⬡ delegation direction · from somewhere → pointing somewhere
🔨 iTerm2 — QC → → 🔒 WezTerm
work done in iTerm2 · QC written to WezTerm's to-do (shape-max-match) · shape-match fit 0.414 (SUSPECT) · rooms-reef mesh, rust daemon ~½s
◎ COMPETENCE SHAPE — regions encircled & named by ShortLex coordinate
the shape the off-lane % describes — each cluster ringed in its own colour, numbered, located on the 144-anchor lattice
1in-lane · ShortLex A,A3 ▸ C,C3 · 12 green blocks
«Tactical selection of the maneuver and beat maximizes signal reach while minimizing noise in the channel. This slice focused on optimizing signal-to-noise ratio, which aligns with the "Tactical selection of the maneuver and beat" aspect. However, it wandered into the "Format clarity (board meeting)" category by detailing specific implementation strategies that were not part of the original ask.»
2in-lane · ShortLex B2,B1 ▸ C1,C3 · 10 green blocks
«R2 — Six needs, reader's perspective: The slice discusses task-aware branches and LLM_PROMPT_CLI priorities but does not address broadcast channels or infrastructure grid topology. This wandered into the "Six needs, reader's perspective" category, which was out of spec for this commit.»
3bleed · ShortLex C1,A1 ▸ C3,A3 · 9 amber blocks
«R3 — Format clarity (board meeting): The iterative loop and hypothesis test cycles are designed to achieve the quarterly goal and target position. This slice wandered into the format clarity category, which was out of spec for this commit as the message never promised it would focus on board meeting details.»
4bleed · ShortLex A2,A ▸ B1,C · 8 amber blocks
«R1 — WHY-belief opens on the information hazard. The slice did not set out to address any of the stated categories but instead delved into capital budgets and their funding needs, which is outside the scope declared in the commit message.»
5bleed · ShortLex A1,C1 ▸ A3,C3 · 7 amber blocks
«R3 — Format clarity (board meeting): The slice focused on format clarity for board meetings but wandered into Quarterly goal targets, which define the objectives measured by the iterative feedback loop and hypothesis test cycle. This category was out of spec for this commit.»
6bleed · ShortLex C1,B3 ▸ C3,C2 · 7 amber blocks
«WHY-belief opens on the information hazard — This slice set out to discuss the efficiency of the infrastructure grid and topology flow but instead wandered into a monologue about cold-audit work. The commit message never promised this discussion, which is outside the specified category.»
7in-lane · ShortLex B2,A ▸ B3,A2 · 6 green blocks
«Bandwidth of a signal and message reach are produced by the daily operations run and cadence. This slice analyzed the operational efficiency and communication effectiveness without expanding into research links or contacts (R6).»
8bleed · ShortLex C,A ▸ A1,A1 · 6 amber blocks
«R5 — Evidence AFTER the form (reach is verify): The commit message mentions adding a rulebook and seeding rules, but these details fall into the R6 category of research links + contact. This slice wandered into providing evidence and context that was not promised by the initial declaration.»
9bleed · ShortLex A2,A2 ▸ B1,B1 · 6 amber blocks
«R3 — Format clarity (board meeting): The slice focused on format and clarity for board meetings but wandered into discussing the financial impact on the floor and ceiling. This was out of spec, as the commit message never promised to address financial impacts.»
10bleed · ShortLex C,A2 ▸ A1,B2 · 5 amber blocks
«R3 — Format clarity (board meeting): The slice focused on explaining compliance requirements but wandered into formatting and presentation details that were not part of the original stated-ask. This included elaborating on laws and regulations in a way that deviated from the intended clarity for board meetings.»
11bleed · ShortLex C1,B ▸ C3,C · 5 amber blocks
«R3 — Format clarity (board meeting): The slice focused on format clarity for board meetings but wandered into detailing operational procedures. This was out of spec, as the commit message did not promise to cover operations.»
12in-lane · ShortLex A,A ▸ B,A1 · 4 green blocks
«Tactics determine the timing and beat required to run the daily operations cadence and execution loop. The code changes focused on optimizing the operational rhythm without venturing into other categories like Six needs or Format clarity.»
