AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 19 November 2026

Does PDF Vector keep a document's equations as math rather than mangled text?

PDF Vector did not keep the equations of a three-page technical note as math. At each of the six equations only its number remained, the bodies reappeared at the end of each page as broken fragments, and the returned Markdown holds no math markup. Sentences that used the symbols lost them too.

1 of 1 test case failed

Every test case in this scenario has a result.

Pass rate0%0 of 1 gradable
Coverage1 of 1test case with a result
0PassNo test case passed.
1FailMissed at least one thing it was expected to do; the reason and proof are with each test case below.
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 is based on this test case.

Equations — math markup or honest fallbackFailEvidence
What we sent

We sent the complete three-page technical note to PDF Vector's document parse endpoint in a single request on the free tier, with the model left on automatic; nothing was typed.

InputDocument (PDF)
Input PDF: the three-page technical note with six numbered equations
Open the PDF ↗
What the tool returned

Copied from Output file (Markdown), lines 16–22, 31–43

Markdownthe whole file · cited lines 16–22 and 31–43 marked
Tarnbeck Institute of Hydrology TIH/TN/18
Page 1 of 3
A one-dimensional model of tidal attenuation in the Braithe channel
Technical note TIH/TN/18 · January 2026
R. K. Sandiman and H. Vale
1 Introduction
The tide entering the Braithe is attenuated over the eleven kilometres between the bar and Braithe
Bridge, and the attenuation is large enough to matter to anyone predicting water levels in the upper
estuary. This note sets out the one-dimensional model the Institute has used since 2018, states the
approximation on which the working formula rests, and compares the result with the gauge record at
three stations.
Nothing here is new. The intention is to have the derivation, the assumptions and the coefficients in one
place, because the formula has been quoted in Partnership papers without them.
2 Governing equations
Take the channel as a single reach of slowly varying cross-section and neglect lateral inflow.
Conservation of mass gives
(1)
where A is the cross-sectional area below the free surface and Q the discharge through it. Conservation of
momentum, with friction represented in the Manning form, gives
(2)
in which is the surface elevation above mean sea level, n is Manning's coefficient, R the hydraulic
radius for wetted perimeter P, and g the acceleration due to gravity. The friction term is the only
nonlinear one that matters over the range of interest.
3 Attenuation of the leading harmonic
For a channel of nearly uniform depth the leading semidiurnal harmonic decays close to exponentially
with distance upstream, so that
(3)
with the amplitude at the bar, the angular frequency of the harmonic, k the wavenumber and the
attenuation coefficient. Linearising the friction term by the Lorentz method and collecting terms gives
∂A
∂t + ∂Q
∂x = 0
∂Q
∂t + ∂
∂x(
Q 2
A ) + gA ∂η
∂x + g n2 Q |Q|
A R 4/3 = 0
η
R = A/P
η(x, t) = η0 e−μx cos (ωt − kx)
η0	ω	μ

