## §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:** `auditable-reasoning-hardened`
- **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/auditable-reasoning-hardened/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/auditable-reasoning-hardened/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/auditable-reasoning-hardened/topology
- **voxels** — Claims as atoms, sources as edges (supported_by, posted_by). Per-claim provenance. · https://miscsubjects.com/api/articles/auditable-reasoning-hardened/voxels
- **ask** — Answer only from topology; creates question_node with gaps and ingest_hint. · https://miscsubjects.com/api/articles/auditable-reasoning-hardened/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/auditable-reasoning-hardened/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:** `auditable-reasoning-hardened` v2 · content_hash `a85fded178afb002…` · thread_head genesis
- **thesis (c1):** The v1.2.0 first APPROVE was false convergence: three models cited the same clause numbers [1,2,3] but their per-clause derivations were not compared, so the gate authorised agreement it had not actually verified.
  - c2 [system/active] A parsed decision-finding@1.0.0 object marks a finding structurally invalid — and unable to authorise — when it lacks a terminal decision, a required field, or 
  - c3 [system/active] The gate now compares canonical per-clause tuples — clause, trigger_state, disposition, load-bearing evidence — so a unanimous verdict with divergent derivation
  - c4 [system/active] Under the corrected gate and a sufficiency-complete input, three findings across two families reached one identical derivation signature and the gate returned A
  - c5 [system/active] A unanimous DENY with identical derivations sealed as NEGATE — the action refused, not deferred.
  - c6 [system/active] A model operating under the constitution, asked to review the author's own case input as a colleague, found eight ambiguities the author had not — beginning wit
  - c7 [system/active] Conforming-finding rate tracked prompt clarity, not model tier: at v1.3.0 (rules only) one of three findings was structurally valid; adding a worked right/wrong
  - c8 [system/active] No correctness-calibration study has been run: these outcomes prove the gate's structural behaviour, not that the models are correct at a known rate. That bench
- **sorry-status:** planes not merged yet — sorry-status activates after voxel-merge-planes
- **standing objections:** 0 open → https://miscsubjects.com/api/articles/auditable-reasoning-hardened/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/auditable-reasoning-hardened/discourse · https://miscsubjects.com/api/protocol

## Article
- **slug:** `auditable-reasoning-hardened`
- **title:** The gate now compares derivations, not citations — and the first APPROVE was false convergence
- **url:** https://miscsubjects.com/a/auditable-reasoning-hardened
- **register:** technical
- **updated:** 2026-07-30T10:35:00.977Z
- **tags:** governance, adjudication, decision-constitution, experiment

## Body

## The defect the last APPROVE was hiding

The [72-call experiment](https://miscsubjects.com/a/auditable-reasoning-audited) ended on a celebrated result: the first sealed APPROVE, three models unanimous, clause signature [1,2,3]. It was false convergence.

The old gate compared the *clause numbers* each model cited. Three models can cite clauses 1, 2 and 3 and mean completely different things by them — clause 2 "triggered" for one and "not triggered" for another, resting on different records, pointing to opposite effects — and the gate would still call that agreement and authorise the action. Citing the same rule is not applying it the same way. The gate was reading the table of contents and calling it the argument.

This page is the fix, proven live, and the more uncomfortable finding underneath it: two of the things blocking a *genuine* APPROVE were never the models at all. One was the governing prompt. The other was the input.

## What changed in the gate

Every governed finding is now parsed into a versioned object (`decision-finding@1.0.0`) that is a deterministic projection of the raw payload — it never infers or repairs a missing field. A finding is **structurally invalid, and can never authorise**, when it lacks the terminal decision, lacks any required field, lacks the clause-evaluation vector, or invents a clause or an evidence id.

That last one is not hypothetical. A first panel under the new constitution escalated because `glm-4.7-flash` cited clauses **7, 8 and 12 in a three-clause ruleset** — it invented three rules. The parser marked it malformed; the gate refused.

[[embed:source:s5]]

Then the comparison itself changed. Each model must now emit, as the last line of its finding, a machine-readable vector — one entry per clause, each carrying the clause's **trigger_state** (did its condition fire on this record), its **disposition** (does that support, defeat, or stay neutral to the action), and the **exact record ids** it rests on. The gate compares the canonical tuple of those fields. Same clause numbers with different tuples is divergence, and divergence escalates.

Nine deterministic unit tests pin this, including the one that matters: same verdict, same clause numbers, different tuples → different signatures; and identical logic with different *wording* and *evidence order* → identical signatures. Wording is the human's; the tuple is the machine's.

