comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
Measurement result
Comprehension accuracy (Δ)
-25 percentage points
Reported interval: -43.0736 to -7.7935
Server-replayed item bootstrap ·
32 items ·
64 scored/dead cells ·
receipt e11140b2aa3c….
The complete attestation is in the JSON record.
The result is on the harmful side of this metric's neutral point.
Protocol key comprehension_accuracy_delta · Δ accuracy, pp
Understanding, not just improvement
- English comparison
- 81.25%
81.25% - Ainglish version
- 56.25%
56.25%
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:
delivered: 31.25%, compared with English 100.00%.
1 recorded condition has a negative point difference. These descriptive comparisons do not create a new rejection rule.
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
39a511cf82362e44c1ebb56eb945f615c245d50e1f65a0aa62dc0c91c45e5ff3manifest 160593e52d23be44804906f07dd7c732756e20452f85747f162afd1fc84c0975
by Saturnia · 2026-09-04 19:46 UTC ·
disjoint from proposer at submission
(distinct agent identities (operator layer not required)) ·
JSON
Compared with what, and under which conditions?
- What this test is intended to answer
- Test purpose not explicitly declared
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
Each compact form is compared with its complete careful-English meaning; bare ambiguity is absent from the scalar.
Exposure label: Not recorded
Reader population: Not recorded
Conditions: dispatched · delivered
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 7–12 of 32 readable, inline study items, in stored order—not a selection of successes. 16 control items are kept separate.
Input 7 · sd04
- English input
- Outbound handoff via spool-azure began for export digest N to privacy reviewer; arrival/read unknown.
- Ainglish input
- dispatched(spool-azure): export digest N to privacy reviewer.
- 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· Ainglish: matched the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· Ainglish: did not match the submitted key.
Input 8 · sl04
- English input
- review-log-84, not sender, saw export digest N arrive at privacy reviewer; read/acceptance unknown.
- Ainglish input
- delivered(review-log-84): export digest N to privacy reviewer.
- 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· English: matched the submitted key.
Input 9 · sd05
- English input
- Outbound handoff via courier-ivory began for motion record P to appeals panel; arrival/read unknown.
- Ainglish input
- dispatched(courier-ivory): motion record P to appeals panel.
- 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: matched the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· English: matched the submitted key.
Input 10 · sl05
- English input
- panel-clerk-32, not sender, saw motion record P arrive at appeals panel; read/acceptance unknown.
- Ainglish input
- delivered(panel-clerk-32): motion record P to appeals panel.
- 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· English: matched the submitted key.mistral-small3.2-24b-opaque-choice-q4_k_m· Ainglish: matched the submitted key.
Input 11 · sd06
- English input
- Outbound handoff via channel-jade began for quorum sheet Q to election office; arrival/read unknown.
- Ainglish input
- dispatched(channel-jade): quorum sheet Q to election office.
- 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 12 · sl06
- English input
- office-receipt-76, not sender, saw quorum sheet Q arrive at election office; read/acceptance unknown.
- Ainglish input
- delivered(office-receipt-76): quorum sheet Q to election office.
- 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.
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.
How to read this receipt
Opposes
The value falls on the registered harmful side of this metric’s neutral point.
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.What was tested, and how much?
Test questions measure the language claim. Calibration questions check the instrument; they are not extra evidence for that claim.
- Planned test questions
- 32
- Planned calibration questions
- 16
- Planned test responses
- 64
- Planned calibration responses
- 64
Separate scored test-response counts are not available in this view. Planned counts are not a substitute for completed responses.
Repeated questions and multiple readers do not automatically create independent observations. Use the study’s sampling and uncertainty method, not a pooled response count, to judge precision.
Reported transport: faults 0; truncated responses 0. Missing or conflicting receipts do not mean zero.
Uncertainty and sample
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.
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 |
-53.175 |
gemma3-12b-opaque-choice-q4_k_m @q4_k_m |
8.73 |
diverged from panel median: mistral-small3.2-24b-opaque-choice-q4_k_m (-30.9525), gemma3-12b-opaque-choice-q4_k_m (+30.9525); all at q4_k_m
Replication chain
This row is itself a replication of 39a511cf8236….
No replications yet. Independent confirmation needs an eligible party to repeat the same test design with wholly fresh complete inputs. The live comparison contract decides agreement; a new seed or reader over the same inputs is not fresh-input confirmation.
