First result · 2026-09-04 19:46 UTC
dispatched(<transport>) / delivered(<witness>) — say which transit event you witnessed, and who witnessed it
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
- comprehension accuracy ·
comprehension_accuracy_delta
How does the wording change correct answers from the declared reader panel? - Reported result
- -25 percentage points
Reported interval: -43.0736 to -7.7935.The value falls on the registered harmful side of this metric’s neutral point.
- English comparison
- Complete, careful English
Declared by the submitter; not a certification of equivalent information.
Each compact form is compared with its complete careful-English meaning; bare ambiguity is absent from the scalar.
- Reader exposure
- Reader exposure not recorded as a structured label
- Named instruments
mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m,gemma3-12b-opaque-choice-q4_k_m@q4_k_mReader population not separately declared.
- Conditions covered
- Separate outcomes retained for all 2 declared conditions
dispatched,deliveredAn 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.
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.
How much input text was reused?
Complete-pair freshness is not available for this receipt.
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
39a511cf82362e44c1ebb56eb945f615c245d50e1f65a0aa62dc0c91c45e5ff3How often did each version lead to the right answer?
- English comparison
- 81.25%
81.25% - Ainglish version
- 56.25%
56.25%
Reported real-item accuracy, not the separate calibration score. Both bars use the same 0–100% scale. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.
Reported item-bootstrap interval: -43.0736 to -7.7935 percentage points.
This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.
Real cases: 32 · Named readers: 2. These are different units; multiple answers to one case are not new cases.
Does the overall result hide differences between conditions?
| Condition | Reported difference | Reported interval | English accuracy | Ainglish accuracy |
|---|---|---|---|---|
dispatched | 18.75 | Not recorded | 62.50% | 81.25% |
delivered | -68.75 | Not recorded | 100.00% | 31.25% |
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. 16 control items are kept separate.
Each result has its own input pages. Positions across the two studies do not imply matched cases.
Input 1 · sd01
- English input
- Outbound handoff via relay-cedar began for rollout plan K to release team; arrival/read unknown.
- Ainglish input
- dispatched(relay-cedar): rollout plan K to release team.
- Question
- Latest proven stage?
- Recorded answer options
sent·arrived·accepted·none- Submitted answer key
- sent. This is the supplied key, not an independent validation of it.
- Condition
- dispatched
Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
gemma3-12b-opaque-choice-q4_k_m· English: did not match the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· English: matched the submitted key.
Input 2 · sl01
- English input
- team-inbox-51, not sender, saw rollout plan K arrive at release team; read/acceptance unknown.
- Ainglish input
- delivered(team-inbox-51): rollout plan K to release team.
- Question
- Latest proven stage?
- Recorded answer options
sent·arrived·accepted·none- Submitted answer key
- arrived. This is the supplied key, not an independent validation of it.
- Condition
- delivered
Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
gemma3-12b-opaque-choice-q4_k_m· Ainglish: did not match the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· English: matched the submitted key.
Input 3 · sd02
- English input
- Outbound handoff via queue-umber began for health trace L to incident desk; arrival/read unknown.
- Ainglish input
- dispatched(queue-umber): health trace L to incident desk.
- Question
- Latest proven stage?
- Recorded answer options
accepted·none·sent·arrived- Submitted answer key
- sent. This is the supplied key, not an independent validation of it.
- Condition
- dispatched
Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
gemma3-12b-opaque-choice-q4_k_m· English: did not match the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· English: matched the submitted key.
Input 4 · sl02
- English input
- desk-log-27, not sender, saw health trace L arrive at incident desk; read/acceptance unknown.
- Ainglish input
- delivered(desk-log-27): health trace L to incident desk.
- Question
- Latest proven stage?
- Recorded answer options
accepted·none·sent·arrived- Submitted answer key
- arrived. This is the supplied key, not an independent validation of it.
- Condition
- delivered
Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
gemma3-12b-opaque-choice-q4_k_m· English: matched the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· Ainglish: did not match the submitted key.
Input 5 · sd03
- English input
- Outbound handoff via bus-willow began for lineage map M to catalog owner; arrival/read unknown.
- Ainglish input
- dispatched(bus-willow): lineage map M to catalog owner.
- Question
- Latest proven stage?
- Recorded answer options
sent·arrived·accepted·none- Submitted answer key
- sent. This is the supplied key, not an independent validation of it.
- Condition
- dispatched
Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
gemma3-12b-opaque-choice-q4_k_m· Ainglish: did not match the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· English: matched the submitted key.
Input 6 · sl03
- English input
- catalog-ack-63, not sender, saw lineage map M arrive at catalog owner; read/acceptance unknown.
- Ainglish input
- delivered(catalog-ack-63): lineage map M to catalog owner.
- Question
- Latest proven stage?
- Recorded answer options
sent·arrived·accepted·none- Submitted answer key
- arrived. This is the supplied key, not an independent validation of it.
- Condition
- delivered
Filed correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
gemma3-12b-opaque-choice-q4_k_m· Ainglish: did not match the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· Ainglish: did not match the submitted key.
Recorded input digest: 697ce0ec002e40cfdf91b7675a20352d6bc712c15d6f4f95774541324d9c2284
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
No structured study scope is declared here. Inspect the immutable manifest; do not infer a comparator or population from the headline.
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
{
"english": 0.8125,
"ainglish": 0.5625,
"chance": 0.25
}
Reader or tokenizer results
[
{
"model": "mistral-small3.2-24b-opaque-choice-q4_k_m",
"value": -53.1749999999999971578290569595992565155029296875,
"precision": "q4_k_m"
},
{
"model": "gemma3-12b-opaque-choice-q4_k_m",
"value": 8.730000000000000426325641456060111522674560546875,
"precision": "q4_k_m"
}
]
Condition results
[
{
"id": "dispatched",
"weight": 1,
"share": 0.5,
"value": 18.75,
"value_lo": null,
"value_hi": null,
"arms": {
"english": 0.625,
"ainglish": 0.8125,
"chance": 0.25
},
"resolution_bound": "resolvable"
},
{
"id": "delivered",
"weight": 1,
"share": 0.5,
"value": -68.75,
"value_lo": null,
"value_hi": null,
"arms": {
"english": 1,
"ainglish": 0.3125,
"chance": 0.25
},
"resolution_bound": "resolvable"
}
]
Exact result and immutable specificationExperiment history
Attempt 3146f737-62ad-405b-9f77-6736bf3d9f60
Content 160593e52d23be44804906f07dd7c732756e20452f85747f162afd1fc84c0975