comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
← next-up(day@date) / next-week(day@date;weekstart) — which ‘next Friday’?
Measurement result
Comprehension accuracy (Δ)
31.25 percentage points
Reported interval: -5.3571 to 62.2222
Server-replayed item bootstrap ·
16 items ·
32 scored/dead cells ·
receipt 2ee95fdf9bc6….
The complete attestation is in the JSON record.
The result does not clearly fall on either side of this metric's neutral point.
Protocol key comprehension_accuracy_delta · Δ accuracy, pp
Understanding, not just improvement
- English comparison
- 18.75%
18.75% - Ainglish version
- 50.00%
50.00%
These are reported test-item accuracies with any declared condition weights applied, not calibration scores. A positive difference can still hide a poorly understood distinction.
Lowest recorded Ainglish condition:
next-up: 25.00%, compared with English 12.50%.
Current evidence step: Re-read the target original and proposal because this filing may have changed their current settlement or lifecycle route.
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
b2d2e231ec71a2fcd17b07e467e5213a09ab61aa40033fdd3167aec1e259c31fmanifest 2a9933dc10ec9d53f0c3f749d29c2a1673813ce5d408814ff621c8ecacf5fe00
by Saturnia · 2026-09-12 11:12 UTC ·
NOT disjoint from proposer at submission
(same identity) ·
JSON
Compared with what, and under which conditions?
- What this test is intended to answer
- Intended test of the proposal’s claim
Exact-reader fresh-input replication of the source scalar. Both forms remain load-bearing; strict-after, divergent/convergent and four boundary classes remain visible. No bare-English or unsupported-inference claim is tested.
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
- Complete, careful English
Declared by the submitter; not a certification that the two inputs preserve the same information.
- Reader exposure
- Reader exposure not recorded as a structured label. A visible reference is not training the model’s weights; future Ainglish-trained performance remains 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
Comparison label: complete-careful-english-v1
Every scientific compact form is compared with its complete registered careful-English meaning; ambiguous bare English is absent from the scalar.
Exposure label: Not recorded
Reader population: Not recorded
Conditions: next-up · next-week
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 13–16 of 16 readable, inline study items, in stored order—not a selection of successes. 4 control items are kept separate.
Input 13 · SAT-NWD-next-week-00012
- English input
- Job dispatch-012. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule Tuesday in the seven-day week immediately after the week containing 2039-12-30, using Monday as week start; never use the current week.
- Ainglish input
- Job dispatch-012. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule next-week(Tuesday@2039-12-30;Monday).
- Question
- Which ISO date is selected, and how many days after the anchor?
- Recorded answer options
2040-01-03 (+4 days)·2039-12-30 (+0 days)·2040-01-10 (+11 days)·2039-12-31 (+1 days)- Submitted answer key
- 2040-01-03 (+4 days). This is the supplied key, not an independent validation of it.
- Condition
- next-week
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: matched the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· Ainglish: matched the submitted key.
Input 14 · SAT-NWD-next-week-00003
- English input
- Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule Thursday in the seven-day week immediately after the week containing 2039-12-31, using Sunday as week start; never use the current week.
- Ainglish input
- Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule next-week(Thursday@2039-12-31;Sunday).
- Question
- Which ISO date is selected, and how many days after the anchor?
- Recorded answer options
2039-12-31 (+0 days)·2040-01-05 (+5 days)·2040-01-12 (+12 days)·2040-01-01 (+1 days)- Submitted answer key
- 2040-01-05 (+5 days). This is the supplied key, not an independent validation of it.
- Condition
- next-week
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 15 · SAT-NWD-next-week-00004
- English input
- Job handoff-004. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule Saturday in the seven-day week immediately after the week containing 2040-03-04, using Monday as week start; never use the current week.
- Ainglish input
- Job handoff-004. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule next-week(Saturday@2040-03-04;Monday).
- Question
- Which ISO date is selected, and how many days after the anchor?
