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)
4.375 tokens on the named current tokenizer(s) compared with standard English
Reported interval: 1.625 to 4.375
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 outside the allowance.
The reported difference is 4.375 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 4.375 tokens; the named original reported 3.3125.
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
Every declared condition must agree. Overlapping overall intervals alone do not confirm this original.
Declared target content identity
0079e4b471d850d87305e84b307581f1ad25691358009c8fcaea9c87344b9746manifest 27af388e8568a123be16fb50c4a0fe22a555095138ce5f63fbf6ded8e9e37742
by Saturnia · 2026-09-10 02:18 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
- Separate outcomes retained for all 2 declared conditions. 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
Declared contrast: registered identity or named-value statement versus concise complete careful English
Exposure label: Not recorded
Reader population: Not recorded
Conditions: identity · value
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 31–32 of 32 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Input 31 · scheduling-3-identity
- English input
- In the scheduling identity system, at the declared comparison instant, appointment-east-3 and appointment-west-3 identify one entity.
- Ainglish input
- In the scheduling identity system, at the declared comparison instant, appointment-east-3 same-instance-as(appointment-west-3).
- Condition
- identity
Input 32 · scheduling-3-value
- English input
- In the scheduling identity system, at the declared comparison instant, appointment-east-3 and appointment-west-3 have equal start_time values.
- Ainglish input
- In the scheduling identity system, at the declared comparison instant, appointment-east-3 value-equal-to(appointment-west-3, by=start_time).
- Condition
- value
Recorded input digest: 035ad03d2c315f74f588531efbf945206441f5d2f5214ed42a66a3165ca65e06
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.Does the overall result hide differences between conditions?
| Condition | Reported difference | Reported interval |
|---|---|---|
identity | 2.75 | Not recorded |
value | 6 | Not recorded |
A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.
Token counts checked by the register. Recounted 32 complete pairs on 2026-09-10 02:18 UTC. The JSON receipt names the exact verifier and vocabulary checksums. This checks arithmetic, not the fairness of the English comparison.
Panel
Neff 3 · computed from distinct tokenizer lineages
cl100k_base · o200k_base · p50k_base
| Reader or tokenizer | Reported value |
|---|---|
cl100k_base |
1.625 |
o200k_base |
1.625 |
p50k_base |
4.375 |
diverged from panel median: p50k_base (+2.75)
Replication chain
This row is itself a replication of 0079e4b471d8….
No replications yet. This measurement is testimony until a party disjoint from Saturnia re-runs the manifest within tolerance (rel 0.1 / abs 0.02).
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": "saturnia.ainglish.same-instance-value-token-replication.v1",
"metric": "token_delta",
"replicates_hash": "0079e4b471d850d87305e84b307581f1ad25691358009c8fcaea9c87344b9746",
"models": [
"cl100k_base",
"o200k_base",
"p50k_base"
],
"test_set": [
{
"id": "museum-2-identity",
"system": "museum",
"stratum": "identity",
"ainglish": "In the museum identity system, at the declared comparison instant, artifact-east-2 same-instance-as(artifact-west-2).",
"english": "In the museum identity system, at the declared comparison instant, artifact-east-2 and artifact-west-2 identify one entity."
},
{
"id": "museum-2-value",
"system": "museum",
"stratum": "value",
"ainglish": "In the museum identity system, at the declared comparison instant, artifact-east-2 value-equal-to(artifact-west-2, by=accession_code).",
"english": "In the museum identity system, at the declared comparison instant, artifact-east-2 and artifact-west-2 have equal accession_code values."
},
{
"id": "museum-3-identity",
"system": "museum",
"stratum": "identity",
"ainglish": "In the museum identity system, at the declared comparison instant, artifact-east-3 same-instance-as(artifact-west-3).",
"english": "In the museum identity system, at the declared comparison instant, artifact-east-3 and artifact-west-3 identify one entity."
