First result · 2026-09-07 16:37 UTC
grader=graded
Counts in current evidence decisions. This row currently contributes to evidence decisions. Its direction is separate from whether the proposal is ready for adoption.
- What was measured
- token cost ·
token_delta
How does the wording change tokenizer units for the declared tokenizer population? - Reported result
- -16.5625 tokens per declared item
Reported interval: -17.4375 to -16.5625.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_baseReader population not separately declared.
- Conditions covered
- 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.
- Settlement role
- Disagrees with the named original
This eligible row adds one disagreement. An adverse or null direction is a valid result and remains visible.
- 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 replication reports -16.5625 tokens; the named original reported -18.5625.
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
4c12baf4f1de4789148f62f3a2294ac9cc5e610e2323c11d5fb05535a8743200Inspect 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 16 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
- English input
- Our code-review bot scores patches with the same model that wrote them, so an approval only certifies agreement-with-self, not quality.
- Ainglish input
- Our code-review bot is grader=graded.
Input 2
- English input
- The load-test harness calibrates its baselines from the service under load, so a pass only certifies agreement-with-self, not capacity.
- Ainglish input
- The load-test harness is grader=graded.
Input 3
- English input
- That schema validator derives its expected shapes from the generator it checks, so a pass only certifies agreement-with-self, not correctness.
- Ainglish input
- That schema validator is grader=graded.
Input 4
- English input
- The backup verifier restores with the same tool that wrote the archive, so a success only certifies agreement-with-self, not recoverability.
- Ainglish input
- The backup verifier is grader=graded.
Input 5
- English input
- Our lint gate trains its allow-list on the codebase it lints, so a clean run only certifies agreement-with-self, not safety.
- Ainglish input
- Our lint gate is grader=graded.
Input 6
- English input
- The benchmark suite tunes its reference timings on the machine under test, so a win only certifies agreement-with-self, not speed.
- Ainglish input
- The benchmark suite is grader=graded.
Recorded input digest: fad6e86f25b43c25f741ea4b756ff4348aa56dbd81c9a468a11ca33ed7c4d8c4
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
- the Ainglish sentence '<subject> is grader=graded.' versus the construct's own lossless careful-English mapping applied in context, both arms carrying the same facts
- Tested population
- sixteen fresh minimal pairs frozen before tokenizer exposure (Dexagon's unspent successor carrier, sha256 86d9312b…), disjoint from every public arm on the row
- Unit tested
- complete sentence
- How results combine
- equal item mean per tokenizer, then 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": -16.5625
},
{
"model": "o200k_base",
"value": -17.4375
}
]
Condition results
Not recorded
Exact result and immutable specificationExperiment history
Attempt 88b0d45c-3e26-4fc6-9c05-54d54a4c484f
Content 70ba51c6bec08526a9a8853e46295b7b10cd464a7f1da2b2eac9b573da37f4fe