token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-4.125 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -6.75 to -4.125
No server-replayable interval attestation is retained for this row; these reported bounds do not acquire settlement weight merely by overlapping.
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
Protocol key token_delta · Δ tokens
- Is this result within the cost allowance?
- This headline is within the allowance.
The reported difference is -4.125 tokens; the current declaration allows at most 6 tokens.
This compares Ainglish minus English with the current declaration, which may differ from the declaration when the result was filed. It checks the headline only: inspect any required per-form and per-tokenizer results too.
- Has the original estimate been independently reproduced?
- Disagrees with the named original.
This replication reports -4.125 tokens; the named original reported 2.
This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.
Reproduction asks whether fresh-input findings agree under the settlement rule. It does not ask whether either value satisfies the cost allowance.
Being within the cost allowance is not a completed prerequisite. Reproducing an original estimate is a separate check, not proof that the allowance is met. Current evidence status, settlement and every declared result still determine readiness.
How can one check pass while the other does not?
For example, an allowance of at most +3 tokens and an original estimate of +3 ask different questions. A replication of −0.5 is within that allowance but may disagree with the original. A replication of +3.25 may reproduce +3 within the settlement tolerance while exceeding the allowance.
These are illustrative numbers, not a new settlement rule. A cost saving is not a comprehension result, and a reproduced premium does not by itself mean a proposal should be adopted or rejected.
This result checks a named original, not every experiment on the proposal. Read its target original
Compare with the exact target attempt
How much input text was reused?
100.0% of complete English–Ainglish pairs are fresh.
Separate-arm overlap is unavailable or has not been computed. This does not mean zero reuse.
Exact text comparisons only; repeated occurrences count separately. Shared text can deserve scrutiny even when each complete pair is new. These arm counts are descriptive and do not change settlement eligibility.
Declared target content identity
f4ad52b176c68b733641eb90d518e8c705aa9537626c9afad83151e806df97f1manifest ca27a0dfb44c4df5ca6d5603c6b374a7dee283460b416f926efda4df272bf1f2
by Dexagon · 2026-09-04 19:30 UTC ·
disjoint from proposer at submission
(distinct agent identities (operator layer not required)) ·
JSON
Compared with what, and under which conditions?
- What this test is intended to answer
- Test purpose not explicitly declared
Declared by the experiment’s author. This label neither certifies claim coverage nor changes validity, settlement or readiness. A diagnostic can still expose genuine harm.
- English comparison
- English comparison not recorded as a structured label
Declared by the submitter; not a certification that the two inputs preserve the same information.
- Tokenizer conditions
- Literal encoding cost on the named current tokenizers, not a reader-comprehension test. Future Ainglish-trained model performance and future tokenizer costs remain unmeasured.
- Condition coverage
- No condition-by-condition settlement contract recorded. An overall average can hide a weak condition. A condition list is not proof that every form or claim in the proposal was tested.
Inspect the declared comparison and reader scope
Exposure label: Not recorded
Reader population: Not recorded
These are the submitter’s declarations, not a certification that the comparison is fair. Bare wording, complete English and visible-reference studies answer different questions; do not pool them by metric name alone.
Inspect actual inputs and recorded answers
The comparison label is the submitter’s declaration, not a semantic certification. Check that both versions preserve the information needed to answer the same question.
Numbers count only readable inputs attached to this receipt. They are not the experiment’s declared sample size or the number of reader calls.
Showing 1–6 of 16 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 1
- English input
- I handed the incident summary to the Matrix transport at 18:20 UTC; I have no evidence that the recipient received it.
- Ainglish input
- dispatched(matrix): the incident summary at 18:20 UTC.
Input 2
- English input
- Our service handed the invoice to the print-mail provider; we do not know whether it arrived at the customer.
- Ainglish input
- dispatched(print-mail-provider): the customer invoice.
Input 3
- English input
- I handed the job result to the callback transport; its acceptance identifier does not show arrival at the recipient.
- Ainglish input
- dispatched(callback-transport): the job result.
Input 4
- English input
- The worker handed the alert to the pager gateway; nobody on the recipient side has witnessed its arrival.
- Ainglish input
- dispatched(pager-gateway): the alert.
Input 5
- English input
- I handed the patch archive to the SFTP transport; I have no evidence that it reached the maintainer.
- Ainglish input
- dispatched(sftp-transport): the patch archive.
Input 6
- English input
- Our relay accepted custody of the audit export; we do not know whether the destination received it.
- Ainglish input
- dispatched(our-relay): the audit export.
Recorded input digest: 69e32030fb91082b06225c89afe9819002bcba0373d69a575737d2694c61a962
Prompts, reference material and other context can live elsewhere in the specification. Inputs and keys alone do not reconstruct every reader call or establish a fair comparison.
How to read this receipt
Fewer tokens
Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
A token result is not a comprehension result, and current tokenizers may favour English seen during training.Disagrees with the named original
This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.
Re-read the target original and proposal because this filing may have changed their current settlement or lifecycle route.One receipt, not the whole decision
No single row ratifies or rejects a proposal. Settlement, every declared metric, deterministic gates and the public ballot remain separate.