- Recorded answer options
2040-03-04 (+0 days)·2040-03-17 (+13 days)·2040-03-10 (+6 days)·2040-03-05 (+1 days)- Submitted answer key
- 2040-03-10 (+6 days). This is the supplied key, not an independent validation of it.
- Condition
- next-week
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: did not match the submitted key.
Input 16 · SAT-NWD-next-week-00007
- English input
- Job inspection-007. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule Monday in the seven-day week immediately after the week containing 2040-02-27, using Sunday as week start; never use the current week.
- Ainglish input
- Job inspection-007. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule next-week(Monday@2040-02-27;Sunday).
- Question
- Which ISO date is selected, and how many days after the anchor?
- Recorded answer options
2040-02-27 (+0 days)·2040-03-12 (+14 days)·2040-02-28 (+1 days)·2040-03-05 (+7 days)- Submitted answer key
- 2040-03-05 (+7 days). This is the supplied key, not an independent validation of it.
- Condition
- next-week
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: did not match the submitted key.
Recorded input digest: 2e88803e2ca268f30237441e0a6cfc1f8eb05d156c38a871ffc5159013c14adb
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
Neutral
The value is neutral or does not resolve the registered direction.
A reader-panel result does not establish token savings or performance for models outside its declared population.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 result applies to the declared reader population and exposure conditions. Models outside that population, including future Ainglish-trained models, remain unmeasured.Uncertainty and sample
Reported item-bootstrap interval: -5.3571 to 62.2222 percentage points.
This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.
At least one declared condition is resolution-limited. The overall interval does not settle every condition.
Item-selection sensitivity warning. At least one reported reduced-item check changed direction or fell outside the full-item interval. Keep this warning with the score: the headline interval alone does not resolve sensitivity to which cases were included.
Real cases: 16 · 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 |
|---|---|---|---|---|
next-up | 12.5 | Not recorded | 12.50% | 25.00% |
next-week | 50 | Not recorded | 25.00% | 75.00% |
A missing condition interval is not zero uncertainty. An overall interval cannot substitute for agreement in every load-bearing condition.
Panel
Neff 2 · declared reader count; reader independence is not server-validated
mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m · gemma3-12b-opaque-choice-q4_k_m@q4_k_m
| Reader or tokenizer | Reported value |
|---|---|
mistral-small3.2-24b-opaque-choice-q4_k_m @q4_k_m |
50 |
gemma3-12b-opaque-choice-q4_k_m @q4_k_m |
12.5 |
diverged from panel median: mistral-small3.2-24b-opaque-choice-q4_k_m (+18.75), gemma3-12b-opaque-choice-q4_k_m (-18.75); all at q4_k_m
Replication chain
This row is itself a replication of b2d2e231ec71….
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.
{
"construct": "next-up / next-week",
"metric": "comprehension_accuracy_delta",
"seed": 2026090205,
"comparator": {
"description": "Every scientific compact form is compared with its complete registered careful-English meaning; ambiguous bare English is absent from the scalar.",
"kind": "complete-careful-english-v1"
},
"study_purpose": "claim_test",
"study_scope": "Exact-reader fresh-input replication of the source scalar. Both forms remain load-bearing; strict-after, divergent/convergent and four boundary classes remain visible. No bare-English or unsupported-inference claim is tested.",
"items_sha256": "2e88803e2ca268f30237441e0a6cfc1f8eb05d156c38a871ffc5159013c14adb",
"items": [
{
"id": "SAT-NWD-next-up-00005",
"ainglish": "Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule next-up(Monday@2037-05-11).",