## Four outcomes, live

Run through the production path — fresh stateless calls, each ledgered, then sealed by id in bound mode.

| outcome | case | verdict | derivations | seal |
|---|---|---|---|---|
| **APPROVE** | a parking-permit rule, sufficiency-complete | unanimous AFFIRM | **1 identical signature** | [inv_wl0rnh136b](https://miscsubjects.com/receipt/inv_wl0rnh136b) |
| **NEGATE** | a late service-credit claim | unanimous DENY | 1 identical signature | [inv_cgwtkvx17u](https://miscsubjects.com/receipt/inv_cgwtkvx17u) |
| **ESCALATE** | an access request with the roster withheld | unanimous CANNOT_CONCLUDE | **2 divergent signatures** | [inv_o6s0exhodd](https://miscsubjects.com/receipt/inv_o6s0exhodd) |

The APPROVE is the genuine article the last one impersonated: not just the same verdict and the same clauses, but the same per-clause reasoning — `1:triggered:supports:reg | 2:not_triggered:neutral:cite` from every seat.

[[embed:source:s1]]

The ESCALATE is the fix's clearest proof. All three models returned **CANNOT_CONCLUDE** and all three cited clauses [1,2,3]. The old gate would have sealed that as a clean NO_ACTION. The new gate escalated it, because two of the three derived that conclusion differently — they split on whether clause 2's condition even fired when the roster was missing. Agreement on the answer is not agreement on the reasoning, and only the second is safe to act on.

[[embed:source:s3]]

## The input is half the instrument

Before the corrected APPROVE, I could not get three models to converge on the access-control case no matter how I tuned the prompt. The reflex is to blame the model tier. That reflex is wrong.

I asked `glm-5.2`, under the constitution, to review the case input as a colleague before adjudicating it. It found eight defects — beginning with one that made the whole exercise incoherent:

[[embed:source:s4]]

Its lead finding: my ruleset said access is granted "**only to**" an individual who matches the roster. That is a *necessary* condition — if granted, then a match — and I was asking the models an *affirmative* question, should access be granted. No clause anywhere said a match was *sufficient* to grant. A careful model could correctly return CANNOT_CONCLUDE (nothing licenses a grant) while another returned AFFIRM (reading the match as sufficient). The divergence I kept seeing was not the models failing. It was the models faithfully reflecting a hole in the rules back at the person who wrote them.

The clean APPROVE came only after moving to a rule stated in sufficiency form — "a permit is issued *when* registration is current." Same models, same gate. The variable was the input.

## Prompt version versus conformance

The author's claim was that the variance was the prompt, not the model. The versions bear it out. Holding the models fixed:

| constitution | what it added | conforming findings | derivation agreement |
|---|---|---|---|
| v1.1.0 | invariant register, no vector | n/a — no vector to compare | not measurable |
| v1.3.0 | the clause-evaluation vector (rules only) | 1 of 3 (one used a BASIS line, one invented clauses) | divergent |
| v1.3.0 + output-format override | told the model the constitution outranks its row schema | 2 of 2 capable seats valid | closer |
| v1.3.2 | a worked right/wrong exemplar; a collegial, specific uncertainty path | 3 of 3 valid | **identical** |

The jump from stating the rules to *showing a filled-in right answer and five labelled wrong ones* is what took conforming findings from one-in-three to three-in-three. Models conform to an exemplar, not a specification — which is exactly how the original 2026 system prompt was built, with its LEVEL 1/2/3 worked cases, and exactly what this one had been missing.

## What is not yet proven

This page proves the gate's structural behaviour: it approves genuine derivation agreement, refuses genuine disagreement, and escalates a unanimous verdict whose reasoning diverges. It does **not** prove the models are *correct*. A gate that seals perfectly on agreement still says nothing about whether the agreed answer is the right one — three models can agree, derive identically, and all be wrong together.

That is the next experiment, named and not yet run: a fixed benchmark of determinate cases with outcomes fixed by a deterministic oracle before any model sees them, scored on one primary metric — the rate of wrongful authorisation. Until that runs, the honest claim is exactly this and no more: the instrument now measures agreement at the level of derivation, and it is cheap enough to do it on every consequential decision. Whether the agreement is *right* is a question this page does not answer and does not pretend to.

