First result · 2026-09-30 14:24 UTC
you-one / you-all — say whether “you” addresses one recipient or the whole group
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
- -5 tokens per declared item
Reported interval: -6 to -5.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 4 declared conditions
you-one-subject,you-one-object,you-all-subject,you-all-objectAn 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 |
|---|---|---|
you-one-subject | -7 | Not recorded |
you-one-object | -7 | Not recorded |
you-all-subject | -3 | Not recorded |
you-all-object | -3 | 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 24 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 · one-sub-aviary-check
- English input
- Private message to Noor: the one addressee denoted by this clause must approve aviary checklist Finch.
- Ainglish input
- Private message to Noor: you-one must approve aviary checklist Finch.
- Condition
- you-one-subject
Input 2 · one-sub-brewery-valve
- English input
- Private message to Tomas: the one addressee denoted by this clause may reset fermentation valve B2.
- Ainglish input
- Private message to Tomas: you-one may reset fermentation valve B2.
- Condition
- you-one-subject
Input 3 · one-sub-canal-permit
- English input
- Private message to Iris: the one addressee denoted by this clause must return canal permit Lock-7.
- Ainglish input
- Private message to Iris: you-one must return canal permit Lock-7.
- Condition
- you-one-subject
Input 4 · one-sub-dental-scan
- English input
- Private message to Kei: the one addressee denoted by this clause may release dental scan Molar-4.
- Ainglish input
- Private message to Kei: you-one may release dental scan Molar-4.
- Condition
- you-one-subject
Input 5 · one-sub-elevator-log
- English input
- Private message to Zara: the one addressee denoted by this clause must reconcile elevator service log.
- Ainglish input
- Private message to Zara: you-one must reconcile elevator service log.
- Condition
- you-one-subject
Input 6 · one-sub-film-negative
- English input
- Private message to Omar: the one addressee denoted by this clause may inspect film negative Cedar.
- Ainglish input
- Private message to Omar: you-one may inspect film negative Cedar.
- Condition
- you-one-subject
Recorded input digest: a8233f8e0761005dfcbdcf43516196e939bc55b11b1dde5867ad83dfb0d0db16
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
- you-one/you-all versus the complete registered English one-addressee or every-addressed-member mapping in the same resolved audience context
- Tested population
- 24 frozen complete addressed messages across 24 new domains, balanced six each across singular/plural by subject/object
- Unit tested
- one complete addressed message with a resolved utterance-time audience
- How results combine
- equal item mean within four form-by-syntax strata; equal stratum weight per tokenizer; least-favourable maximum tokenizer mean
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": -6
},
{
"model": "o200k_base",
"value": -6
},
{
"model": "p50k_base",
"value": -5
}
]
Condition results
[
{
"id": "you-one-subject",
"weight": 1,
"share": 0.25,
"value": -7,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
},
{
"id": "you-one-object",
"weight": 1,
"share": 0.25,
"value": -7,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
},
{
"id": "you-all-subject",
"weight": 1,
"share": 0.25,
"value": -3,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
},
{
"id": "you-all-object",
"weight": 1,
"share": 0.25,
"value": -3,
"value_lo": null,
"value_hi": null,
"arms": null,
"resolution_bound": "not_applicable"
}
]
Exact result and immutable specificationExperiment history
Attempt 7bdc1fa8-b353-41a4-add7-6cdc31506394
Content 55658a051185aba1fda7bc32b4d9c00f10a0817d198b4c5344a93aefbad6d65c