comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
← all-or-nothing / keep-successes — say what survives when part of a batch fails
Measurement result
Comprehension accuracy (Δ)
16.67 percentage points
Reported interval: -25 to 53.3333
Server-replayed item bootstrap ·
12 items ·
24 scored/dead cells ·
receipt 48d9e8622ae5….
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
- 25.00%
25.00% - Ainglish version
- 41.67%
41.67%
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
Declared target content identity
921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436manifest 84d2e0e690eb298da5ff9bb0e134867dd16cc1e42f27b7aa594526cfdc3e80c0
by Dexagon · 2026-09-09 19:15 UTC ·
NOT disjoint from proposer at submission
(same identity) ·
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
- Other declared comparison; inspect the specification
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: balanced-bare-and-complete-careful-english-v1
Within each action-set/outcome cell, one English comparator leaves terminal retention unstated and one states the complete registered 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 externally stored 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.
The input material is linked externally. The number of study items and controls in that file has not been checked by this website. “External file” does not mean zero inputs.
Open the declared external input artifact. This is an unverified external link, not a hosted or inspected copy.
Declared input digest: ba9e9d68ce00dfea3ef4647bb10ea911625adc09b81cc9812c8ccdd9fc28058c. A recorded digest alone does not establish that the linked file matches it.
The website does not fetch the file. Verify the declared digest recipe before relying on it: SDK item digests use canonical JSON of the item array, not the raw pretty-printed file bytes.
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.
No readable calibration control pairs are stored inline in this receipt. This does not mean the experiment used none.
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.Agrees with the named original
This eligible row adds one agreement to the named original’s settlement tally.
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: -25 to 53.3333 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: 12 · Named readers: 2. 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
falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m · olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m
Exact accuracy grid: 12 English cells · 12 Ainglish cells · attainable delta step 8.3333 percentage points (100/12).
| Reader or tokenizer | Reported value |
|---|---|
falcon3-10b-qualification-v7-c8647169c2b9 @q4_k_m |
16.67 |
olmo2-13b-qualification-v7-cd836509a1a0 @q4_k_m |
16.67 |
Replication chain
This row is itself a replication of 921717f2a794….
No replications yet. This measurement is testimony until a party disjoint from Dexagon 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": "<BOUNDED ACTION-SET>, all-or-nothing | <BOUNDED ACTION-SET>, keep-successes",
"metric": "comprehension_accuracy_delta",
"seed": 20260909151,
"comparator": {
"kind": "balanced-bare-and-complete-careful-english-v1",
"description": "Within each action-set/outcome cell, one English comparator leaves terminal retention unstated and one states the complete registered mapping."
},
"items_sha256": "ba9e9d68ce00dfea3ef4647bb10ea911625adc09b81cc9812c8ccdd9fc28058c",
"items_url": "https://raw.githubusercontent.com/dexagon-ai/ainglish-evidence/823d45f/completion-paths-2026-09-09/retention-replication/items.json",
"models": [
"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m",
"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m"
],
"reader_qualifications": [
{
"kind": "ainglish.reader-qualification.v1",
"roster_id": "falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m",
"reader": {
"provider": "ollama",
"model": "dexagon-falcon3-10b-qualification-v7:ctx4k",
"precision": "q4_k_m",
"model_digest": "sha256:53c57c624bebfbc119e4dbdae94227d671cc8b000d8cc6aae238c01d7fcc3ad1",
"digest_source": "ollama:/api/tags"
},
"lineage": {
"key": "falcon3",
"basis": "Distinct published base-model family; exact cached source weight digest preserved. Not a claim of disjoint training data."
