First result · 2026-09-24 10:45 UTC
text-fixed(ref) / meaning-fixed(ref) — declare which invariants a referenced passage must preserve
Not yet counting in evidence decisions. This row remains available for assessment, but does not currently carry a counting evidence result.
- What was measured
- token cost ·
token_delta
How does the wording change tokenizer units for the declared tokenizer population? - Reported result
- -22.1875 tokens per declared item
Reported interval: -22.875 to -22.1875.Fewer tokens on the named current tokenizers; this is the encoded-length difference, not the proposal decision.
- English comparison
- English comparison not recorded as a structured label
Declared by the submitter; not a certification of equivalent information.
- Tokenizer conditions
- Literal encoding cost on the named current tokenizers; not comprehension.
- Named instruments
cl100k_base,o200k_base,p50k_baseReader population not separately declared.
- Conditions covered
- Separate outcomes retained for all 2 declared conditions
text-fixed,meaning-fixedAn overall average can hide a weak condition. A condition list is not proof that every form or claim in the proposal was tested.
- Settlement role
- Awaiting independent settlement
An original reports one result. It does not confirm itself.
- 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?
- Awaiting independent settlement.
An original reports one result. It does not confirm itself.
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.
Does the overall result hide differences between conditions?
| Condition | Reported difference | Reported interval |
|---|---|---|
text-fixed | -19.25 | Not recorded |
meaning-fixed | -25.125 | Not recorded |
A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.
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 32 readable, inline study items, in stored order—not a selection of successes. 0 control items are kept separate.
Each result has its own input pages. Positions across the two studies do not imply matched cases.
Input 1 · permit-condition
- English input
- You must copy the operating-permit condition into notice Alder-3 while preserving the exact decoded Unicode sequence of permit@ah17§5, including case, punctuation, whitespace, line breaks, spelling, and normalization.
- Ainglish input
- req: copy the operating-permit condition into notice Alder-3, text-fixed(permit@ah17§5).
- Condition
- text-fixed
Input 2 · aircraft-log
- English input
- You must reproduce the aircraft log entry in release Bronze-3 while preserving the exact decoded Unicode sequence of log@bk42:L18, including case, punctuation, whitespace, line breaks, spelling, and normalization.
- Ainglish input
- req: reproduce the aircraft log entry in release Bronze-3, text-fixed(log@bk42:L18).
- Condition
- text-fixed
Input 3 · pathology-result
- English input
- You must insert the pathology result into chart Cirrus-3 while preserving the exact decoded Unicode sequence of result@cm68¶3, including case, punctuation, whitespace, line breaks, spelling, and normalization.
- Ainglish input
- req: insert the pathology result into chart Cirrus-3, text-fixed(result@cm68¶3).
- Condition
- text-fixed
Input 4 · constitutional-clause
- English input
- You must quote the constitutional clause in memorandum Dogwood-3 while preserving the exact decoded Unicode sequence of clause@dn25§9, including case, punctuation, whitespace, line breaks, spelling, and normalization.
- Ainglish input
- req: quote the constitutional clause in memorandum Dogwood-3, text-fixed(clause@dn25§9).
- Condition
- text-fixed
Input 5 · safety-sheet
- English input
- You must mirror the safety-data warning on card Ember-3 while preserving the exact decoded Unicode sequence of sds@ep74:L7, including case, punctuation, whitespace, line breaks, spelling, and normalization.
- Ainglish input
- req: mirror the safety-data warning on card Ember-3, text-fixed(sds@ep74:L7).
- Condition
- text-fixed
Input 6 · accession-label
- English input
- You must transcribe the accession label into catalogue Flint-3 while preserving the exact decoded Unicode sequence of label@fq36¶2, including case, punctuation, whitespace, line breaks, spelling, and normalization.
- Ainglish input
- req: transcribe the accession label into catalogue Flint-3, text-fixed(label@fq36¶2).
- Condition
- text-fixed
Recorded input digest: 330d115e8f33fb4b7edbca1571aa907664c8ba20658de0136ee8f306efc3f74d
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.
Declared population, method and retained outcomes
- Compared with
- text-fixed(ref) / meaning-fixed(ref) versus complete careful English specifying the exact textual or semantic invariants
- Tested population
- 32 frozen complete reference-preservation requests across 32 domains, balanced sixteen per invariant type
- Unit tested
- one complete request with a referenced passage and preservation invariant
- How results combine
- equal item mean per tokenizer, then least-favourable maximum tokenizer mean; retain equal-weight literal-form strata
These are the study author’s declarations. A finding applies to this tested scope; this summary does not establish that another study is comparable.
Absolute arm results, reader-specific results and condition results below are retained values, not a newly pooled analysis. Accuracy arms use fractions from 0 to 1; their difference uses percentage points.
Absolute arm results
Not recorded
Reader or tokenizer results
[
{
"model": "cl100k_base",
"value": -22.34375
},
{
"model": "o200k_base",
"value": -22.1875
},
{
"model": "p50k_base",
"value": -22.875
}
]
Condition results
[
{
"id": "text-fixed",
"weight": 1,
"share": 0.5,
"value": -19.25,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
},
{
"id": "meaning-fixed",
"weight": 1,
"share": 0.5,
"value": -25.125,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
}
]
Exact result and immutable specificationExperiment history
Attempt 3a3497d6-ba5a-41a8-b790-acbfb21677c7
Content 6a835615fd28cd8ac9b72946998d8b2fcf8a57f12ea58a13e5251185db44dacb