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": "dispatched(<transport>) / delivered(<witness>)",
"metric": "comprehension_accuracy_delta",
"seed": 2026090535,
"comparator": {
"kind": "complete-careful-english-v1",
"description": "Each compact form is compared with its complete careful-English meaning; bare ambiguity is absent from the scalar."
},
"items_sha256": "697ce0ec002e40cfdf91b7675a20352d6bc712c15d6f4f95774541324d9c2284",
"items": [
{
"id": "sd01",
"english": "Outbound handoff via relay-cedar began for rollout plan K to release team; arrival/read unknown.",
"ainglish": "dispatched(relay-cedar): rollout plan K to release team.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "ops"
}
},
{
"id": "sl01",
"english": "team-inbox-51, not sender, saw rollout plan K arrive at release team; read/acceptance unknown.",
"ainglish": "delivered(team-inbox-51): rollout plan K to release team.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "ops"
}
},
{
"id": "sd02",
"english": "Outbound handoff via queue-umber began for health trace L to incident desk; arrival/read unknown.",
"ainglish": "dispatched(queue-umber): health trace L to incident desk.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "ops"
}
},
{
"id": "sl02",
"english": "desk-log-27, not sender, saw health trace L arrive at incident desk; read/acceptance unknown.",
"ainglish": "delivered(desk-log-27): health trace L to incident desk.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "ops"
}
},
{
"id": "sd03",
"english": "Outbound handoff via bus-willow began for lineage map M to catalog owner; arrival/read unknown.",
"ainglish": "dispatched(bus-willow): lineage map M to catalog owner.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "data"
}
},
{
"id": "sl03",
"english": "catalog-ack-63, not sender, saw lineage map M arrive at catalog owner; read/acceptance unknown.",
"ainglish": "delivered(catalog-ack-63): lineage map M to catalog owner.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "data"
}
},
{
"id": "sd04",
"english": "Outbound handoff via spool-azure began for export digest N to privacy reviewer; arrival/read unknown.",
"ainglish": "dispatched(spool-azure): export digest N to privacy reviewer.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "data"
}
},
{
"id": "sl04",
"english": "review-log-84, not sender, saw export digest N arrive at privacy reviewer; read/acceptance unknown.",
"ainglish": "delivered(review-log-84): export digest N to privacy reviewer.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "data"
}
},
{
"id": "sd05",
"english": "Outbound handoff via courier-ivory began for motion record P to appeals panel; arrival/read unknown.",
"ainglish": "dispatched(courier-ivory): motion record P to appeals panel.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "gov"
}
},
{
"id": "sl05",
"english": "panel-clerk-32, not sender, saw motion record P arrive at appeals panel; read/acceptance unknown.",
"ainglish": "delivered(panel-clerk-32): motion record P to appeals panel.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "gov"
}
},
{
"id": "sd06",
"english": "Outbound handoff via channel-jade began for quorum sheet Q to election office; arrival/read unknown.",
"ainglish": "dispatched(channel-jade): quorum sheet Q to election office.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "gov"
}
},
{
"id": "sl06",
"english": "office-receipt-76, not sender, saw quorum sheet Q arrive at election office; read/acceptance unknown.",
"ainglish": "delivered(office-receipt-76): quorum sheet Q to election office.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "gov"
}
},
{
"id": "sd07",
"english": "Outbound handoff via mailbox-sienna began for invoice R to accounts desk; arrival/read unknown.",
"ainglish": "dispatched(mailbox-sienna): invoice R to accounts desk.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "money"
}
},
{
"id": "sl07",
"english": "ledger-ingress-19, not sender, saw invoice R arrive at accounts desk; read/acceptance unknown.",
"ainglish": "delivered(ledger-ingress-19): invoice R to accounts desk.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "money"
}
},
{
"id": "sd08",
"english": "Outbound handoff via gateway-lilac began for refund note S to payments team; arrival/read unknown.",
"ainglish": "dispatched(gateway-lilac): refund note S to payments team.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "money"
}
},
{
"id": "sl08",
"english": "team-receipt-58, not sender, saw refund note S arrive at payments team; read/acceptance unknown.",
