AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 28 September 2026

Can Mistral AI keep footnotes at the bottom of the page attached to the content they annotate?

Mistral AI keeps footnotes out of the body flow and links each marker to its note. The Markdown output places 13 footnotes after the page bodies in source order, and the 26 marker occurrences each appear once inline and once at their notes, so the association is preserved.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 with a result
Coverage1 of 1test cases with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

The test case

Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above counts this row.

Footnote — out of body flow, associatedPassEvidence
What we sent
InputDocument (PDF)
Four-page born-digital journal offprint with body text and footnotes set at different sizes on the same page. From outside the graded run; shown for context, not graded.
Open the PDF ↗
Key momentsp. 1, 2, 4 ↗
What the tool returned
Markdown33 lines
*Estuarine Policy Review*, 41.2 (2026), 143-158

# The 1974 Braithe Order and the limits of consent

HELENA M. CROYDE

The Braithe Estuary Order 1974 is usually described as a consenting instrument, and for most of its life it has been used as one. Article 6(2), on which everything in this article turns, requires the Harbour Board to obtain the written consent of the riparian owners before works are carried out on the intertidal foreshore.$^{1}$ What the article does not say, and what the Board's practice for thirty years assumed it said, is that a consent once given runs with the land.

The assumption was not an unreasonable one. The drafting committee had before it a memorandum from the Board's own solicitor which treated consent as attaching to the works rather than to the owner,$^{2}$ and the article was drawn in language which, read quickly, supports that reading. But the memorandum was not adopted, and the words 'the owner for the time being' were struck out of the draft at the committee's second meeting.

The consequence went unnoticed for a long time because it seldom mattered. Ownership of the relevant foreshore changed hands twice between 1974 and 2003, and on each occasion the Board sought a fresh consent as a matter of course, without ever asking whether it was obliged to.$^{3}$

The question surfaced, when it did, for a reason unconnected with ownership. In 1998 the Board began keeping its consent correspondence on a single file rather than with the works papers, and the file made visible what thirty years of separate folders had hidden: that no two consents were in the same terms, that four of them were addressed to people who had by then sold, and that one had been given by a tenant whose lease had expired. The clerk who noticed it recorded the fact and no more.

It is worth pausing on the word 'owners'. The Order uses it in three places and defines it in none, and the committee plainly took its meaning to be settled by the general law. That was a defensible view in 1974, when the foreshore between the training wall and Thrimby Point was held in three parcels and the identity of each owner was a matter of local knowledge. It is a less defensible view now, and the Board's difficulty in the 2011 season had as much to do with finding the owners as with the terms on which they were willing to consent.$^{4}$

The committee cannot be blamed for this. Its brief was to produce an instrument that would let the Board dredge and maintain without a private Act for every campaign, and it did so in eleven articles and a schedule. Consent was one paragraph of one article, and the committee's own view, minuted twice, was that the paragraph restated the law rather than adding to it. Whether that view was right is the subject of the first part of what follows.

None of this would matter if article 6(2) were merely procedural. The argument of this article is that it is not: that the consent requirement was the price of the compulsory powers conferred by article 4, and that reading it as a formality which passes with the land empties the bargain the Order struck.

$^{1}$ Braithe Estuary Order 1974, art. 6(2). The Order is reproduced in full in the appendix to R. Sandiman, *The Braithe Estuary: A Documentary History* (Vardenne, 1988), 211-24.

$^{2}$ Minutes of the Harbour Board, 14 May 1973 (Braithe Record Office, BHB/3/17), 4.

$^{3}$ The point was not argued in *Tarbert v Braithe Harbour Board* [1981] 2 EstLR 88, where both parties proceeded on the assumption that art. 6(2) applied.

$^{4}$ The Board's file on the 2011 consents (Braithe Record Office, BHB/11/4) contains three letters returned undelivered and a note of a telephone call to a solicitor in Winnipeg.

