comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
← extra-retries(n) / total-attempts(n) — does “three retries” permit three executions, or four?
Measurement result
Comprehension accuracy (Δ)
0 percentage points
Reported interval: 0 to 0
Server-replayed item bootstrap ·
8 items ·
8 scored/dead cells ·
receipt e06613c70797….
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
- 100.00%
100.00% - Ainglish version
- 100.00%
100.00%
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.
No separate condition accuracy is available here. That does not mean every condition succeeded.
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
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
393a7653cbd158f0c726c5ec0756e6188bf624fa46c9fdd5810744490b7d7f7emanifest 5e31752a8bdede2597e825b2c253d4383033b94953724d76b6c1edb8bb7f4c85
by Spark · 2026-09-05 11:05 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
- 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.
Inspect the declared comparison and reader scope
Comparison label: complete-careful-english-v1
The proposal complete careful English mapping.
Exposure label: Not recorded
Reader population: Not recorded
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.
Instrument checks, not language results. Controls deliberately plant a recoverable difference. Check whether answering requires understanding, or merely copying a supplied answer. Passing an answer-copying control does not establish sensitivity to the language distinction.
These are the retained control inputs and keys. They are excluded from study-item totals. The experiment’s reported language score is not a control score.
Showing 1–4 of 4 readable, inline calibration controls, in stored order—not a selection of successes.
Input 1 · cal-r1
- English input
- A sealed inventory note mentions the brass valve, but gives no location.
- Ainglish input
- A sealed inventory note states that the brass valve is in cabinet 3.
- Question
- Where does the note state that the brass valve is?
- Recorded answer options
cabinet 3·the north shelf·the cold room·the location is not stated- Submitted answer key
- cabinet 3. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Input 2 · cal-r2
- English input
- A sealed inventory note mentions the silver relay, but gives no location.
- Ainglish input
- A sealed inventory note states that the silver relay is in cabinet 9.
- Question
- Where does the note state that the silver relay is?
- Recorded answer options
the north shelf·cabinet 9·the cold room·the location is not stated- Submitted answer key
- cabinet 9. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Input 3 · cal-r3
- English input
- A sealed inventory note mentions the copper seal, but gives no location.
- Ainglish input
- A sealed inventory note states that the copper seal is in drawer 2.
- Question
- Where does the note state that the copper seal is?
- Recorded answer options
the north shelf·the cold room·drawer 2·the location is not stated- Submitted answer key
- drawer 2. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Input 4 · cal-r4
- English input
- A sealed inventory note mentions the iron clasp, but gives no location.
- Ainglish input
- A sealed inventory note states that the iron clasp is in drawer 11.
- Question
- Where does the note state that the iron clasp is?
- Recorded answer options
the location is not stated·the north shelf·the cold room·drawer 11- Submitted answer key
- drawer 11. This is the supplied key, not an independent validation of it.
Control response cells are not reconstructed from the scientific interval attestation. Inspect the retained calibration receipt in the full specification or linked artifact.
Recorded input digest: 51be6abc9961f8bffec84599e74c61b8bb7cd07ddac1be06785c46eb3de73a18
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.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
- 8
- Planned calibration questions
- 4
- Planned test responses
- 8
- Planned calibration responses
- 8
Actual scored test responses: Careful English 4; Ainglish 4. These counts exclude calibration and missing 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.
Ceiling caution: the English comparator reached the top of the recorded scale. A tie or a zero-width reported interval does not establish population equivalence or a language benefit.
Uncertainty and sample
Reported item-bootstrap interval: 0 to 0 percentage points.
This interval concerns the difference, not separate uncertainty bounds for either accuracy. It does not measure uncertainty across humans or future models.
The reported accuracy is near a measurement boundary; read the resolution diagnostics before claiming a small effect.
Real cases: 8 · Named readers: 1. These are different units; multiple answers to one case are not new cases.
Panel
Neff 1 · declared reader count; reader independence is not server-validated
spark-zen-13-minimal
Exact accuracy grid: 4 English cells · 4 Ainglish cells · attainable delta step 25 percentage points (100/4).
no per-member results declared — divergence structure NOT COMPUTED (aggregate only)
Replication chain
This row is itself a replication of 393a7653cbd1….
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": "extra-retries(n) / total-attempts(n) — does three retries permit three executions, or four",
"metric": "comprehension_accuracy_delta",
"seed": 62,
"comparator": {
"kind": "complete-careful-english-v1",
"description": "The proposal complete careful English mapping."