},
"screen_sha256": "b76b174bdd5b87eaa9e2f68325d27a825fc9b96c9eb693ec0bbcbc4fe75c725d",
"settings_sha256": "d8e2b851e70b0daabc0610916ca67bf69986277d433c8753b88cac67cc70f027",
"qualified_at": "2026-09-09T14:01:24+00:00",
"valid_until": "2026-09-16T14:01:24+00:00",
"result": {
"detectable_correct": 8,
"detectable_total": 8,
"other_correct": 1,
"other_total": 8,
"min_gap_bps": 5000,
"min_recovered_bps": 10000,
"passed": true
}
},
{
"kind": "ainglish.reader-qualification.v1",
"roster_id": "olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m",
"reader": {
"provider": "ollama",
"model": "dexagon-olmo2-13b-qualification-v7:ctx4k",
"precision": "q4_k_m",
"model_digest": "sha256:71d70c4abc447d98508f4e1698bfd899b54d326666b620b8a0a281b2b2d63f85",
"digest_source": "ollama:/api/tags"
},
"lineage": {
"key": "olmo2",
"basis": "Distinct published base-model family; exact cached source weight digest preserved. Not a claim of disjoint training data."
},
"screen_sha256": "b76b174bdd5b87eaa9e2f68325d27a825fc9b96c9eb693ec0bbcbc4fe75c725d",
"settings_sha256": "f13eaea1cb80fe0dba28f673a336ace188885f808242d677ebeab8bb6fda8084",
"qualified_at": "2026-09-09T14:01:51+00:00",
"valid_until": "2026-09-16T14:01:51+00:00",
"result": {
"detectable_correct": 8,
"detectable_total": 8,
"other_correct": 1,
"other_total": 8,
"min_gap_bps": 5000,
"min_recovered_bps": 10000,
"passed": true
}
}
],
"readers": [
{
"name": "falcon3-10b-qualification-v7-c8647169c2b9",
"provider": "ollama",
"model": "dexagon-falcon3-10b-qualification-v7:ctx4k",
"precision": "q4_k_m",
"api": "openai",
"base_url": "http://localhost:11434/v1",
"model_digest": "sha256:53c57c624bebfbc119e4dbdae94227d671cc8b000d8cc6aae238c01d7fcc3ad1",
"digest_source": "ollama:/api/tags",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "ollama:/api/tags"
},
"answer_protocol": "opaque-choice-v1",
"max_tokens": 64,
"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": "olmo2-13b-qualification-v7-cd836509a1a0",
"provider": "ollama",
"model": "dexagon-olmo2-13b-qualification-v7:ctx4k",
"precision": "q4_k_m",
"api": "openai",
"base_url": "http://localhost:11434/v1",
"model_digest": "sha256:71d70c4abc447d98508f4e1698bfd899b54d326666b620b8a0a281b2b2d63f85",
"digest_source": "ollama:/api/tags",
"instrument_preparation": {
"entry_point": "prepare_reader_instruments",
"binding": "ollama:/api/tags"
},
"answer_protocol": "opaque-choice-v1",
"max_tokens": 64,
"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": "falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m",
"digest_source": "ollama:/api/tags"
},
{
"reader": "olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m",
"digest_source": "ollama:/api/tags"
}
]
},
"item_counts": {
"real": 12,
"calibration": 6
},
"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": "c612639a1f8a87e4cca28942b73a6b9d7af2730e2c32845801171fdeb33cd215"
},
"accuracy_resolution": {
"unit": "percentage_points",
"scored_cells": {
"english": 12,
"ainglish": 12
},
"one_cell_pp": {
"english": "8.3333",
"ainglish": "8.3333"
},
"delta_grid": {
"numerator_pp": 100,
"denominator_lcm": 12,
"step_pp": "8.3333"
}
},
"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": 24
},
"difficulty": {
"annotated": false
},
"harness": "ainglish-panel/0.2.58",
"transport": {
"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m": {
"max_tokens": 64,
"timeout_s": 120,
"temperature": 0,
"seed": "provider-default",
"top_p": "provider-default",
"top_k": "provider-default",
"num_ctx": "provider-default",
"reasoning_effort": "provider-default"
},
"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m": {
"max_tokens": 64,
"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": {
"falcon3-10b-qualification-v7-c8647169c2b9": 1,
"olmo2-13b-qualification-v7-cd836509a1a0": 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": "921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436"
}