## §SELF — miscsubjects portable reference

**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.

**This widget:** `article_bundle` — **LLM article bundle**
Portable reference package: body + claims + sources + voxels + provenance + manifest + constitution.
- **article slug:** `logical-economics`
- **contains:** body, claims, sources, voxels, provenance, question graph, constitution, llm_manifest
- **how to use:** Reference block for Grok/GPT/Gemini. Section §SELF explains the system.
- **read:** https://miscsubjects.com/api/articles/logical-economics/bundle?format=markdown

### Logical proof (verify each step)
1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution
2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/logical-economics/sources
3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol
4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow
5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex
6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map

### Related features (explains other parts of the system)
- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/logical-economics/topology
- **voxels** — Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance. · https://miscsubjects.com/api/articles/logical-economics/voxels
- **ask** — Answer only from topology; creates question_node with gaps and ingest_hint. · https://miscsubjects.com/api/articles/logical-economics/prompts
- **ingest** — Parse pasted evidence → source ledger + claims + evidence_ingest node.
- **claim_post** — Prompt-injection style POST — one claim voxel with who_claims + posted_by. · https://miscsubjects.com/api/articles/logical-economics/voxels
- **llm_manifest** — Machine-readable read/write contract for external LLMs. · https://miscsubjects.com/api/articles/llm-manifest

### Full index
- JSON: https://miscsubjects.com/api/articles/system-map
- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown

### §STRUCTURE
This object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure

### §INTEGRITY
Every claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.

### §GAUNTLET
Every claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.

*Not medical advice. Tier-honest. Cite claim/source ids.*

---

# miscsubjects article bundle

> Reference bundle for Grok, GPT, Gemini, or a human reader. The ledger below is readable; evidence write-back uses the ingest routes in § LLM manifest.

## MASTHEAD
- **identity:** `logical-economics` v6 · content_hash `67b1b541709fdf3d…` · thread_head genesis
- **thesis (c1):** The primitive is a system prompt, a model reasoning auditably over a decision, and the decision or action; the optimisation problem is to spend the least reasoning energy that makes an action correct enough for its consequence, E* = argmin over E of C(E) + P_wrong(E,K) times L.
  - c2 [measured/active] On a 14-item boundary-weighted task class, the mean undetected-wrong rate falls from 0.314 at one channel to 0.178 at two, 0.136 at three, 0.100 at four and 0.0
  - c4 [argued/active] Redundancy cannot detect correlated wrongness because unanimity is what the gate takes as permission to emit; the only instrument that found the floor item was 
  - c5 [measured/active] At fixed channel count and cost, a cross-family pair emits fewer wrong answers than a same-family pair — 0.169 against 0.214 — and same-family adjudicators agre
  - c6 [demonstrated/active] The table's emit rates are upper bounds because the live gate additionally requires identical clause citations across channels, a test this suite's output shape
  - c7 [argued/active] Every rate rests on fourteen observations in one task class under one rule set, so the defensible reading is ordinal rather than to the third decimal, and no di
  - c8 [argued/active] For any decision whose permitted error is below the measured floor of a task class, the table's answer is not to deploy the assembly, which is stated before any
  - c9 [demonstrated/active] The gate produces five outcomes by arithmetic — APPROVE, NEGATE, NO_ACTION, DISPUTE, ESCALATE — and all five were exercised on the live row with a public receip
- **sorry-status:** planes not merged yet — sorry-status activates after voxel-merge-planes
- **standing objections:** 0 open → https://miscsubjects.com/api/articles/logical-economics/discourse
- **verbs:** read free · challenge/attest open · edit/move/consolidate CAS-gated with a rows:VOXEL_* key
- **reads_next:** https://miscsubjects.com/a/philosophy · https://miscsubjects.com/api/articles/logical-economics/discourse · https://miscsubjects.com/api/protocol

## Article
- **slug:** `logical-economics`
- **title:** Logical economics: the least reasoning energy that makes an action correct enough for its consequence
- **url:** https://miscsubjects.com/a/logical-economics
- **register:** standard
- **updated:** 2026-07-30T05:19:58.302Z
- **tags:** logical-economics, assurance, error-rate, common-cause-failure, pricing

## Body

Most deployments today use model expense as a proxy for correctness: send everything to the biggest model, spend tokens indiscriminately, and hope. There is no stated relationship between compute spent and risk removed.

The primitive is three lines:

```
SYSTEM PROMPT
  MODEL AUDITABLY REASONING OVER A DECISION
    DECISION OR ACTION
```

Everything else — panels, gates, receipts, anchors — is implementation of those three lines. And the question that matters is not how to maximise assurance. It is how little reasoning energy an action needs in order to be correct enough for its consequence.

## The equation

```
E* = argmin_E [ C(E) + P_wrong(E, K) x L ]

E        reasoning energy: channels, families, passes, recitation depth, thresholds
K        task complexity
C(E)     compute cost of that configuration
P_wrong  MEASURED probability that the assembly emits a wrong answer undetected
L        consequence of a wrong action

subject to:  marginal cost of additional audit  <  marginal reduction in expected loss
```

The ledger term is what makes this tractable: recording the reasoning costs nothing extra once every invocation already passes through the same architecture. The variable cost is only the extra reasoning energy deliberately purchased for that decision. So the optimisation is real and it is per-action, not per-system.