13bleed · ShortLex A,A1 ▸ A,B1 · 4 amber blocks
«A strategy lattice frames how capital and the dollar floor fund long-horizon finance across the substrate. This slice wandered into "R3 — Format clarity (board meeting)" despite the commit message focusing on strategic framing. The work touched a category not promised by the ask.»
14bleed · ShortLex A3,B3 ▸ B1,C2 · 4 amber blocks
«R3 — Format clarity (board meeting): The slice focused on format clarity for board meetings but wandered into discussing consistent speed and tempo beats, which is about infrastructure grid dynamics. This was out of spec for the commit message.»
15bleed · ShortLex B3,A3 ▸ C2,B1 · 3 amber blocks
«R3 — Format clarity (board meeting): The slice focused on optimizing power flow but instead delved into route topology and grid paths. This wandered into format clarity without the commit message promising such detail.»
16in-lane · ShortLex A2,C2 ▸ A3,C3 · 2 green blocks
«R3 — Format clarity (board meeting): The slice focused on explaining the financial implications for capital flow and pipeline delivery rates. This aligns with the stated intent of providing format clarity.»
17bleed · ShortLex A,C1 ▸ A,C2 · 2 amber blocks
«R3 — Format clarity (board meeting): The slice focused on explaining the strategic substrates but wandered into format clarity issues, detailing the long-horizon lattice and iterative processes. This was not part of the original ask.»
18bleed · ShortLex C1,A ▸ C2,A · 2 amber blocks
«R3 — Format clarity (board meeting): The slice focused on format and presentation details rather than strategic hypotheses or operational testing. This wandered into format clarity, which was not part of the original stated-ask.»
19bleed · ShortLex C1,C3 ▸ C2,C3 · 2 amber blocks
«R3 — Format clarity (board meeting): The slice focused on optimizing flow throughput and delivery rate across the pipeline. This wandered into R5 — Evidence AFTER the form (reach is verify), where it discussed evidence and verification steps, which were not promised in the commit message.»
20in-lane · ShortLex A3,A2 · 1 green block
«R3 — Format clarity (board meeting): The slice focused on explaining the financial requirements for occupying the quarterly goal position. This aligns with the format clarity needed for board meetings.»
21in-lane · ShortLex A3,B2 · 1 green block
«R3 — Format clarity (board meeting): This slice set out to ensure format clarity for board meetings. It stayed focused on providing sufficient capital funds details, which aligns with the declared category.»
22in-lane · ShortLex B2,A3 · 1 green block
«R3 — Format clarity (board meeting): This slice clarified exchange rates for a deal, which aligns with the format needed for board meetings. However, it wandered into R7 — Peer-convening tone, not a vendor pitch, providing unnecessary marketing language.»
23bleed · ShortLex C,C2 · 1 amber block
«R1 — WHY-belief opens on the information hazard. The slice focused on explaining why certain operations were necessary and transparently addressed potential risks. However, it wandered into R3 — Format clarity (board meeting), where it detailed operational procedures in a way that was more suitable for board meetings than the current context.»
24bleed · ShortLex A3,A1 · 1 amber block
«R5 — Evidence AFTER the form (reach is verify): The slice provided evidence for dollar floor assets and budget runway, which was not part of the original stated-ask. This wandered into a category that was out of spec for this commit.»
25bleed · ShortLex B2,A · 1 amber block
«R3 — Format clarity (board meeting): The slice focused on setting the exchange rate for value built upon a long-horizon strategy substrate frame. This wandered into R6 — Research links + contact, which was out of spec for this commit.»
26bleed · ShortLex C3,B1 · 1 amber block
«Continuous pipeline flow throughput and delivery rate were measured by the speed and tempo of the beat. This slice wandered into "Format clarity (board meeting)"—the commit message did not promise this category but the code/changelog introduced it.»
