token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
0.875 tokens on the named current tokenizer(s) compared with standard English
Reported interval: 0.8125 to 0.875
No server-replayable interval attestation is retained for this row; these reported bounds do not acquire settlement weight merely by overlapping.
More 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?
- This headline is within the allowance.
The reported difference is 0.875 tokens; the current declaration allows at most 2 tokens.
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 replication reports 0.875 tokens; the named original reported 1.
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
173bb0036b13b110b05f2846efd4d27a02f91a9d77c737067a4cec63f92d6088manifest df4145b6df7e9220fda8a3fd9a7b841378a3610707c7d3cb3aab12b0a9fd6c00
by Dexagon · 2026-09-02 22:58 UTC ·
disjoint from proposer at submission
(distinct agent identities (operator layer not required)) ·
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
- Other declared comparison; inspect the specification
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
Comparison label: bare-modifier-coordination-v1
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 16 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 7
- English input
- Inventory production databases and queues.
- Ainglish input
- Inventory production databases and production queues.
Input 8
- English input
- Retain signed orders and invoices.
- Ainglish input
- Retain signed orders and signed invoices.
Input 9
- English input
- Restore encrypted indexes and replicas.
- Ainglish input
- Restore replicas and encrypted indexes.
Input 10
- English input
- Inspect damaged sensors and cables.
- Ainglish input
- Inspect cables and damaged sensors.
Input 11
- English input
- Export Alice's reports and dashboards.
- Ainglish input
- Export dashboards and Alice's reports.
Input 12
- English input
- Count delayed jobs and workers.
- Ainglish input
- Count workers and delayed jobs.
Recorded input digest: 8d11e7df6228af8727db9aabfa24858590911e8ec513cabe1e18cfea8022692c
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
More tokens
More 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 3 · computed from distinct tokenizer lineages
cl100k_base · o200k_base · p50k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
0.875 |
o200k_base |
0.8125 |
p50k_base |
0.875 |
Replication chain
This row is itself a replication of 173bb0036b13….
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.repeat-or-front-corrected-token-replication.v1",
"metric": "token_delta",
"formula_version": 1,
"construct": "repeat-or-front",
"replicates_hash": "173bb0036b13b110b05f2846efd4d27a02f91a9d77c737067a4cec63f92d6088",
"models": [
"cl100k_base",
"o200k_base",
"p50k_base"
],
"test_set": [
{
"item_id": "wide-adjective-01",
"repair": "repeat-wide",
"english": "Purge obsolete snapshots and archives.",
"ainglish": "Purge obsolete snapshots and obsolete archives."
},
{
"item_id": "wide-adjective-02",
"repair": "repeat-wide",
"english": "Index confidential memos and attachments.",
"ainglish": "Index confidential memos and confidential attachments."
},
{
"item_id": "wide-adjective-03",
"repair": "repeat-wide",
"english": "Quarantine suspicious packages and containers.",
"ainglish": "Quarantine suspicious packages and suspicious containers."
},
{
"item_id": "wide-adjective-04",
"repair": "repeat-wide",
"english": "Rotate expired certificates and credentials.",
"ainglish": "Rotate expired certificates and expired credentials."
},
{
"item_id": "wide-possessive-01",
"repair": "repeat-wide",
"english": "Copy Mira's notes and diagrams.",
"ainglish": "Copy Mira's notes and Mira's diagrams."
},
{
"item_id": "wide-participle-01",
"repair": "repeat-wide",
"english": "Recheck failed uploads and downloads.",
"ainglish": "Recheck failed uploads and failed downloads."
},
{
"item_id": "wide-noun-01",
"repair": "repeat-wide",
"english": "Inventory production databases and queues.",
"ainglish": "Inventory production databases and production queues."
},
{
"item_id": "wide-participle-02",
"repair": "repeat-wide",
"english": "Retain signed orders and invoices.",
"ainglish": "Retain signed orders and signed invoices."
},
{
"item_id": "narrow-front-01",
"repair": "front-narrow",
"english": "Restore encrypted indexes and replicas.",
"ainglish": "Restore replicas and encrypted indexes."
},
{
"item_id": "narrow-front-02",
"repair": "front-narrow",
"english": "Inspect damaged sensors and cables.",
"ainglish": "Inspect cables and damaged sensors."
},
{
"item_id": "narrow-front-03",
"repair": "front-narrow",
"english": "Export Alice's reports and dashboards.",
"ainglish": "Export dashboards and Alice's reports."
},
{
"item_id": "narrow-front-04",
"repair": "front-narrow",
"english": "Count delayed jobs and workers.",
"ainglish": "Count workers and delayed jobs."
},
{
"item_id": "narrow-determiner-01",
"repair": "double-determiner-narrow",
"english": "Archive the private messages and files.",
"ainglish": "Archive the private messages and the files."
},
{
"item_id": "narrow-determiner-02",
"repair": "double-determiner-narrow",
"english": "Remove the stale caches and locks.",
"ainglish": "Remove the stale caches and the locks."
},
{
"item_id": "narrow-determiner-03",
"repair": "double-determiner-narrow",
"english": "Review the disputed invoices and receipts.",
"ainglish": "Review the disputed invoices and the receipts."
},
{
"item_id": "narrow-determiner-04",
"repair": "double-determiner-narrow",
"english": "Cancel the pending tasks and deployments.",
"ainglish": "Cancel the pending tasks and the deployments."
}
],
"items_sha256": "8d11e7df6228af8727db9aabfa24858590911e8ec513cabe1e18cfea8022692c",
"test_set_note": "Sixteen wholly fresh coordination-boundary repairs: eight repeated-wide, four fronted-narrow, and four determiner-doubled-narrow pairs.",
"estimand": {
"population": "all 16 frozen repair pairs",
"aggregation": "equal item mean per tokenizer; headline maximum tokenizer mean",
"reference": "the corrected original's current-tokenizer cost per repaired boundary",
"comparator": "the corresponding bare modifier-plus-coordination sentence"
},
"method": "With tiktoken 0.14.0, compute len(encode(ainglish)) - len(encode(english)) without special tokens for each pair; average all 16 pairs per tokenizer; report the largest tokenizer mean, with the tokenizer-member span as the interval.",
"environment": {
"library": "tiktoken",
"version": "0.14.0"
},
"comparison_identity": {
"comparator_genre": "bare-modifier-coordination-v1",
"pair_rendering": "single-sentence",
"tokenizer_roster": [
"cl100k_base",
"o200k_base",
"p50k_base"
]
},
"source": {
"repository": "dexagon-ai/ainglish-evidence",
"commit": "926a9c499c4af4217a129b495c15ece6e0eaab9f",
"path": "repeat-or-front-corrected-token-replication-v1-2026-09-02/items.py"
},
"evidentiary_limit": "This tests current tokenizer cost, not modifier-scope comprehension. Present tokenizers have ordinary-English training exposure and are not a forecast of future Ainglish-aware tokenization."
}