"english": "Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule the first Monday strictly after 2037-05-11; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2037-05-18 (+7 days)",
"2037-05-11 (+0 days)",
"2037-05-25 (+14 days)",
"2037-05-12 (+1 days)"
],
"answer": "2037-05-18 (+7 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Monday",
"target_weekday": "Monday",
"weekstart": "Monday",
"epoch": "ordinary",
"same_weekday": true,
"constructors_diverge": false,
"days_after_anchor": 7
}
},
{
"id": "SAT-NWD-next-up-00002",
"ainglish": "Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule next-up(Wednesday@2037-05-12).",
"english": "Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule the first Wednesday strictly after 2037-05-12; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2037-05-20 (+8 days)",
"2037-05-13 (+1 days)",
"2037-05-12 (+0 days)",
"2037-05-14 (+2 days)"
],
"answer": "2037-05-13 (+1 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Tuesday",
"target_weekday": "Wednesday",
"weekstart": "Sunday",
"epoch": "ordinary",
"same_weekday": false,
"constructors_diverge": true,
"days_after_anchor": 1
}
},
{
"id": "SAT-NWD-next-up-00001",
"ainglish": "Job briefing-001. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule next-up(Friday@2038-04-28).",
"english": "Job briefing-001. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule the first Friday strictly after 2038-04-28; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2038-05-07 (+9 days)",
"2038-04-28 (+0 days)",
"2038-04-30 (+2 days)",
"2038-04-29 (+1 days)"
],
"answer": "2038-04-30 (+2 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Wednesday",
"target_weekday": "Friday",
"weekstart": "Monday",
"epoch": "month-boundary",
"same_weekday": false,
"constructors_diverge": true,
"days_after_anchor": 2
}
},
{
"id": "SAT-NWD-next-up-00000",
"ainglish": "Job calibration-000. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule next-up(Sunday@2038-04-29).",
"english": "Job calibration-000. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule the first Sunday strictly after 2038-04-29; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2038-04-29 (+0 days)",
"2038-05-09 (+10 days)",
"2038-04-30 (+1 days)",
"2038-05-02 (+3 days)"
],
"answer": "2038-05-02 (+3 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Thursday",
"target_weekday": "Sunday",
"weekstart": "Sunday",
"epoch": "month-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 3
}
},
{
"id": "SAT-NWD-next-up-00006",
"ainglish": "Job dispatch-006. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule next-up(Tuesday@2039-12-30).",
"english": "Job dispatch-006. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule the first Tuesday strictly after 2039-12-30; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2040-01-03 (+4 days)",
"2039-12-30 (+0 days)",
"2040-01-10 (+11 days)",
"2039-12-31 (+1 days)"
],
"answer": "2040-01-03 (+4 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Friday",
"target_weekday": "Tuesday",
"weekstart": "Monday",
"epoch": "year-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 4
}
},
{
"id": "SAT-NWD-next-up-00003",
"ainglish": "Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule next-up(Thursday@2039-12-31).",
"english": "Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule the first Thursday strictly after 2039-12-31; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2039-12-31 (+0 days)",
"2040-01-05 (+5 days)",
"2040-01-12 (+12 days)",
"2040-01-01 (+1 days)"
],
"answer": "2040-01-05 (+5 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Saturday",
"target_weekday": "Thursday",
"weekstart": "Sunday",
"epoch": "year-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 5
}
},
{
"id": "SAT-NWD-next-up-00008",
"ainglish": "Job handoff-008. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule next-up(Saturday@2040-03-04).",
"english": "Job handoff-008. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule the first Saturday strictly after 2040-03-04; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2040-03-04 (+0 days)",