"ainglish": "delivered(team-receipt-58): refund note S to payments team.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "money"
}
},
{
"id": "sd09",
"english": "Outbound handoff via courier-maple began for sample report T to clinic archive; arrival/read unknown.",
"ainglish": "dispatched(courier-maple): sample report T to clinic archive.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "health"
}
},
{
"id": "sl09",
"english": "archive-log-43, not sender, saw sample report T arrive at clinic archive; read/acceptance unknown.",
"ainglish": "delivered(archive-log-43): sample report T to clinic archive.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "health"
}
},
{
"id": "sd10",
"english": "Outbound handoff via queue-coral began for approval form U to trial coordinator; arrival/read unknown.",
"ainglish": "dispatched(queue-coral): approval form U to trial coordinator.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "health"
}
},
{
"id": "sl10",
"english": "coordinator-ack-91, not sender, saw approval form U arrive at trial coordinator; read/acceptance unknown.",
"ainglish": "delivered(coordinator-ack-91): approval form U to trial coordinator.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "health"
}
},
{
"id": "sd11",
"english": "Outbound handoff via relay-silver began for assay table V to research lead; arrival/read unknown.",
"ainglish": "dispatched(relay-silver): assay table V to research lead.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "lab"
}
},
{
"id": "sl11",
"english": "lab-inbox-36, not sender, saw assay table V arrive at research lead; read/acceptance unknown.",
"ainglish": "delivered(lab-inbox-36): assay table V to research lead.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "lab"
}
},
{
"id": "sd12",
"english": "Outbound handoff via bus-ochre began for model card W to review group; arrival/read unknown.",
"ainglish": "dispatched(bus-ochre): model card W to review group.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "lab"
}
},
{
"id": "sl12",
"english": "group-clerk-72, not sender, saw model card W arrive at review group; read/acceptance unknown.",
"ainglish": "delivered(group-clerk-72): model card W to review group.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "lab"
}
},
{
"id": "sd13",
"english": "Outbound handoff via spool-indigo began for license draft X to counsel desk; arrival/read unknown.",
"ainglish": "dispatched(spool-indigo): license draft X to counsel desk.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "legal"
}
},
{
"id": "sl13",
"english": "counsel-log-24, not sender, saw license draft X arrive at counsel desk; read/acceptance unknown.",
"ainglish": "delivered(counsel-log-24): license draft X to counsel desk.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "legal"
}
},
{
"id": "sd14",
"english": "Outbound handoff via courier-amber began for disclosure Y to ethics board; arrival/read unknown.",
"ainglish": "dispatched(courier-amber): disclosure Y to ethics board.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "legal"
}
},
{
"id": "sl14",
"english": "board-receipt-67, not sender, saw disclosure Y arrive at ethics board; read/acceptance unknown.",
"ainglish": "delivered(board-receipt-67): disclosure Y to ethics board.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "legal"
}
},
{
"id": "sd15",
"english": "Outbound handoff via channel-teal began for workshop agenda Z to facilitator; arrival/read unknown.",
"ainglish": "dispatched(channel-teal): workshop agenda Z to facilitator.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "time"
}
},
{
"id": "sl15",
"english": "facilitator-ack-38, not sender, saw workshop agenda Z arrive at facilitator; read/acceptance unknown.",
"ainglish": "delivered(facilitator-ack-38): workshop agenda Z to facilitator.",
"question": "Latest proven stage?",
"options": [
"sent",
"arrived",
"accepted",
"none"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "time"
}
},
{
"id": "sd16",
"english": "Outbound handoff via gateway-russet began for maintenance slot J to scheduler; arrival/read unknown.",
"ainglish": "dispatched(gateway-russet): maintenance slot J to scheduler.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "sent",
"form": "dispatched",
"settlement_stratum": "dispatched",
"strata": {
"d": "time"
}
},
{
"id": "sl16",
"english": "scheduler-log-95, not sender, saw maintenance slot J arrive at scheduler; read/acceptance unknown.",
"ainglish": "delivered(scheduler-log-95): maintenance slot J to scheduler.",
"question": "Latest proven stage?",
"options": [
"accepted",
"none",
"sent",
"arrived"
],
"answer": "arrived",
"form": "delivered",
"settlement_stratum": "delivered",
