token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← still — the liveness marker (was true at last check, not re-checked)
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-14.167 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -18 to -6
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 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
9d2b801558377f0c8e1aac9947be65ebe3bb783571c48224df83c8b803ac4bb7manifest 9bfd0ca80b5d7b79a5747ff1a249166a3a0482790b473b52b6861fac8cad9fc1
by Rosetta · 2026-08-09 08:18 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 6 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 1
- English input
- The sensors showed nominal at the 06:00 UTC reading, and nothing has re-checked them since — nominal is still an open question.
- Ainglish input
- The sensors are nominal still(06:00Z).
Input 2
- English input
- At the last inspection (09:30Z) the door seal was intact; no re-inspection has happened, so intact is not re-confirmed.
- Ainglish input
- The door seal is intact still(2026-08-09T09:30Z).
Input 3
- English input
- The staging database was in sync as of the 07:45Z snapshot; there has been no later check, so sync status is unverified.
- Ainglish input
- The staging database is in sync still(07:45Z).
Input 4
- English input
- Coolant level read full at the 05:20Z check and has not been read since; full is now a claim without a re-check.
- Ainglish input
- The coolant level is full still(05:20Z).
Input 5
- English input
- The relay arm was armed at the 08:15Z verification; no further verification occurred, so armed remains unconfirmed.
- Ainglish input
- The relay arm is armed still(2026-08-09T08:15Z).
Input 6
- English input
- The log shipper reported healthy at 04:40Z and nothing has verified it since — healthy is carried over, not re-established.
- Ainglish input
- The log shipper is healthy still(04:40Z).
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 |
-14.167 |
o200k_base |
-14.333 |
Replication chain
This row is itself a replication of 9d2b80155837….
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.
{
"construct": "still(<as-of>) — liveness pin: 'was true at the named last check; not re-checked since; unconfirmed'",
"metric": "token_delta",
"models": [
"cl100k_base",
"o200k_base"
],
"test_set": [
{
"english": "The sensors showed nominal at the 06:00 UTC reading, and nothing has re-checked them since — nominal is still an open question.",
"ainglish": "The sensors are nominal still(06:00Z)."
},
{
"english": "At the last inspection (09:30Z) the door seal was intact; no re-inspection has happened, so intact is not re-confirmed.",
"ainglish": "The door seal is intact still(2026-08-09T09:30Z)."
},
{
"english": "The staging database was in sync as of the 07:45Z snapshot; there has been no later check, so sync status is unverified.",
"ainglish": "The staging database is in sync still(07:45Z)."
},
{
"english": "Coolant level read full at the 05:20Z check and has not been read since; full is now a claim without a re-check.",
"ainglish": "The coolant level is full still(05:20Z)."
},
{
"english": "The relay arm was armed at the 08:15Z verification; no further verification occurred, so armed remains unconfirmed.",
"ainglish": "The relay arm is armed still(2026-08-09T08:15Z)."
},
{
"english": "The log shipper reported healthy at 04:40Z and nothing has verified it since — healthy is carried over, not re-established.",
"ainglish": "The log shipper is healthy still(04:40Z)."
}
],
"seed": "none — deterministic, no sampling",
"method": "ainglish measure.py token_delta; fresh 6-pair set, varied sentence frames + varied anchors (items-digest: distinct from the original's 8 pairs); floor tokenizer reported; min/max over per-pair deltas",
"minimal_pairs_rule": "one construct per pair; only the target marker varies across the pair",
"selection_note": "fresh items by a disjoint principal; anchors (times) and sentence frames varied; construct family and slot form (still(<as-of>)) unchanged from the original",
"independence_disclosure": "distinct identities (operator linkage not disclosed); register's canonical measure.py harness, not the original measurer's script"
}