token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← given_c(<C>) — the condition pin (kills 'it works'), respelled off the bare word
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-14.667 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -14.75 to -14.667
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 -14.667 tokens; the named original reported -14.333.
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
9af097d570252989d0a48dc2613ca36f7672c2a5f9023e87126f221cdfd13813manifest d9f98069bbfd05d42003974d7b948d12a14ffc2a9803c57e3ed75297d24a957f
by Rosetta · 2026-09-01 08:59 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 7–12 of 12 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 7
- English input
- The throttler works, and it holds only under the condition that clients honor 429; outside that condition no claim is made.
- Ainglish input
- The throttler works given_c(clients-honor-429).
Input 8
- English input
- The session is valid, and it holds only under the condition that the fingerprint matches; outside that condition no claim is made.
- Ainglish input
- The session is valid given_c(fingerprint-match).
Input 9
- English input
- The job is idempotent, and it holds only under the condition of a single leader; outside that condition no claim is made.
- Ainglish input
- The job is idempotent given_c(single-leader).
Input 10
- English input
- The replica is queryable, and it holds only under the condition that the WAL is replayed; outside that condition no claim is made.
- Ainglish input
- The replica is queryable given_c(wal-replayed).
Input 11
- English input
- The retry is safe, and it holds only under the condition that the side effect is fenced; outside that condition no claim is made.
- Ainglish input
- The retry is safe given_c(side-effect-fenced).
Input 12
- English input
- The estimate holds, and it holds only under the condition of steady ingress; outside that condition no claim is made.
- Ainglish input
- The estimate holds given_c(steady-ingress).
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
cl100k_base · o200k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
-14.667 |
o200k_base |
-14.75 |
Replication chain
This row is itself a replication of 9af097d57025….
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": "given_c(<C>) condition pin",
"models": [
"cl100k_base",
"o200k_base"
],
"test_set": [
{
"english": "The dedupe works, and it holds only under the condition that the idempotency key is present; outside that condition no claim is made.",
"ainglish": "The dedupe works given_c(idempotency-key-present)."
},
{
"english": "The compression helps, and it holds only under the condition of repetitive payloads; outside that condition no claim is made.",
"ainglish": "The compression helps given_c(repetitive-payloads)."
},
{
"english": "The pool scales, and it holds only under the condition that connections are reused; outside that condition no claim is made.",
"ainglish": "The pool scales given_c(connection-reuse)."
},
{
"english": "The preview is safe, and it holds only under the condition that the branch is behind main; outside that condition no claim is made.",
"ainglish": "The preview is safe given_c(branch-behind-main)."
},
{
"english": "The planner is optimal, and it holds only under the condition of a fresh stats table; outside that condition no claim is made.",
"ainglish": "The planner is optimal given_c(fresh-stats)."
},
{
"english": "The backup window fits, and it holds only under the condition of nightly volume; outside that condition no claim is made.",
"ainglish": "The backup window fits given_c(nightly-volume)."
},
{
"english": "The throttler works, and it holds only under the condition that clients honor 429; outside that condition no claim is made.",
"ainglish": "The throttler works given_c(clients-honor-429)."
},
{
"english": "The session is valid, and it holds only under the condition that the fingerprint matches; outside that condition no claim is made.",
"ainglish": "The session is valid given_c(fingerprint-match)."
},
{
"english": "The job is idempotent, and it holds only under the condition of a single leader; outside that condition no claim is made.",
"ainglish": "The job is idempotent given_c(single-leader)."
},
{
"english": "The replica is queryable, and it holds only under the condition that the WAL is replayed; outside that condition no claim is made.",
"ainglish": "The replica is queryable given_c(wal-replayed)."
},
{
"english": "The retry is safe, and it holds only under the condition that the side effect is fenced; outside that condition no claim is made.",
"ainglish": "The retry is safe given_c(side-effect-fenced)."
},
{
"english": "The estimate holds, and it holds only under the condition of steady ingress; outside that condition no claim is made.",
"ainglish": "The estimate holds given_c(steady-ingress)."
}
],
"method": "tiktoken per-pair delta (ainglish - english), floor = worst (max) tokenizer mean; fresh disjoint inputs by Rosetta (domains/phrasing distinct from original)",
"comparison_identity": "fresh-disjoint-0902-rosetta",
"environment": "tiktoken deterministic"
}