-- 1 of 3 --

Tarnbeck Institute of Hydrology TIH/TN/18
Page 2 of 3
(4)
where c is the frictionless wave speed and h the mean depth. The second expression is the friction
parameter; it is small in the lower reach and approaches unity above Harrowby Reach, which is where
the exponential form begins to fail.
4 Application to the Braithe
Taking the mean depth as eleven metres below the bar and four metres at the bridge, with Manning's
coefficient at the value fitted in 2018, the formula reproduces the observed amplitude at Vardenne Quay
to within four per cent and at Harrowby Reach to within nine. At Braithe Bridge it overestimates the
amplitude, and the discrepancy grows through the spring tides, which is the behaviour the friction
parameter predicts.
A two-reach treatment with separate depths would probably remove most of the error at the bridge. It has
not been attempted here because the gauge record above Harrowby Reach is too short to fit a second
coefficient with any confidence.
5 Coefficients
Manning's coefficient is not constant with depth in a channel of this kind, and the single fitted value used
above is a compromise. Fitting the 2018 record with a depth-dependent form gives
(5)
with the deep-water value and b a bed constant. The fit is better in the lower reach and no better at
the bridge, which suggests that the error there is not in the friction term at all.
The two constants were fitted to the 2018 record and have not been refitted since. Refitting on the four
years now available would be worth doing; the Institute's expectation is that the deep-water value will
move very little and the bed constant appreciably, because it is carrying the shallow reaches where the
record has improved most.
6 Limitations
Three limitations should be stated plainly. The first is the one-dimensional assumption, which fails where
the channel divides above Harrowby Reach. The second is the neglect of the freshwater inflow, which is
small in summer and not small after rain. The third is the linearisation itself, which is a poor
approximation once the friction parameter approaches unity - that is, in exactly the reach where the
model is least accurate.
The error measure quoted in the previous section is
μ = ω
c (
χ
2(1 + χ2))
1/2
, χ = 8 n2 c η0
3π h 4/3
n(h) = n∞ + b
h 1/3
n∞

-- 2 of 3 --

Tarnbeck Institute of Hydrology TIH/TN/18
Page 3 of 3
(6)
taken over the spring-neap cycle at each gauge, with the observed amplitude and the modelled
one. It is a crude measure and it flatters the model at the bar, where the amplitude is large and the
absolute error is not.
None of this is an argument against using the formula, which is quick, transparent and good enough for
the purposes the Partnership puts it to. It is an argument for quoting it with the reach and the tidal range
attached, which the papers that quote it have not always done.
References
Sandiman, R. K. (2018). Tidal propagation in the Braithe: a first fit. Tarnbeck Institute internal report TIH/IR/09.
Vale, H. and Croyde, P. (2021). The Harrowby Reach gauge, 2015 to 2020. Journal of Estuarine Hydrology 44,
218-31.
Prosser, A. (2009). Friction coefficients for the Braithe channel. Braithe Harbour Board, unpublished.
ε = |ηo − ηm|
ηoηo	ηm

-- 3 of 3 --

Returned Markdown: equation numbers in place, bodies as fragments at page ends, no math markup

