lane not declared · bleed
21bleed · ShortLex A,C2 A.Strategy × C2.Operations.Loop → fim-artifact · fim artifact 3d print · 1 amber block
fired from the code, not the ask · lane not declared · bleed
22bleed · ShortLex C,C2 C.Operations × C2.Operations.Loop → deployment · deploy vercel build push · 1 amber block
fired from the code, not the ask · lane not declared · bleed
⎇ attestation · decidable facts — recompute-it-yourself, no trust in the sender
LANE: OUT
deterministic — σ / tolerance vs the 25% off-lane threshold + lattice placement; NOT a probability, NOT a risk-price
✅ DECIDABLE: WHERE this work landed is provable & re-runnable — recompute this LANE verdict yourself. WHETHER it is bug-free is UNDECIDABLE (Rice) — we do NOT claim that.
placement: C3,CB,C1 · Operations·Flow × Operations
σ (placement measurement): 1.14 shape-match σ
sensor: metal CXMF9VMM29 · attest MFkwEwYHKoZIzj0CAQYIKoZIzj0D… (ecdsa-p256-sha256)
ed25519 signature: valid 44e92f4a71c8… · signer fc0fb4d5709e…
gridHash: 8a4b87022885 (reef the σ was measured against)
binary: b409b4c1dedd815b… daemon sha256 · 525.64ns/walk
⬛ TOLERANCE — the highest-signal read
651 green · 368 amber · 352 red · off-lane 26% vs 25% — ⚠ TOO MANY out-of-lane — drifting
proof of insurability · priced from the geometry, not the code
VERDICT: PRICEABLE
NATURE: Top-Down · Horizontal line — one actor (Tactics.Deal) across many patients · Systemic blast radius
VECTOR: Tactics.Deal directing Ops.Flow (B2 → C3)
ABSTRACTION RUPTURE: Moderate — macro Tactics→Operations, prefix 2→2, line spans 12 lanes
RATIONALE: Exposure flows top-down (intent→execution); priceable with a loading.
study evidence · resilience = the folding-point · sealed 3-arm run
RESILIENCE (folding-point): holds to 0% adversarial corruption before it abstains
SIGNAL vs dead-reef null: · p (null-subtracted)
DECAY · HONEST-NULL: 0% monotonic · 0 false mints → NOT
one survival curve, two readouts: an option pays while it holds · insurance pays if it folds. reproduce: npx thetacog pmu-verify
epistemic perimeter · what we can price (the transaction terms)
DESCRIBABLE region: 0 / 24 lattice cells pass the fence (the rest are out-of-scope, not failures)
CALIBRATION: MIS-CALIBRATED (sold-percentile vs delivered-rate, err —)
THIS COMMIT: 1177 intent · 1406 reality anchors lit
SELLABLE NOW: nothing tradeable yet — un-calibrated (mean error — > 0.10)
why small: provisional sensor (SimHash→gzip-NCD pending) · 144-cell map · this commit's scope. We quote only where the instrument grips — the perimeter IS the contract.
rolling resilience · last 24 days (this commit in context)
VELOCITY: 1822 commits (~76/day)
CORRECTION TAX: 14% (248 folded back to fix) — the org-level resilience read
REEF σ̄: 3.12 ▼ · ρ 0.7671 · STABLE (not inflating its own grip — anti-Goodhart)
what you're looking at: the whole map is your competence lattice — both edges are the same 144 ShortLex anchors (what you do × what you act on). Each lit cell is one place this commit said something (its message + docs) and did something (its code). Colour = whether saying and doing landed in the same lane.
green — in lane: you worked where you declared. This is the competence; more green is better.
amber — bleed: code touched a neighbour you didn't mention. A little is normal — nobody declares everything.
red — drift: code fired in an orthogonal lane (the surgeon doing plumbing) and enough of it to flip the aggregate. Red ≈ 0 is what good looks like.
the pink ring is this commit's coordinate — where its work actually concentrated on the lattice.
so, this commit: 651 green, 368 amber, 352 red → off-lane 26% against a 25% tolerance — ⚠ TOO MANY out-of-lane — drifting.