⛓ produced on attested silicon · sealed receipt — verify without trusting the sender
✓ silicon CXMF9VMM29 · attest MFkwEwYHKoZIzj0CAQYIKoZIzj0D… (ecdsa-p256-sha256)
✓ ran in builder · iTerm2 3.6.6 · room-id 6102acc3e4a9…
✓ daemon sha256 ae77cbf95a43bda8… · gate 1.7296ns/cmp
✓ sealed receipt run-2026-06-28T18-56-03-827Z-c8c3e5a3 · payload dd09335902c4e871… · band gold
✓ on-chip 797.09ns/walk · pipeline 584ms · lens 144 seeds/1455ms · seed-lib 8a4b87022885
✓ lens health global separation 26b · half-tile grip 8.5b → ROBUST
✓ BEARER POLICY sha256 75c7c2480feb0de5… · ed25519 sig e29425e0fa80… · signer fc0fb4d5709e… — binds input+lens+verdict + instrument health; attached as policy-2f0ab9b5d.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 5eaa828bffab… · lattice 8a4b87022885
② WORK NODE produced the work — reality 8603c8556812…
③ ATTESTOR (3rd party) reads the A↔B drift, trustlessly via the sealed receipt above:
TOLERANCE: INSIDE (16% off-lane vs 25%)
BARTER FLAG: CLOSE — inside tolerance — the option exercises; accept the work and settle (barter close)
🔬 instrument attestation · on-chip self-test — the sensor tried to break itself before it signed
Signal DecayPASS σ 0%→56.9 50%→5.9 100%→0 — σ responds to signal
Semantic SubstitutionPARTIAL reef vocabulary absent from corpus (code-dominant input → semantic grip gap)
Repo CalibrationPARTIAL reef maps 40% of last 25 commits · center-of-mass C1,A1×2 A1,C3×2 B2,B3×1
why this isn't gzip: NCD/compression gives a scalar with no frame. This is a located drift on a grounded 144-anchor ShortLex lattice, traversed by the recursive definer-walk (not a flat distance). The Substitution row IS the discriminator — gzip survives a meaning-swap; a semantic reef collapses.
⬛ TOLERANCE — the highest-signal read
337 green · 553 amber · 0 red · off-lane 16% vs 25% — in lane, some bleed
proof of insurability · priced from the geometry, not the code
VERDICT: INSURABLE
NATURE: In-Lane
VECTOR: —
ABSTRACTION RUPTURE: —
RATIONALE: Declared risk matches actual exposure; insurable at face value.
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: 0σ · 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: 1489 intent · 919 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: 1146 commits (~48/day)
CORRECTION TAX: 21% (235 folded back to fix) — the org-level resilience read
REEF σ̄: 0.57 ▼ · 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: 337 green, 553 amber, 0 red → off-lane 16% against a 25% tolerance — in lane, some bleed.
PMU · on-commit dogfood · the chip's own anatomy
the verdict · commit 2f0ab9b5d
1 · did this commit drift?
NO — in lane (off-lane 16%, tolerance 25%)
bleeding some reality fired outside the declared lanes — amber bleed, below the alarm flip · vs your last 10 commits: p40 of last 10 — normal for you lately
2 · can you trust that reading?
σ_drift 0.21 — WEAK
weak panel story is not yet evidence · vs your last 10: p30 of last 10 — normal for you lately · why low: usually a thin grip (only 36 reality vs 12 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?
B,B3 Tactics × Tactics·Signal → B2,C Tactics·Deal × Operations
read it as actor × patient: this commit is mostly Tactics × Tactics·Signal work acting on Tactics·Deal × Operations (grip 0.734). this is the commit's COORDINATE — where the work lives — not a judgement; the panels below (◎ marks this cell) are what judge it
next: read the maps as sketch, not evidence — converge the seed library before citing this
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 2f0ab9b5d — 144×144 lattice triptych (on-chip)
◎ the ingest chose B,B3 — Tactics × Tactics·Signal — acting on B2,C — Tactics·Deal × Operations (grip 0.734) · the walk starts at the ACTOR's row · 2 file(s)
⏱ ingest 250.7ms (corpus→lattice) · definer walk 727ms (row→transpose→row, ballistic XOR per hop) · total 1311ms
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) · 3% 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) · 3% 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
B,B3 — Tactics × Tactics·Signal (actor) acting on B2,C — Tactics·Deal × Operations (patient) · grip 0.734
actor seed B,B3 — Tactical selection of the maneuver and beat maximizes signal reach while minimizing noise in the channel. 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. Signal-to-noise is the inverse cube of bandwidth — narrow the channel, the message arrives; broaden it, recipients tune out. The right channel is the one whose floor matches the message's importance. 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. A broadcast that addresses everyone addresses no one. Precision over reach until the address is calibrated; only then does scale convert prospects into recipients rather than into unsubscribes. 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. Repetition is the cost of being heard. Three sends to one recipient beats one send to three; the first send announces, the second send is heard, the third send is remembered. 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. Every message carries provenance. The sender's history is half the message's weight; an unknown sender pays in attention what a known sender pays in seconds saved.