143

144

HELENA M. CROYDE

Copied from Proof 1 · Output file (Markdown), lines 1–33 · an excerpt; the link below opens the whole file

Open the Markdown file ↗
Proof 1Output file (Markdown)
Complete Markdown conversion of the offprint, with footnotes emitted after each page's body and markers shown as LaTeX superscripts. From outside the graded run; shown for context, not graded.
Part of this file is printed above, under What the tool returned. Show the whole file
Markdown91 lines
*Estuarine Policy Review*, 41.2 (2026), 143-158

# The 1974 Braithe Order and the limits of consent

HELENA M. CROYDE

The Braithe Estuary Order 1974 is usually described as a consenting instrument, and for most of its life it has been used as one. Article 6(2), on which everything in this article turns, requires the Harbour Board to obtain the written consent of the riparian owners before works are carried out on the intertidal foreshore.$^{1}$ What the article does not say, and what the Board's practice for thirty years assumed it said, is that a consent once given runs with the land.

The assumption was not an unreasonable one. The drafting committee had before it a memorandum from the Board's own solicitor which treated consent as attaching to the works rather than to the owner,$^{2}$ and the article was drawn in language which, read quickly, supports that reading. But the memorandum was not adopted, and the words 'the owner for the time being' were struck out of the draft at the committee's second meeting.

The consequence went unnoticed for a long time because it seldom mattered. Ownership of the relevant foreshore changed hands twice between 1974 and 2003, and on each occasion the Board sought a fresh consent as a matter of course, without ever asking whether it was obliged to.$^{3}$

The question surfaced, when it did, for a reason unconnected with ownership. In 1998 the Board began keeping its consent correspondence on a single file rather than with the works papers, and the file made visible what thirty years of separate folders had hidden: that no two consents were in the same terms, that four of them were addressed to people who had by then sold, and that one had been given by a tenant whose lease had expired. The clerk who noticed it recorded the fact and no more.

It is worth pausing on the word 'owners'. The Order uses it in three places and defines it in none, and the committee plainly took its meaning to be settled by the general law. That was a defensible view in 1974, when the foreshore between the training wall and Thrimby Point was held in three parcels and the identity of each owner was a matter of local knowledge. It is a less defensible view now, and the Board's difficulty in the 2011 season had as much to do with finding the owners as with the terms on which they were willing to consent.$^{4}$

The committee cannot be blamed for this. Its brief was to produce an instrument that would let the Board dredge and maintain without a private Act for every campaign, and it did so in eleven articles and a schedule. Consent was one paragraph of one article, and the committee's own view, minuted twice, was that the paragraph restated the law rather than adding to it. Whether that view was right is the subject of the first part of what follows.

None of this would matter if article 6(2) were merely procedural. The argument of this article is that it is not: that the consent requirement was the price of the compulsory powers conferred by article 4, and that reading it as a formality which passes with the land empties the bargain the Order struck.

$^{1}$ Braithe Estuary Order 1974, art. 6(2). The Order is reproduced in full in the appendix to R. Sandiman, *The Braithe Estuary: A Documentary History* (Vardenne, 1988), 211-24.

$^{2}$ Minutes of the Harbour Board, 14 May 1973 (Braithe Record Office, BHB/3/17), 4.

$^{3}$ The point was not argued in *Tarbert v Braithe Harbour Board* [1981] 2 EstLR 88, where both parties proceeded on the assumption that art. 6(2) applied.

$^{4}$ The Board's file on the 2011 consents (Braithe Record Office, BHB/11/4) contains three letters returned undelivered and a note of a telephone call to a solicitor in Winnipeg.

143

144

HELENA M. CROYDE

That changed with the sediment recharge programme. Placement of dredged material on the upper foreshore is works within the meaning of article 3, as the Board has always accepted, and the programme requires placement in the same locations year after year. A consent that expires with a conveyance is an expensive thing to administer, and by 2009 the Board was asking whether article 6(2) meant what it appeared to mean.$^{5}$

The answer its advisers gave - that the article requires consent from the owner at the date of the works, and that a consent given by a predecessor in title is of no effect - has never been tested in proceedings. It is, I shall argue, the right answer, and the reasons for it lie in the committee's treatment of a quite different problem: the position of tenants.$^{6}$

The remainder of this article is in three parts. The first sets out the drafting history of article 6(2) from the committee's papers. The second considers the Board's practice between 1974 and 2009, which is better documented than the drafting and is more revealing about what the article was thought to mean. The third turns to the tenancy question, and to the reason the committee's solution to it makes the wider reading impossible.

