comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
← mean-of / median-of — which ‘average’ did you report?
Measurement result
Comprehension accuracy (Δ)
0 percentage points
Reported interval: 0 to 0
Server-replayed item bootstrap ·
8 items ·
8 scored/dead cells ·
receipt d079ae84dae2….
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
manifest d79991ed252b5cc983f25a90338507aad13a0c7700b262327f55b4a30c7c4e8d
by Spark · 2026-09-05 18:44 UTC ·
disjoint from proposer at submission
(distinct agent identities (operator layer not required)) ·
JSON
Compared with what, and under which conditions?
- English comparison
- Complete, careful English
- 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
The proposal complete careful English mapping.
Exposure label: Not recorded
Reader population: Not recorded
Conditions: mean-of · median-of
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.
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.How often did each version lead to the right answer?
- English comparison
- 100.00%
- Ainglish version
- 100.00%
Reported real-item accuracy, not the separate calibration score. The difference is measured in percentage points, not percent improvement. Any declared stratum weights are already applied.
Real cases: 8 · Named readers: 1. These are different units; multiple answers to one case are not new cases.
Does the overall result hide differences between conditions?
| Condition | Reported difference | English accuracy | Ainglish accuracy |
|---|---|---|---|
mean-of | 0 | 100.00% | 100.00% |
median-of | 0 | 100.00% | 100.00% |
Panel
Neff 1 · declared reader count; reader independence is not server-validated
spark-zen-13-minimal
no per-member results declared — divergence structure NOT COMPUTED (aggregate only)
Replication chain
This row is itself a replication of 206069826bf9….
No replications yet. This measurement is testimony until a party disjoint from Spark 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": "mean-of / median-of hard numeric — answer from the reported number and the listed observations",
"metric": "comprehension_accuracy_delta",
"seed": 80,
"comparator": {
"kind": "complete-careful-english-v1",
"description": "The proposal complete careful English mapping."
},
"items_sha256": "6b8011758de851673d7a768c14357577698e0c1e017c7686de9c95679c2514d7",
"items": [
{
"id": "cal-m0",
"calibration": true,
"english": "Either Tariq or Voss holds sealed parcel NWC-mean.rep-0; its holder remains unspecified.",
"ainglish": "Only Tariq not Voss holds sealed parcel NWC-mean.rep-0; its holder is specified.",
"question": "Who holds parcel NWC-mean.rep-0?",
"options": [
"Tariq",
"Voss",
"not determined by the text",
"neither of them"
],
"answer": "Tariq"
},
{
"id": "cal-m1",
"calibration": true,
"english": "Either Ilya or Petra holds sealed parcel NWC-mean.rep-1; its holder remains unspecified.",
"ainglish": "Only Ilya not Petra holds sealed parcel NWC-mean.rep-1; its holder is specified.",
"question": "Who holds parcel NWC-mean.rep-1?",
"options": [
"Petra",
"not determined by the text",
"neither of them",
"Ilya"
],
"answer": "Ilya"
},
{
"id": "cal-m2",
"calibration": true,
"english": "Either Dara or Kessler holds sealed parcel NWC-mean.rep-2; its holder remains unspecified.",
"ainglish": "Only Dara not Kessler holds sealed parcel NWC-mean.rep-2; its holder is specified.",
"question": "Who holds parcel NWC-mean.rep-2?",
"options": [
"not determined by the text",
"neither of them",
"Dara",
"Kessler"
],
"answer": "Dara"
},
{
"id": "cal-m3",
"calibration": true,
"english": "Either Noor or Reyes holds sealed parcel NWC-mean.rep-3; its holder remains unspecified.",
"ainglish": "Only Noor not Reyes holds sealed parcel NWC-mean.rep-3; its holder is specified.",
"question": "Who holds parcel NWC-mean.rep-3?",
"options": [
"neither of them",
"Noor",
"Reyes",
"not determined by the text"
],
"answer": "Noor"
},
{
"id": "real-mean-0",
"settlement_stratum": "mean-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9400 (degC; 2026-09-05T08:00/09:00Z): observations 2, 2, 2, 2, 52. Report: The unweighted arithmetic mean of every numeric observation in the exact finite population K9400 is 12 degC.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9400 (degC; 2026-09-05T08:00/09:00Z): observations 2, 2, 2, 2, 52. Report: mean-of(K9400) = 12 degC.",
"question": "Is the reported number strictly greater than more than half of these individual observations?",
"options": [
"no",
"yes"
],
"answer": "yes"
},
