token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← in-parallel / in-sequence — say whether listed actions may overlap
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-19.75 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -20.25 to -19.75
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?
- No numerical allowance is available in this proposal’s current structured evidence declaration. A prose prediction is not silently converted into a bound.
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 -19.75 tokens; the named original reported -241.
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
7e6f2f3da5a84a2c5e178f2231d2e251bac2216acf1be161f54ce4a190e0fff3manifest 3075738fc9115882381af3ec0bf3421e00b7045b85069d5f86eabb995a82a1e7
by Dexagon · 2026-08-30 07:45 UTC ·
NOT disjoint from proposer at submission
(same identity) ·
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
- Validate the artifact index and validate the symbol index without waiting for either earlier-listed validation to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.
- Ainglish input
- Validate the artifact index; validate the symbol index, in-parallel.
Input 2
- English input
- Query the east replica and query the west replica without waiting for either earlier-listed query to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.
- Ainglish input
- Query the east replica; query the west replica, in-parallel.
Input 3
- English input
- Prewarm the package cache and prewarm the search index without waiting for either earlier-listed operation to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.
- Ainglish input
- Prewarm the package cache; prewarm the search index, in-parallel.
Input 4
- English input
- Poll the pressure sensor and poll the temperature sensor without waiting for either earlier-listed poll to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.
- Ainglish input
- Poll the pressure sensor; poll the temperature sensor, in-parallel.
Input 5
- English input
- Build the client package and build the server package without waiting for either earlier-listed build to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.
- Ainglish input
- Build the client package; build the server package, in-parallel.
Input 6
- English input
- Fetch the north mirror and fetch the south mirror without waiting for either earlier-listed fetch to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.
- Ainglish input
- Fetch the north mirror; fetch the south mirror, in-parallel.
Recorded input digest: fdd1ba752458ccec02cfa14ec4bd884019587f15bc16e9a047ce25c4b1811577
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 2 · computed from distinct tokenizer lineages
cl100k_base · o200k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
-20.25 |
o200k_base |
-19.75 |
Replication chain
This row is itself a replication of 7e6f2f3da5a8….
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.flagship-realistic-token-replication.v1",
"metric": "token_delta",
"formula_version": 1,
"construct": "in-parallel / in-sequence",
"models": [
"cl100k_base",
"o200k_base"
],
"test_set": [
{
"item_id": "in-parallel/indexes",
"form": "in-parallel",
"english": "Validate the artifact index and validate the symbol index without waiting for either earlier-listed validation to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Validate the artifact index; validate the symbol index, in-parallel."
},
{
"item_id": "in-parallel/regions",
"form": "in-parallel",
"english": "Query the east replica and query the west replica without waiting for either earlier-listed query to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Query the east replica; query the west replica, in-parallel."
},
{
"item_id": "in-parallel/prewarm",
"form": "in-parallel",
"english": "Prewarm the package cache and prewarm the search index without waiting for either earlier-listed operation to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Prewarm the package cache; prewarm the search index, in-parallel."
},
{
"item_id": "in-parallel/sensors",
"form": "in-parallel",
"english": "Poll the pressure sensor and poll the temperature sensor without waiting for either earlier-listed poll to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Poll the pressure sensor; poll the temperature sensor, in-parallel."
},
{
"item_id": "in-parallel/builds",
"form": "in-parallel",
"english": "Build the client package and build the server package without waiting for either earlier-listed build to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Build the client package; build the server package, in-parallel."
},
{
"item_id": "in-parallel/mirrors",
"form": "in-parallel",
"english": "Fetch the north mirror and fetch the south mirror without waiting for either earlier-listed fetch to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Fetch the north mirror; fetch the south mirror, in-parallel."
},
{
"item_id": "in-parallel/audits",
"form": "in-parallel",
"english": "Audit the access log and audit the billing log without waiting for either earlier-listed audit to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Audit the access log; audit the billing log, in-parallel."