The argument is narrow in one respect that should be stated at the outset. I am concerned with article 6(2) as it stands, and not with whether it ought to stand. There is a good case, which the Board has put to the department more than once, for amending the Order so that a consent binds successors in title on notice. That case is not weakened by the reading advanced here; if anything it is strengthened, because an amendment is only necessary if the article means what I say it means.

A word about the sources is needed before the argument begins. The committee's papers survive in two series, one in the Braitha Record Office and one, less complete but better ordered, among the Harbour Board's deposited records. The two do not always agree about what was decided, and where they conflict I have preferred the Record Office copy, which was made at the time and initialled.$^{7}$

The second part of the argument rests on the Board's practice, and practice is harder to document than drafting. What survives is the consent correspondence itself: forty-one exchanges between 1974 and 2009, of which thirty-four are complete. They are unremarkable letters, and their interest lies entirely in what nobody writing them thought worth arguing about.

Three of the exchanges are worth reading in full and are printed in the appendix. The first, from 1976, is the only one in which an owner refused; the second, from 1989, is the only one in which the Board treated a consent as continuing without saying so; and the third, from 2004, is the one the advisers had in front of them in 2009. Together they show a practice that was consistent in what it did and inconsistent in what it assumed.

I have not attempted a comparison with the other estuarine orders of the period, though several use language close to article 6(2) and one, the Marnhead Order 1971, appears to have been its model. The comparison would be worth making. It would also be a different article, and would not settle the question this one is about.

$^{5}$ Report of the Committee on Estuarine Consents (Cmnd 6712, 1977), paras 88-94.

$^{6}$ See further A. Prosser, 'Consent and its conditions' (1994) 12 EPR 3, 9-14, whose account of the 1977 committee differs from mine at one point of substance.

$^{7}$ The Harbour Board series appears to have been reconstructed in 1981, probably for the purposes of the Tarbert litigation.

THE 1974 BRAITHE ORDER AND THE LIMITS OF CONSENT

145

The committee's papers are in two series and neither is complete. What survives of the drafting is a bundle of eleven documents: four memoranda, the minutes of six meetings, and a marked-up print of the draft Order with two hands on it, one of them the secretary's.$^{8}$

The sequence that matters begins at the second meeting, on 14 May 1973, at which the solicitor's memorandum was considered and not adopted. The minute is short and gives no reason, which has led more than one writer to treat the decision as a formality.$^{9}$ The marked-up print shows that it was not. The words 'the owner for the time being' are struck through in the secretary's hand, and beside them, in the other hand, is written 'not without the tenancy point'.

That note is the hinge of this article. It ties the deletion to the tenancy question, which the committee took up at its fourth meeting and settled in a way that makes the wider reading of article 6(2) impossible. The connection appears not to have been noticed before, and the tenancy discussion is worth setting out at length.$^{10}$

The problem the committee faced was this. Much of the foreshore between the training wall and Thrimby Point was let, in 1973 as now, on grazing tenancies of a year and less. If consent ran with the land, a consent given by an owner would bind a tenant who had not been asked; if it did not, the Board would have to seek consent from whoever held the land at the date of the works, tenant or owner. The committee wanted neither result and said so in terms.

$^{8}$ Braithe Record Office, BHB/3/14-24. The marked-up print is BHB/3/22.

$^{9}$ Notably Prosser, 'Consent and its conditions', 7, who calls the deletion 'tidying'.

$^{10}$ Minutes of the fourth meeting, 9 July 1973 (Braithe Record Office, BHB/3/19), 2-6.

146

HELENA M. CROYDE

Its solution was article 6(3), which nobody reads: consent is required from 'the owner and, where the land is let for a term of more than one year, the tenant'. The threshold of a year is the committee's own and appears nowhere else in the Order.$^{11}$

Article 6(3) only makes sense on the narrow reading. If consent ran with the land, a tenant's consent would run with the tenancy, and a threshold of a year would protect nobody: a grazing tenant of eleven months would be bound by a consent given by a predecessor's landlord, which is precisely the result the committee said it wished to avoid. On the narrow reading the threshold does what the minute says it was for.

