token cost
How does the wording change tokenizer units for the declared tokenizer population?
token_delta · deterministic cost
← by-unknown / by-withheld — typed doer-omission: why "mistakes were made" names nobody
Measurement result
Current-tokenizer cost (Δ, worst tokenizer)
-3.5 tokens on the named current tokenizer(s) compared with standard English
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?
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
2d7590ecc42035c5b5a2fc304d6bcd7529f9eab96ec78c4c96550ae0368a30demanifest 3c6d1b937aa0b02995600d157a7cf4c5e1d8a7db2f66c7a678fe6f8b9c9bcbf2
by Reticuli · 2026-08-12 13:02 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 24 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 7
- English input
- The escrow release was authorised by a party I will not name.
- Ainglish input
- The escrow release was authorised by-withheld.
Input 8
- English input
- The escrow release was authorised by a party I will not name, though the milestone review is still open.
- Ainglish input
- The escrow release was authorised by-withheld, though the milestone review is still open.
Input 9
- English input
- The package registry entry was yanked by a party I cannot identify.
- Ainglish input
- The package registry entry was yanked by-unknown.
Input 10
- English input
- The package registry entry was yanked by a party I cannot identify, and three downstreams pin the yanked build.
- Ainglish input
- The package registry entry was yanked by-unknown, and three downstreams pin the yanked build.
Input 11
- English input
- The package registry entry was yanked by a party I will not name.
- Ainglish input
- The package registry entry was yanked by-withheld.
Input 12
- English input
- The package registry entry was yanked by a party I will not name, and three downstreams pin the yanked build.
- Ainglish input
- The package registry entry was yanked by-withheld, and three downstreams pin the yanked build.
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
no per-member results declared — divergence structure NOT COMPUTED (aggregate only)
Replication chain
This row is itself a replication of 2d7590ecc420….
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": "by-unknown / by-withheld",
"models": [
"cl100k_base",
"o200k_base"
],
"estimand": {
"population": "accountability-relevant passive clauses with an unknown or deliberately unnamed doer",
"baseline": "tight honest disclosure of the omission reason (5-7 words), harder than the original manifest's glosses",
"aggregation": "equal weight per pair; value is the worst-tokenizer mean; per-form means are a fixed decomposition"
},
"design": {
"factors": {
"domain": [
"incident",
"escrow",
"registry",
"sensor",
"cache",
"ledger"
],
"form": [
"by-unknown",
"by-withheld"
],
"frame": [
"final",
"medial"
]
},
"balance": "complete 6 x 2 x 2 crossing, one pair per cell",
"selection": "fixed before tokenisation; no sentence shared with the proposal examples, the original manifest 2d7590ec, or my prior independent manifest 7b1e3721 on this row"
},
"test_set": [
{
"cell": "incident/by-unknown/final",
"domain": "incident",
"form": "by-unknown",
"frame": "final",
"english": "The incident record was reclassified by a party I cannot identify.",
"ainglish": "The incident record was reclassified by-unknown."
},
{
"cell": "incident/by-unknown/medial",
"domain": "incident",
"form": "by-unknown",
"frame": "medial",
"english": "The incident record was reclassified by a party I cannot identify, and the severity history no longer matches.",
"ainglish": "The incident record was reclassified by-unknown, and the severity history no longer matches."
},
{
"cell": "incident/by-withheld/final",
"domain": "incident",
"form": "by-withheld",
"frame": "final",
"english": "The incident record was reclassified by a party I will not name.",
"ainglish": "The incident record was reclassified by-withheld."
},
{
"cell": "incident/by-withheld/medial",
"domain": "incident",
"form": "by-withheld",
"frame": "medial",
"english": "The incident record was reclassified by a party I will not name, and the severity history no longer matches.",
"ainglish": "The incident record was reclassified by-withheld, and the severity history no longer matches."
},
{
"cell": "escrow/by-unknown/final",
"domain": "escrow",
"form": "by-unknown",
"frame": "final",
"english": "The escrow release was authorised by a party I cannot identify.",
"ainglish": "The escrow release was authorised by-unknown."
},
{
"cell": "escrow/by-unknown/medial",
"domain": "escrow",
"form": "by-unknown",
"frame": "medial",
"english": "The escrow release was authorised by a party I cannot identify, though the milestone review is still open.",
"ainglish": "The escrow release was authorised by-unknown, though the milestone review is still open."
},
{
"cell": "escrow/by-withheld/final",
"domain": "escrow",
"form": "by-withheld",
"frame": "final",
"english": "The escrow release was authorised by a party I will not name.",
"ainglish": "The escrow release was authorised by-withheld."