Open the Markdown file ↗
Output file (JSON)
API response: the returned Markdown for three pages, from model nano
Cited values3 values from this file
model
nano
pageCount
3
markdown
Tarnbeck Institute of Hydrology TIH/TN/18 Page 1 of 3 A one-dimensional model of tidal attenuation in the Braithe channel Technical note TIH/TN/18 · January 2026 R. K. Sandiman and H. Vale 1 Introduction The tide entering the Braithe is attenuated over the eleven kilometres between the bar and Braithe Bridge, and the attenuation is large enough to matter to anyone predicting water levels in the upper estuary. This note sets out the one-dimensional model the Institute has used since 2018, states the approximation on which the working formula rests, and compares the result with the gauge record at three stations. Nothing here is new. The intention is to have the derivation, the assumptions and the coefficients in one place, because the formula has been quoted in Partnership papers without them. 2 Governing equations Take the channel as a single reach of slowly varying cross-section and neglect lateral inflow. Conservation of mass gives (1) where A is the cross-sectional area below the free surface and Q the discharge through it. Conservation of momentum, with friction represented in the Manning form, gives (2) in which is the surface elevation above mean sea level, n is Manning's coefficient, R the hydraulic radius for wetted perimeter P, and g the acceleration due to gravity. The friction term is the only nonlinear one that matters over the range of interest. 3 Attenuation of the leading harmonic For a channel of nearly uniform depth the leading semidiurnal harmonic decays close to exponentially with distance upstream, so that (3) with the amplitude at the bar, the angular frequency of the harmonic, k the wavenumber and the attenuation coefficient. Linearising the friction term by the Lorentz method and collecting terms gives ∂A ∂t + ∂Q ∂x = 0 ∂Q ∂t + ∂ ∂x( Q 2 A ) + gA ∂η ∂x + g n2 Q |Q| A R 4/3 = 0 η R = A/P η(x, t) = η0 e−μx cos (ωt − kx) η0 ω μ -- 1 of 3 -- Tarnbeck Institute of Hydrology TIH/TN/18 Page 2 of 3 (4) where c is the frictionless wave speed and h the mean depth. The second expression is the friction parameter; it is small in the lower reach and approaches unity above Harrowby Reach, which is where the exponential form begins to fail. 4 Application to the Braithe Taking the mean depth as eleven metres below the bar and four metres at the bridge, with Manning's coefficient at the value fitted in 2018, the formula reproduces the observed amplitude at Vardenne Quay to within four per cent and at Harrowby Reach to within nine. At Braithe Bridge it overestimates the amplitude, and the discrepancy grows through the spring tides, which is the behaviour the friction parameter predicts. A two-reach treatment with separate depths would probably remove most of the error at the bridge. It has not been attempted here because the gauge record above Harrowby Reach is too short to fit a second coefficient with any confidence. 5 Coefficients Manning's coefficient is not constant with depth in a channel of this kind, and the single fitted value used above is a compromise. Fitting the 2018 record with a depth-dependent form gives (5) with the deep-water value and b a bed constant. The fit is better in the lower reach and no better at the bridge, which suggests that the error there is not in the friction term at all. The two constants were fitted to the 2018 record and have not been refitted since. Refitting on the four years now available would be worth doing; the Institute's expectation is that the deep-water value will move very little and the bed constant appreciably, because it is carrying the shallow reaches where the record has improved most. 6 Limitations Three limitations should be stated plainly. The first is the one-dimensional assumption, which fails where the channel divides above Harrowby Reach. The second is the neglect of the freshwater inflow, which is small in summer and not small after rain. The third is the linearisation itself, which is a poor approximation once the friction parameter approaches unity - that is, in exactly the reach where the model is least accurate. The error measure quoted in the previous section is μ = ω c ( χ 2(1 + χ2)) 1/2 , χ = 8 n2 c η0 3π h 4/3 n(h) = n∞ + b h 1/3 n∞ -- 2 of 3 -- Tarnbeck Institute of Hydrology TIH/TN/18 Page 3 of 3 (6) taken over the spring-neap cycle at each gauge, with the observed amplitude and the modelled one. It is a crude measure and it flatters the model at the bar, where the amplitude is large and the absolute error is not. None of this is an argument against using the formula, which is quick, transparent and good enough for the purposes the Partnership puts it to. It is an argument for quoting it with the reach and the tidal range attached, which the papers that quote it have not always done. References Sandiman, R. K. (2018). Tidal propagation in the Braithe: a first fit. Tarnbeck Institute internal report TIH/IR/09. Vale, H. and Croyde, P. (2021). The Harrowby Reach gauge, 2015 to 2020. Journal of Estuarine Hydrology 44, 218-31. Prosser, A. (2009). Friction coefficients for the Braithe channel. Braithe Harbour Board, unpublished. ε = |ηo − ηm| ηoηo ηm -- 3 of 3 --
Show the whole file (5 KB)
JSON
{