patient seed B2,C — Terms of a deal and the exchange rate influence the daily operations run and execution cadence. 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. The deal sets the exchange rate between two value substrates. Mis-priced exchange is a slow-bleed; correctly priced exchange compounds both sides, because each cycle of trade enriches the bench on both ends. Terms are the API between two organizations — every clause is a contract method that survives the handshake. Renegotiation is the breaking change; the deal is the stable interface either side can build against. Negotiation closes at the moment both parties' BATNAs cross. Push past that point and you've bought regret at retail; stop short and you've left margin on the table that the next deal will not return to you. A signed counterparty is more valuable than an unsigned promise. The signature is the substrate; the conversation that preceded it is the exhaust the signature converted into substrate.
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) · 1% 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) · 1% agree 144×144 (axes = the 144 ShortLex anchors on both sides)
TOLERANCE · cloud topology (dim green in-shape · hot amber bleed · red orthogonal concentration)
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) 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 · 7% 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 · 7% overlap 144×144 (axes = identical 144 ShortLex-3 names both sides)
shortlex-3 zone occupancy (lit cells per diagonal square)
INTENT: 3 in the 3×3 ABC corner · 5 in the 9×9 A1..C3 square · 1769 in the 132×132 children square · 317 cross-zone
REALITY: 0 in the 3×3 ABC corner · 9 in the 9×9 A1..C3 square · 1963 in the 132×132 children square · 370 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 12 claims @ θ 0.5938 · reality 36 claims @ θ 0.6094 · projection 616ms
SHAPE-MATCH σ = 0.21 — the real intent↔reality definer walk vs random-reality (actual 0.0524 vs random 0.046). >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: A3 · Fund — 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=armed — orthogonal out-of-lane 16% vs tolerance 25%.
337 green · 553 amber · 0 red · 154 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 69% (no distinctive match)
reality 69% (no distinctive match)
B,B Tactics is the choice of which leverage to pull at which beat.
intent 63% (no distinctive match)
reality 63% (no distinctive match)
C,C Operations is the loop that runs whether anyone watches.
intent 70% (no distinctive match)
reality 67% (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 70% (no distinctive match)
reality 67% (no distinctive match)
A2,A2 The target is the cell coordinate the system MUST occupy by end-of-quarter.
intent 77% (no distinctive match)
reality 67% (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 69% (no distinctive match)
reality 64% (no distinctive match)
B1,B1 Latency is the price of a missed beat.
intent 67% (no distinctive match)
reality 70% (no distinctive match)
B2,B2 The deal sets the exchange rate between two value substrates.
intent 75% (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 72% (no distinctive match)
reality 66% (no distinctive match)
C1,C1 Power flows where the grid lets it.
intent 78% (no distinctive match)
reality 66% (no distinctive match)
C2,C2 Each iteration is a hypothesis tested against the ground truth of the world.
intent 63% (no distinctive match)
reality 67% (no distinctive match)
C3,C3 Flow is the rate at which committed work crosses the finish line.
intent 78% (no distinctive match)
reality 72% (no distinctive match)
commit context — 2 file(s)
feat(cog): Vector 7 — the Cognitive Token Split as a SQLite rulebook (qwen ↔ claude)

Every LLM call flows through scripts/llm-prompt.sh, whose default lane is the
EXPENSIVE claude -p with only env-flag overrides — nothing decided, per cognitive
TASK, whether a call needed Claude or should run on free local qwen. Reader /
monologue / cold-audit work (which BY DESIGN wants the weaker model — the stricter
bar; a strong model gap-fills muddy prose into a false pass) silently burned Claude.

This adds the rulebook:
- scripts/cog/model-route.mjs — tc_model_rulebook (task → lane + rationale + call_site)
  and tc_cognitive_token_ledger (measured split), in the canonical data/thetacoach.db.