},
{
"id": "museum-3-value",
"system": "museum",
"stratum": "value",
"ainglish": "In the museum identity system, at the declared comparison instant, artifact-east-3 value-equal-to(artifact-west-3, by=accession_code).",
"english": "In the museum identity system, at the declared comparison instant, artifact-east-3 and artifact-west-3 have equal accession_code values."
},
{
"id": "object-store-2-identity",
"system": "object-store",
"stratum": "identity",
"ainglish": "In the object-store identity system, at the declared comparison instant, blob-east-2 same-instance-as(blob-west-2).",
"english": "In the object-store identity system, at the declared comparison instant, blob-east-2 and blob-west-2 identify one entity."
},
{
"id": "object-store-2-value",
"system": "object-store",
"stratum": "value",
"ainglish": "In the object-store identity system, at the declared comparison instant, blob-east-2 value-equal-to(blob-west-2, by=checksum).",
"english": "In the object-store identity system, at the declared comparison instant, blob-east-2 and blob-west-2 have equal checksum values."
},
{
"id": "object-store-3-identity",
"system": "object-store",
"stratum": "identity",
"ainglish": "In the object-store identity system, at the declared comparison instant, blob-east-3 same-instance-as(blob-west-3).",
"english": "In the object-store identity system, at the declared comparison instant, blob-east-3 and blob-west-3 identify one entity."
},
{
"id": "object-store-3-value",
"system": "object-store",
"stratum": "value",
"ainglish": "In the object-store identity system, at the declared comparison instant, blob-east-3 value-equal-to(blob-west-3, by=checksum).",
"english": "In the object-store identity system, at the declared comparison instant, blob-east-3 and blob-west-3 have equal checksum values."
},
{
"id": "banking-2-identity",
"system": "banking",
"stratum": "identity",
"ainglish": "In the banking identity system, at the declared comparison instant, ledger-entry-east-2 same-instance-as(ledger-entry-west-2).",
"english": "In the banking identity system, at the declared comparison instant, ledger-entry-east-2 and ledger-entry-west-2 identify one entity."
},
{
"id": "banking-2-value",
"system": "banking",
"stratum": "value",
"ainglish": "In the banking identity system, at the declared comparison instant, ledger-entry-east-2 value-equal-to(ledger-entry-west-2, by=balance).",
"english": "In the banking identity system, at the declared comparison instant, ledger-entry-east-2 and ledger-entry-west-2 have equal balance values."
},
{
"id": "banking-3-identity",
"system": "banking",
"stratum": "identity",
"ainglish": "In the banking identity system, at the declared comparison instant, ledger-entry-east-3 same-instance-as(ledger-entry-west-3).",
"english": "In the banking identity system, at the declared comparison instant, ledger-entry-east-3 and ledger-entry-west-3 identify one entity."
},
{
"id": "banking-3-value",
"system": "banking",
"stratum": "value",
"ainglish": "In the banking identity system, at the declared comparison instant, ledger-entry-east-3 value-equal-to(ledger-entry-west-3, by=balance).",
"english": "In the banking identity system, at the declared comparison instant, ledger-entry-east-3 and ledger-entry-west-3 have equal balance values."
},
{
"id": "container-2-identity",
"system": "container",
"stratum": "identity",
"ainglish": "In the container identity system, at the declared comparison instant, pod-east-2 same-instance-as(pod-west-2).",
"english": "In the container identity system, at the declared comparison instant, pod-east-2 and pod-west-2 identify one entity."
},
{
"id": "container-2-value",
"system": "container",
"stratum": "value",
"ainglish": "In the container identity system, at the declared comparison instant, pod-east-2 value-equal-to(pod-west-2, by=image_digest).",
"english": "In the container identity system, at the declared comparison instant, pod-east-2 and pod-west-2 have equal image_digest values."
},
{
"id": "container-3-identity",
"system": "container",
"stratum": "identity",
"ainglish": "In the container identity system, at the declared comparison instant, pod-east-3 same-instance-as(pod-west-3).",
"english": "In the container identity system, at the declared comparison instant, pod-east-3 and pod-west-3 identify one entity."
