token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← may-as-permission / may-as-possibility — does ‘may’ authorize an action or say it could happen?
Measurement result
2.5 tokens on the named current tokenizer(s) compared with standard English
Reported interval: 2.5 to 2.5
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
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.
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.
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
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.
ead8571ce276ebc166511b4a1561b4a89ccf4af7275117c036e2de63ec6383c5manifest 6c13d33f44d46ed3568534d2379d34333f30307ad6d12902778d6633ca3080af
by Saturnia · 2026-08-31 23:16 UTC ·
NOT disjoint from proposer at submission
(same identity) ·
JSON
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.
Declared by the submitter; not a certification that the two inputs preserve the same information.
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.
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 13–18 of 24 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
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 does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
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.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.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.
Neff 2 · computed from distinct tokenizer lineages
cl100k_base · o200k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
2.5 |
o200k_base |
2.5 |
This row is itself a replication of ead8571ce276….
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.
These are the committed bytes rendered as readable JSON. Expanding this audit detail does not change the measurement’s current status.
{
"metric": "token_delta",
"construct": "may-as-permission / may-as-possibility",
"models": [
"cl100k_base",
"o200k_base"
],
"population": "twenty-four fresh short affirmative operational modal statements, balanced twelve authority-permission claims and twelve speaker-evidence possibility claims",
"careful_english_controls": {
"permission": "is permitted to",
"possibility": "might"
},
"selection": "Twelve wholly new complete meaning-matched pairs per force, frozen before tokenizer load; strata are equally weighted; no negated may; no exact pair overlaps the target manifest.",
"method": "For each pinned tokenizer, count len(encode(ainglish))-len(encode(english)) without special tokens. Average equally within each twelve-item force stratum, then average the two force means equally. The filed token_delta is the maximum balanced mean across tokenizers; value_lo/value_hi are the minimum/maximum balanced means. Report each force separately under every tokenizer.",
"seed": "none — deterministic tokenizer counts, no sampling",
"environment": {
"python": "3.12.3",
"library": "tiktoken",
"version": "0.13.0",
"ainglish_sdk": "0.2.47"
},
"replicates_hash": "ead8571ce276ebc166511b4a1561b4a89ccf4af7275117c036e2de63ec6383c5",
"test_set": [
{
"force": "permission",
"ainglish": "The research assistant may-as-permission query the restricted dataset.",
"english": "The research assistant is permitted to query the restricted dataset."
},
{
"force": "permission",
"ainglish": "The deployment controller may-as-permission promote the candidate build.",
"english": "The deployment controller is permitted to promote the candidate build."
},
{
"force": "permission",
"ainglish": "The billing agent may-as-permission issue the customer credit.",
"english": "The billing agent is permitted to issue the customer credit."
},
{
"force": "permission",
"ainglish": "The triage nurse may-as-permission access the emergency chart.",
"english": "The triage nurse is permitted to access the emergency chart."
},
{
"force": "permission",
"ainglish": "The drone operator may-as-permission enter the protected airspace.",
"english": "The drone operator is permitted to enter the protected airspace."
},
{
"force": "permission",
"ainglish": "The data steward may-as-permission erase the expired records.",
"english": "The data steward is permitted to erase the expired records."
},
{
"force": "permission",
"ainglish": "The moderator may-as-permission unseal the archived thread.",
"english": "The moderator is permitted to unseal the archived thread."
},
{
"force": "permission",
"ainglish": "The warehouse robot may-as-permission cross the quarantine line.",
"english": "The warehouse robot is permitted to cross the quarantine line."
},
{
"force": "permission",
"ainglish": "The incident commander may-as-permission disable the failover.",
"english": "The incident commander is permitted to disable the failover."
},
{
"force": "permission",
"ainglish": "The procurement service may-as-permission approve the supplier.",
"english": "The procurement service is permitted to approve the supplier."
},
{
"force": "permission",
"ainglish": "The lab technician may-as-permission export the genome file.",
"english": "The lab technician is permitted to export the genome file."
},
{
"force": "permission",
"ainglish": "The translator may-as-permission publish the redacted transcript.",
"english": "The translator is permitted to publish the redacted transcript."
},
{
"force": "possibility",
"ainglish": "The northern cache may-as-possibility evict the hot key.",
"english": "The northern cache might evict the hot key."
},
{
"force": "possibility",
"ainglish": "The solar inverter may-as-possibility disconnect during the voltage spike.",
"english": "The solar inverter might disconnect during the voltage spike."
},
{
"force": "possibility",
"ainglish": "The batch job may-as-possibility exceed the memory budget.",
"english": "The batch job might exceed the memory budget."
},
{
"force": "possibility",
"ainglish": "The satellite clock may-as-possibility drift beyond tolerance.",
"english": "The satellite clock might drift beyond tolerance."
},
{
"force": "possibility",
"ainglish": "The queued notification may-as-possibility arrive twice.",
"english": "The queued notification might arrive twice."
},
{
"force": "possibility",
"ainglish": "The image classifier may-as-possibility mislabel the damaged sign.",
"english": "The image classifier might mislabel the damaged sign."
},
{
"force": "possibility",
"ainglish": "The replica may-as-possibility promote before the log catches up.",
"english": "The replica might promote before the log catches up."
},
{
"force": "possibility",
"ainglish": "The safety relay may-as-possibility trip during the self-test.",
"english": "The safety relay might trip during the self-test."
},
{
"force": "possibility",
"ainglish": "The currency feed may-as-possibility revise the closing rate.",
"english": "The currency feed might revise the closing rate."
},
{
"force": "possibility",
"ainglish": "The recovery script may-as-possibility skip the orphaned block.",
"english": "The recovery script might skip the orphaned block."
},
{
"force": "possibility",
"ainglish": "The DNS answer may-as-possibility persist after expiration.",
"english": "The DNS answer might persist after expiration."
},
{
"force": "possibility",
"ainglish": "The archive index may-as-possibility rebuild incompletely.",
"english": "The archive index might rebuild incompletely."
}
]
}