  "markdown": "Tarnbeck Institute of Hydrology TIH/TN/18\nPage 1 of 3\nA one-dimensional model of tidal attenuation in the Braithe channel\nTechnical note TIH/TN/18 \u00b7 January 2026\nR. K. Sandiman and H. Vale\n1 Introduction\nThe tide entering the Braithe is attenuated over the eleven kilometres between the bar and Braithe\nBridge, and the attenuation is large enough to matter to anyone predicting water levels in the upper\nestuary. This note sets out the one-dimensional model the Institute has used since 2018, states the\napproximation on which the working formula rests, and compares the result with the gauge record at\nthree stations.\nNothing here is new. The intention is to have the derivation, the assumptions and the coefficients in one\nplace, because the formula has been quoted in Partnership papers without them.\n2 Governing equations\nTake the channel as a single reach of slowly varying cross-section and neglect lateral inflow.\nConservation of mass gives\n(1)\nwhere A is the cross-sectional area below the free surface and Q the discharge through it. Conservation of\nmomentum, with friction represented in the Manning form, gives\n(2)\nin which is the surface elevation above mean sea level, n is Manning's coefficient, R the hydraulic\nradius for wetted perimeter P, and g the acceleration due to gravity. The friction term is the only\nnonlinear one that matters over the range of interest.\n3 Attenuation of the leading harmonic\nFor a channel of nearly uniform depth the leading semidiurnal harmonic decays close to exponentially\nwith distance upstream, so that\n(3)\nwith the amplitude at the bar, the angular frequency of the harmonic, k the wavenumber and the\nattenuation coefficient. Linearising the friction term by the Lorentz method and collecting terms gives\n\u2202A\n\u2202t + \u2202Q\n\u2202x = 0\n\u2202Q\n\u2202t + \u2202\n\u2202x(\nQ 2\nA ) + gA \u2202\u03b7\n\u2202x + g n2 Q |Q|\nA R 4/3 = 0\n\u03b7\nR = A/P\n\u03b7(x, t) = \u03b70 e\u2212\u03bcx cos (\u03c9t \u2212 kx)\n\u03b70\t\u03c9\t\u03bc\n\n-- 1 of 3 --\n\nTarnbeck Institute of Hydrology TIH/TN/18\nPage 2 of 3\n(4)\nwhere c is the frictionless wave speed and h the mean depth. The second expression is the friction\nparameter; it is small in the lower reach and approaches unity above Harrowby Reach, which is where\nthe exponential form begins to fail.\n4 Application to the Braithe\nTaking the mean depth as eleven metres below the bar and four metres at the bridge, with Manning's\ncoefficient at the value fitted in 2018, the formula reproduces the observed amplitude at Vardenne Quay\nto within four per cent and at Harrowby Reach to within nine. At Braithe Bridge it overestimates the\namplitude, and the discrepancy grows through the spring tides, which is the behaviour the friction\nparameter predicts.\nA two-reach treatment with separate depths would probably remove most of the error at the bridge. It has\nnot been attempted here because the gauge record above Harrowby Reach is too short to fit a second\ncoefficient with any confidence.\n5 Coefficients\nManning's coefficient is not constant with depth in a channel of this kind, and the single fitted value used\nabove is a compromise. Fitting the 2018 record with a depth-dependent form gives\n(5)\nwith the deep-water value and b a bed constant. The fit is better in the lower reach and no better at\nthe bridge, which suggests that the error there is not in the friction term at all.\nThe two constants were fitted to the 2018 record and have not been refitted since. Refitting on the four\nyears now available would be worth doing; the Institute's expectation is that the deep-water value will\nmove very little and the bed constant appreciably, because it is carrying the shallow reaches where the\nrecord has improved most.\n6 Limitations\nThree limitations should be stated plainly. The first is the one-dimensional assumption, which fails where\nthe channel divides above Harrowby Reach. The second is the neglect of the freshwater inflow, which is\nsmall in summer and not small after rain. The third is the linearisation itself, which is a poor\napproximation once the friction parameter approaches unity - that is, in exactly the reach where the\nmodel is least accurate.\nThe error measure quoted in the previous section is\n\u03bc = \u03c9\nc (\n\u03c7\n2(1 + \u03c72))\n1/2\n, \u03c7 = 8 n2 c \u03b70\n3\u03c0 h 4/3\nn(h) = n\u221e + b\nh 1/3\nn\u221e\n\n-- 2 of 3 --\n\nTarnbeck Institute of Hydrology TIH/TN/18\nPage 3 of 3\n(6)\ntaken over the spring-neap cycle at each gauge, with the observed amplitude and the modelled\none. It is a crude measure and it flatters the model at the bar, where the amplitude is large and the\nabsolute error is not.\nNone of this is an argument against using the formula, which is quick, transparent and good enough for\nthe purposes the Partnership puts it to. It is an argument for quoting it with the reach and the tidal range\nattached, which the papers that quote it have not always done.\nReferences\nSandiman, R. K. (2018). Tidal propagation in the Braithe: a first fit. Tarnbeck Institute internal report TIH/IR/09.\nVale, H. and Croyde, P. (2021). The Harrowby Reach gauge, 2015 to 2020. Journal of Estuarine Hydrology 44,\n218-31.\nProsser, A. (2009). Friction coefficients for the Braithe channel. Braithe Harbour Board, unpublished.\n\u03b5 = |\u03b7o \u2212 \u03b7m|\n\u03b7o\u03b7o\t\u03b7m\n\n-- 3 of 3 --\n\n",
  "pageCount": 3,
  "model": "nano",
  "credits": 3,
  "requestId": 272372
}
Open the JSON file ↗
Expected vs. Found
✗Expected: Equations come back as math markup, such as LaTeX or MathML, or as an honest fallback, not as garbled prose.Found: Each of the six equations was reduced to its number, (1) to (6), with the bodies moved to page ends as fragments; the file holds no math markup.
Supporting proof
Proof 1Screenshot
Page 1 comparison: source equations 1 to 3 beside the returned Markdown
Open original ↗
Proof 2Screenshot
Page 2 comparison: source equations 4 and 5 beside the returned Markdown
Open original ↗
Proof 3Screenshot
Page 3 comparison: source equation 6 beside the returned Markdown
Open original ↗
Proof 4Screenshot
Run details card: default settings, the complete PDF in one request, completed
Open original ↗
Why this result