There is a further point, smaller but harder to answer. The committee considered and rejected a draft in which consent was expressed to bind 'successors in title'. The rejected words are in the same marked-up print, struck through in the same hand.$^{12}$ A committee that struck out 'the owner for the time being' and 'successors in title' at consecutive meetings was not tidying.

The remainder of the drafting history adds little. The Order was settled at the sixth meeting and went to the department unchanged in this respect. The department's own file, which I have not seen, is said to contain nothing on article 6 at all.$^{13}$

$^{11}$ Braith the Estuary Order 1974, art. 6(3). The threshold is discussed at the fourth meeting, *ibid.*, 5.

$^{12}$ Braith the Record Office, BHB/3/22, fo. 4.

$^{13}$ I am grateful to the departmental records officer for a search, and for the confirmation that the file was weeded in 1998.
Open the Markdown file ↗
Key momentslines 43, 87, 89
Expected vs. Found
What this scenario evaluates

These are scenario-level criteria. Each test case's Expected and Found are listed separately.

  • Whether the footnote is kept outside the main body flow.
  • Whether the footnote remains present.
  • Whether the footnote stays associated with the content it annotates.
How this scenario is judged →
✓Found: Footnotes stayed out of the body, remained present, and each marker linked to its note.
Supporting proof
Proof 2Screenshot
Run-metadata card for Mistral Document AI TC30 showing the default OCR pipeline, single pass, and no flag tuning.
Open original ↗
Why this result

The conversion kept each footnote separate from the body text, placed the notes after each page, and preserved the marker-to-note links. The evidence shows 13 notes and 26 marker occurrences, with each number appearing once inline and once in its note.

Also observed on this row

Text layer typos. The output contains transcription errors in the text layer, including 'Braitha' and 'Braith the'. These appear in footnote-related lines.

Math superscript markers. The markers are rendered as LaTeX superscripts inside math delimiters, not Markdown footnote syntax. A renderer without math support would show them literally.

Extra italics applied. Three titles are italicized even though the source shows them in roman, and the masthead's italics are only partly preserved.

Tested by Chandresh Bisht · evidence dated 10 September 2026

Configuration and setup

How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.

Software that produced the output
Mistral AI
Build or version
mistral-ocr-latest (model id echoed by the API; dated version not exposed)
Plan or tier
Mistral La Plateforme (metered OCR endpoint)
Model
mistral-ocr-latest
Surface
REST API
Set up before the run
The complete PDF had a page with body text that referenced a footnote at the bottom of the page, and Mistral AI converted it to Markdown with its default one-pass pipeline.
mode
Document AI default OCR pipeline, single pass, no flag tuning
endpoint
https://api.mistral.ai/v1/ocr
pipeline
default OCR pipeline
pass mode
single pass
flag tuning
no flag tuning
Tested
10 September 2026 · Chandresh Bisht

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.

The rules
  • Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
  • Fail: at least one expected behaviour clearly didn't happen; the row says which and quotes the tool.
  • Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the row says what's missing.

Where this sits in the benchmark

This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.

History of this result

What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.

from the publication record
6 October 2026First publishedConverting a complex PDF into clean Markdown with a hosted API v1

Act on this result

Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/pdf-to-markdown-apis/results/mistral-ai/footnotes-at-the-bottom-of-the-page · 1 pass · 0 fail · coverage 1/1 · graded 2026-09-28

The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.

Verify the proof files

These files support this result. Open a file to inspect the original evidence.

Proof 2 · Screenshot ↗image/png · 53 KB
Input · Document (PDF) ↗application/pdf · 152 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Proof 1 · Output file (Markdown)0a889e791fbf6a7c22069a3ea2950efc09b6ef5a24036f2d6e232c621edd8d49
Proof 2 · Screenshot3307ffd94c42fd167bed62f4e528f7d249d92fde17bf552174792a04af00fa56
Input · Document (PDF)fce3c87776b6f1b8f34dcfb0f6a274b5954edcb3d33ff7ee84840dfe2afbc1ad