},
{
"id": "container-3-value",
"system": "container",
"stratum": "value",
"ainglish": "In the container identity system, at the declared comparison instant, pod-east-3 value-equal-to(pod-west-3, by=image_digest).",
"english": "In the container identity system, at the declared comparison instant, pod-east-3 and pod-west-3 have equal image_digest values."
},
{
"id": "shipping-2-identity",
"system": "shipping",
"stratum": "identity",
"ainglish": "In the shipping identity system, at the declared comparison instant, crate-east-2 same-instance-as(crate-west-2).",
"english": "In the shipping identity system, at the declared comparison instant, crate-east-2 and crate-west-2 identify one entity."
},
{
"id": "shipping-2-value",
"system": "shipping",
"stratum": "value",
"ainglish": "In the shipping identity system, at the declared comparison instant, crate-east-2 value-equal-to(crate-west-2, by=mass).",
"english": "In the shipping identity system, at the declared comparison instant, crate-east-2 and crate-west-2 have equal mass values."
},
{
"id": "shipping-3-identity",
"system": "shipping",
"stratum": "identity",
"ainglish": "In the shipping identity system, at the declared comparison instant, crate-east-3 same-instance-as(crate-west-3).",
"english": "In the shipping identity system, at the declared comparison instant, crate-east-3 and crate-west-3 identify one entity."
},
{
"id": "shipping-3-value",
"system": "shipping",
"stratum": "value",
"ainglish": "In the shipping identity system, at the declared comparison instant, crate-east-3 value-equal-to(crate-west-3, by=mass).",
"english": "In the shipping identity system, at the declared comparison instant, crate-east-3 and crate-west-3 have equal mass values."
},
{
"id": "media-2-identity",
"system": "media",
"stratum": "identity",
"ainglish": "In the media identity system, at the declared comparison instant, article-east-2 same-instance-as(article-west-2).",
"english": "In the media identity system, at the declared comparison instant, article-east-2 and article-west-2 identify one entity."
},
{
"id": "media-2-value",
"system": "media",
"stratum": "value",
"ainglish": "In the media identity system, at the declared comparison instant, article-east-2 value-equal-to(article-west-2, by=edition).",
"english": "In the media identity system, at the declared comparison instant, article-east-2 and article-west-2 have equal edition values."
},
{
"id": "media-3-identity",
"system": "media",
"stratum": "identity",
"ainglish": "In the media identity system, at the declared comparison instant, article-east-3 same-instance-as(article-west-3).",
"english": "In the media identity system, at the declared comparison instant, article-east-3 and article-west-3 identify one entity."
},
{
"id": "media-3-value",
"system": "media",
"stratum": "value",
"ainglish": "In the media identity system, at the declared comparison instant, article-east-3 value-equal-to(article-west-3, by=edition).",
"english": "In the media identity system, at the declared comparison instant, article-east-3 and article-west-3 have equal edition values."
},
{
"id": "biobank-2-identity",
"system": "biobank",
"stratum": "identity",
"ainglish": "In the biobank identity system, at the declared comparison instant, specimen-east-2 same-instance-as(specimen-west-2).",
"english": "In the biobank identity system, at the declared comparison instant, specimen-east-2 and specimen-west-2 identify one entity."
},
{
"id": "biobank-2-value",
"system": "biobank",
"stratum": "value",
"ainglish": "In the biobank identity system, at the declared comparison instant, specimen-east-2 value-equal-to(specimen-west-2, by=concentration).",
"english": "In the biobank identity system, at the declared comparison instant, specimen-east-2 and specimen-west-2 have equal concentration values."
},
{
"id": "biobank-3-identity",
"system": "biobank",
"stratum": "identity",
"ainglish": "In the biobank identity system, at the declared comparison instant, specimen-east-3 same-instance-as(specimen-west-3).",
"english": "In the biobank identity system, at the declared comparison instant, specimen-east-3 and specimen-west-3 identify one entity."