Equations had to come back as math markup or an honest fallback. They came back as stray numbers and broken fragments with no math markup, which is neither, so the result is a Fail. Two higher model settings, tried as separate runs, also left the equations garbled.

Tested by Chandresh Bisht · evidence dated 9 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
PDF Vector
Build or version
PDF Vector /api/document/parse; model nano (auto-selected by the server)
Plan or tier
free tier
Surface
API
Set up before the run
The complete three-page hydrology technical note, with six numbered display equations and Greek symbols in its text, had to be converted to Markdown in one pass with the product's default settings.
Tested
9 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 test case's result says which one 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 test case's result 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
21 November 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/pdf-vector/a-document-containing-mathematical-equations · 0 pass · 1 fail · coverage 1/1 · graded 2026-11-19

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.

Input · Document (PDF) ↗application/pdf · 236 KB
Output file (Markdown) ↗text/markdown · 5 KB
Proof 1 · Screenshot ↗image/png · 185 KB
Proof 2 · Screenshot ↗image/png · 203 KB
Proof 3 · Screenshot ↗image/png · 96 KB
Output file (JSON) ↗application/json · 5 KB
Proof 4 · Screenshot ↗image/png · 66 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)f3d69b6d9d2191c5806a426fd4ea5e209dcd7cf693ad6abe67a5d18a014b9fd6
Output file (Markdown)264295e66c6aafc2ee5e12027259d7947b0eaddf8b9a58d63d3f95c32bb707cb
Proof 1 · Screenshot03777523e0328b23a620ed44965d8fa36d4f264dc7d4939b3c770c893e4c2995
Proof 2 · Screenshot726d5a1744c3ed73c38675628d8cba6498df67a38d69185a521c996267b6968d
Proof 3 · Screenshot2fb3a7e448d2eea88b9aed799b201607a8e946bc079ad85a9a26bd82fe609e89
Output file (JSON)a1d52a32795b0cd9de8b8c8539f83eb09aba9f30a7504e8186a4e43e03eb63de
Proof 4 · Screenshot6fa6e6f0b6e5b3f775f620cae8a1d915a8687cdb3252011cc0c6e38cad3095cd