⛓ produced on attested silicon · sealed receipt — verify without trusting the sender
silicon CXMF9VMM29 · attest MFkwEwYHKoZIzj0CAQYIKoZIzj0D… (ecdsa-p256-sha256)
ran in architect · VS Code 3.9.16 · room-id e643c506059e…
daemon sha256 b409b4c1dedd815b… · gate 1.9933ns/cmp
sealed receipt run-2026-07-14T13-11-19-366Z-00be0d35 · payload 4ae1e67f9917c96c… · band gold
on-chip 525.64ns/walk · pipeline 1150ms · lens 144 seeds/1239ms · seed-lib 8a4b87022885
BEARER POLICY sha256 9f81cde7c37a6597… · ed25519 sig 44e92f4a71c8… · signer fc0fb4d5709e… — binds input+lens+verdict + instrument health; attached as policy-74449cc69.json (verify: node scripts/pmu/verify-policy.mjs)
⬡ three-node attestation · spec + work + a trustless 3rd party
① SPEC NODE serves the spec + the 144-semantics lattice — intent d42aba530e8c… · lattice 8a4b87022885
② WORK NODE produced the work — reality 97727668c00d…
③ ATTESTOR (3rd party) reads the A↔B drift, trustlessly via the sealed receipt above:
TOLERANCE: OUTSIDE (26% off-lane vs 25%)
BARTER FLAG: INSURE — outside tolerance but gripped — price the insurance / renegotiate the spec before settling
PMU · on-commit dogfood · the chip's own anatomy
View this commit: ◎ the full commit page on thetadriven.com (same output as this email) · ⌥ the actual commit on GitHub
the verdict · commit 74449cc69
1 · did this commit drift?
YES — out of lane (26% orthogonal vs the 25% tolerance)
alarm too much reality fired in ORTHOGONAL lanes — the aggregate flip; this is the drift the instrument exists to catch · vs your last 10 commits: p45 of last 10 — normal for you lately
2 · can you trust that reading?
σ_drift 1.14 — WEAK
weak panel story is not yet evidence · vs your last 10: p50 of last 10 — normal for you lately · why low: usually a thin grip (only 31 reality vs 25 intent claims sensed) or a seed library not yet converged — low σ means "don't lean on the maps", NOT "the commit is bad"
3 · where does this commit live?
C3,C Operations·Flow × Operations → B,C1 Tactics × Operations·Grid
read it as actor × patient: this commit is mostly Operations·Flow × Operations work acting on Tactics × Operations·Grid (grip 0.797). this is the commit's COORDINATE — where the work lives — not a judgement; the panels below (◎ marks this cell) are what judge it · drift concentrates in lane B2 · Tactics·Deal — read that row on the TOLERANCE panel
next: read the maps as sketch, not evidence — converge the seed library before citing this · open the TOLERANCE panel and chase the red rows — undeclared work shipped
what this instrument measures: drift = what this commit SAID (message + docs) vs what it DID (code), sensed and walked on the chip — a deterministic read, not an LLM opinion. in reading order: ① the verdict (above) → ② the maps (the raw sense grids, then the leaf-walk clouds that bridge them, then DELTA/TOLERANCE judging the result) → ③ the numbers, contextualized (every value with band · verdict · percentile · what it leads to) → ④ expert detail, collapsed (attestation · receipts · timings · σ inputs).
commit 74449cc69 — 144×144 lattice triptych (on-chip)
◎ the ingest chose C3,C — Operations·Flow × Operations — acting on B,C1 — Tactics × Operations·Grid (grip 0.797) · the walk starts at the ACTOR's row · 2 file(s)
ingest 766.3ms (corpus→lattice) · definer walk 898ms (row→transpose→row, ballistic XOR per hop) · total 2048ms
ingest here = commit-scoped SENSING only (this commit's message + changed files → lit anchors) — deep seed authoring lives in the reef-self-loop, off the commit path
rows = ACTOR (lens) · cols = PATIENT (object) · diagonal = self-reference; ◎ at actor-row × patient-col — every panel, same orientation. Heat above the diagonal = actors ranking ShortLex-earlier than their patients (the walk follows definers uphill in rank).