  14 seeded rules grounded in real call-sites: read/sense/diverge → qwen (ghost-read,
  voice-audit, sense-gate-read, reframe, region-narrate); grade/author/compile → claude
  (grade, author, compose, compile-reef, lexicon). --init/--task/--list/--learn/--report.
- scripts/llm-prompt.sh — a task-aware branch (priority 0): LLM_PROMPT_TASK consults the
  rulebook and routes the choke point; explicit LLM_PROMPT_CLI still wins; logs the call
  split to the ledger. The .db is a local materialization (re-seed

scripts/cog/model-route.mjs
scripts/llm-prompt.sh
③ the numbers, contextualized — value · band · verdict · percentile · what it leads to
shape-match σ · 0.21 weak p30 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) · 337 green · 553 amber · 0 red · off-lane 16% bleeding p40 of last 10
some reality fired outside the declared lanes — amber bleed, below the alarm flip → glance at the TOLERANCE panel — amber clusters show where reality leaned out
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 · 3% mostly-disjoint p15 of last 10
docs and code light different cells — normal for a code-heavy commit; the WALK is what bridges them → nothing to do — judge alignment by σ and the walk panels, not this raw overlap
good looks like: green overlap WITHOUT being a copy — near-100% is self-similarity (a docs-only read), not alignment
drift (XOR %) · 0.743% of compared cells disagree close p30 of last 10
intent and reality mostly agree cell-for-cell → nothing to chase
the walks (how the heatmaps were made) · intent 128 hops → ply 7 · reality 129 hops → ply 8 · 727ms 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,A2, reality at B,C2 · B3,A2 · C3,A — 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 1451/20736 (7%) · reality 890/20736 (4.3%) 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) · 0.41 (n=10) → target 6 weak distance 0.93 · read the maps as sketch, not evidence — converge the seed library before citing this
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 1455ms · grid attached (input seed → SimHash sanity check) · ✅ on-chip 797.09ns/walk · 3.937ms · 3047748 walks/sec · 42 / 144 lit (measured on silicon, this commit) · ✅ triptych rendered · pipeline 584ms · render 458ms · 154 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)1.7296 ns / driven comparison · walk @ gate rate 498.1 ns
cache witnessL1 4.33 ns · DRAM 387.43 ns · miss ×89.5
daemon binarysha256 ae77cbf95a43bda8… (the attested silicon path)
run receiptrun-2026-06-28T18-56-03-827Z-c8c3e5a3 · payload dd09335902c4e871… · band gold
timingsingest 250.7ms · definer-walk+σ 727ms · render 458ms · pipeline 584ms · 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: 128 hops / 128 chip processes / 128 anchors lit, ended at B2,A2 (ply 7 — the definers-of-definers) · REALITY: 129 hops / 129 chip processes / 129 anchors lit, ended at B,C2 · B3,A2 · C3,A (ply 8 — the definers-of-definers) · walks concentrate at block-heads by the ShortLex-ascending follow
per-stageresolve 0.1ms · invariants 1.6ms · sense 250.6ms · sigma 0.3ms · binarize 0.1ms · project 17.2ms · xor 0.1ms · walk 128.7ms · claudbridge 149.4ms
walk start B,B3 (STABLE attractor) · 257 hops · maxPly 8
σ — defined by its inputsσ = (cos(intentCloud, realityCloud) − μ of 12 bit-shuffled-reality impostor walks) / sd · INPUTS: intent 12 claims @ θ 0.672 (msg + 0 docs + 0 tests) · reality 36 claims @ θ 0.703 (2 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 0.0524 vs random 0.046 → σ_drift · weak · panel story is not yet evidence
shortlex-3 projection616ms · intent zones 3/5/1769 (+317 cross) · reality zones 0/9/1963 (+370 cross) · zone 3 = candidate children, pre-ratchet
orthogonality (seed 144)144/144 unique · 143/144 openings · pairwise sim 0.367 · junk 0
intent documents(message only)

Produced on the chip by the running pipeline (scripts/pmu/pipeline.mjs → runPipeline → walk + xor), commit-scoped · on-chip per-walk 797.09ns (this commit). Recompute: node scripts/pmu/commit-triptych.mjs --commit 2f0ab9b5d

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 2f0ab9b5d, the same artifact emailed on commit — published so the claim is verifiable on the open web. Recompute it yourself: npx thetacog-mcp attest-demo.