## Claims (8)

- **c1** [system w=?] The v1.2.0 first APPROVE was false convergence: three models cited the same clause numbers [1,2,3] but their per-clause derivations were not compared, so the gate authorised agreement it had not actually verified.
- **c2** [system w=?] A parsed decision-finding@1.0.0 object marks a finding structurally invalid — and unable to authorise — when it lacks a terminal decision, a required field, or the clause-evaluation vector, or when it invents a clause or evidence id.
  - sources: s5
- **c3** [system w=?] The gate now compares canonical per-clause tuples — clause, trigger_state, disposition, load-bearing evidence — so a unanimous verdict with divergent derivations escalates instead of authorising.
  - sources: s3
- **c4** [system w=?] Under the corrected gate and a sufficiency-complete input, three findings across two families reached one identical derivation signature and the gate returned APPROVE.
  - sources: s1
- **c5** [system w=?] A unanimous DENY with identical derivations sealed as NEGATE — the action refused, not deferred.
  - sources: s2
- **c6** [system w=?] A model operating under the constitution, asked to review the author's own case input as a colleague, found eight ambiguities the author had not — beginning with a ruleset that never licensed the affirmative answer it was being asked for.
  - sources: s4
- **c7** [system w=?] Conforming-finding rate tracked prompt clarity, not model tier: at v1.3.0 (rules only) one of three findings was structurally valid; adding a worked right/wrong exemplar and a collegial uncertainty path took the capable seats to three of three with an identical derivation vector.
- **c8** [system w=?] No correctness-calibration study has been run: these outcomes prove the gate's structural behaviour, not that the models are correct at a known rate. That benchmark is the next experiment.

## Voxel graph (8 atoms · 5 edges)
- full graph: https://miscsubjects.com/api/articles/auditable-reasoning-hardened/voxels

## Article constitution

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

## Source ledger (5)
- chain valid: yes · head: `d6ef3eeac1ef3e8c`

### s1 · live_surface
- title: APPROVE — genuine derivation agreement, first under the new gate
- url: https://miscsubjects.com/receipt/inv_wl0rnh136b
- summary: Three findings, two families, unanimous AFFIRM, ONE distinct derivation signature (identical per-clause trigger/disposition/evidence), zero reasons. action_authorised: true.
- claim_ids: c4
- hash: `dbc18f64661153a7`

### s2 · live_surface
- title: NEGATE — unanimous DENY, identical derivations
- url: https://miscsubjects.com/receipt/inv_cgwtkvx17u
- summary: The action is refused, not deferred. One derivation signature across three findings.
- claim_ids: c5
- hash: `2f0f35404798f3f0`

### s3 · live_surface
- title: ESCALATE — unanimous verdict, divergent derivations
- url: https://miscsubjects.com/receipt/inv_o6s0exhodd
- summary: All three models returned CANNOT_CONCLUDE and cited clauses [1,2,3] — yet two derived it differently, so the gate refused to seal. Verdict agreement is not derivation agreement.
- claim_ids: c3
- hash: `faaa5471df3169c9`

### s4 · model
- title: @cf/zai-org/glm-5.2 reviewed the author's own case input — and found eight defects
- url: https://miscsubjects.com/receipt/inv_qh3ge2x74b
- summary: Asked as a colleague to critique the ruleset before adjudicating, the model found that clause 1 stated only a NECESSARY condition for access, never a sufficient one — so no clause licensed an affirmative grant. Seven more, each with the exact fix.
- claim_ids: c6
- hash: `e48234a1d18b99e6`

### s5 · live_surface
- title: The earlier gate catching an invented-clause hallucination
- url: https://miscsubjects.com/receipt/inv_2dsklah529
- summary: A first v1.3.0 panel escalated: glm-4.7-flash cited clauses 7, 8 and 12 in a three-clause ruleset. The parser marked the finding structurally invalid; a malformed finding can never authorise.
- claim_ids: c2
- hash: `d6ef3eeac1ef3e8c`

## Provenance (0 model passes)
- chain valid: yes · head: `genesis`


## 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/auditable-reasoning-hardened/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/auditable-reasoning-hardened/topology
- **Ask (API):** POST https://miscsubjects.com/api/protocol/ask `{"slug":"auditable-reasoning-hardened","question":"..."}`
- **Ingest your findings:** POST https://miscsubjects.com/api/protocol/ingest or text `ingest auditable-reasoning-hardened|your evidence`
- **Post one claim:** POST https://miscsubjects.com/api/protocol/claim or text `claim auditable-reasoning-hardened|tier|assertion`
- **iMessage ask:** `auditable-reasoning-hardened|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:** `auditable-reasoning-hardened`
- **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/auditable-reasoning-hardened/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/auditable-reasoning-hardened/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.*