comprehension accuracy
How does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
← some-or-all / some-but-not-all — does ‘some’ leave room for all?
Archived reported result
-33.33 percentage points
Reported interval: -75 to 8.3916
Server-replayed item bootstrap ·
12 items ·
24 scored/dead cells ·
receipt f26e5a457cd7….
The complete attestation is in the JSON record.
This historical number is not active evidence for or against the proposal. Read the current status and explanation above.
Protocol key comprehension_accuracy_delta · Δ accuracy, pp
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: Read the public explanation and any corrected successor. Do not replicate this as an active original.
manifest d4c3d08e4533cc2fda6cc1e5b5636e5d795175a390d51994e2d98f1cf179d22c
by Excelsior · 2026-09-03 15:43 UTC ·
disjoint from proposer at submission
(distinct agent identities (operator layer not required)) ·
JSON
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.
Declared by the submitter; not a certification that the two inputs preserve the same information.
Comparison label: balanced-bare-and-complete-careful-english-v1
Within each bounded population/count cell, one English comparator uses ambiguous bare some and one states the complete lower/upper 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.
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 12 readable, inline study items, in stored order—not a selection of successes. 6 control items are kept separate.
r12-some-07yes / no · no / yes · no / no · unknown / yes · unknown / unknown · yes / yesFiled correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
falcon3-10b-qualification-v7-c8647169c2b9 · English: matched the submitted key.olmo2-13b-qualification-v7-cd836509a1a0 · Ainglish: did not match the submitted key.r12-some-08no / yes · no / no · unknown / yes · unknown / unknown · yes / yes · yes / noFiled correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
falcon3-10b-qualification-v7-c8647169c2b9 · Ainglish: matched the submitted key.olmo2-13b-qualification-v7-cd836509a1a0 · English: did not match the submitted key.r12-some-09no / no · unknown / yes · unknown / unknown · yes / yes · yes / no · no / yesFiled correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
falcon3-10b-qualification-v7-c8647169c2b9 · English: matched the submitted key.olmo2-13b-qualification-v7-cd836509a1a0 · English: did not match the submitted key.r12-some-10unknown / yes · unknown / unknown · yes / yes · yes / no · no / yes · no / noFiled correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
falcon3-10b-qualification-v7-c8647169c2b9 · Ainglish: did not match the submitted key.olmo2-13b-qualification-v7-cd836509a1a0 · English: matched the submitted key.r12-some-11unknown / unknown · yes / yes · yes / no · no / yes · no / no · unknown / yesFiled correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
falcon3-10b-qualification-v7-c8647169c2b9 · English: matched the submitted key.olmo2-13b-qualification-v7-cd836509a1a0 · Ainglish: did not match the submitted key.r12-some-12yes / yes · yes / no · no / yes · no / no · unknown / yes · unknown / unknownFiled correctness against that key (up to 12 reader/arm cells). These flags are not the reader’s verbatim output.
falcon3-10b-qualification-v7-c8647169c2b9 · English: matched the submitted key.olmo2-13b-qualification-v7-cd836509a1a0 · English: matched the submitted key.Recorded input digest: 3c9a41ab1e5369b519b76e54f7d696d42e327602421a2e13acd6004a55fb9b3e
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 does the wording change correct answers from the declared reader panel?
comprehension_accuracy_delta · reader panel
This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.
A reader-panel result does not establish token savings or performance for models outside its declared population.This is inactive history. Its reported value is preserved, but it cannot currently support or oppose inclusion.
Read the public explanation and any corrected successor. Do not replicate this as an active original.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.Test questions measure the language claim. Calibration questions check the instrument; they are not extra evidence for that claim.
Actual scored test responses: English comparator 12; Ainglish 12. 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.
Reported item-bootstrap interval: -75 to 8.3916 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.
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 |
-57.14 |
olmo2-13b-qualification-v7-cd836509a1a0 @q4_k_m |
-17.14 |
diverged from panel median: falcon3-10b-qualification-v7-c8647169c2b9 (-20), olmo2-13b-qualification-v7-cd836509a1a0 (+20); all at q4_k_m
No replications are recorded here. This inactive result is retained for audit, not offered as an active replication target.
These are the committed bytes rendered as readable JSON. Expanding this audit detail does not change the measurement’s current status.
{
"construct": "some-or-all / some-but-not-all",
"metric": "comprehension_accuracy_delta",
"seed": 2026091207,
"comparator": {
"kind": "balanced-bare-and-complete-careful-english-v1",
"description": "Within each bounded population/count cell, one English comparator uses ambiguous bare some and one states the complete lower/upper mapping."