The 12 canonical lanes (rows top→bottom, cols left→right): A·Strategy · B·Tactics · C·Operations · A1·Law · A2·Goal · A3·Fund · B1·Speed · B2·Deal · B3·Signal · C1·Grid · C2·Loop · C3·Flow
PAIR LATTICE (the map we normally see)
PRE-WALK SENSE · INTENT grid — the snapshot, no point of view
the no-point-of-view snapshot — what the sensor lit before any walk; the leaf walk below is what bridges the two grids
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
PRE-WALK SENSE · INTENT grid — the snapshot, no point of view 144×144 (axes = the 144 ShortLex anchors on both sides)
PRE-WALK SENSE · REALITY grid — the snapshot, no point of view
the no-point-of-view snapshot, reality side — same sensor law
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
PRE-WALK SENSE · REALITY grid — the snapshot, no point of view 144×144 (axes = the 144 ShortLex anchors on both sides)
PRE-WALK Δ · straight comparison of the two ingested grids (green both · cyan intent-only · amber reality-only) · 7% overlap · ◎ = where the competence pixel sits in the raw overlap
good = green overlap without being a copy — near-100% is self-similarity, not alignment
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
PRE-WALK Δ · straight comparison of the two ingested grids (green both · cyan intent-only · amber reality-only) · 7% overlap · ◎ = where the competence pixel sits in the raw overlap 144×144 (axes = the 144 ShortLex anchors on both sides)
◎ the pixel this commit belongs to
C3,C — Operations·Flow × Operations (actor) acting on B,C1 — Tactics × Operations·Grid (patient) · grip 0.797
actor seed C3,C — Pipeline throughput and delivery rate determine the necessary cadence for the daily operations run and execution. Flow is the rate at which committed work crosses the finish line. Inventory accumulates upstream; flow is the only thing the customer pays for, and the only thing the operator can measure honestly. Movement is the irreversible delivery of value across the boundary. Anything stationary is cost; anything moving is either revenue, deferred revenue, or the exhaust of revenue not yet realized. Throughput dominates utilization. A ninety-nine-percent utilized system at low throughput pays the same wages as a fifty-percent utilized system at twice the throughput, but the second one ships the customer's order. Operations is the loop that runs whether anyone watches. The daily commit, the hourly hook, the per-request fingerprint — the substrate of the substrate, ambient and unwatched. Process is what you forget to do; ops is what does itself. Convert manual moves into ambient state, because the tax of remembering compounds faster than the tax of automating. The daily friction is the diff between your intent and your harness. Close the diff or pay the tax twice — once in the slip, once in the apology to the next agent. Operations earns its keep by being boring. The day the routine is interesting is the day it has already failed and is being narrated rather than executed.
patient seed B,C1 — Leverage in tactics determines the timing of power flow through the infrastructure grid and route topology. Power flows where the grid lets it. Choose connections before topologies; the topology is what the connections compose, and a connection added later is a topology silently rewritten. Latency is geography expressed in milliseconds. The grid IS the map of where compute meets storage meets bandwidth; the map is the territory at the scale the request actually traverses. Infrastructure decisions are reversible at ten-times the cost of being right the first time. Buy the irreversibility down before you provision the easy decisions, because the easy decisions ride on the irreversible ones. A connection between two systems is a contract that outlasts the systems on either end. Wire-protocols outlive the processes they connect; the wire is the substrate, the endpoints are the exhaust. Tactics is the choice of which leverage to pull at which beat. Not what we want, but how the want lands on Tuesday: the sequence of irreversible commitments, each made before the next one's information is available. Speed of feedback dominates speed of execution. Tactics that converge fast beat tactics that compute long, because the loop closes around the world's response before the world has moved. The tactical map is a ranked list of moves where each move carries a cost-of-delay. Pick the move whose cost of doing it tomorrow exceeds the cost of doing it imperfectly today. Execution is a sequence of bets made under uncertainty. Tactics is the discipline of betting the right size on the bet whose information value pays for the loss-if-wrong.