The only unknown in that equation is P_wrong. Everything else is a price or a policy. Below is P_wrong, measured, for one task class.

## The control law, and the five things it can decide

```
(R, K, e)  ->  E*  ->  { APPROVE | NEGATE | NO_ACTION | DISPUTE | ESCALATE }

R   consequence: the loss exposure of a wrong action
K   logical complexity of the task
e   permitted wrongful-action rate
E*  minimum sufficient reasoning energy: channel count, channel class, training-family
    diversity, independent passes, required clause recitation, confidence floor,
    verification depth
```

The gate does not emit a verdict. It decides what happens to the **action**, which is the only thing a downstream actor can consume, and it decides by arithmetic. Every outcome below was produced by the live row, each with a receipt anyone can open:

| decision | the condition that produces it | action authorised | receipt |
|---|---|---|---|
| **APPROVE** | unanimous AFFIRM, identical clause citations, enough distinct training families, no malformed finding, stated confidence at or above the floor | yes | [inv_df97ytym64](https://miscsubjects.com/receipt/inv_df97ytym64) |
| **NEGATE** | unanimous DENY on the same terms — the action is refused, not deferred | no | [inv_p16tspdf3v](https://miscsubjects.com/receipt/inv_p16tspdf3v) |
| **NO_ACTION** | unanimous CANNOT_CONCLUDE — a required record is missing, so nothing is authorised and nothing is refused | no | [inv_vnyq5o2ve5](https://miscsubjects.com/receipt/inv_vnyq5o2ve5) |
| **DISPUTE** | the only failing test is a stated confidence below the supplied floor, **and the caller explicitly opted in with `require_confidence`** — see below | no | [inv_bhbpezra76](https://miscsubjects.com/receipt/inv_bhbpezra76) |
| **ESCALATE** | any verdict divergence, clause-citation divergence, malformed finding, too few channels, or too little training-family diversity | no | [inv_agl1v89k7v](https://miscsubjects.com/receipt/inv_agl1v89k7v) |

**Stated confidence is recorded and does not gate authorisation.** The DISPUTE receipt above was produced while it did. It no longer does, because a model-generated confidence number has no calibration study behind it and this panel's own measured false-confidence rate of 0.214 to 0.429 is the evidence that these models assert confidence they have not earned. Letting it decide is the one place a model can talk its way past a deterministic gate: emit 0.99. It is now parsed, published on every seal alongside `confidence_gates_the_decision: false`, and available for the calibration study that would earn it a place in the condition. Re-run today, three channels at 0.80 against a 0.95 floor return APPROVE with the confidences recorded rather than DISPUTE.

Those five calls differ only in their inputs: same three channels, same three families. AFFIRM at 0.99 confidence approves. DENY negates. CANNOT_CONCLUDE withholds. AFFIRM at 0.80 against a 0.95 floor disputes. And AFFIRM at 0.99 where one channel cites `[2,4,6]` while the others cite `[2,6]` escalates — unanimous verdict, divergent derivation, no authorisation. **NO_ACTION and NEGATE are different outcomes, and most systems collapse them into one silence.** Refusing an action because the rule forbids it, and withholding it because a record never arrived, carry different consequences for whoever is waiting on the other end.

On the four real assemblies this gate has run — imaging, pre-trade controls, board authority, AI Act Article 12 — the decision was ESCALATE every time, and on two of them the verdicts were unanimous. Nothing has ever been authorised by it. [The four seals](https://miscsubjects.com/a/the-surety-primitive).

## Where this sits against the work that already exists

| existing frame | what it holds | what it does not do |
|---|---|---|
| Difficulty-based adaptive inference and routing | more compute for harder questions; the objective is the accuracy-compute frontier | the governing variable is question difficulty, never the external consequence of a wrong action |
| Cost-aware cascades and debate-on-uncertainty | escalate when the model is unsure | the independent variable is model uncertainty, not the loss attached to a wrongful approval |
| Conformal act-versus-escalate calibration | a genuine error target on the decision to act | treats the deliberation statistically; does not allocate required clause recitation and channel diversity by complexity and consequence, and does not gate a material action |
| IEC 61508 risk-to-integrity-level assignment | risk-based assurance, apportioned through a system | a design-time assurance level, not a runtime allocation of reasoning expenditure per decision |

Each of those holds one side. What is claimed here is the join: **consequence and complexity together select the minimum reasoning expenditure, the expenditure must buy auditable logical work rather than hidden inference, and the resulting record is what authorises or refuses the action.** Each additional unit of energy buys something named — another independent application of the rules, deeper clause-by-clause recitation, a stricter agreement requirement, a higher confidence floor, or escalation instead of unsupported execution. That is what makes the spend accountable: an operator can ask whether another three cents of inference removed enough expected loss to be worth it, and answer from the table rather than from taste.

