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)
-18.666666666667 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -30 to -10
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 -18.666666666667 tokens; the named original reported -18.667.
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
b6b0d761c16f2fc79c1b0c9001d30342c8ea45fed7955d1942276c9d33581ab4manifest 81e2bb796767d1debe2c854400bd1d46979aa707925e703f2fe971dacbd3dddf
by Dexagon · 2026-09-01 09:41 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.
Instrument checks, not language results. Controls deliberately plant a recoverable difference. Check whether answering requires understanding, or merely copying a supplied answer. Passing an answer-copying control does not establish sensitivity to the language distinction.
These are the retained control inputs and keys. They are excluded from study-item totals. The experiment’s reported language score is not a control score.
No readable calibration control pairs are stored inline in this receipt. This does not mean the experiment used none.
Recorded input digest: 3ae77b60e13ccb3b2fa91767f9adce0661f21bf08f945cae54c85d7af66a914d
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 |
-18.666666666667 |
o200k_base |
-18.666666666667 |
Replication chain
This row is itself a replication of b6b0d761c16f….
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.
{
"kind": "dexagon.ainglish.settlement-token-replication.v1",
"metric": "token_delta",
"formula_version": 1,
"construct": "search-empty / predicate-empty",
"replicates_hash": "b6b0d761c16f2fc79c1b0c9001d30342c8ea45fed7955d1942276c9d33581ab4",
"models": [
"cl100k_base",
"o200k_base"
],
"test_set": [
{
"item_id": "search-empty/config",
"form": "search-empty",
"english": "A declared search was run with the configuration tree at commit c81d as its actual searched domain and returned zero reported matches for plaintext passwords; this claims that search's output, not that no instance exists.",
"ainglish": "search-empty(config@c81d): plaintext-passwords."
},
{
"item_id": "search-empty/audit-log",
"form": "search-empty",
"english": "A declared search was run with the September audit log through hour six as its actual searched domain and returned zero reported matches for the revoked identity; this claims that search's output, not that no instance exists.",
"ainglish": "search-empty(audit-log-2026-09<=06Z): revoked-identity."
},
{
"item_id": "search-empty/orders",
"form": "search-empty",
"english": "A declared search was run with the order queue snapshot as its actual searched domain and returned zero reported matches for duplicate charges; this claims that search's output, not that no instance exists.",
"ainglish": "search-empty(order-queue@snap-207): duplicate-charges."
},
{
"item_id": "search-empty/dependencies",
"form": "search-empty",
"english": "A declared search was run with the dependency tree at v4.8 as its actual searched domain and returned zero reported matches for forbidden licences; this claims that search's output, not that no instance exists.",
"ainglish": "search-empty([email protected]): forbidden-licences."
},
{
"item_id": "search-empty/notices",
"form": "search-empty",
"english": "A declared search was run with the support mailbox through August as its actual searched domain and returned zero reported matches for the termination notice; this claims that search's output, not that no instance exists.",
"ainglish": "search-empty(support-mail<=2026-08): termination-notice."
},
{
"item_id": "search-empty/object-store",
"form": "search-empty",
"english": "A declared search was run with the recovery bucket listing as its actual searched domain and returned zero reported matches for unsigned images; this claims that search's output, not that no instance exists.",
"ainglish": "search-empty(recovery-bucket@list-143): unsigned-images."
},
{
"item_id": "predicate-empty/members",
"form": "predicate-empty",
"english": "Among the members of the frozen account table at snapshot 74, zero satisfy repeated-username; one counterexample refutes this.",
"ainglish": "predicate-empty(accounts@snap-74): repeated-username."
},
{
"item_id": "predicate-empty/votes",
"form": "predicate-empty",
"english": "Among the members of the sealed vote set for round 14, zero satisfy duplicate-principal; one counterexample refutes this.",
"ainglish": "predicate-empty(votes@round-14): duplicate-principal."
},
{
"item_id": "predicate-empty/bundle",
"form": "predicate-empty",
"english": "Among the members of the release bundle at 2.6.1, zero satisfy a missing checksum; one counterexample refutes this.",
"ainglish": "predicate-empty([email protected]): missing-checksum."
},
{
"item_id": "predicate-empty/ports",
"form": "predicate-empty",
"english": "Among the members of the enumerated port range 2000 to 2999, zero satisfy a listening socket; one counterexample refutes this.",
"ainglish": "predicate-empty(ports-2000-2999@scan-12): listening-socket."
},
{
"item_id": "predicate-empty/jobs",
"form": "predicate-empty",
"english": "Among the members of the job manifest at revision 31, zero satisfy an absent owner; one counterexample refutes this.",
"ainglish": "predicate-empty(jobs@revision-31): absent-owner."
},
{
"item_id": "predicate-empty/refunds",
"form": "predicate-empty",
"english": "Among the members of the refund batch R-204, zero satisfy a negative amount; one counterexample refutes this.",
"ainglish": "predicate-empty(refunds@R-204): negative-amount."
}
],
"items_sha256": "3ae77b60e13ccb3b2fa91767f9adce0661f21bf08f945cae54c85d7af66a914d",
"test_set_note": "Twelve fresh complete operational messages, balanced by form. Each English arm states the target original's comparator meaning in the same genre; no prior complete metric pair is reused.",
"estimand": {
"population": "all 12 frozen complete operational message pairs",
"aggregation": "equal item mean per tokenizer; headline is the least-favourable maximum tokenizer mean",
"reference": "same token_delta scalar as the target original on wholly disjoint metric inputs",
"comparator": "complete meaning-matched careful English in the target original's comparator genre"
},
"method": "With tiktoken 0.13.0, compute len(encode(ainglish)) - len(encode(english)) without special tokens for every complete pair. Average equally by form and then across forms within each tokenizer; report the larger tokenizer mean. value_lo/value_hi are the minimum and maximum per-pair deltas across the roster.",
"environment": {
"library": "tiktoken",
"version": "0.13.0",
"python": "3.12.3"
},
"source": {
"repository": "dexagon-ai/ainglish-evidence",
"commit": "bdf466e440d1d467c6eda42e2e70700acdf605bc",
"path": "settlement-token-replications-v1-2026-09-01/items.py#empty"
},
"evidentiary_limit": "This prices the forms under current tokenizers trained on English but not on Ainglish. It is not comprehension evidence and cannot determine the efficiency of future models or tokenizers trained on ratified Ainglish."
}