INTENT · leaf-walk clouds · BLUE→VIOLET by ply (◎ = the competence pixel: actor∩patient)
good = the clouds concentrate where the commit SAYS it works
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
INTENT · leaf-walk clouds · BLUE→VIOLET by ply (◎ = the competence pixel: actor∩patient) 144×144 (axes = the 144 ShortLex anchors on both sides)
REALITY · leaf-walk clouds · ORANGE→RED by ply (◎ = the same pixel — the shared perspective)
good = the same clouds as intent — shipped where declared
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
REALITY · leaf-walk clouds · ORANGE→RED by ply (◎ = the same pixel — the shared perspective) 144×144 (axes = the 144 ShortLex anchors on both sides)
DELTA · graded cloud divergence (green agree · magenta declared-not-done · amber done-not-declared) · 6% agree
good = mostly green; magenta = said-not-done (chase it in the code), amber = done-not-said (chase it in the docs)
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
DELTA · graded cloud divergence (green agree · magenta declared-not-done · amber done-not-declared) · 6% agree 144×144 (axes = the 144 ShortLex anchors on both sides)
TOLERANCE · cloud topology (dim green in-shape · hot amber bleed · red orthogonal concentration) · ⚠ TOO MANY
red only matters above the flip — a few amber is normal bleed
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
TOLERANCE · cloud topology (dim green in-shape · hot amber bleed · red orthogonal concentration) · ⚠ TOO MANY 144×144 (axes = the 144 ShortLex anchors on both sides)
SHORTLEX-3 PROJECTION (ABC · A1..C3 · the 132 children — candidate, pre-ratchet)
PROJECTED INTENT · the commit’s claims, head→axis_i tail→axis_j (cyan)
the three-length view — good = claims land inside their own zone
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
PROJECTED INTENT · the commit’s claims, head→axis_i tail→axis_j (cyan) 144×144 (axes = identical 144 ShortLex-3 names both sides)
PROJECTED REALITY · same projection law (amber)
same projection law — good = reality occupies the zones intent does
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
PROJECTED REALITY · same projection law (amber) 144×144 (axes = identical 144 ShortLex-3 names both sides)
STRAIGHT COMPARISON · green both · cyan intent-only · amber reality-only · 4% overlap
good = the zones agree; cross-zone scatter is the drift to read
ABC
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
A1–C3
ABC
A1–C3
A1A–O
A2A–O
A3A–O
B1A–O
B2A–O
B3A–O
C1A–N
C2A–N
C3A–N
STRAIGHT COMPARISON · green both · cyan intent-only · amber reality-only · 4% overlap 144×144 (axes = identical 144 ShortLex-3 names both sides)
shortlex-3 zone occupancy (lit cells per diagonal square)
INTENT: 2 in the 3×3 ABC corner · 6 in the 9×9 A1..C3 square · 824 in the 132×132 children square · 158 cross-zone
REALITY: 1 in the 3×3 ABC corner · 14 in the 9×9 A1..C3 square · 1275 in the 132×132 children square · 423 cross-zone
axes: identical 144 ShortLex names both sides (symmetric); weights asymmetric
zone 3 = candidate children, pre-ratchet (repo-derived dumps not yet past the perturbation-probe gate) · intent 25 claims @ θ 0.625 · reality 31 claims @ θ 0.625 · projection 1146ms
SHAPE-MATCH σ = 1.14 — the real intent↔reality definer walk vs random-reality (actual 0.0796 vs random 0.055). >0 = the walk distinguishes real alignment from noise; aggregate over independent walks → the divergent series.
σ_drift · weak · panel story is not yet evidence
Most out-of-lane row: B2 · Deal — that lane is drifting most (read the red band in that row).
Three-colour tolerance (out-of-lane = reality fires where intent is weak, in orthogonal blocks): green=in-lane agreement · amber=a few out-of-lane (tolerated) · red=FIRED — orthogonal out-of-lane 26% vs tolerance 25%.
651 green · 368 amber · 352 red · 225 XOR-friction cells.
Both axes = the 144 ShortLex anchors, cell=row⊕col, on the chip. INTENT=docs+rules · REALITY=code · DELTA=friction.
tile dump — what the SimHash matched on the diagonal (inspect the sensor; tap to expand)
A,A The lattice we build today is what next year's underwriter inherits.
intent 73% data/pmu/public-claims.json — single source of truth. Each claim carries its RE-RUN COMMAND and
reality 77% { "_readme": [ "THE NUMBERS WE ARE ALLOWED TO SAY OUT LOUD. Single source of truth.", "", "WHY
B,B Tactics is the choice of which leverage to pull at which beat.
intent 70% (no distinctive match)
reality 70% (no distinctive match)
C,C Operations is the loop that runs whether anyone watches.
intent 80% (no distinctive match)
reality 72% (no distinctive match)
A1,A1 EU AI Act Article 14 requires human-on-the-loop oversight, with the supervisor able to interrupt the system at
intent 77% (no distinctive match)
reality 69% (no distinctive match)
A2,A2 The target is the cell coordinate the system MUST occupy by end-of-quarter.
intent 75% (no distinctive match)
reality 66% (no distinctive match)
A3,A3 Every dollar builds either the floor (substrate that lifts future bets) or the ceiling (cap on the next round)
intent 70% (no distinctive match)
reality 70% (no distinctive match)
B1,B1 Latency is the price of a missed beat.
intent 66% (no distinctive match)
reality 66% (no distinctive match)
B2,B2 The deal sets the exchange rate between two value substrates.