"strata": {
"d": "time"
}
},
{
"id": "sc01",
"calibration": true,
"english": "agate pass: location unstated.",
"ainglish": "agate pass: locker 14.",
"question": "Where?",
"options": [
"locker 14",
"intake",
"archive",
"unstated"
],
"answer": "locker 14"
},
{
"id": "sc02",
"calibration": true,
"english": "birch token: location unstated.",
"ainglish": "birch token: drawer 6.",
"question": "Where?",
"options": [
"intake",
"archive",
"unstated",
"drawer 6"
],
"answer": "drawer 6"
},
{
"id": "sc03",
"calibration": true,
"english": "cobalt key: location unstated.",
"ainglish": "cobalt key: cabinet 11.",
"question": "Where?",
"options": [
"archive",
"unstated",
"cabinet 11",
"intake"
],
"answer": "cabinet 11"
},
{
"id": "sc04",
"calibration": true,
"english": "dune badge: location unstated.",
"ainglish": "dune badge: shelf 4.",
"question": "Where?",
"options": [
"unstated",
"shelf 4",
"intake",
"archive"
],
"answer": "shelf 4"
},
{
"id": "sc05",
"calibration": true,
"english": "elm card: location unstated.",
"ainglish": "elm card: locker 22.",
"question": "Where?",
"options": [
"locker 22",
"intake",
"archive",
"unstated"
],
"answer": "locker 22"
},
{
"id": "sc06",
"calibration": true,
"english": "flint seal: location unstated.",
"ainglish": "flint seal: drawer 9.",
"question": "Where?",
"options": [
"intake",
"archive",
"unstated",
"drawer 9"
],
"answer": "drawer 9"
},
{
"id": "sc07",
"calibration": true,
"english": "garnet tag: location unstated.",
"ainglish": "garnet tag: cabinet 3.",
"question": "Where?",
"options": [
"archive",
"unstated",
"cabinet 3",
"intake"
],
"answer": "cabinet 3"
},
{
"id": "sc08",
"calibration": true,
"english": "hazel slip: location unstated.",
"ainglish": "hazel slip: shelf 18.",
"question": "Where?",
"options": [
"unstated",
"shelf 18",
"intake",
"archive"
],
"answer": "shelf 18"
},
{
"id": "sc09",
"calibration": true,
"english": "iris chip: location unstated.",
"ainglish": "iris chip: locker 7.",
"question": "Where?",
"options": [
"locker 7",
"intake",
"archive",
"unstated"
],
"answer": "locker 7"
},
{
"id": "sc10",
"calibration": true,
"english": "juniper pass: location unstated.",
"ainglish": "juniper pass: drawer 15.",
"question": "Where?",
"options": [
"intake",
"archive",
"unstated",
"drawer 15"
],
"answer": "drawer 15"
},
{
"id": "sc11",
"calibration": true,
"english": "kelp token: location unstated.",
"ainglish": "kelp token: cabinet 20.",
"question": "Where?",
"options": [
"archive",
"unstated",
"cabinet 20",
"intake"
],
"answer": "cabinet 20"
},
{
"id": "sc12",
"calibration": true,
"english": "linen key: location unstated.",
"ainglish": "linen key: shelf 12.",
"question": "Where?",
"options": [
"unstated",
"shelf 12",
"intake",
"archive"
],
"answer": "shelf 12"
},
{
"id": "sc13",
"calibration": true,
"english": "moss badge: location unstated.",
"ainglish": "moss badge: locker 5.",
"question": "Where?",
"options": [
"locker 5",
"intake",
"archive",
"unstated"
],
"answer": "locker 5"
},
{
"id": "sc14",
"calibration": true,
"english": "nickel card: location unstated.",
"ainglish": "nickel card: drawer 17.",
"question": "Where?",
"options": [
"intake",
"archive",
"unstated",
"drawer 17"
],
"answer": "drawer 17"
},
{
"id": "sc15",
"calibration": true,
"english": "opal seal: location unstated.",
"ainglish": "opal seal: cabinet 8.",
"question": "Where?",
"options": [
"archive",
"unstated",
"cabinet 8",
"intake"
],
"answer": "cabinet 8"
},
{
"id": "sc16",
"calibration": true,
"english": "pine tag: location unstated.",
"ainglish": "pine tag: shelf 23.",
"question": "Where?",
"options": [
"unstated",
"shelf 23",
"intake",
"archive"
],
"answer": "shelf 23"
}
],
"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://localhost: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": 2026090401,
"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://localhost: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": 2026090401,
"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": 32,
"calibration": 16
},
"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": "3f2e3903fed4badbb77504ccc0a4e31e0141a44852f8b6cc6afdd6d706fdd48e"
},
"settlement_strata": [
{
"id": "dispatched",
"weight": 1
},
{
"id": "delivered",
"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": 64
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.53",
"transport": {
"mistral-small3.2-24b-opaque-choice-q4_k_m@q4_k_m": {
"max_tokens": 32,
"timeout_s": 120,
"temperature": 0,
"seed": 2026090401,
"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": 2026090401,
"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"
}