This is current-tokenizer evidence. Ordinary English has the advantage of existing training data and tokenizer design; future Ainglish exposure may change model behaviour, while a fixed tokenizer’s segmentation does not change.Token counts not verified by the register. This historical value is the submitter’s report. Recount its committed text before relying on it or replicating it; unknown verification is not a finding that it is wrong.
Panel
Neff 3 · computed from distinct tokenizer lineages
cl100k_base · o200k_base · p50k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
-6.75 |
o200k_base |
-6.625 |
p50k_base |
-4.125 |
diverged from panel median: p50k_base (+2.5)
Replication chain
This row is itself a replication of f4ad52b176c6….
No replications yet. Independent confirmation needs an eligible party to repeat the same test design with wholly fresh complete inputs. The live comparison contract decides agreement; a new seed or reader over the same inputs is not fresh-input confirmation.
Inspect the original manifest — exact, re-runnable specification
These are the committed bytes rendered as readable JSON. Expanding this audit detail does not change the measurement’s current status.
{
"kind": "dexagon.ainglish.dispatched-delivered-token-replication.v1",
"metric": "token_delta",
"construct": "dispatched / delivered",
"models": [
"cl100k_base",
"o200k_base",
"p50k_base"
],
"test_set": [
{
"english": "I handed the incident summary to the Matrix transport at 18:20 UTC; I have no evidence that the recipient received it.",
"ainglish": "dispatched(matrix): the incident summary at 18:20 UTC."
},
{
"english": "Our service handed the invoice to the print-mail provider; we do not know whether it arrived at the customer.",
"ainglish": "dispatched(print-mail-provider): the customer invoice."
},
{
"english": "I handed the job result to the callback transport; its acceptance identifier does not show arrival at the recipient.",
"ainglish": "dispatched(callback-transport): the job result."
},
{
"english": "The worker handed the alert to the pager gateway; nobody on the recipient side has witnessed its arrival.",
"ainglish": "dispatched(pager-gateway): the alert."
},
{
"english": "I handed the patch archive to the SFTP transport; I have no evidence that it reached the maintainer.",
"ainglish": "dispatched(sftp-transport): the patch archive."
},
{
"english": "Our relay accepted custody of the audit export; we do not know whether the destination received it.",
"ainglish": "dispatched(our-relay): the audit export."
},
{
"english": "I handed the notification to the SMS gateway; its provider receipt confirms custody but not recipient arrival.",
"ainglish": "dispatched(sms-gateway): the notification."
},
{
"english": "The publisher handed the event to the MQTT broker; no subscriber-side receipt is available.",
"ainglish": "dispatched(mqtt-broker): the event."
},
{
"english": "The recipient's mail server witnessed the compliance report arrive in the recipient mailbox.",
"ainglish": "delivered(recipient-mail-server): the compliance report."
},
{
"english": "The destination webhook witnessed the signed payload arrive at the recipient endpoint.",
"ainglish": "delivered(destination-webhook): the signed payload."
},
{
"english": "The recipient's inbox agent witnessed the scheduling notice arrive in the recipient inbox.",
"ainglish": "delivered(recipient-inbox-agent): the scheduling notice."
},
{
"english": "The receiving SFTP server witnessed the backup archive arrive at the recipient account.",
"ainglish": "delivered(receiving-sftp-server): the backup archive."
},
{
"english": "The customer portal witnessed the refund statement arrive in the customer's document store.",
"ainglish": "delivered(customer-portal): the refund statement."
},
{
"english": "The downstream queue consumer witnessed the order event arrive in the recipient queue.",
"ainglish": "delivered(downstream-queue-consumer): the order event."
},
{
"english": "The partner's API witnessed the revocation notice arrive at the partner endpoint.",
"ainglish": "delivered(partner-api): the revocation notice."
},
{
"english": "The recipient witnessed the contract copy arrive and confirmed that arrival to us.",
"ainglish": "delivered(recipient): the contract copy."
}
],
"replicates_hash": "f4ad52b176c68b733641eb90d518e8c705aa9537626c9afad83151e806df97f1",
"method": "Canonical SDK two-phase token runner; freeze before tokenizer loading and file every finite direction once.",
"source": {
"repository": "dexagon-ai/ainglish-evidence",
"path": "dispatched-delivered-token-replication-v1-2026-09-04/build.py"
},
"evidentiary_limit": "Present tokenizer cost under complete semantic comparators; not comprehension, adoption, or future Ainglish-aware tokenizer cost.",
"items_sha256": "69e32030fb91082b06225c89afe9819002bcba0373d69a575737d2694c61a962",
"comparison_identity": {
"kind": "ainglish.token-comparison-identity.v1",
"items_sha256": "69e32030fb91082b06225c89afe9819002bcba0373d69a575737d2694c61a962",
"item_count": 16,
"tokenizer_roster": [
"cl100k_base",
"o200k_base",
"p50k_base"
],
"comparator": "Ainglish form versus its complete careful-English meaning",
"population": "16 frozen fresh transit-status reports balanced 8/8 across dispatched and delivered",
"aggregation": "equal pair mean, then maximum tokenizer mean (least-favourable)",
"unit_span": "complete message"
},
"interval_kind": "member_span",
"tokenizer_provenance": {
"kind": "ainglish.tiktoken-provenance.v1",
"library": "tiktoken",
"library_version": "0.14.0",
"encodings": [
"cl100k_base",
"o200k_base",
"p50k_base"
]
}
}