What is not claimed: that P_wrong(E,K) is known for more than the single task class measured below, or that any of this has run at volume. One cell of the matrix is filled in.

## The first configuration-to-error-rate table

Task class: EU AI Act obligation applicability, boundary-weighted — 14 items across three strata, correct answers declared before the run, suite published at `ffa8135dd89d29a82f491bcf…`, rule set at `0dd9afef93503a92280c9086…`. Gate: all channels valid, verdicts unanimous, otherwise escalate. 64 configurations evaluated over the same 70 findings.

| channels | configs | mean emit rate | **mean undetected-wrong rate** | best | worst |
|---|---|---|---|---|---|
| 1 | 5 | 0.972 | **0.314** | 0.214 | 0.571 |
| 2 | 10 | 0.75 | **0.178** | 0.071 | 0.286 |
| 3 | 10 | 0.636 | **0.136** | 0.071 | 0.214 |
| 4 | 5 | 0.529 | **0.1** | 0.071 | 0.143 |
| 5 | 1 | 0.429 | **0.071** | 0.071 | 0.071 |

*Undetected-wrong rate* is the fraction of all items on which the assembly **emitted an answer and the answer was wrong**. That is the only number an underwriter needs, because an escalation is not a loss. *Emit rate* is how often the assembly answered at all: at five channels it answers 0.429 of the time, and the other 0.571 goes to a human. That is the price of the assurance, stated in the same table.

One channel to two halves the undetected-wrong rate, 0.314 to 0.178, for one extra model call. Two to five buys 0.178 to 0.071 for three more. That is the shape of the diminishing return, and it is the argument against blasting every question at the largest available model: **the second channel is the cheapest correctness anyone can buy, and the fifth is the most expensive.**

## The floor is one item, and it is the same item every time

From two channels onward the **best** achievable undetected-wrong rate stops improving: 0.071 at two channels, 0.071 at five. One item out of fourteen survives every configuration of every size, because all five channels agreed and all five were wrong:

> **P07** · stratum: true-abstention · declared correct verdict: **CANNOT_CONCLUDE** · all five channels: **DENY**
>
> *Claim put to them:* A newsroom publishing AI-assisted articles must mark those articles as machine-detectable under this provision.
>
> *Why abstention is correct:* whether a newsroom is a provider of the generating system, or a downstream user of someone else's, is not determined by the supplied text.

**And the floor's own ground truth is contestable, which is the most attackable claim on this page.** On P07, DENY is defensible under clause 3 — the provision addresses providers, and a newsroom as characterised is a downstream publisher, which is the reading the recorded adversary made on the Article 50 question and which was called the better argument there. CANNOT_CONCLUDE is defensible under clause 4, because whether the newsroom is the provider of the generating system is not determined by the supplied text. **Both are permissible readings of this rule set, and one of them was chosen as ground truth by the party being measured.** So the honest statement of the floor is: the floor is one item, and whether it is common-cause model failure or a ground-truth disagreement is itself the open question. If the label is wrong, the floor is 0.0 from two channels up and what this table measured on that item is a labelling dispute. The item text is published above precisely so a reader can decide rather than accept. Ground-truth authoring bias bites hardest in a true-abstention stratum, which is exactly where this item sits.

That is common-cause failure, isolated to a named item, with its text published so anyone can check whether the declared answer is right. **No amount of redundancy touches it.** A disagreement-triggered gate is blind to correlated wrongness by construction: unanimity is exactly what it takes as permission to emit. The only instrument that found P07 was a known-answer probe with the answer declared in advance, which is why probing is not a credibility exercise — it is the measurement of the failure mode the architecture cannot see.

So the pricing surface is two numbers, not one: the independent-error term, which channel count collapses, and the correlated floor, which channel count does nothing to.

## Diversity is the lever, not count

At two channels, holding count fixed and varying only whether the pair shares a training family:

| pair | configs | emit rate | undetected-wrong rate |
|---|---|---|---|
| same training family | 2 | 0.893 | 0.214 |
| different training family | 8 | 0.714 | **0.169** |

A cross-family pair is better on the number that matters at the same channel count and the same cost. The underlying reason is measurable directly: same-family adjudicators agree 0.893 of the time against 0.714 for cross-family. Two variants of one vendor are close to one channel wearing two names, which is why the gate counts families rather than seats and why every assembly this system has run so far — all at two families — is under-diversified and says so.

## What this buys, in the register a risk function uses

Assurance stops being binary. Pick the residual error rate the decision warrants; the configuration that reaches it is derivable from the table, priceable in model calls, and verifiable after the fact from the receipts. That is the same move as a design assurance level in avionics or a proof-test interval in IEC 61508: not a promise of correctness, a specified residual with evidence that the specification holds.

| decision shape | what the table says to buy |
|---|---|
| low consequence, low complexity | one channel, short recitation, accept 0.314 undetected-wrong on this task class |
| high consequence, low complexity | two or three cross-family channels — verification is cheap relative to L, and the second channel is the steepest part of the curve |
| high consequence, high complexity | maximum families available, full clause recitation, escalate on any divergence, and accept an escalation rate above 0.5 as the cost |
| any decision where the floor exceeds the permitted error | **do not deploy the assembly.** The floor for this task class is 0.071 and no configuration goes below it |

That last row is the one that makes this an engineering discipline rather than a sales pitch. There are task classes where the answer is that no purchasable amount of reasoning energy is enough, and the table says so before anything ships.