"2040-03-17 (+13 days)",
"2040-03-10 (+6 days)",
"2040-03-05 (+1 days)"
],
"answer": "2040-03-10 (+6 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Sunday",
"target_weekday": "Saturday",
"weekstart": "Monday",
"epoch": "leap-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 6
}
},
{
"id": "SAT-NWD-next-up-00015",
"ainglish": "Job inspection-015. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule next-up(Monday@2040-02-27).",
"english": "Job inspection-015. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule the first Monday strictly after 2040-02-27; exclude the anchor and make no calendar-week claim.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2040-02-27 (+0 days)",
"2040-03-12 (+14 days)",
"2040-02-28 (+1 days)",
"2040-03-05 (+7 days)"
],
"answer": "2040-03-05 (+7 days)",
"form": "next-up",
"settlement_stratum": "next-up",
"strata": {
"anchor_weekday": "Monday",
"target_weekday": "Monday",
"weekstart": "Sunday",
"epoch": "leap-boundary",
"same_weekday": true,
"constructors_diverge": false,
"days_after_anchor": 7
}
},
{
"id": "SAT-NWD-next-week-00005",
"ainglish": "Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule next-week(Monday@2037-05-11;Monday).",
"english": "Job archive-005. 2037-05-11 is Monday; target Monday; weeks start Monday. Schedule Monday in the seven-day week immediately after the week containing 2037-05-11, using Monday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2037-05-18 (+7 days)",
"2037-05-11 (+0 days)",
"2037-05-25 (+14 days)",
"2037-05-12 (+1 days)"
],
"answer": "2037-05-18 (+7 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Monday",
"target_weekday": "Monday",
"weekstart": "Monday",
"epoch": "ordinary",
"same_weekday": true,
"constructors_diverge": false,
"days_after_anchor": 7
}
},
{
"id": "SAT-NWD-next-week-00002",
"ainglish": "Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule next-week(Wednesday@2037-05-12;Sunday).",
"english": "Job backup-002. 2037-05-12 is Tuesday; target Wednesday; weeks start Sunday. Schedule Wednesday in the seven-day week immediately after the week containing 2037-05-12, using Sunday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2037-05-13 (+1 days)",
"2037-05-20 (+8 days)",
"2037-05-12 (+0 days)",
"2037-05-27 (+15 days)"
],
"answer": "2037-05-20 (+8 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Tuesday",
"target_weekday": "Wednesday",
"weekstart": "Sunday",
"epoch": "ordinary",
"same_weekday": false,
"constructors_diverge": true,
"days_after_anchor": 8
}
},
{
"id": "SAT-NWD-next-week-00000",
"ainglish": "Job briefing-000. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule next-week(Friday@2038-04-28;Monday).",
"english": "Job briefing-000. 2038-04-28 is Wednesday; target Friday; weeks start Monday. Schedule Friday in the seven-day week immediately after the week containing 2038-04-28, using Monday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2038-04-30 (+2 days)",
"2038-04-28 (+0 days)",
"2038-05-07 (+9 days)",
"2038-05-14 (+16 days)"
],
"answer": "2038-05-07 (+9 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Wednesday",
"target_weekday": "Friday",
"weekstart": "Monday",
"epoch": "month-boundary",
"same_weekday": false,
"constructors_diverge": true,
"days_after_anchor": 9
}
},
{
"id": "SAT-NWD-next-week-00001",
"ainglish": "Job calibration-001. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule next-week(Sunday@2038-04-29;Sunday).",
"english": "Job calibration-001. 2038-04-29 is Thursday; target Sunday; weeks start Sunday. Schedule Sunday in the seven-day week immediately after the week containing 2038-04-29, using Sunday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2038-04-29 (+0 days)",
"2038-05-09 (+10 days)",
"2038-04-30 (+1 days)",
"2038-05-02 (+3 days)"
],
"answer": "2038-05-02 (+3 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Thursday",
"target_weekday": "Sunday",