intent 69% (no distinctive match)
reality 69% (no distinctive match)
B3,B3 Signal-to-noise is the inverse cube of bandwidth — narrow the channel, the message arrives; broaden it, recipi
intent 77% (no distinctive match)
reality 77% (no distinctive match)
C1,C1 Power flows where the grid lets it.
intent 73% (no distinctive match)
reality 70% (no distinctive match)
C2,C2 Each iteration is a hypothesis tested against the ground truth of the world.
intent 69% (no distinctive match)
reality 72% (no distinctive match)
C3,C3 Flow is the rate at which committed work crosses the finish line.
intent 81% (no distinctive match)
reality 70% (no distinctive match)
commit context — 2 file(s)
feat(pmu): pin the numbers we say out loud — and gate them

HARVESTED THE MEASURED/UNMEASURED BOUNDARY INTO AN ENFORCEABLE RULE, not another doc a future
session won't read.

THE RISK: every figure we quote to an underwriter — 0.90 · 0.30 · 4.48σ · the AUC set — lived only
in PROSE, scattered across a dozen architecture docs and now several outreach docs. Nothing stopped
a future session carrying a STALE number into a room with Mike Carls, who builds frequency/severity
models for a living. ONE unsubstantiable figure contaminates every measured one beside it — which is
precisely why an unbounded precision claim is more dangerous than the 30% miss it would be deployed
to defend.

data/pmu/public-claims.json — single source of truth. Each claim carries its RE-RUN COMMAND and one
of exactly three statuses. There is no fourth:
  MEASURED   — a property of the INSTRUMENT. Provable in a lab, no world required.
               determinism · speed · separation 0.90 · out-of-universe 10/10 · SCRAMBLED-NULL FLOOR
               4.48σ (the null-hypothesis test — the number nobody quotes and an analytics leader
               respects most; lead with it AHEAD of 0.90) · paraphrase-invariance 0.3

data/pmu/public-claims.json
tests/pmu/public-claims-are-pinned.test.mjs
③ the numbers, contextualized — value · band · verdict · percentile · what it leads to
shape-match σ · 1.14 weak p50 of last 10
panel story is not yet evidence → read the maps as sketch, not evidence — converge the seed library before citing this
good looks like: positive on an aligned commit (phantom P1: sigmaPositive) · ≥6 clears the trust floor · ≥8.5 verified-reef · 0–3 = panel story not yet evidence
tolerance (edge cells) · 651 green · 368 amber · 352 red · off-lane 26% alarm p45 of last 10
too much reality fired in ORTHOGONAL lanes — the aggregate flip; this is the drift the instrument exists to catch → open the TOLERANCE panel and chase the red rows — undeclared work shipped
good looks like: red ≈ 0 and orthogonal off-lane < 10% on an in-lane commit (phantom P1: redZero, offPctBelow 10) — a few amber is normal bleed
pre-walk overlap · 7% overlapping p45 of last 10
the two ingests share real ground without being copies — the healthy middle → nothing to do — this is the healthy shape
good looks like: green overlap WITHOUT being a copy — near-100% is self-similarity (a docs-only read), not alignment
drift (XOR %) · 1.085% of compared cells disagree close p95 of last 10
intent and reality mostly agree cell-for-cell → nothing to chase
the walks (how the heatmaps were made) · intent 125 hops → ply 7 · reality 131 hops → ply 8 · 898ms inside-budget
both cascades ran to extinction inside the time budget — the read is complete · each hop = one real on-chip ballistic process; intent ended at B2,B2 · C2,B · C2,C1, reality at B3,A2 — the definers-of-definers the recursion concentrated on → the ply story in the panels is complete
good looks like: both sides finish inside the 2500ms budget; clouds concentrate at block-heads (the ShortLex-ascending follow), early plies heavy, deep plies faint
lattice fill · intent 1121/20736 (5.4%) · reality 1371/20736 (6.6%) walkable
a real, walkable lattice (~4% is the density target) — the walk had ground to cover → nothing to do
the ladder — what's climbing · weakest link first
→ weakest · intersection-specific words/tile (median) · 5 (over 144 tiles) → target 70 parent-echo distance 0.93 · author intersection-specific seeds (what does B,A3 say that NEITHER parent says alone?) — the single highest-leverage number in the system