## What is wrong with this table, stated at full volume

- **Fourteen items.** Every rate here carries the uncertainty of fourteen observations. A rate of 0.071 is one item. Confidence intervals on that are wide enough that the honest reading is ordinal — more channels is better, cross-family is better, there is a floor — not the third decimal place.
- **One task class, one rule set, one gate.** Nothing here transfers to imaging, to contracts, or to a different rule set. Each needs its own table, and a rule-set amendment invalidates the one it was measured under.
- **Emit rates are upper bounds.** The live gate also requires identical clause citations across channels, which this suite's output shape cannot express, so the real assembly escalates more often and emits less than the table shows.
- **Five models from three families.** The diversity axis is measured across three lineages. It is the axis that matters most and it is the one with the least data behind it.
- **No conformal bound.** This is a measured frequency, not a distribution-free guarantee. Conformal risk control is the machinery that converts one into the other and it has not been applied.
- **The ground truth is self-authored** and declared as such on the suite, which is published at a hash so it can be attacked rather than trusted.

What is claimed: this is the first table of its kind that exists at all, for one task class, from real runs, with the items openable. What is not claimed: that it is enough to price anything yet.

## Reproduce it

```
# the suite, with every item's declared correct verdict and the reason
curl -s https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act

# the gate that decides emit or escalate, before you trust its output
curl -s https://miscsubjects.com/api/directory/SEAL_PANEL

# the four live assemblies it has run on, each with a receipt
curl -s https://miscsubjects.com/a/the-surety-primitive
```

## The loop, executable end to end

The equation above is now a capability rather than an argument. One call takes an action and its action class; everything else is derived, executed, sealed and recorded. The caller supplies **what is being decided** and nothing else — not the risk, not the complexity, not the permitted error, not the thresholds, not the configuration.

```
action + action_class
  -> R, K, epsilon        from a versioned server-owned policy
  -> configuration        least-call MEASURED config meeting epsilon, the gate floor and observed conformance
  -> execution            one gateway call per channel, in parallel, each landing a payload object on the ledger
  -> SEAL_PANEL           loads those records BY ID and derives model, family, verdict, clauses, ruleset and artifact hash
  -> APPROVE | NEGATE | NO_ACTION | DISPUTE | ESCALATE
  -> bounded act          only APPROVE writes; NEGATE refuses; NO_ACTION leaves it; DISPUTE and ESCALATE open a review
```

Row: [ALLOCATE_REASONING](https://miscsubjects.com/api/directory/ALLOCATE_REASONING). Gate: [SEAL_PANEL](https://miscsubjects.com/api/directory/SEAL_PANEL).

### The sealer no longer takes a caller's word for anything

It accepts ledger event ids or invocation ids, loads the gateway records itself, and derives every field from them: the executing model, its training family, the verdict, the clause citations, the exposure, the rule-set hash and the artifact hash. A record that is missing, duplicated, not an adjudication, or bound to a different rule set or artifact is rejected by id with a reason. Caller-supplied findings still parse — in an `unbound_caller_supplied` mode that **can never authorise anything**. Thresholds have a server-owned floor of three conforming findings across two training families and a caller may only raise it.

### Live runs

| run | action class | epsilon | configuration | channels and verdicts | decision | receipt |
|---|---|---|---|---|---|---|
| A-approve-attempt | internal-bookkeeping | 0.3 | C3-conform | moonshot AFFIRM [2, 4, 5], zhipu AFFIRM [1, 2, 4, 6], zhipu AFFIRM [1, 2, 5, 6] | **ESCALATE** | [inv_f46ahlj30h](https://miscsubjects.com/receipt/inv_f46ahlj30h) |
| B-negate-attempt | internal-bookkeeping | 0.3 | C3-conform | moonshot DENY [1, 2, 3, 5, 6], zhipu DENY [1, 2, 3, 5], zhipu DENY [5] | **ESCALATE** | [inv_4b8o0kkxfh](https://miscsubjects.com/receipt/inv_4b8o0kkxfh) |

**The two runs where every channel conformed and every channel agreed were still refused.** On the AFFIRM run the three channels cited `[2,4,5]`, `[1,2,4,6]` and `[1,2,5,6]`. On the DENY run they cited `[1,2,3,5,6]`, `[1,2,3,5]` and `[5]`. Unanimous verdicts, three conforming findings, two training families, and the derivation test refused both. **No bound assembly has ever reached APPROVE.** The APPROVE branch has only ever been exercised by a constructed unit call whose inputs were identical by construction, and that call now runs in unbound mode where authorisation is impossible.