"weekstart": "Sunday",
"epoch": "month-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 3
}
},
{
"id": "SAT-NWD-next-week-00012",
"ainglish": "Job dispatch-012. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule next-week(Tuesday@2039-12-30;Monday).",
"english": "Job dispatch-012. 2039-12-30 is Friday; target Tuesday; weeks start Monday. Schedule Tuesday in the seven-day week immediately after the week containing 2039-12-30, using Monday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2040-01-03 (+4 days)",
"2039-12-30 (+0 days)",
"2040-01-10 (+11 days)",
"2039-12-31 (+1 days)"
],
"answer": "2040-01-03 (+4 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Friday",
"target_weekday": "Tuesday",
"weekstart": "Monday",
"epoch": "year-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 4
}
},
{
"id": "SAT-NWD-next-week-00003",
"ainglish": "Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule next-week(Thursday@2039-12-31;Sunday).",
"english": "Job export-003. 2039-12-31 is Saturday; target Thursday; weeks start Sunday. Schedule Thursday in the seven-day week immediately after the week containing 2039-12-31, using Sunday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2039-12-31 (+0 days)",
"2040-01-05 (+5 days)",
"2040-01-12 (+12 days)",
"2040-01-01 (+1 days)"
],
"answer": "2040-01-05 (+5 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Saturday",
"target_weekday": "Thursday",
"weekstart": "Sunday",
"epoch": "year-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 5
}
},
{
"id": "SAT-NWD-next-week-00004",
"ainglish": "Job handoff-004. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule next-week(Saturday@2040-03-04;Monday).",
"english": "Job handoff-004. 2040-03-04 is Sunday; target Saturday; weeks start Monday. Schedule Saturday in the seven-day week immediately after the week containing 2040-03-04, using Monday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2040-03-04 (+0 days)",
"2040-03-17 (+13 days)",
"2040-03-10 (+6 days)",
"2040-03-05 (+1 days)"
],
"answer": "2040-03-10 (+6 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Sunday",
"target_weekday": "Saturday",
"weekstart": "Monday",
"epoch": "leap-boundary",
"same_weekday": false,
"constructors_diverge": false,
"days_after_anchor": 6
}
},
{
"id": "SAT-NWD-next-week-00007",
"ainglish": "Job inspection-007. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule next-week(Monday@2040-02-27;Sunday).",
"english": "Job inspection-007. 2040-02-27 is Monday; target Monday; weeks start Sunday. Schedule Monday in the seven-day week immediately after the week containing 2040-02-27, using Sunday as week start; never use the current week.",
"question": "Which ISO date is selected, and how many days after the anchor?",
"options": [
"2040-02-27 (+0 days)",
"2040-03-12 (+14 days)",
"2040-02-28 (+1 days)",
"2040-03-05 (+7 days)"
],
"answer": "2040-03-05 (+7 days)",
"form": "next-week",
"settlement_stratum": "next-week",
"strata": {
"anchor_weekday": "Monday",
"target_weekday": "Monday",
"weekstart": "Sunday",
"epoch": "leap-boundary",
"same_weekday": true,
"constructors_diverge": false,
"days_after_anchor": 7
}
},
{
"id": "SAT-NWD-cal-01",
"calibration": true,
"calibration_scope": "target-independent",
"ainglish": "A sealed note says Iris's token is in bay 12.",
"english": "A sealed note mentions Iris's token but gives no location.",
"question": "Where does the note place Iris's token?",
"options": [
"bay 12",
"dispatch desk",
"archive room",
"not stated"
],
"answer": "bay 12"
},
{
"id": "SAT-NWD-cal-02",
"calibration": true,
"calibration_scope": "target-independent",
"ainglish": "A sealed note says Marek's token is in locker 31.",
"english": "A sealed note mentions Marek's token but gives no location.",
"question": "Where does the note place Marek's token?",
"options": [
"locker 31",
"dispatch desk",
"archive room",
"not stated"
],
"answer": "locker 31"
},
{
"id": "SAT-NWD-cal-03",
"calibration": true,
"calibration_scope": "target-independent",
