miscsubjectsAI governance
Evidence review · technical

Proof of coverage: how to prove an AI examined every record it was given

bundle · json · system map · manifest

Every copy includes §SELF — what this is, proof chain, and links to every other feature. No context required.

§SELF — this page explains the system
## §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:** `human_page` — **Human article page**
Rendered article with claims, sources, copy widgets, ask prompts.
- **article slug:** `proof-of-coverage`
- **contains:** rendered article, copy widgets, claims, sources, ask prompts
- **how to use:** Use Copy for LLM or Copy system map — both paste without context.
- **read:** https://miscsubjects.com/a/proof-of-coverage

### 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/proof-of-coverage/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)
- **bundle** — Portable reference package: body + claims + sources + voxels + provenance + manifest + constitution. · https://miscsubjects.com/api/articles/proof-of-coverage/bundle?format=markdown
- **ask** — Answer only from topology; creates question_node with gaps and ingest_hint. · https://miscsubjects.com/api/articles/proof-of-coverage/prompts
- **topology** — Claims, sources, anecdotes, user reports, related embeds, question graph slice — for ask/ROUTER. · https://miscsubjects.com/api/articles/proof-of-coverage/topology

### 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.*

What proof of coverage is

Proof of coverage is a way of recording machine work so that a stranger can check whether every item that was supposed to be examined actually was. It has two parts: a list of the items, written down before the work starts, and one record per examination, written by the system doing the work rather than by the model. Completeness is then a subtraction between the two lists.

The problem it solves comes up whenever software is asked to look at many things and report back. A company asks an AI system to review thirty days of employee records for a specific risk. The system answers: reviewed, three concerns found. Nothing in that answer says how many records existed, which ones were opened, which failed to open, or which rule was applied to each. There is no artifact to check, so the answer has to be believed or discarded. That is true no matter how good the model is, because the missing thing is not intelligence. It is bookkeeping.

GPT-5.6web appOpenAI
examinedclaim:coverage-needs-a-denominator
Without the declared universe, “the AI checked everything” is unverifiable.
Agreed — coverage requires a declared denominator
— GPT-5.6 (web app) · Jul 27, 2026
2026-07-27 00:00s7 · #0dc65990e917

A second model, asked the same question with none of the first answer in front of it, stopped in the same place.

Kimikimi.com web appMoonshot
examinedclaim:coverage-needs-a-denominator
Your “one door” is only as good as your proof that nothing slipped through it.
Agreed — same conclusion, independent pass
— Kimi (kimi.com web app) · Jul 27, 2026
2026-07-27 00:00s8 · #e61852e926fb

The four objects

Everything below is built out of four record types. Nothing else is required.

ObjectWhat it isWritten when
universeA named set of items to be examined, with a frozen count and the rule that decides membershipOnce, before any work
objectOne item in that set, with a stable id and a hash of its contentOnce per item, at enrolment
procedureA versioned description of the test to apply — the prompt, the model, the threshold, the toolOnce per version
passOne examination of one object by one actor under one procedure, with the resultOnce per examination

"Universe" is the load-bearing word. It is the denominator: the number the coverage percentage is divided by. If it is not written down and frozen before the work starts, it can be adjusted afterwards to match whatever got done, and then the coverage figure means nothing.

What a pass record contains

The record is written by the execution environment — the code that calls the model — never by the model itself. A model asked to report its own work can produce a fluent description of an examination that did not happen. The environment cannot, because it only writes the record after the call returns, and it fills the fields from the call itself.

json · 15 linestap to unfold
json
{
  "universe_id": "u_2026_07_27_gate_a_faces",
  "object_id": "face:8f2a1c9d4b6e0175",
  "object_hash": "sha256:8f2a1c9d…0a1b2c",
  "procedure": "match@v3.1",
  "actor": "vision-model-a@operator-1",
  "input_envelope_hash": "sha256:1b9f…7d21",
  "output": "no_match",
  "confidence": 0.02,
  "started_at": "2026-07-27T18:04:11.221Z",
  "duration_ms": 412,
  "receipt": "sha256:c4d5…9e08",
  "prev": "sha256:aa01…4f6b",
  "hash": "sha256:bb02…7c1d"
}

Field by field, and why each one is not optional:

FieldWhy it is there
object_hashBinds the result to the exact bytes examined. Without it, the record refers to a name, and the thing behind the name can change.
procedureVersioned. "Reviewed for risk" is not checkable; match@v3.1 is, because the version resolves to a stored prompt, model id and threshold.
actorWhich model, which endpoint, which operator ran it. Two actors disagreeing about one object is a fact worth keeping.
input_envelope_hashHash of everything sent — prompt, parameters, attachments. Makes the call repeatable by a third party.
outputA value from a fixed set the procedure declares, not free text. Free text cannot be counted.
receiptThe provider's own identifier for the call, when one exists. Independent corroboration that the call occurred.
prev, hashThe chain. Explained below.
GPT-5.6web appOpenAI
examinedclaim:model-narration-is-proof
Model self-report is not proof. A model saying “I checked the image and found nothing” can itself be fabricated, incomplete, or post-hoc pattern matching.
Refuted — the environment must produce the record, not the model
— GPT-5.6 (web app) · Jul 27, 2026
2026-07-27 00:00s9 · #e232898b2b52

The same requirement exists in software supply-chain security, where a signed statement binds a claim to the digest of the artifact rather than to its filename. The shape is borrowed, not invented.

The chain, and what it stops

Each pass record hashes its own contents together with the hash of the record before it:

js
// hash = sha256(prev + canonical_json(record_without_hash))
async function chain(prev, record) {
  const body = JSON.stringify(record, Object.keys(record).sort());
  const bytes = new TextEncoder().encode(prev + body);
  const digest = await crypto.subtle.digest('SHA-256', bytes);
  return [...new Uint8Array(digest)].map(b => b.toString(16).padStart(2, '0')).join('');
}

Without the chain, the easiest way to produce a perfect coverage report is to delete the passes that failed. With it, deleting one record breaks the hash of every record after it, and a verifier that recomputes the chain from the first entry finds the break. The chain does not prevent deletion. It makes deletion visible, which is the most any append-only record can do.

Coverage is a query, not a claim

With the four object types in place, "did it examine everything" stops being a question about the system's honesty:

sql
SELECT
  u.declared_count,
  COUNT(DISTINCT p.object_id) FILTER (WHERE p.output <> 'error') AS examined,
  u.declared_count - COUNT(DISTINCT p.object_id) FILTER (WHERE p.output <> 'error') AS missing
FROM universe u
LEFT JOIN pass p
  ON p.universe_id = u.id
 AND p.procedure = 'match@v3.1'
WHERE u.id = 'u_2026_07_27_gate_a_faces';

A result of 4812 | 4790 | 22 is a real answer: twenty-two enrolled objects have no successful pass under that procedure, and a second query names them. "The system reviewed the records" is not an answer, because nothing in it can come back as twenty-two.

The same table answers the questions that matter after the fact. Which objects were examined more than once. Where two actors disagreed. Which objects nobody touched.

ActorObjectPassesResult
vision-model-a@operator-1face:F-18421no match
vision-model-b@operator-2image:I-99211no match
vision-model-c@operator-3image:I-99212match, confidence 0.31
doc-model-a@operator-4receipt:R-44081accepted

Two actors reached opposite conclusions about image:I-9921. In separate systems that contradiction never meets. On one object table it is a row, and it can be escalated by a rule rather than by luck.

The identity rule sets the denominator, so it is written first

The hardest part of this method is not the storage. It is deciding what counts as one object, and that decision has to be recorded before enrolment, because it fixes the number everything is divided by.

For faces in footage: is a person appearing in eleven frames one object or eleven? Is a face at nine pixels wide an object or an unusable detection? Two detections five seconds apart that the tracker joined — one object, or two with a link?

The rule is stored on the universe as text a person can read and as code that runs:

json
{
  "id": "u_2026_07_27_gate_a_faces",
  "declared_count": 4812,
  "frozen_at": "2026-07-27T18:00:00Z",
  "identity_rule": "One object per tracked face-track with >= 3 detections and minimum bounding box 40px. Tracks broken by more than 2s of occlusion are separate objects. Detections below 40px are enrolled as unusable and excluded from the denominator.",
  "identity_rule_impl": "sha256:9c41…b07e",
  "excluded": 337,
  "exclusion_reason": "below minimum resolution"
}

Note excluded. Objects the rule throws out are counted and reported, never silently dropped. A universe that declares 4,812 objects and 337 exclusions is checkable. A universe that declares 4,812 and mentions nothing else is a universe where the exclusions are wherever the operator wanted them.

Enrolling a system it does not cooperate with

The other system does not need to adopt any of this. Records are pulled through whatever interface exists — an API, an export, a database replica, a directory of files — and converted into objects at that boundary. Nothing is asked of the counterparty, so nothing depends on their agreement.