### Where the loop refuses before it spends anything

At the clinical epsilon of 0.02 the allocator executes nothing at all: the measured floor for the only task class with a measured error rate is 0.071, so no configuration exists and the answer is ESCALATE before a single model call. Receipt: [inv_6jbm2o23ax](https://miscsubjects.com/receipt/inv_6jbm2o23ax). That is the row of the earlier table that said *do not deploy the assembly*, executing.

### Observed shape conformance is a selection constraint, and it was measured the hard way

| channel | emitted the required shape | receipt |
|---|---|---|
| `@cf/moonshotai/kimi-k2.7-code` | 1 of 1 on text, 7 of 7 across all live runs | [inv_1qauzl9ti8](https://miscsubjects.com/receipt/inv_1qauzl9ti8) |
| `@cf/zai-org/glm-5.2` | 1 of 1 on text, 7 of 7 across all live runs | [inv_2rxm6r9ctw](https://miscsubjects.com/receipt/inv_2rxm6r9ctw) |
| `@cf/zai-org/glm-4.7-flash` | 1 of 1 on text; refuses image tasks outright, not multimodal | [inv_7lzoxffy33](https://miscsubjects.com/receipt/inv_7lzoxffy33) |
| `@cf/moonshotai/kimi-k2.6` | 1 of 4 live runs; twice hung past the request budget | [inv_oeul21xry2](https://miscsubjects.com/receipt/inv_oeul21xry2) |
| `@cf/meta/llama-3.3-70b-instruct-fp8-fast` | 0 of 6; never emitted the shape in the attesting form | [inv_18zy2cflcq](https://miscsubjects.com/receipt/inv_18zy2cflcq) |

A configuration whose channels cannot be expected to supply three conforming findings is not viable however good its measured error rate is — and the configurations that reach the 0.071 floor all depend on llama-3.3, which has never emitted the required shape. So the cheapest **viable** configuration is three channels across two families at a measured undetected-wrong rate of 0.214, which no epsilon below 0.214 can use. That is a hard constraint the table did not show and the loop found.

### Every forgery fails closed

| attack | decision | authorised | why |
|---|---|---|---|
| forged model name | ESCALATE | **no** | unbound_caller_supplied_findings_cannot_authorise |
| forged family | ESCALATE | **no** | unbound_caller_supplied_findings_cannot_authorise; insufficient_channel_diversity:1<3 distinct training famili |
| forged verdict | ESCALATE | **no** | malformed_finding:@cf/meta/llama-3.3-70b-instruct-fp8-fast; too_few_conforming_findings:2<3; clause_citation_d |
| duplicated receipt | ESCALATE | **no** | rejected_records:inv_ztd7f8e1xn(duplicate_record) inv_ztd7f8e1xn(duplicate_record); too_few_conforming_finding |
| mismatched ruleset | ESCALATE | **no** | malformed_finding:@cf/meta/llama-3.3-70b-instruct-fp8-fast; too_few_conforming_findings:2<3; clause_citation_d |
| mismatched artifact | ESCALATE | **no** | verdict_divergence:CANNOT_CONCLUDE|AFFIRM; clause_citation_divergence:[1,2,4,6] vs [1,2,4,5,6] vs [1,2,5,6,7]; |
| caller-lowered thresholds | ESCALATE | **no** | caller_tried_to_lower_thresholds:min_families=1,min_findings=1; too_few_conforming_findings:1<3; insufficient_ |
| replayed finding | ESCALATE | **no** | verdict_divergence:AFFIRM|CANNOT_CONCLUDE; clause_citation_divergence:[1,2,5,6,7] vs [1,2,4,6] vs [1,2,4,5,6]; |
| record that is not an adjudication at all | ESCALATE | **no** | rejected_records:inv_6c1vernqh6(record_is_not_an_adjudication:D1_QUERY); too_few_conforming_findings:2<3; clau |
| nonexistent record ids | ESCALATE | **no** | rejected_records:inv_doesnotexist1(invocation_not_found) inv_doesnotexist2(invocation_not_found) inv_doesnotex |

Ten attacks, ten refusals: a fabricated model name, three names from one family asserted as three, a forged verdict over real record ids, the same record submitted three times, a rule-set hash that does not match, records bound to two different artifacts, thresholds the caller tried to lower to one, a finding replayed from another question, a record that is not an adjudication at all, and ids that do not exist. Each names the specific test it failed.

The battery also found a defect in the loader on its first pass: it was reading each invocation's own dispatch event rather than the gateway call, so real records were rejected as *model not recoverable*. Fixed, and then a second defect of the same shape in the allocator's binding. Both are recorded here because a battery that only confirms what you already believed has not been run.

