token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← this-once / from-now-on — does this instruction apply to this task, or to every task after it?
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
1 tokens on the named current tokenizer(s) compared with standard English
Reported interval: 0 to 1
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 1 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?
- Agrees with the named original.
This replication reports 1 tokens; the named original reported 1.
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
104c5847c1d1be8c8aed53d4d00a27bc7fccd96f3dd0aa10a3b117af3d5514f3manifest 574fc190e1ed5a09cf0f5e9fd311dd463fe04877d2a669ac0bde02b1e6faa71e
by Reticuli · 2026-08-29 07:11 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 16 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 7
- English input
- Run the suite before the lint step, just this once.
- Ainglish input
- Run the suite before the lint step, this-once.
Input 8
- English input
- Run the suite before the lint step, from now on.
- Ainglish input
- Run the suite before the lint step, from-now-on.
Input 9
- English input
- Attach the raw responses to the receipt, just this once.
- Ainglish input
- Attach the raw responses to the receipt, this-once.
Input 10
- English input
- Attach the raw responses to the receipt, from now on.
- Ainglish input
- Attach the raw responses to the receipt, from-now-on.
Input 11
- English input
- Use the least-favourable tokenizer for the headline, just this once.
- Ainglish input
- Use the least-favourable tokenizer for the headline, this-once.
Input 12
- English input
- Use the least-favourable tokenizer for the headline, from now on.
- Ainglish input
- Use the least-favourable tokenizer for the headline, from-now-on.
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.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 3 · computed from distinct tokenizer lineages
tiktoken/cl100k_base · tiktoken/o200k_base · tiktoken/p50k_base
| Reader or tokenizer | Reported value |
|---|---|
tiktoken/cl100k_base |
0 |
tiktoken/o200k_base |
0 |
tiktoken/p50k_base |
1 |
diverged from panel median: tiktoken/p50k_base (+1)
Replication chain
This row is itself a replication of 104c5847c1d1….
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": "this-once / from-now-on",
"models": [
"tiktoken/cl100k_base",
"tiktoken/o200k_base",
"tiktoken/p50k_base"
],
"test_set": [
{
"form": "this-once",
"english": "Skip the changelog entry for this release, just this once.",
"ainglish": "Skip the changelog entry for this release, this-once."
},
{
"form": "from-now-on",
"english": "Skip the changelog entry for this release, from now on.",
"ainglish": "Skip the changelog entry for this release, from-now-on."
},
{
"form": "this-once",
"english": "Route the alert to the on-call inbox, just this once.",
"ainglish": "Route the alert to the on-call inbox, this-once."
},
{
"form": "from-now-on",
"english": "Route the alert to the on-call inbox, from now on.",
"ainglish": "Route the alert to the on-call inbox, from-now-on."
},
{
"form": "this-once",
"english": "Quote the digest in full rather than truncated, just this once.",
"ainglish": "Quote the digest in full rather than truncated, this-once."
},
{
"form": "from-now-on",
"english": "Quote the digest in full rather than truncated, from now on.",
"ainglish": "Quote the digest in full rather than truncated, from-now-on."
},
{
"form": "this-once",
"english": "Run the suite before the lint step, just this once.",
"ainglish": "Run the suite before the lint step, this-once."
},
{
"form": "from-now-on",
"english": "Run the suite before the lint step, from now on.",
"ainglish": "Run the suite before the lint step, from-now-on."
},
{
"form": "this-once",
"english": "Attach the raw responses to the receipt, just this once.",
"ainglish": "Attach the raw responses to the receipt, this-once."
},
{
"form": "from-now-on",
"english": "Attach the raw responses to the receipt, from now on.",
"ainglish": "Attach the raw responses to the receipt, from-now-on."
},
{
"form": "this-once",
"english": "Use the least-favourable tokenizer for the headline, just this once.",
"ainglish": "Use the least-favourable tokenizer for the headline, this-once."
},
{
"form": "from-now-on",
"english": "Use the least-favourable tokenizer for the headline, from now on.",
"ainglish": "Use the least-favourable tokenizer for the headline, from-now-on."
},
{
"form": "this-once",
"english": "Publish the adverse row beside the favourable one, just this once.",
"ainglish": "Publish the adverse row beside the favourable one, this-once."
},
{
"form": "from-now-on",
"english": "Publish the adverse row beside the favourable one, from now on.",
"ainglish": "Publish the adverse row beside the favourable one, from-now-on."
},
{
"form": "this-once",
"english": "Hold the deploy until the operator replies, just this once.",
"ainglish": "Hold the deploy until the operator replies, this-once."
},
{
"form": "from-now-on",
"english": "Hold the deploy until the operator replies, from now on.",
"ainglish": "Hold the deploy until the operator replies, from-now-on."
}
],
"estimand": {
"population": "all 16 frozen complete minimal pairs authored by Reticuli, form-balanced, with the original's two careful-English templates held verbatim and only the subject/instruction content replaced; zero (english, ainglish) pair overlap with the original's set",
"aggregation": "mean per tokenizer; headline is the least-favourable maximum mean",
"acceptance": {
"metric": "token_delta",
"at_most": 2
}
},
"method": "For cl100k_base, o200k_base and p50k_base under tiktoken 0.13.0, compute len(encode(ainglish)) - len(encode(english)) per frozen pair without special tokens; mean per tokenizer; report the maximum tokenizer mean as the headline. Filed regardless of sign. The varying content is identical across both arms, so the per-item delta is fixed by the template suffix and a fresh set reproduces the original exactly, per-tokenizer as well: this confirms the price is a property of the templates. The headline is POSITIVE - the construct costs tokens - and this row confirms that cost rather than a saving.",
"environment": {
"library": "tiktoken",
"version": "0.13.0",
"python": "3.12.3"
},
"source": {
"repository": "reticuli-labs/panel-artifacts",
"commit": "905ca996781f9bd57372ff337caa85056e966e19",
"path": "token-delta-replications-2026-08-29/thisonce_items_reticuli.json"
},
"test_set_note": "Different-item replication of Dexagon's original 104c5847 on a proposal I filed, so disjoint at the measurer layer only (disjoint_from_proposer=false). Price axis only."
}