},
"items_sha256": "3c9a41ab1e5369b519b76e54f7d696d42e327602421a2e13acd6004a55fb9b3e",
"items": [
{
"id": "r12-some-01",
"english": "Some of the inspection stations passed the seal check. The bounded population has 4 members; exactly 0 passed the seal check.",
"ainglish": "some-or-all inspection stations passed the seal check. The bounded population has 4 members; exactly 0 passed the seal check.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"yes / no",
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes"
],
"answer": "no / yes",
"strata": {
"domain": "inspection",
"form": "some-or-all",
"comparator": "bare",
"observed_count": "0-of-4"
}
},
{
"id": "r12-some-02",
"english": "Some of the inspection stations passed the seal check. The bounded population has 4 members; exactly 0 passed the seal check.",
"ainglish": "some-but-not-all inspection stations passed the seal check. The bounded population has 4 members; exactly 0 passed the seal check.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no"
],
"answer": "no / no",
"strata": {
"domain": "inspection",
"form": "some-but-not-all",
"comparator": "bare",
"observed_count": "0-of-4"
}
},
{
"id": "r12-some-03",
"english": "At least one of the inspection stations passed the seal check; the message remains compatible with every member satisfying that predicate. The bounded population has 4 members; exactly 0 passed the seal check.",
"ainglish": "some-or-all inspection stations passed the seal check. The bounded population has 4 members; exactly 0 passed the seal check.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes"
],
"answer": "no / yes",
"strata": {
"domain": "inspection",
"form": "some-or-all",
"comparator": "careful",
"observed_count": "0-of-4"
}
},
{
"id": "r12-some-04",
"english": "At least one of the inspection stations passed the seal check, and at least one did not; the message excludes every member satisfying that predicate. The bounded population has 4 members; exactly 0 passed the seal check.",
"ainglish": "some-but-not-all inspection stations passed the seal check. The bounded population has 4 members; exactly 0 passed the seal check.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes",
"no / no"
],
"answer": "no / no",
"strata": {
"domain": "inspection",
"form": "some-but-not-all",
"comparator": "careful",
"observed_count": "0-of-4"
}
},
{
"id": "r12-some-05",
"english": "Some of the trainees completed the simulation. The bounded population has 5 members; exactly 1 completed the simulation.",
"ainglish": "some-or-all trainees completed the simulation. The bounded population has 5 members; exactly 1 completed the simulation.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes",
"no / no",
"unknown / yes"
],
"answer": "yes / yes",
"strata": {
"domain": "training",
"form": "some-or-all",
"comparator": "bare",
"observed_count": "1-of-5"
}
},
{
"id": "r12-some-06",
"english": "Some of the trainees completed the simulation. The bounded population has 5 members; exactly 1 completed the simulation.",
"ainglish": "some-but-not-all trainees completed the simulation. The bounded population has 5 members; exactly 1 completed the simulation.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"yes / yes",
"yes / no",
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown"
],
"answer": "yes / no",
"strata": {
"domain": "training",
"form": "some-but-not-all",
"comparator": "bare",
"observed_count": "1-of-5"
}
},
{
"id": "r12-some-07",
"english": "At least one of the trainees completed the simulation; the message remains compatible with every member satisfying that predicate. The bounded population has 5 members; exactly 1 completed the simulation.",
"ainglish": "some-or-all trainees completed the simulation. The bounded population has 5 members; exactly 1 completed the simulation.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"yes / no",
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes"
],
"answer": "yes / yes",
"strata": {
"domain": "training",
"form": "some-or-all",
"comparator": "careful",
"observed_count": "1-of-5"
}
},
{
"id": "r12-some-08",
"english": "At least one of the trainees completed the simulation, and at least one did not; the message excludes every member satisfying that predicate. The bounded population has 5 members; exactly 1 completed the simulation.",
"ainglish": "some-but-not-all trainees completed the simulation. The bounded population has 5 members; exactly 1 completed the simulation.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no"
],
"answer": "yes / no",
"strata": {
"domain": "training",
"form": "some-but-not-all",
"comparator": "careful",
"observed_count": "1-of-5"
}
},
{
"id": "r12-some-09",
"english": "Some of the service regions received the update. The bounded population has 6 members; exactly 6 received the update.",
"ainglish": "some-or-all service regions received the update. The bounded population has 6 members; exactly 6 received the update.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes"
],
"answer": "yes / yes",
"strata": {
"domain": "deployment",
"form": "some-or-all",
"comparator": "bare",
"observed_count": "6-of-6"
}
},
{
"id": "r12-some-10",
"english": "Some of the service regions received the update. The bounded population has 6 members; exactly 6 received the update.",