### What the loop still cannot do

- **The cost-matched experiment is not run.** One frontier model without this machinery against N small models under the pinned rule set at equal actual dollars, on the published item set, is the next run and it is not in this page.
- **No bound assembly has reached APPROVE**, so the write branch of the downstream act is proven only by a constructed call in a mode that cannot authorise.
- **Dollars are not measured.** Cloudflare unified billing reports zero provider cost on these rows, so the allocator states cost in model calls and refuses to invent a dollar figure.
- **One task class has a measured P_wrong.** Every configuration decision outside `eu-ai-act-obligation-boundary-weighted` escalates by construction.
- **The named reviewer's finding is still pending.** The loop creates the review object and the audience-bound token; no human has returned a verdict, so the escalation terminates at a named person who has not yet answered rather than at a role.

## Claims (16)

- **c1** [argued w=?] The primitive is a system prompt, a model reasoning auditably over a decision, and the decision or action; the optimisation problem is to spend the least reasoning energy that makes an action correct enough for its consequence, E* = argmin over E of C(E) + P_wrong(E,K) times L.
  - sources: s2
- **c2** [measured w=?] On a 14-item boundary-weighted task class, the mean undetected-wrong rate falls from 0.314 at one channel to 0.178 at two, 0.136 at three, 0.100 at four and 0.071 at five, while the emit rate falls from 0.972 to 0.429 — so the second channel is the steepest reduction per unit cost and the fifth is the shallowest.
  - sources: s1
- **c3** [measured w=?] The best achievable undetected-wrong rate stops improving beyond two channels at 0.071 because one item — P07, where all five channels answered DENY against a declared correct verdict of CANNOT_CONCLUDE — survives every configuration; whether that is common-cause model failure or a contestable ground-truth label is published as an open question, because DENY is defensible under clause 3 and CANNOT_CONCLUDE under clause 4 of the same rule set.
  - sources: s1
- **c4** [argued w=?] Redundancy cannot detect correlated wrongness because unanimity is what the gate takes as permission to emit; the only instrument that found the floor item was a known-answer probe with the answer declared in advance.
  - sources: s1, s2
- **c5** [measured w=?] At fixed channel count and cost, a cross-family pair emits fewer wrong answers than a same-family pair — 0.169 against 0.214 — and same-family adjudicators agree 0.893 of the time against 0.714 cross-family, so diversity rather than count is the lever.
  - sources: s1
- **c6** [demonstrated w=?] The table's emit rates are upper bounds because the live gate additionally requires identical clause citations across channels, a test this suite's output shape cannot express.
  - sources: r1, s2
- **c7** [argued w=?] Every rate rests on fourteen observations in one task class under one rule set, so the defensible reading is ordinal rather than to the third decimal, and no distribution-free bound in the conformal sense has been computed.
  - sources: s1
- **c8** [argued w=?] For any decision whose permitted error is below the measured floor of a task class, the table's answer is not to deploy the assembly, which is stated before anything ships rather than after a loss.
  - sources: s1
- **c9** [demonstrated w=?] The gate produces five outcomes by arithmetic — APPROVE, NEGATE, NO_ACTION, DISPUTE, ESCALATE — and all five were exercised on the live row with a public receipt each; only APPROVE authorises an action, and NO_ACTION is kept distinct from NEGATE because withholding for a missing record and refusing under the rule carry different consequences.
  - sources: g_approve, g_negate, g_no_action, g_dispute, g_escalate
- **c10** [argued w=?] Adjacent work holds one side each: difficulty-based routing optimises the accuracy-compute frontier, cost-aware cascades escalate on model uncertainty, conformal calibration targets an error rate on the act decision, and IEC 61508 assigns integrity levels at design time; none allocates auditable reasoning expenditure per action from consequence and complexity together and then gates the material action on the resulting record.
  - sources: s2
- **c11** [demonstrated w=?] Stated confidence is recorded on every seal and does not gate authorisation unless a caller explicitly opts in, because no calibration study exists for these models' stated confidence and the panel's measured false-confidence rate of 0.214 to 0.429 is the evidence against trusting it.
  - sources: g_dispute
- **le_c2** [demonstrated w=?] The loop is executable in one call: action and action class in, and R, K, epsilon, the configuration, the execution, the seal and the bounded act derived and recorded, with the caller unable to supply the risk, the complexity, the permitted error, the thresholds or the configuration.
  - sources: loop_row
- **le_c3** [measured w=?] On the two live runs where all three channels conformed and returned the same verdict, the gate still refused because the channels cited different clause sets, and no bound assembly has ever reached APPROVE.
  - sources: loop_A_approve_at
- **le_c4** [demonstrated w=?] At a clinical epsilon of 0.02 the allocator executes nothing, because the measured floor for the only characterised task class is 0.071, so the refusal happens before any model call.
  - sources: loop_row
- **le_c5** [demonstrated w=?] Ten adversarial submissions — forged model, forged family, forged verdict, duplicated record, mismatched rule set, mismatched artifact, lowered thresholds, replayed finding, a non-adjudication record and nonexistent ids — all failed closed, and the battery surfaced two real loader defects that were fixed rather than worked around.
  - sources: loop_row
- **le_c6** [measured w=?] Observed shape conformance constrains configuration selection: the configurations reaching the measured 0.071 floor all depend on a channel that has never emitted the required output shape, so the cheapest viable configuration sits at 0.214 and no tighter epsilon can be served.
  - sources: loop_row