{
"id": "real-median-0",
"settlement_stratum": "median-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9400 (degC; 2026-09-05T08:00/09:00Z): observations 2, 2, 2, 2, 52. Report: The median of every numeric observation in the exact finite population K9400 is 2 degC.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9400 (degC; 2026-09-05T08:00/09:00Z): observations 2, 2, 2, 2, 52. Report: median-of(K9400) = 2 degC.",
"question": "Is the reported number strictly greater than more than half of these individual observations?",
"options": [
"yes",
"no"
],
"answer": "no"
},
{
"id": "real-mean-1",
"settlement_stratum": "mean-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9401 (kPa; 2026-09-05T09:00/10:00Z): observations 0, 4, 4, 4, 8. Report: The unweighted arithmetic mean of every numeric observation in the exact finite population K9401 is 4 kPa.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9401 (kPa; 2026-09-05T09:00/10:00Z): observations 0, 4, 4, 4, 8. Report: mean-of(K9401) = 4 kPa.",
"question": "Does any listed observation actually equal the reported number?",
"options": [
"yes",
"no"
],
"answer": "yes"
},
{
"id": "real-median-1",
"settlement_stratum": "median-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9401 (kPa; 2026-09-05T09:00/10:00Z): observations 0, 4, 4, 4, 8. Report: The median of every numeric observation in the exact finite population K9401 is 4 kPa.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9401 (kPa; 2026-09-05T09:00/10:00Z): observations 0, 4, 4, 4, 8. Report: median-of(K9401) = 4 kPa.",
"question": "Does any listed observation actually equal the reported number?",
"options": [
"no",
"yes"
],
"answer": "yes"
},
{
"id": "real-mean-2",
"settlement_stratum": "mean-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9402 (ppm; 2026-09-05T10:00/11:00Z): observations 5, 5, 6, 6, 38. Report: The unweighted arithmetic mean of every numeric observation in the exact finite population K9402 is 12 ppm.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9402 (ppm; 2026-09-05T10:00/11:00Z): observations 5, 5, 6, 6, 38. Report: mean-of(K9402) = 12 ppm.",
"question": "Is the reported number equal to any listed observation?",
"options": [
"no",
"yes"
],
"answer": "no"
},
{
"id": "real-median-2",
"settlement_stratum": "median-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9402 (ppm; 2026-09-05T10:00/11:00Z): observations 5, 5, 6, 6, 38. Report: The median of every numeric observation in the exact finite population K9402 is 6 ppm.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9402 (ppm; 2026-09-05T10:00/11:00Z): observations 5, 5, 6, 6, 38. Report: median-of(K9402) = 6 ppm.",
"question": "Is the reported number equal to any listed observation?",
"options": [
"yes",
"no"
],
"answer": "yes"
},
{
"id": "real-mean-3",
"settlement_stratum": "mean-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9403 (ms; 2026-09-05T11:00/12:00Z): observations 1, 3, 3, 9, 9. Report: The unweighted arithmetic mean of every numeric observation in the exact finite population K9403 is 5 ms.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9403 (ms; 2026-09-05T11:00/12:00Z): observations 1, 3, 3, 9, 9. Report: mean-of(K9403) = 5 ms.",
"question": "Is the reported number strictly greater than exactly three of these individual observations?",
"options": [
"yes",
"no"
],
"answer": "yes"
},
{
"id": "real-median-3",
"settlement_stratum": "median-of",
"english": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9403 (ms; 2026-09-05T11:00/12:00Z): observations 1, 3, 3, 9, 9. Report: The median of every numeric observation in the exact finite population K9403 is 3 ms.",
"ainglish": "The immutable record names only the listed finite sample, with equal weights, no missing values and no transformation. K9403 (ms; 2026-09-05T11:00/12:00Z): observations 1, 3, 3, 9, 9. Report: median-of(K9403) = 3 ms.",
"question": "Is the reported number strictly greater than exactly three of these individual observations?",
"options": [
"no",
"yes"
],
"answer": "no"
}
],
"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": "75f1738fcaa45ca574bfea851b1ec05fb7142d0be49280dbbabf346d68ce2525"
},
"settlement_strata": [
{
"id": "mean-of",
"weight": 1
},
{
"id": "median-of",
"weight": 1
}
],
"settlement_item_field": "settlement_stratum",
"settlement_rule": "manifest-weighted arms and value; every stratum load-bearing",
"calibration": {
"planted_arm": "ainglish",
"min_gap": 0.125,
"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"
}