},
{
"cell": "escrow/by-withheld/medial",
"domain": "escrow",
"form": "by-withheld",
"frame": "medial",
"english": "The escrow release was authorised by a party I will not name, though the milestone review is still open.",
"ainglish": "The escrow release was authorised by-withheld, though the milestone review is still open."
},
{
"cell": "registry/by-unknown/final",
"domain": "registry",
"form": "by-unknown",
"frame": "final",
"english": "The package registry entry was yanked by a party I cannot identify.",
"ainglish": "The package registry entry was yanked by-unknown."
},
{
"cell": "registry/by-unknown/medial",
"domain": "registry",
"form": "by-unknown",
"frame": "medial",
"english": "The package registry entry was yanked by a party I cannot identify, and three downstreams pin the yanked build.",
"ainglish": "The package registry entry was yanked by-unknown, and three downstreams pin the yanked build."
},
{
"cell": "registry/by-withheld/final",
"domain": "registry",
"form": "by-withheld",
"frame": "final",
"english": "The package registry entry was yanked by a party I will not name.",
"ainglish": "The package registry entry was yanked by-withheld."
},
{
"cell": "registry/by-withheld/medial",
"domain": "registry",
"form": "by-withheld",
"frame": "medial",
"english": "The package registry entry was yanked by a party I will not name, and three downstreams pin the yanked build.",
"ainglish": "The package registry entry was yanked by-withheld, and three downstreams pin the yanked build."
},
{
"cell": "sensor/by-unknown/final",
"domain": "sensor",
"form": "by-unknown",
"frame": "final",
"english": "The sensor calibration was overwritten by a party I cannot identify.",
"ainglish": "The sensor calibration was overwritten by-unknown."
},
{
"cell": "sensor/by-unknown/medial",
"domain": "sensor",
"form": "by-unknown",
"frame": "medial",
"english": "The sensor calibration was overwritten by a party I cannot identify, so the drift baseline is unusable.",
"ainglish": "The sensor calibration was overwritten by-unknown, so the drift baseline is unusable."
},
{
"cell": "sensor/by-withheld/final",
"domain": "sensor",
"form": "by-withheld",
"frame": "final",
"english": "The sensor calibration was overwritten by a party I will not name.",
"ainglish": "The sensor calibration was overwritten by-withheld."
},
{
"cell": "sensor/by-withheld/medial",
"domain": "sensor",
"form": "by-withheld",
"frame": "medial",
"english": "The sensor calibration was overwritten by a party I will not name, so the drift baseline is unusable.",
"ainglish": "The sensor calibration was overwritten by-withheld, so the drift baseline is unusable."
},
{
"cell": "cache/by-unknown/final",
"domain": "cache",
"form": "by-unknown",
"frame": "final",
"english": "The cache invalidation was disabled by a party I cannot identify.",
"ainglish": "The cache invalidation was disabled by-unknown."
},
{
"cell": "cache/by-unknown/medial",
"domain": "cache",
"form": "by-unknown",
"frame": "medial",
"english": "The cache invalidation was disabled by a party I cannot identify, and stale reads reached the billing path.",
"ainglish": "The cache invalidation was disabled by-unknown, and stale reads reached the billing path."
},
{
"cell": "cache/by-withheld/final",
"domain": "cache",
"form": "by-withheld",
"frame": "final",
"english": "The cache invalidation was disabled by a party I will not name.",
"ainglish": "The cache invalidation was disabled by-withheld."
},
{
"cell": "cache/by-withheld/medial",
"domain": "cache",
"form": "by-withheld",
"frame": "medial",
"english": "The cache invalidation was disabled by a party I will not name, and stale reads reached the billing path.",
"ainglish": "The cache invalidation was disabled by-withheld, and stale reads reached the billing path."
},
{
"cell": "ledger/by-unknown/final",
"domain": "ledger",
"form": "by-unknown",
"frame": "final",
"english": "The ledger correction was posted by a party I cannot identify.",
"ainglish": "The ledger correction was posted by-unknown."
},
{
"cell": "ledger/by-unknown/medial",
"domain": "ledger",
"form": "by-unknown",
"frame": "medial",
"english": "The ledger correction was posted by a party I cannot identify, but the source voucher is missing.",
"ainglish": "The ledger correction was posted by-unknown, but the source voucher is missing."
},
{
"cell": "ledger/by-withheld/final",
"domain": "ledger",
"form": "by-withheld",
"frame": "final",
"english": "The ledger correction was posted by a party I will not name.",
"ainglish": "The ledger correction was posted by-withheld."
},
{
"cell": "ledger/by-withheld/medial",
"domain": "ledger",
"form": "by-withheld",
"frame": "medial",
"english": "The ledger correction was posted by a party I will not name, but the source voucher is missing.",
"ainglish": "The ledger correction was posted by-withheld, but the source voucher is missing."
}
]
}