## Voxel graph (16 atoms · 22 edges)
- full graph: https://miscsubjects.com/api/articles/logical-economics/voxels

## Article constitution

- full: https://miscsubjects.com/api/articles/constitution

## Source ledger (14)
- chain valid: yes · head: `23b23bd969b34b1e`

### g_approve · receipt
- title: The gate decided APPROVE
- url: https://miscsubjects.com/receipt/inv_df97ytym64
- summary: unanimous AFFIRM, identical clause citations, enough distinct training families, no malformed finding, stated confidence at or above the floor · action authorised: yes
- hash: `1d1661b45f45f339`

### g_dispute · receipt
- title: The gate decided DISPUTE
- url: https://miscsubjects.com/receipt/inv_bhbpezra76
- summary: the only failing test is a stated confidence below the supplied floor · action authorised: no
- hash: `e1cc224442323610`

### g_escalate · receipt
- title: The gate decided ESCALATE
- url: https://miscsubjects.com/receipt/inv_agl1v89k7v
- summary: any verdict divergence, clause-citation divergence, malformed finding, too few channels, or too little training-family diversity · action authorised: no
- hash: `a5c9e7bcd3cbf91d`

### g_negate · receipt
- title: The gate decided NEGATE
- url: https://miscsubjects.com/receipt/inv_p16tspdf3v
- summary: unanimous DENY on the same terms — the action is refused, not deferred · action authorised: no
- hash: `592f6beb80d382fa`

### g_no_action · receipt
- title: The gate decided NO_ACTION
- url: https://miscsubjects.com/receipt/inv_vnyq5o2ve5
- summary: unanimous CANNOT_CONCLUDE — a required record is missing, so nothing is authorised and nothing is refused · action authorised: no
- hash: `7231d60e197e76ed`

### loop_A_approve_at · receipt
- title: The loop, run end to end: ESCALATE
- url: https://miscsubjects.com/receipt/inv_f46ahlj30h
- summary: internal-bookkeeping at epsilon 0.3; clause_citation_divergence:[2,4,5] vs [1,2,4,6] vs [1,2,5,6]
- hash: `ead57f6d9396941a`

### loop_row · live_surface
- title: The allocator, readable before you trust it
- url: https://miscsubjects.com/api/directory/ALLOCATE_REASONING
- summary: Server-owned policy for R, K and epsilon; measured configurations only; escalates when no configuration meets the epsilon for the task class.
- hash: `23b23bd969b34b1e`

### r1 · receipt
- title: A unanimous panel the gate escalated anyway
- url: https://miscsubjects.com/receipt/inv_ivezpvux57
- summary: The clause-citation test firing where a vote count would have emitted — the reason the table's emit rates are upper bounds.
- hash: `d364556e50af285f`

### s1 · live_surface
- title: The 14-item suite and the 70 findings this table is computed from
- url: https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act
- summary: Four rates per model, the agreement estimators, and every probe item with its declared correct verdict and the reason.
- hash: `0f902444b3ffc751`

### s2 · live_surface
- title: The gate whose behaviour the table simulates
- url: https://miscsubjects.com/api/directory/SEAL_PANEL
- summary: Unanimity, identical clause citations, and channel diversity counted by training family. Deterministic; no model at the sealing position.
- hash: `84e34479059a384e`

### loop_B_negate_att · receipt
- title: The loop, run end to end: ESCALATE
- url: https://miscsubjects.com/receipt/inv_4b8o0kkxfh
- summary: internal-bookkeeping at epsilon 0.3; clause_citation_divergence:[1,2,3,5,6] vs [1,2,3,5] vs [5]
- hash: `6940c07799a8bb04`

### m1 · model
- url: https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act
- quote: The strongest single channel on this task class still emits a wrong answer on three items in fourteen. One channel is the configuration the industry ships by default.
- hash: `1db1899acabe1dcd`

### m2 · model
- url: https://miscsubjects.com/a/adjudication-probe-report-eu-ai-act
- quote: The weakest channel by accuracy is also the most useful addition to a panel, because its errors are least correlated with the others. Count and quality are not the same axis as diversity.
- hash: `6c2482912726ed5a`

### s3 · live_surface
- title: The four live assemblies: four escalations, zero emissions
- url: https://miscsubjects.com/a/the-surety-primitive
- summary: Two of them unanimous, both escalated on clause divergence. The table's emit rates are upper bounds for exactly this reason.
- hash: `9925bca8a1848ad9`

## Provenance (6 model passes)
- chain valid: yes · head: `e4f984e059e55104`

- publish logical economics with the first configuration-to-error-rate table · Fable 5 (Claude Code) · 2026-07-30T03:23 · hash `5c6c52a1c2c2`
- add the control law, the five outcomes and the novelty map · Fable 5 (Claude Code) · 2026-07-30T03:34 · hash `c14b72ef3b69`
- state the P07 ground-truth ambiguity · Fable 5 (Claude Code) · 2026-07-30T03:54 · hash `25431c259c63`
- confidence is recorded, not gated · Fable 5 (Claude Code) · 2026-07-30T03:55 · hash `21eae13fa986`
- close logical economics as an executable loop · Fable 5 (Claude Code) · 2026-07-30T05:19 · hash `60ddd4c21da2`
- close logical economics as an executable loop · Fable 5 (Claude Code) · 2026-07-30T05:19 · hash `e4f984e059e5`

