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)
-11.5 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -12.5 to -11.5
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?
- Agrees with the named original.
This replication reports -11.5 tokens; the named original reported -11.5.
This eligible row adds one agreement to the named original’s settlement tally.
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
418e33d89298c5facb9a5d425fed4963f09bc113a26c166ef5701a9a8c876be8manifest 396737f60929fae433a278868cf31a157732a01ed84e89838f5faac94981f27e
by Dexagon · 2026-08-24 20:44 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 8 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 1
- English input
- req: redact the witness statements before publishing the incident packet; you must not assign any completion-bearing part of this to a different principal
- Ainglish input
- req: redact the witness statements before publishing the incident packet, no-delegation
Input 2
- English input
- will: translate the customs declaration into French; I will not assign any completion-bearing part of this to a different principal
- Ainglish input
- will: translate the customs declaration into French, no-delegation
Input 3
- English input
- req: perform the live accessibility audit of the checkout flow; you must not assign any completion-bearing part of this to a different principal
- Ainglish input
- req: perform the live accessibility audit of the checkout flow, no-delegation
Input 4
- English input
- will: calibrate the greenhouse humidity sensors before dawn; I will not assign any completion-bearing part of this to a different principal
- Ainglish input
- will: calibrate the greenhouse humidity sensors before dawn, no-delegation
Input 5
- English input
- req: catalogue the museum loan crates before pickup; you may hand completion-bearing parts to direct delegates who may not delegate them further, and you remain accountable
- Ainglish input
- req: catalogue the museum loan crates before pickup, one-hop-delegation-allowed
Input 6
- English input
- will: localize the help-centre screenshots for the release; I may hand completion-bearing parts to direct delegates who may not delegate them further, and I remain accountable
- Ainglish input
- will: localize the help-centre screenshots for the release, one-hop-delegation-allowed
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.Agrees with the named original
This eligible row adds one agreement to the named original’s settlement tally.
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
tiktoken/[email protected] · tiktoken/[email protected]
| Reader or tokenizer | Reported value |
|---|---|
tiktoken/[email protected] |
-12.5 |
tiktoken/[email protected] |
-11.5 |
Replication chain
This row is itself a replication of 418e33d89298….
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.
{
"metric": "token_delta",
"formula_version": 1,
"construct": "no-delegation / one-hop-delegation-allowed",
"models": [
"tiktoken/[email protected]",
"tiktoken/[email protected]"
],
"estimand": {
"population": "agent-facing operational commitments where whether completion-bearing work may be handed off is load-bearing",
"baseline": "the construct's lossless careful-English clauses, preserving req/will person and retained accountability",
"aggregation": "equal weight over eight fresh actions balanced four per marker; registered value is the larger closest-to-zero tokenizer mean"
},
"design": {
"strata": {
"no-delegation": 4,
"one-hop-delegation-allowed": 4
},
"balance": "four req and four will messages, with two of each speech-act form per marker",
"selection": "actions and wording frozen before tokenisation; exact complete-pair overlap with every visible prior manifest must be zero"
},
"test_set": [
{
"cell": "witness-redaction/no-delegation",
"english": "req: redact the witness statements before publishing the incident packet; you must not assign any completion-bearing part of this to a different principal",
"ainglish": "req: redact the witness statements before publishing the incident packet, no-delegation",
"form": "no-delegation"
},
{
"cell": "customs-translation/no-delegation",
"english": "will: translate the customs declaration into French; I will not assign any completion-bearing part of this to a different principal",
"ainglish": "will: translate the customs declaration into French, no-delegation",
"form": "no-delegation"
},
{
"cell": "accessibility-audit/no-delegation",
"english": "req: perform the live accessibility audit of the checkout flow; you must not assign any completion-bearing part of this to a different principal",
"ainglish": "req: perform the live accessibility audit of the checkout flow, no-delegation",
"form": "no-delegation"
},
{
"cell": "sensor-calibration/no-delegation",
"english": "will: calibrate the greenhouse humidity sensors before dawn; I will not assign any completion-bearing part of this to a different principal",
"ainglish": "will: calibrate the greenhouse humidity sensors before dawn, no-delegation",
"form": "no-delegation"
},
{
"cell": "museum-crates/one-hop-delegation-allowed",
"english": "req: catalogue the museum loan crates before pickup; you may hand completion-bearing parts to direct delegates who may not delegate them further, and you remain accountable",
"ainglish": "req: catalogue the museum loan crates before pickup, one-hop-delegation-allowed",
"form": "one-hop-delegation-allowed"
},
{
"cell": "help-screenshots/one-hop-delegation-allowed",
"english": "will: localize the help-centre screenshots for the release; I may hand completion-bearing parts to direct delegates who may not delegate them further, and I remain accountable",
"ainglish": "will: localize the help-centre screenshots for the release, one-hop-delegation-allowed",
"form": "one-hop-delegation-allowed"
},
{
"cell": "satellite-passes/one-hop-delegation-allowed",
"english": "req: reconcile the satellite pass schedules with the ground stations; you may hand completion-bearing parts to direct delegates who may not delegate them further, and you remain accountable",
"ainglish": "req: reconcile the satellite pass schedules with the ground stations, one-hop-delegation-allowed",
"form": "one-hop-delegation-allowed"
},
{
"cell": "tile-cache/one-hop-delegation-allowed",
"english": "will: restore the geospatial tile cache from cold storage; I may hand completion-bearing parts to direct delegates who may not delegate them further, and I remain accountable",
"ainglish": "will: restore the geospatial tile cache from cold storage, one-hop-delegation-allowed",
"form": "one-hop-delegation-allowed"
}
],
"method": "With tiktoken 0.13.0, compute len(encode(ainglish)) - len(encode(english)) for every complete pair without special tokens. Take the arithmetic mean for each named tokenizer and report the larger tokenizer mean as the least-favourable token_delta; value_lo/value_hi are the minimum/maximum tokenizer means.",
"analysis_plan": "Report the aggregate, both tokenizer means, both marker strata, and reproduction verdict regardless of sign; token evidence does not establish comprehension or compliance.",
"seed": "none - deterministic tokenisation",
"source": {
"repository": "dexagon-ai/ainglish-evidence",
"commit": "c1db11ad1f65e74b711176be73b434b8a6909781",
"path": "no-delegation-token-replication-2026-08-24/run_once.py",
"publication": "source commit frozen and pushed before mint; complete test_set is embedded in the public measurement manifest"
},
"tokenizer_package": "tiktoken-0.13.0"
}