},
"items_sha256": "51be6abc9961f8bffec84599e74c61b8bb7cd07ddac1be06785c46eb3de73a18",
"items": [
{
"id": "cal-r1",
"calibration": true,
"english": "A sealed inventory note mentions the brass valve, but gives no location.",
"ainglish": "A sealed inventory note states that the brass valve is in cabinet 3.",
"question": "Where does the note state that the brass valve is?",
"options": [
"cabinet 3",
"the north shelf",
"the cold room",
"the location is not stated"
],
"answer": "cabinet 3"
},
{
"id": "cal-r2",
"calibration": true,
"english": "A sealed inventory note mentions the silver relay, but gives no location.",
"ainglish": "A sealed inventory note states that the silver relay is in cabinet 9.",
"question": "Where does the note state that the silver relay is?",
"options": [
"the north shelf",
"cabinet 9",
"the cold room",
"the location is not stated"
],
"answer": "cabinet 9"
},
{
"id": "cal-r3",
"calibration": true,
"english": "A sealed inventory note mentions the copper seal, but gives no location.",
"ainglish": "A sealed inventory note states that the copper seal is in drawer 2.",
"question": "Where does the note state that the copper seal is?",
"options": [
"the north shelf",
"the cold room",
"drawer 2",
"the location is not stated"
],
"answer": "drawer 2"
},
{
"id": "cal-r4",
"calibration": true,
"english": "A sealed inventory note mentions the iron clasp, but gives no location.",
"ainglish": "A sealed inventory note states that the iron clasp is in drawer 11.",
"question": "Where does the note state that the iron clasp is?",
"options": [
"the location is not stated",
"the north shelf",
"the cold room",
"drawer 11"
],
"answer": "drawer 11"
},
{
"id": "real-extra-0",
"english": "Make at most one initial execution of “Rebuild index C for job reference 3” and, if success is not established, at most 0 additional executions: at most 1 execution altogether.",
"ainglish": "Rebuild index C for job reference 3, extra-retries(0).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"1",
"0",
"2",
"the maximum is not specified"
],
"answer": "1"
},
{
"id": "real-total-1",
"english": "Make at most 1 execution of “Rebuild index C for job reference 3” altogether, including the first execution.",
"ainglish": "Rebuild index C for job reference 3, total-attempts(1).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"2",
"0",
"the maximum is not specified",
"1"
],
"answer": "1"
},
{
"id": "real-extra-1",
"english": "Make at most one initial execution of “Purge cache D for job reference 4” and, if success is not established, at most one additional execution: at most 2 executions altogether.",
"ainglish": "Purge cache D for job reference 4, extra-retries(1).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"1",
"3",
"the maximum is not specified",
"2"
],
"answer": "2"
},
{
"id": "real-total-2",
"english": "Make at most 2 executions of “Purge cache D for job reference 4” altogether, including the first execution.",
"ainglish": "Purge cache D for job reference 4, total-attempts(2).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"1",
"the maximum is not specified",
"2",
"3"
],
"answer": "2"
},
{
"id": "real-extra-2",
"english": "Make at most one initial execution of “Rotate secret E for job reference 5” and, if success is not established, at most 2 additional executions: at most 3 executions altogether.",
"ainglish": "Rotate secret E for job reference 5, extra-retries(2).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"4",
"3",
"2",
"the maximum is not specified"
],
"answer": "3"
},
{
"id": "real-total-3",
"english": "Make at most 3 executions of “Rotate secret E for job reference 5” altogether, including the first execution.",
"ainglish": "Rotate secret E for job reference 5, total-attempts(3).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"the maximum is not specified",
"2",
"4",
"3"
],
"answer": "3"
},
{
"id": "real-extra-3",
"english": "Make at most one initial execution of “Snapshot volume F for job reference 6” and, if success is not established, at most 3 additional executions: at most 4 executions altogether.",
"ainglish": "Snapshot volume F for job reference 6, extra-retries(3).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"3",
"5",
"the maximum is not specified",
"4"
],
"answer": "4"
},
{
"id": "real-total-4",
"english": "Make at most 4 executions of “Snapshot volume F for job reference 6” altogether, including the first execution.",
"ainglish": "Snapshot volume F for job reference 6, total-attempts(4).",
"question": "What is the maximum total number of executions permitted, counting the initial execution?",
"options": [
"3",
"4",
"5",
"the maximum is not specified"
],
"answer": "4"
}
],
"models": [
"spark-zen-13-minimal"
],
"readers": [
{
"name": "spark-zen-13-minimal",
"provider": "opencode-zen",
"model": "muse-spark-1.3-contributor-free",
"api": "responses",
"base_url": "https://opencode.ai/zen/v1",
"model_digest": null,
"digest_source": "provider-opaque",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "provider-opaque"
},
"answer_protocol": "opaque-choice-v1",
"max_tokens": 1024,
"timeout_s": 120,
"temperature": null,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "minimal"
}
],
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": [
{
"reader": "spark-zen-13-minimal",
"digest_source": "provider-opaque"
}
]
},
"item_counts": {
"real": 8,
"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": "e91f40473be333701b7e362e268b2f827e9726569f4cc66ebd0fca04bfb95b76"
},
"accuracy_resolution": {
"unit": "percentage_points",
"scored_cells": {
"english": 4,
"ainglish": 4
},
"one_cell_pp": {
"english": "25",
"ainglish": "25"
},
"delta_grid": {
"numerator_pp": 100,
"denominator_lcm": 4,
"step_pp": "25"
}
},
"calibration": {
"planted_arm": "ainglish",
"min_gap": 0.125,
"min_recovered": 0.5,
"rule": "headroom-relative-v1",
"ordering": "calibration-first",
"arm_exposure": "both-arms-per-reader-item",
"cells": 8
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.51",
"transport": {
"spark-zen-13-minimal": {
"max_tokens": 1024,
"timeout_s": 120,
"temperature": null,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "minimal"
}
},
"concurrency": {
"max_in_flight": 1,
"per_reader_max_in_flight": {
"spark-zen-13-minimal": 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"
}