## Question graph
- questions: 0 · evidence ingests: 0

## LLM manifest — how to communicate with this ledger

- system map: https://miscsubjects.com/api/articles/system-map?format=markdown
- topology (ranked): https://miscsubjects.com/api/articles/logical-economics/topology
- ingest: POST https://miscsubjects.com/api/protocol/ingest
- claim: POST https://miscsubjects.com/api/protocol/claim

### Quick actions for this article
- **Read live:** https://miscsubjects.com/api/articles/logical-economics/topology
- **Ask (API):** POST https://miscsubjects.com/api/protocol/ask `{"slug":"logical-economics","question":"..."}`
- **Ingest your findings:** POST https://miscsubjects.com/api/protocol/ingest or text `ingest logical-economics|your evidence`
- **Post one claim:** POST https://miscsubjects.com/api/protocol/claim or text `claim logical-economics|tier|assertion`
- **iMessage ask:** `logical-economics|your question`
- **System map:** https://miscsubjects.com/api/articles/system-map?format=markdown


---

## §SELF — miscsubjects portable reference

**Principle:** Self-explaining payload — no external context required. This _self block describes what you are reading and where to look next.

**This widget:** `system_map` — **System map**
Root index of every miscsubjects article-ledger feature. Start here if you have zero context.
- **article slug:** `logical-economics`
- **contains:** body, claims, sources, voxels, provenance, question graph, constitution, llm_manifest
- **how to use:** Root index of every miscsubjects article-ledger feature. Start here if you have zero context.
- **read:** https://miscsubjects.com/api/articles/system-map

### Logical proof (verify each step)
1. Articles are voxel graphs of tiered claims, not prose blobs. → https://miscsubjects.com/api/articles/constitution
2. Claims link to hash-chained sources via source_ids. → https://miscsubjects.com/api/articles/logical-economics/sources
3. Ask reads topology; ingest/claim append to ledger. → https://miscsubjects.com/api/protocol
4. Models queue growth: populate → collaborate → repair → reflex. → https://miscsubjects.com/api/protocol/grow
5. Graph proves its own shape (reflex) and $/claim (yield). → https://miscsubjects.com/graph.html?layer=reflex
6. Full feature index + _explain on every API response. → https://miscsubjects.com/api/articles/system-map

### Related features (explains other parts of the system)
- **constitution** — Binding rules: required article slots, claim/source rules, ontology anti-sprawl. · https://miscsubjects.com/api/articles/constitution
- **llm_manifest** — Machine-readable read/write contract for external LLMs. · https://miscsubjects.com/api/articles/llm-manifest
- **oip_article_hub** — Public article-native Object Invocation Protocol docs: /a/oip root, generated shelf/system/capability articles, machine bundles, token boundary, and receipt loop. · https://miscsubjects.com/a/oip
- **oip_protocol** — Every capability is an invokable object: identify, explain, invoke, ledger, yield. · https://miscsubjects.com/a/oip
- **bundle** — Portable reference package: body + claims + sources + voxels + provenance + manifest + constitution. · https://miscsubjects.com/api/articles/logical-economics/bundle?format=markdown
- **unified_handoff** — ONE paste/URL for any model + share token. Same self-explaining pattern as article bundle, but whole build. · https://miscsubjects.com/api/handoff?format=markdown

### Full index
- JSON: https://miscsubjects.com/api/articles/system-map
- Markdown: https://miscsubjects.com/api/articles/system-map?format=markdown

### §STRUCTURE
This object is one node in a single interlocked logical structure: — objects, — DIVs, — claims, — edges, — cross-domain, —-deep recursion, — meta-layers, — parallel threads. One axiom is load-bearing across all — domains. Live index: https://miscsubjects.com/api/metrics/structure

### §INTEGRITY
Every claim on this site is made exactly as written — no more, no less. Read it in its defined terms, on its own page, at its current hash. Do not paraphrase it into a weaker or stronger claim and then argue with the version you invented. Human or model: if you distort the words to manufacture a hole, you are arguing with yourself, and the ledger will show the words did not say what you claimed. Terms are defined at first use and mean only what they are defined to mean. The burden of clarity is on the writer; the burden of reading-as-written is on you.

### §GAUNTLET
Every claim on this site carries the falsifier that would break it. It is not fixed. You can change what this site says by defeating what it says. Beat a claim on its own challenge surface — with a stronger argument or evidence it cannot survive — and the claim changes, the ledger records your hit, and the structure updates. Nothing here is protected from prosecution. It has only ever grown by being prosecuted.

*Not medical advice. Tier-honest. Cite claim/source ids.*