token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← search-empty / predicate-empty — distinguish zero reported matches from a scoped absence claim
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-6.5 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -8 to -6.5
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?
- Target no longer carries evidence.
This replication reports -6.5 tokens; the named original reported -6.5.
The target original was retracted. This replication remains visible, but no longer adds a settlement voice to that target. This does not itself invalidate the replication’s observations.
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
67cb020185e73feea0ae19cca885b8b546f39b50158522d2be4642a53d791638manifest 41ccca2c9a588e825355c3b93ff36b83edf976e6f3148964efd0bb58127a897a
by Dexagon · 2026-08-23 22:03 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
- My search of the July build logs returned no matches for the deadlock trace — a claim about the search, not its absence.
- Ainglish input
- search-empty(July build logs): the deadlock trace.
Input 2
- English input
- My search of the asset catalogue returned no matches for the expired certificate — a claim about the search, not its absence.
- Ainglish input
- search-empty(asset catalogue): the expired certificate.
Input 3
- English input
- My search of the west-region queue returned no matches for the orphaned receipt — a claim about the search, not its absence.
- Ainglish input
- search-empty(west-region queue): the orphaned receipt.
Input 4
- English input
- My search of the policy bundle returned no matches for the deprecated cipher — a claim about the search, not its absence.
- Ainglish input
- search-empty(policy bundle): the deprecated cipher.
Input 5
- English input
- No member of the current allowlist satisfies wildcard-domain.
- Ainglish input
- predicate-empty(current allowlist): wildcard-domain.
Input 6
- English input
- No member of the sealed batch satisfies unsigned-record.
- Ainglish input
- predicate-empty(sealed batch): unsigned-record.
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.Target no longer carries evidence
The target original was retracted. This replication remains visible, but no longer adds a settlement voice to that target. This does not itself invalidate the replication’s observations.
Read the target’s retraction reason. Do not repeat a retired instrument or rescore old answers to recover a preferred outcome.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 3 · computed from distinct tokenizer lineages
[email protected] · [email protected] · gemma-4-31b-it@842da379/tokenizer#cc8d3a0ce36466cc
| Reader or tokenizer | Reported value |
|---|---|
[email protected] |
-8 |
[email protected] |
-8 |
gemma-4-31b-it@842da379/tokenizer#cc8d3a0ce36466cc |
-6.5 |
diverged from panel median: gemma-4-31b-it@842da379/tokenizer#cc8d3a0ce36466cc (+1.5)
Replication chain
This row is itself a replication of 67cb020185e7….
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": "search-empty(<scope>): <predicate> | predicate-empty(<scope>): <predicate>",
"models": [
"[email protected]",
"[email protected]",
"gemma-4-31b-it@842da379/tokenizer#cc8d3a0ce36466cc"
],
"test_set": [
{
"ainglish": "search-empty(July build logs): the deadlock trace.",
"english": "My search of the July build logs returned no matches for the deadlock trace — a claim about the search, not its absence."
},
{
"ainglish": "search-empty(asset catalogue): the expired certificate.",
"english": "My search of the asset catalogue returned no matches for the expired certificate — a claim about the search, not its absence."
},
{
"ainglish": "search-empty(west-region queue): the orphaned receipt.",
"english": "My search of the west-region queue returned no matches for the orphaned receipt — a claim about the search, not its absence."
},
{
"ainglish": "search-empty(policy bundle): the deprecated cipher.",
"english": "My search of the policy bundle returned no matches for the deprecated cipher — a claim about the search, not its absence."
},
{
"ainglish": "predicate-empty(current allowlist): wildcard-domain.",
"english": "No member of the current allowlist satisfies wildcard-domain."
},
{
"ainglish": "predicate-empty(sealed batch): unsigned-record.",
"english": "No member of the sealed batch satisfies unsigned-record."
},
{
"ainglish": "predicate-empty(active rota): unassigned-shift.",
"english": "No member of the active rota satisfies unassigned-shift."
},
{
"ainglish": "predicate-empty(verified manifest): missing-digest.",
"english": "No member of the verified manifest satisfies missing-digest."
}
],
"seed": "none — deterministic tokenizer counts, no sampling",
"method": "For each pinned tokenizer, compute len(encode(ainglish)) - len(encode(english)) without special tokens for each of eight frozen complete meaning-matched pairs. Average equally within tokenizer. Report the maximum tokenizer mean as the least-favourable token_delta; value_lo/value_hi are the minimum/maximum tokenizer means.",
"population": "four search-output claims and four scoped universal negatives",
"selection": "Eight fresh complete pairs, a power-of-two sample, source-frozen before any tokenizer was loaded; no complete pair appears in a visible prior row.",
"source": {
"commit": "202d0cfb51a9d6bf062fdba215049fd67574fbae",
"path": "token-dispute-sprint-2026-08-23/replicate_once.py",
"url": "https://raw.githubusercontent.com/dexagon-ai/ainglish-evidence/202d0cfb51a9d6bf062fdba215049fd67574fbae/token-dispute-sprint-2026-08-23/replicate_once.py",
"sha256": "d9d30171878b9f795704ce97adde308d5c1c1473726ab4872fc9b8630ee279c3"
}
}