"ainglish": "A sealed note says Nadia's token is in shelf 47.",
"english": "A sealed note mentions Nadia's token but gives no location.",
"question": "Where does the note place Nadia's token?",
"options": [
"shelf 47",
"dispatch desk",
"archive room",
"not stated"
],
"answer": "shelf 47"
},
{
"id": "SAT-NWD-cal-04",
"calibration": true,
"calibration_scope": "target-independent",
"ainglish": "A sealed note says Oren's token is in vault 58.",
"english": "A sealed note mentions Oren's token but gives no location.",
"question": "Where does the note place Oren's token?",
"options": [
"vault 58",
"dispatch desk",
"archive room",
"not stated"
],
"answer": "vault 58"
}
],
"models": [
"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m",
"gemma3-12b-opaque-choice-q4_k_m@q4_k_m"
],
"readers": [
{
"name": "mistral-small3.2-24b-opaque-choice-q4_k_m",
"provider": "ollama",
"model": "dexagon-mistral-small3.2-24b-pp-task:ctx4k",
"precision": "q4_k_m",
"api": "openai",
"base_url": "http://127.0.0.1:11434/v1",
"model_digest": "sha256:6629ee92de51c9a1367e1331cfa9ef6a77058a44a6a3e18ab524b2d0404252de",
"digest_source": "ollama:/api/tags",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "ollama:/api/tags"
},
"answer_protocol": "opaque-choice-v1",
"max_tokens": 32,
"timeout_s": 120,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
},
{
"name": "gemma3-12b-opaque-choice-q4_k_m",
"provider": "ollama",
"model": "dexagon-gemma3-12b-pp-task:ctx4k",
"precision": "q4_k_m",
"api": "openai",
"base_url": "http://127.0.0.1:11434/v1",
"model_digest": "sha256:de1f65ea3438dfcc7c3387802b9425a140fb01ecc79edf4924a13fab051eb68f",
"digest_source": "ollama:/api/tags",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "ollama:/api/tags"
},
"answer_protocol": "opaque-choice-v1",
"max_tokens": 32,
"timeout_s": 120,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
}
],
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": [
{
"reader": "mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m",
"digest_source": "ollama:/api/tags"
},
{
"reader": "gemma3-12b-opaque-choice-q4_k_m@q4_k_m",
"digest_source": "ollama:/api/tags"
}
]
},
"item_counts": {
"real": 16,
"calibration": 4
},
"interval_kind": "bootstrap_items",
"interval_estimator": {
"kind": "ainglish.panel.bootstrap-items-attestation.v1",
"algorithm": "sha256-counter-modulo-v1",
"draws": 2000,
"sampling_unit": "item",
"quantiles": [
"0.025",
"0.975"
],
"items_index_sha256": "ff1a1181fb10e0a17cb3b436b5197371bda737ab3d548d9b092b05021bbc35ec"
},
"settlement_strata": [
{
"id": "next-up",
"weight": 1
},
{
"id": "next-week",
"weight": 1
}
],
"settlement_item_field": "settlement_stratum",
"settlement_rule": "manifest-weighted arms and value; every stratum load-bearing",
"calibration": {
"planted_arm": "ainglish",
"min_gap": 0.5,
"min_recovered": null,
"rule": "absolute-gap-v1",
"ordering": "calibration-first",
"arm_exposure": "both-arms-per-reader-item",
"cells": 16
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.60",
"transport": {
"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m": {
"max_tokens": 32,
"timeout_s": 120,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
},
"gemma3-12b-opaque-choice-q4_k_m@q4_k_m": {
"max_tokens": 32,
"timeout_s": 120,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
}
},
"concurrency": {
"max_in_flight": 1,
"per_reader_max_in_flight": {
"mistral-small3.2-24b-opaque-choice-q4_k_m": 1,
"gemma3-12b-opaque-choice-q4_k_m": 1
},
"result_order": "deterministic-plan-order",
"calibration_barrier": true,
"automatic_retries": false
},
"transport_faults": {
"total": 0,
"retried": false,
"per_cell": []
},
"transport_truncations": {
"total": 0,
"per_reader_cell": [],
"by_cell": {
"english": 0,
"ainglish": 0
},
"imbalanced_across_cells": false
},
"protocol": "panel.py counterbalanced real arms + both-arms-per-reader-item planted-effect calibration gate",
"replicates_hash": "b2d2e231ec71a2fcd17b07e467e5213a09ab61aa40033fdd3167aec1e259c31f"
}