token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← unless — the plain-English falsifier (claim tag in words)
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-15.417 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -16.417 to -15.417
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 -15.417 tokens; the named original reported -15.833.
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
8b019968385012f2826195cae0eebaa1cebf3f9e71d448dc8e07138a1fb44ddcmanifest 88c89323a60b35f5c29130665726b29a0a63f9072e906fcda81a630399f49505
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 snapshot restored; what would refute this is a checksum mismatch, and that falsifier is part of the claim.
- Ainglish input
- The snapshot restored unless(checksum-mismatch).
Input 8
- English input
- The quota was applied; what would refute this is a usage overage, and that falsifier is part of the claim.
- Ainglish input
- The quota was applied unless(usage-overage).
Input 9
- English input
- The token expired correctly; what would refute this is a late acceptance, and that falsifier is part of the claim.
- Ainglish input
- The token expired correctly unless(late-acceptance).
Input 10
- English input
- The rollout completed; what would refute this is a stuck pod, and that falsifier is part of the claim.
- Ainglish input
- The rollout completed unless(stuck-pod).
Input 11
- English input
- The audit trail is complete; what would refute this is a gap in the sequence, and that falsifier is part of the claim.
- Ainglish input
- The audit trail is complete unless(sequence-gap).
Input 12
- English input
- The retry budget held; what would refute this is an exhausted bucket, and that falsifier is part of the claim.
- Ainglish input
- The retry budget held unless(exhausted-bucket).
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 |
-15.417 |
o200k_base |
-16.417 |
Replication chain
This row is itself a replication of 8b0199683850….
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": "unless(<F>) plain-English falsifier",
"models": [
"cl100k_base",
"o200k_base"
],
"test_set": [
{
"english": "The ETL pipeline finished; what would refute this is a missing partition in the target table, and that falsifier is part of the claim.",
"ainglish": "The ETL pipeline finished unless(missing-partition)."
},
{
"english": "The webhook was delivered; what would refute this is a 5xx in the delivery log, and that falsifier is part of the claim.",
"ainglish": "The webhook was delivered unless(delivery-5xx)."
},
{
"english": "The search index is current; what would refute this is a stale shard, and that falsifier is part of the claim.",
"ainglish": "The search index is current unless(stale-shard)."
},
{
"english": "The secrets were rotated; what would refute this is an old key in the vault, and that falsifier is part of the claim.",
"ainglish": "The secrets were rotated unless(old-vault-key)."
},
{
"english": "The DB is consistent; what would refute this is a split-brain marker, and that falsifier is part of the claim.",
"ainglish": "The DB is consistent unless(split-brain-marker)."
},
{
"english": "The canary is healthy; what would refute this is a p95 breach, and that falsifier is part of the claim.",
"ainglish": "The canary is healthy unless(p95-breach)."
},
{
"english": "The snapshot restored; what would refute this is a checksum mismatch, and that falsifier is part of the claim.",
"ainglish": "The snapshot restored unless(checksum-mismatch)."
},
{
"english": "The quota was applied; what would refute this is a usage overage, and that falsifier is part of the claim.",
"ainglish": "The quota was applied unless(usage-overage)."
},
{
"english": "The token expired correctly; what would refute this is a late acceptance, and that falsifier is part of the claim.",
"ainglish": "The token expired correctly unless(late-acceptance)."
},
{
"english": "The rollout completed; what would refute this is a stuck pod, and that falsifier is part of the claim.",
"ainglish": "The rollout completed unless(stuck-pod)."
},
{
"english": "The audit trail is complete; what would refute this is a gap in the sequence, and that falsifier is part of the claim.",
"ainglish": "The audit trail is complete unless(sequence-gap)."
},
{
"english": "The retry budget held; what would refute this is an exhausted bucket, and that falsifier is part of the claim.",
"ainglish": "The retry budget held unless(exhausted-bucket)."
}
],
"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"
}