That is affordable because record shapes repeat. Different products, same structure:

ShapeFields that always existExamples
Collectioncursor or offset, page size, total or last-page markeralmost every list API
Record with identityid, created, updated, owneremployee, customer, patient rows
Transactiontwo parties, amount, currency, timestamp, statuspayment processors, banks, ledgers
Messagesender, recipients, body, thread id, timestampemail, chat, ticket systems
Media with detectionsbinary, checksum, detected regions with coordinates and confidenceimage and video pipelines
Operationinputs, actor, authority, effects, outputslogs, audit trails, job runners
Kimikimi.com web appMoonshot
examinedclaim:finite-shapes
Payments: Stripe, Square, PayPal, Plaid — same shape, different field names.
Agreed — a new system is a classification, not an integration
— Kimi (kimi.com web app) · Jul 27, 2026
2026-07-27 00:00s10 · #daa3fe75852e

An enrolment template is written once per shape. A new system is then matched to a shape, its field names bound to the template's, and its records converted. The cost of the thousandth system is a classification and a field mapping, not another integration project.

The remaining difficulty is real but ordinary: throughput, deduplication when the same underlying thing appears in two systems, ordering when timestamps disagree, and identity resolution when two records may be the same person. None of it changes the four object types.

What it costs to store a billion passes

Rates below are Cloudflare's published D1 prices, page last updated 2026-04-21. A pass record with full 64-character hashes serialises to 659 bytes.

ItemArithmeticResult
Writing 1,000,000,000 passes1,000 million × $1.00/million$1,000 once
Storing them1e9 × 659 B = 659 GB; (659 − 5) × $0.75$490.50 / month
Full-table coverage recount1e9 rows read × $0.001/million$1.00 per recount
Indexed coverage query on one universethousands of rows readfractions of a cent

A recount over a billion examinations costs a dollar. The reason this is not already normal practice is not the bill.

What this does not prove

Coverage is proof that a procedure ran over every enrolled object. It is not proof that the procedure was right.

GPT-5.6web appOpenAI
examinedclaim:coverage-proves-correctness
Execution correctness: every intended object was processed under the intended procedure. World correctness: the resulting judgment was actually true. Ten models can consistently make the same error.
Partially refuted — coverage proves the first only
— GPT-5.6 (web app) · Jul 27, 2026
2026-07-27 00:00s11 · #3edb4dfa7647

Ten models can apply the same wrong rule, sign cleanly, and produce a ledger with 100% coverage over a bad conclusion. Anyone offering a coverage figure as evidence that a conclusion is correct is misreading it, or wants it misread.

What the structure does buy is that the wrong conclusion now has an address. The error attaches to a named object, a versioned procedure and a named actor, so a contradicting pass, a later real-world outcome, or a human adjudication can be attached to the same object and compared against it. A wrong answer stops evaporating and starts accumulating a record that can be used against it.

What already exists

None of the parts are new. The gap is specific and worth naming precisely.

PROV models entities, activities and agents — the pass, in other words — and has no concept of a declared set that the activities were supposed to cover.

SLSA and in-toto bind a claim to a digest and name the builder, which is exactly the shape a pass record needs, applied to build artifacts.

Traces record operations and their relationships, are commonly sampled, and expire on a retention policy. Nothing in a trace says how many spans should have existed.

Lineage tracks which job read which dataset. It answers questions at table granularity, not per row.

The missing piece across all of them is the same: a frozen, stored count of what was supposed to be examined, sitting next to the records of what was. Whether some system elsewhere already stores that has not been verified here — patents and defence procurement have not been searched, and until they are, the honest position is unknown rather than novel.

Evidence · 11 sources · swipe →chain 3edb4dfa7647 · verify chain · provenance
1 / 11
GPT-5.6web appOpenAI
examinedclaim:coverage-needs-a-denominator
Without the declared universe, “the AI checked everything” is unverifiable.
Agreed — coverage requires a declared denominator
— GPT-5.6 (web app) · Jul 27, 2026
2026-07-27 00:00s7 · #0dc65990e917
Kimikimi.com web appMoonshot
examinedclaim:coverage-needs-a-denominator
Your “one door” is only as good as your proof that nothing slipped through it.
Agreed — same conclusion, independent pass
— Kimi (kimi.com web app) · Jul 27, 2026
2026-07-27 00:00s8 · #e61852e926fb
GPT-5.6web appOpenAI
examinedclaim:model-narration-is-proof
Model self-report is not proof. A model saying “I checked the image and found nothing” can itself be fabricated, incomplete, or post-hoc pattern matching.
Refuted — the environment must produce the record, not the model
— GPT-5.6 (web app) · Jul 27, 2026
2026-07-27 00:00s9 · #e232898b2b52
Kimikimi.com web appMoonshot
examinedclaim:finite-shapes
Payments: Stripe, Square, PayPal, Plaid — same shape, different field names.
Agreed — a new system is a classification, not an integration
— Kimi (kimi.com web app) · Jul 27, 2026
2026-07-27 00:00s10 · #daa3fe75852e
GPT-5.6web appOpenAI
examinedclaim:coverage-proves-correctness
Execution correctness: every intended object was processed under the intended procedure. World correctness: the resulting judgment was actually true. Ten models can consistently make the same error.
Partially refuted — coverage proves the first only
— GPT-5.6 (web app) · Jul 27, 2026
2026-07-27 00:00s11 · #3edb4dfa7647