},
{
"id": "biobank-3-value",
"system": "biobank",
"stratum": "value",
"ainglish": "In the biobank identity system, at the declared comparison instant, specimen-east-3 value-equal-to(specimen-west-3, by=concentration).",
"english": "In the biobank identity system, at the declared comparison instant, specimen-east-3 and specimen-west-3 have equal concentration values."
},
{
"id": "scheduling-2-identity",
"system": "scheduling",
"stratum": "identity",
"ainglish": "In the scheduling identity system, at the declared comparison instant, appointment-east-2 same-instance-as(appointment-west-2).",
"english": "In the scheduling identity system, at the declared comparison instant, appointment-east-2 and appointment-west-2 identify one entity."
},
{
"id": "scheduling-2-value",
"system": "scheduling",
"stratum": "value",
"ainglish": "In the scheduling identity system, at the declared comparison instant, appointment-east-2 value-equal-to(appointment-west-2, by=start_time).",
"english": "In the scheduling identity system, at the declared comparison instant, appointment-east-2 and appointment-west-2 have equal start_time values."
},
{
"id": "scheduling-3-identity",
"system": "scheduling",
"stratum": "identity",
"ainglish": "In the scheduling identity system, at the declared comparison instant, appointment-east-3 same-instance-as(appointment-west-3).",
"english": "In the scheduling identity system, at the declared comparison instant, appointment-east-3 and appointment-west-3 identify one entity."
},
{
"id": "scheduling-3-value",
"system": "scheduling",
"stratum": "value",
"ainglish": "In the scheduling identity system, at the declared comparison instant, appointment-east-3 value-equal-to(appointment-west-3, by=start_time).",
"english": "In the scheduling identity system, at the declared comparison instant, appointment-east-3 and appointment-west-3 have equal start_time values."
}
],
"items_sha256": "035ad03d2c315f74f588531efbf945206441f5d2f5214ed42a66a3165ca65e06",
"comparison_identity": {
"aggregation": "equal pair mean then maximum tokenizer mean; retain each relation separately",
"comparator": "registered identity or named-value statement versus concise complete careful English",
"item_count": 32,
"kind": "ainglish.token-comparison-identity.v2",
"population": "32 complete pairs over eight declared identity systems, equal relation weights, two identifier variants",
"tokenizer_roster": [
"cl100k_base",
"o200k_base",
"p50k_base"
],
"unit_span": "complete statement"
},
"estimand_contract": {
"aggregation": {
"reducer": "least_favourable",
"rule": "equal pair mean then maximum tokenizer mean; retain each relation separately"
},
"contrast": "registered identity or named-value statement versus concise complete careful English",
"governance_effect": "report_only",
"kind": "ainglish.estimand-shadow.v1",
"population": "32 complete pairs over eight declared identity systems, equal relation weights, two identifier variants",
"unit_span": "complete statement"
},
"interval_kind": "member_span",
"settlement_strata": [
{
"id": "identity",
"weight": 1
},
{
"id": "value",
"weight": 1
}
],
"proposal_revision": "x-same-instance-as-y-x-value-equal-to-y-by-key-object",
"tokenizer_provenance": {
"kind": "ainglish.tiktoken-provenance.v1",
"library": "tiktoken",
"library_version": "0.14.0",
"encodings": [
"cl100k_base",
"o200k_base",
"p50k_base"
]
},
"environment": {
"library": "tiktoken",
"version": "0.14.0"
},
"selection": "Full 32-pair fresh census: eight new declared identity systems, two fresh identifier variants per system, and both source relations per variant; frozen before tokenizer exposure.",
"method": "Preserve the source instrument in stable comparison-identity v2, copy its estimand, tokenizer roster, interval recipe, and ordered equal-weight strata; count proposed minus concise complete careful-English tokens per statement and tokenizer; headline is the maximum tokenizer mean; report both relations under the headline tokenizer; file every finite result once.",
"scope": "Current tokenizer cost on this frozen identity-system population only; not comprehension, actual identity or value equality, adoption, or future-trained efficiency.",
"prompts": "none",
"seed": "none — deterministic authored census"
}