σ_drift (commit panel, median last 10 non-docs-only) · -0.07 (n=10) → target 6 noise distance 1 · do not act on the panels — on a docs-only commit this is expected; otherwise fix the ingest and re-run
σ_response pass count · 32/144 → target 144 thin distance 0.78 · raise seed richness (the reef GDD loop) — pass count follows intersection-specific words
σ_localize (latest targeted edit) · 0.61 @ B3,B3 → target 6 chance distance 0.9 · iterate the ingest until the target zone owns its own edit — the brain-surgeon read does not yet hold
sweep coverage (deterministic top-rank hits) · 23/46 → target 46 majority distance 0.5 · chase the missing tiles in the sweep — each convert lifts σ_panel directly
seed orthogonality (distinct openings) · 143/144 → target 144 converging distance 0.01 · fix the few shared openings — tile-dump-inspect names them
σ_panel (joint rank certainty) · 10.63 → target 6 beyond-doubt distance 0 · cite the distribution-level claim (carry the independence caveat)
next move (picked by the system, not session memory): intersection-specific words/tile (median) is furthest from target weighted by leverage (5 (over 144 tiles) vs target 70 → distance 0.93 × leverage 1 = 0.93) — author intersection-specific seeds (what does B,A3 say that NEITHER parent says alone?) — the single highest-leverage number in the system
④ expert detail — chain ✅ reef · ✅ on-chip · ✅ hardware · ✅ render — attestation · receipts · timings · σ inputs (tap to expand)
chain✅ reef sensed — 144 seeds → SimHash in 1239ms · grid attached (input seed → SimHash sanity check) · ✅ on-chip 525.64ns/walk · 7.002ms · 1713918 walks/sec · 42 / 144 lit (measured on silicon, this commit) · ✅ triptych rendered · pipeline 1150ms · render 846ms · 225 XOR-friction nodes
hardware root of trustserial CXMF9VMM29 · UUID 43C33AB6… · attest MFkwEwYHKoZIzj0CAQYIKoZIzj0D… (ecdsa-p256-sha256 · hw-derived fallback, weaker than Secure Enclave)
gate (XOR+popcount)1.9933 ns / driven comparison · walk @ gate rate 574.1 ns
cache witnessL1 2.13 ns · DRAM 456.66 ns · miss ×214.3
daemon binarysha256 b409b4c1dedd815b… (the attested silicon path)
run receiptrun-2026-07-14T13-11-19-366Z-00be0d35 · payload 4ae1e67f9917c96c… · band gold
timingsingest 766.3ms · definer-walk+σ 898ms · render 846ms · pipeline 1150ms · ingest = commit-scoped SENSING only (msg + changed files → lattice); deep seed authoring lives in the reef-self-loop, off the commit path
walks (this heatmap)INTENT: 125 hops / 125 chip processes / 125 anchors lit, ended at B2,B2 · C2,B · C2,C1 (ply 7 — the definers-of-definers) · REALITY: 131 hops / 131 chip processes / 131 anchors lit, ended at B3,A2 (ply 8 — the definers-of-definers) · walks concentrate at block-heads by the ShortLex-ascending follow
per-stageresolve 0.1ms · invariants 2.4ms · sense 766.2ms · sigma 0.2ms · binarize 0ms · project 84.9ms · xor 0.1ms · walk 108.8ms · claudbridge 95.5ms
walk start C3,C (STABLE attractor) · 256 hops · maxPly 8
σ — defined by its inputsσ = (cos(intentCloud, realityCloud) − μ of 12 bit-shuffled-reality impostor walks) / sd · INPUTS: intent 25 claims @ θ 0.719 (msg + 0 docs + 1 tests) · reality 31 claims @ θ 0.719 (0 code) · walk topK 2 decay 0.5 ply≤8 budget 2500ms · seed-lib 8a4b87022885 — σ comparisons are only valid at equal inputs
σ rawheat-cosine 0.0796 vs random 0.055 → σ_drift · weak · panel story is not yet evidence
shortlex-3 projection1146ms · intent zones 2/6/824 (+158 cross) · reality zones 1/14/1275 (+423 cross) · zone 3 = candidate children, pre-ratchet
orthogonality (seed 144)144/144 unique · 143/144 openings · pairwise sim 0.367 · junk 0
intent documentspublic-claims-are-pinned.test.mjs

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 525.64ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit 74449cc69

Commit artifacts (open on a computer — Gmail mobile won't follow file:// links; the inline images above are the phone-viewable form): reef grid · this triptych · the HDL — all three are also attached to this email.

This is the on-chip drift receipt for commit 74449cc69, the same artifact emailed on commit — published so the claim is verifiable on the open web. Recompute it yourself: npx thetacog-mcp attest-demo.