Key evidence

9 claims · tier-ranked · API
system
Coverage cannot be verified without a stored count of the objects that were supposed to be examined.
sources: s7, s8
system
Coverage is a subtraction between the object table and the pass table, not a statement produced by a model.
system
The identity rule — what counts as one object — must be written down before enrolment, because it sets the denominator.
system
A pass record is only evidence if the execution environment writes it and binds it to the hash of the exact input; a model's own account of its work is not evidence.
sources: s9, s2, s3
system
Hash-chaining pass records makes silent deletion detectable, because removing a row breaks every hash after it.
system
Most systems present a small number of record shapes, so enrolling the thousandth system is a classification against an existing template rather than a new integration.
sources: s10
system
At Cloudflare D1's published rates, one billion pass records cost $1,000 to write once, about $490 per month to store, and $1.00 for a full-table coverage recount.
sources: s6
system
PROV, OpenTelemetry and OpenLineage each record operations, and none of them stores a declared universe, so none can answer a coverage question by itself.
sources: s1, s4, s5
system
A coverage proof shows a procedure ran over every enrolled object. It does not show the procedure was correct.
sources: s11
Ask this article · 8 suggested prompts

Text the build (+14245134626) or WhatsApp — slug|question creates a question node. Paste evidence with ingest slug|q:NODE_ID|your paste.

What does the ledger say about this (system tier): "Coverage cannot be verified without a stored count of the objects that were supposed to be examined."?
ask proof-of-coverage claim c1 · paste includes §SELF
What does the ledger say about this (system tier): "Coverage is a subtraction between the object table and the pass table, not a statement produced by a model."?
ask proof-of-coverage claim c2 · paste includes §SELF
What does the ledger say about this (system tier): "The identity rule — what counts as one object — must be written down before enrolment, because it sets the denominator."?
ask proof-of-coverage claim c3 · paste includes §SELF
What does the ledger say about this (system tier): "A pass record is only evidence if the execution environment writes it and binds it to the hash of the exact input; a model's own account of …"?
ask proof-of-coverage claim c4 · paste includes §SELF
What does the ledger say about this (system tier): "Hash-chaining pass records makes silent deletion detectable, because removing a row breaks every hash after it."?
ask proof-of-coverage claim c5 · paste includes §SELF
What does the ledger say about this (system tier): "Most systems present a small number of record shapes, so enrolling the thousandth system is a classification against an existing template ra…"?
ask proof-of-coverage claim c6 · paste includes §SELF
What can you answer from your catalogue about Proof of coverage: how to prove an AI examined every record it was given — and what remains open or unverified?
ask proof-of-coverage gaps · paste includes §SELF
What are the strongest objections or counter-evidence on record against Proof of coverage: how to prove an AI examined every record it was given?
ask proof-of-coverage objections · paste includes §SELF
proof-of-coverage · posted 2026-07-28 · updated 2026-07-28 · 1 prior revision · unattributed
Ledger API & provenance
Live ledger · 50 payloads · 0 turns
recent activity · inspect
JCI_TRAFFIC jci · HTTP 200 · 2026-07-29 05:08
JCI_TRAFFIC jci · HTTP 200 · 2026-07-29 02:04
JCI_TRAFFIC jci · HTTP 200 · 2026-07-29 00:04
JCI_TRAFFIC jci · HTTP 200 · 2026-07-28 23:45
JCI_CLASSIFY jci · HTTP 200 · 2026-07-28 23:45
JCI_TRAFFIC jci · HTTP 200 · 2026-07-28 23:28
view full ledger & cards →
REST + ledger
read GET /api/articles/proof-of-coverage · GET /api/articles/proof-of-coverage?format=post (the editable body)
create/replace POST /api/articles/proof-of-coverage · PUT /api/articles/proof-of-coverage (replace, keeps revision) · PATCH /api/articles/proof-of-coverage (merge)
delete DELETE /api/articles/proof-of-coverage
writes need header x-terminal-key
LLM bundle GET /api/articles/proof-of-coverage/bundle?format=markdown — body + claims + sources + provenance + manifest
post claim POST /api/protocol/claim · iMessage claim proof-of-coverage|tier|assertion
system map GET /api/articles/system-map?format=markdown — root index; every widget self-explains via §SELF / _self
Add your experience or question
Think this article is wrong?
Dispute this article in Claim Audit →