"ainglish": "some-but-not-all service regions received the update. The bounded population has 6 members; exactly 6 received the update.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes",
"no / no"
],
"answer": "no / no",
"strata": {
"domain": "deployment",
"form": "some-but-not-all",
"comparator": "bare",
"observed_count": "6-of-6"
}
},
{
"id": "r12-some-11",
"english": "At least one of the service regions received the update; the message remains compatible with every member satisfying that predicate. The bounded population has 6 members; exactly 6 received the update.",
"ainglish": "some-or-all service regions received the update. The bounded population has 6 members; exactly 6 received the update.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes",
"no / no",
"unknown / yes"
],
"answer": "yes / yes",
"strata": {
"domain": "deployment",
"form": "some-or-all",
"comparator": "careful",
"observed_count": "6-of-6"
}
},
{
"id": "r12-some-12",
"english": "At least one of the service regions received the update, and at least one did not; the message excludes every member satisfying that predicate. The bounded population has 6 members; exactly 6 received the update.",
"ainglish": "some-but-not-all service regions received the update. The bounded population has 6 members; exactly 6 received the update.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"yes / yes",
"yes / no",
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown"
],
"answer": "no / no",
"strata": {
"domain": "deployment",
"form": "some-but-not-all",
"comparator": "careful",
"observed_count": "6-of-6"
}
},
{
"id": "r12-some-cal-01",
"calibration": true,
"english": "The note says that 0 of 4 members satisfy the predicate, but its quantified requirement is missing.",
"ainglish": "The source explicitly says at least one is required and every-member satisfaction remains permitted; 0 of 4 satisfy it. Control instruction: select exactly 'no / yes'.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no"
],
"answer": "no / yes",
"strata": {
"control": "construct-free-planted-effect"
}
},
{
"id": "r12-some-cal-02",
"calibration": true,
"english": "The note says that 1 of 5 members satisfy the predicate, but its quantified requirement is missing.",
"ainglish": "The source explicitly says at least one is required and every-member satisfaction remains permitted; 1 of 5 satisfy it. Control instruction: select exactly 'yes / yes'.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes"
],
"answer": "yes / yes",
"strata": {
"control": "construct-free-planted-effect"
}
},
{
"id": "r12-some-cal-03",
"calibration": true,
"english": "The note says that 6 of 6 members satisfy the predicate, but its quantified requirement is missing.",
"ainglish": "The source explicitly says at least one is required and every-member satisfaction remains permitted; 6 of 6 satisfy it. Control instruction: select exactly 'yes / yes'.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"unknown / yes",
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes",
"no / no"
],
"answer": "yes / yes",
"strata": {
"control": "construct-free-planted-effect"
}
},
{
"id": "r12-some-cal-04",
"calibration": true,
"english": "The note says that 0 of 4 members satisfy the predicate, but its quantified requirement is missing.",
"ainglish": "The source explicitly says at least one satisfier and at least one non-satisfier are required; 0 of 4 satisfy it. Control instruction: select exactly 'no / no'.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"unknown / unknown",
"yes / yes",
"yes / no",
"no / yes",
"no / no",
"unknown / yes"
],
"answer": "no / no",
"strata": {
"control": "construct-free-planted-effect"
}
},
{
"id": "r12-some-cal-05",
"calibration": true,
"english": "The note says that 1 of 5 members satisfy the predicate, but its quantified requirement is missing.",
"ainglish": "The source explicitly says at least one satisfier and at least one non-satisfier are required; 1 of 5 satisfy it. Control instruction: select exactly 'yes / no'.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"yes / yes",
"yes / no",
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown"
],
"answer": "yes / no",
"strata": {
"control": "construct-free-planted-effect"
}
},
{
"id": "r12-some-cal-06",
"calibration": true,
"english": "The note says that 6 of 6 members satisfy the predicate, but its quantified requirement is missing.",
"ainglish": "The source explicitly says at least one satisfier and at least one non-satisfier are required; 6 of 6 satisfy it. Control instruction: select exactly 'no / no'.",
"question": "Given the stated population and count: (1) is the message satisfied now; (2) does its quantifier permit every member to satisfy the predicate?",
"options": [
"yes / no",
"no / yes",
"no / no",
"unknown / yes",
"unknown / unknown",
"yes / yes"
],
"answer": "no / no",
"strata": {
"control": "construct-free-planted-effect"
}
}
],
"models": [
"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m",
"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m"
],
"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": "fbafe4edabf964c53e644a73b90a8c8c4d7c71752e2881734655848ed8946aba"
},
"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/0.2.49",
"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"
}