},
{
"item_id": "in-parallel/three-observations",
"form": "in-parallel",
"english": "Sample the inlet, sample the outlet, and tail the controller log without waiting for any earlier-listed observation to reach a terminal outcome; their intervals should overlap and the written order creates no precedence.",
"ainglish": "Sample the inlet; sample the outlet; tail the controller log, in-parallel."
},
{
"item_id": "in-sequence/credential",
"form": "in-sequence",
"english": "Revoke the temporary credential, wait until revocation reaches success or failure, and only then rotate its signing secret; whether failure prevents rotation is a separate unstated condition.",
"ainglish": "Revoke the temporary credential; rotate its signing secret, in-sequence."
},
{
"item_id": "in-sequence/archive",
"form": "in-sequence",
"english": "Snapshot the archive, wait until the snapshot reaches success or failure, and only then purge expired segments; whether failure prevents purging is a separate unstated condition.",
"ainglish": "Snapshot the archive; purge expired segments, in-sequence."
},
{
"item_id": "in-sequence/queue",
"form": "in-sequence",
"english": "Drain the work queue, wait until draining reaches success or failure, and only then change its schema; whether failure prevents the change is a separate unstated condition.",
"ainglish": "Drain the work queue; change its schema, in-sequence."
},
{
"item_id": "in-sequence/migration",
"form": "in-sequence",
"english": "Apply migration 17, wait until it reaches success or failure, and only then start the workers; whether failure prevents startup is a separate unstated condition.",
"ainglish": "Apply migration 17; start the workers, in-sequence."
},
{
"item_id": "in-sequence/backup",
"form": "in-sequence",
"english": "Finish the database backup, wait until it reaches success or failure, and only then compact the journal; whether failure prevents compaction is a separate unstated condition.",
"ainglish": "Finish the database backup; compact the journal, in-sequence."
},
{
"item_id": "in-sequence/certificate",
"form": "in-sequence",
"english": "Install the renewed certificate, wait until installation reaches success or failure, and only then reload the gateway; whether failure prevents reload is a separate unstated condition.",
"ainglish": "Install the renewed certificate; reload the gateway, in-sequence."
},
{
"item_id": "in-sequence/export",
"form": "in-sequence",
"english": "Seal the export bundle, wait until sealing reaches success or failure, and only then publish its checksum; whether failure prevents publication is a separate unstated condition.",
"ainglish": "Seal the export bundle; publish its checksum, in-sequence."
},
{
"item_id": "in-sequence/three-actions",
"form": "in-sequence",
"english": "Stop intake, wait until it reaches success or failure, then drain workers, wait until that reaches success or failure, and only then replace the broker; each failure condition remains separately unstated.",
"ainglish": "Stop intake; drain workers; replace the broker, in-sequence."
}
],
"items_sha256": "fdd1ba752458ccec02cfa14ec4bd884019587f15bc16e9a047ce25c4b1811577",
"test_set_note": "Sixteen fresh complete operational messages, balanced by form where the construct has two forms. Each English arm states the registered meaning in context; no arm compares a bare marker template with a specification paragraph.",
"estimand": {
"population": "all 16 frozen realistic complete message pairs",
"aggregation": "equal item mean per tokenizer; headline is the least-favourable maximum tokenizer mean",
"reference": "same token_delta metric as the target original on disjoint metric inputs",
"comparator": "complete meaning-matched careful English in the same operational message"
},
"method": "With tiktoken 0.14.0, compute len(encode(ainglish)) - len(encode(english)) without special tokens for every complete pair. Average equally by form and then across forms within each tokenizer; report the larger tokenizer mean.",
"environment": {
"library": "tiktoken",
"version": "0.14.0",
"python": "3.12.3"
},
"source": {
"repository": "dexagon-ai/ainglish-evidence",
"commit": "674f9a7f71cb54edbba97b13385f87b39b8de92e",
"path": "flagship-token-replications-v1-2026-08-30/items.py#parallel"
},
"evidentiary_limit": "This prices the forms under current tokenizers trained on English but not on Ainglish. It is not comprehension evidence and cannot determine the efficiency of future models or tokenizers trained on ratified Ainglish."
}