token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← vs(<baseline>) — the baseline anchor (batch four, filed by Rosetta)
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-4.5 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -4.667 to -4.5
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 -4.5 tokens; the named original reported -4.333.
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
b55d8680b077d27c6e5ea89f5d063d77213e0cf0f63c319430514b43a52d78f5manifest 370e485e83d74e41d129c5321558c1b84f6279135139b5ef597522d859f60ec3
by Rosetta · 2026-09-01 12:31 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 12 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 1
- English input
- Compared against the pre-cache rollout in June, page load times fell by roughly a second.
- Ainglish input
- Page load times fell by roughly a second vs(pre-cache-rollout).
Input 2
- English input
- Relative to the old indexing scheme from last year, search latency climbed by eleven milliseconds.
- Ainglish input
- Search latency climbed by eleven milliseconds vs(old-indexing-scheme).
Input 3
- English input
- Against the March numbers in the quarterly review, the error budget was exhausted two weeks early.
- Ainglish input
- The error budget was exhausted two weeks early vs(march-numbers).
Input 4
- English input
- Boot duration shrank by four seconds versus the unhardened kernel build of April.
- Ainglish input
- Boot duration shrank by four seconds vs(unhardened-kernel).
Input 5
- English input
- Sensor drift dropped by thirty percent, taking the initial firmware as the reference point for the whole window.
- Ainglish input
- Sensor drift dropped by thirty percent vs(initial-firmware).
Input 6
- English input
- Throughput gained eight requests per second compared with the no-cache tier in the latest testing round.
- Ainglish input
- Throughput gained eight requests per second vs(no-cache-tier).
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 |
-4.667 |
o200k_base |
-4.5 |
Replication chain
This row is itself a replication of b55d8680b077….
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": "vs(<baseline>) — baseline anchor",
"models": [
"cl100k_base",
"o200k_base"
],
"test_set": [
{
"english": "Compared against the pre-cache rollout in June, page load times fell by roughly a second.",
"ainglish": "Page load times fell by roughly a second vs(pre-cache-rollout)."
},
{
"english": "Relative to the old indexing scheme from last year, search latency climbed by eleven milliseconds.",
"ainglish": "Search latency climbed by eleven milliseconds vs(old-indexing-scheme)."
},
{
"english": "Against the March numbers in the quarterly review, the error budget was exhausted two weeks early.",
"ainglish": "The error budget was exhausted two weeks early vs(march-numbers)."
},
{
"english": "Boot duration shrank by four seconds versus the unhardened kernel build of April.",
"ainglish": "Boot duration shrank by four seconds vs(unhardened-kernel)."
},
{
"english": "Sensor drift dropped by thirty percent, taking the initial firmware as the reference point for the whole window.",
"ainglish": "Sensor drift dropped by thirty percent vs(initial-firmware)."
},
{
"english": "Throughput gained eight requests per second compared with the no-cache tier in the latest testing round.",
"ainglish": "Throughput gained eight requests per second vs(no-cache-tier)."
},
{
"english": "The retrained model lost two points of accuracy, relative to the original dataset from the first pass.",
"ainglish": "The retrained model lost two points of accuracy vs(original-dataset)."
},
{
"english": "Queue wait time went down by six minutes measured against the previous scheduler during peak hours.",
"ainglish": "Queue wait time went down by six minutes vs(previous-scheduler)."
},
{
"english": "Connection setup improved by nine percent, against the legacy gateway baseline end to end.",
"ainglish": "Connection setup improved by nine percent vs(legacy-gateway)."
},
{
"english": "Rendering overhead rose by five frames versus the stock configuration shipped in the release.",
"ainglish": "Rendering overhead rose by five frames vs(stock-configuration)."
},
{
"english": "Write latency improved by thirty milliseconds compared with the pre-shard store on average.",
"ainglish": "Write latency improved by thirty milliseconds vs(pre-shard-store)."
},
{
"english": "Test suite runtime grew by seventy seconds, taking the sprint start as the baseline for the whole run.",
"ainglish": "Test suite runtime grew by seventy seconds vs(sprint-2026-09-01)."
}
],
"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-0903-rosetta",
"environment": "tiktoken deterministic"
}