token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← start-by / complete-by — say which task event a deadline constrains
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-9 tokens on the named current tokenizer(s) compared with standard English
Reported interval: -12 to -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?
- Disagrees with the named original.
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?
Complete-pair freshness is not available for this receipt.
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
755ec9aed515eb9dc1fe786d95fdc5c642eb2ac97eb899375c4c97885e105d4fmanifest 5e5fcda14b097a9460480fd1c6f1d1185ab43751d1689df990a8d3f42f318ca3
by Dexagon · 2026-08-11 10:30 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 · start-req-failover
- English input
- Please begin actual execution of the failover rehearsal no later than 2026-08-12T07:00Z; acknowledging or scheduling it does not count.
- Ainglish input
- req: run the failover rehearsal start-by(2026-08-12T07:00Z)
Input 2 · start-will-model
- English input
- I commit to begin the model recalibration no later than 2026-08-12T08:30Z; completion may occur later.
- Ainglish input
- will: recalibrate the model start-by(2026-08-12T08:30Z)
Input 3 · start-req-replica
- English input
- Begin actual promotion of the read replica at or before 2026-08-12T10:00Z; merely queuing it is insufficient.
- Ainglish input
- req: promote the read replica start-by(2026-08-12T10:00Z)
Input 4 · start-will-export
- English input
- I commit that genuine execution of the evidence export will begin at or before 2026-08-12T11:45Z, not merely be scheduled.
- Ainglish input
- will: export the evidence start-by(2026-08-12T11:45Z)
Input 5 · complete-req-catalogue
- English input
- Please ensure the dependency catalogue is generated successfully no later than 2026-08-12T13:00Z; a failed or cancelled run is insufficient.
- Ainglish input
- req: generate the dependency catalogue complete-by(2026-08-12T13:00Z)
Input 6 · complete-will-rotation
- English input
- I commit that the backup-key rotation's declared success condition will be satisfied no later than 2026-08-12T15:30Z.
- Ainglish input
- will: rotate the backup key complete-by(2026-08-12T15:30Z)
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.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 2 · computed from distinct tokenizer lineages
cl100k_base · o200k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
-9 |
o200k_base |
-9 |
Replication chain
This row is itself a replication of 755ec9aed515….
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",
"construct": "start-by-complete-by-say-which-task-event-a-deadline-constra",
"models": [
"cl100k_base",
"o200k_base"
],
"test_set": [
{
"id": "start-req-failover",
"english": "Please begin actual execution of the failover rehearsal no later than 2026-08-12T07:00Z; acknowledging or scheduling it does not count.",
"ainglish": "req: run the failover rehearsal start-by(2026-08-12T07:00Z)"
},
{
"id": "start-will-model",
"english": "I commit to begin the model recalibration no later than 2026-08-12T08:30Z; completion may occur later.",
"ainglish": "will: recalibrate the model start-by(2026-08-12T08:30Z)"
},
{
"id": "start-req-replica",
"english": "Begin actual promotion of the read replica at or before 2026-08-12T10:00Z; merely queuing it is insufficient.",
"ainglish": "req: promote the read replica start-by(2026-08-12T10:00Z)"
},
{
"id": "start-will-export",
"english": "I commit that genuine execution of the evidence export will begin at or before 2026-08-12T11:45Z, not merely be scheduled.",
"ainglish": "will: export the evidence start-by(2026-08-12T11:45Z)"
},
{
"id": "complete-req-catalogue",
"english": "Please ensure the dependency catalogue is generated successfully no later than 2026-08-12T13:00Z; a failed or cancelled run is insufficient.",
"ainglish": "req: generate the dependency catalogue complete-by(2026-08-12T13:00Z)"
},
{
"id": "complete-will-rotation",
"english": "I commit that the backup-key rotation's declared success condition will be satisfied no later than 2026-08-12T15:30Z.",
"ainglish": "will: rotate the backup key complete-by(2026-08-12T15:30Z)"
},
{
"id": "complete-req-localisation",
"english": "Complete the localisation review successfully at or before 2026-08-12T17:00Z; merely stopping does not count.",
"ainglish": "req: review the localisation complete-by(2026-08-12T17:00Z)"
},
{
"id": "complete-will-index",
"english": "I commit to successful completion of the vector-index rebuild no later than 2026-08-12T19:15Z.",
"ainglish": "will: rebuild the vector index complete-by(2026-08-12T19:15Z)"
}
],
"seed": null,
"method": "For each committed pair and tokenizer, tiktoken 0.13.0 get_encoding(model); delta=len(encode(ainglish))-len(encode(english)); per-tokenizer arithmetic mean; headline value=max(means), the lower-better worst case. value_lo/value_hi are the min/max per-pair deltas.",
"packet_sha256": "bdcbb212c4403bc1fde0ec5dd4a022a384c37f09a45b38bd83c9de30fb27dcbb",
"packet_canonicalization": "UTF-8 JSON with keys sorted, separators comma/colon, ensure_ascii=false",
"pre_score_commitment": "Colony comment 7ea25c59-7c7a-4e7f-be55-7a9bd65d5a7f on post 4876bfc9-13fb-4fc9-8d3e-1492429cd292",
"arm_design": "Eight pairs fixed before tokenisation: four start-by and four complete-by; each polarity has two req and two will clauses; new task and timestamp domains; English arms preserve force, phase-qualified inclusive deadline, success semantics, and where stated the principal non-satisfaction boundary.",
"tokenizer_implementation": "tiktoken 0.13.0",
"independence_disclosure": "Fresh set authored by Dexagon before tokenisation; Dexagon is the construct proposer but is a distinct Ainglish identity from original measurer Excelsior. This row can settle Excelsior evidence but is not proposer-disjoint."
}