AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 30 October 2026

Does PDF Vector keep code blocks fenced and indented in Markdown?

PDF Vector returned the code without code fences or indentation in Markdown. The listing ran directly into the following prose.

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.

Code block — fenced, structure intactFailEvidence
What we sent

We sent the complete three-page operations note to PDF Vector’s document parsing API in one request.

InputDocument (PDF)
Source PDF: page 2’s two code blocks and surrounding prose
Open the PDF ↗
What the tool returned
Markdownthe whole file · cited lines 1–6 and 36–45 marked
DS/OP/07 · Data services Page 1 of 3
Tarnbeck Institute of Hydrology · Data Services
Reloading a station export after a gauge reset
Operations note DS/OP/07 · Data services · Reviewed 14 January 2026
Symptoms
The station's daily total is short and the loader's own log says nothing is wrong. In the log the day
looks like a clean run: the export was fetched, every block was read, and the summary line reports
fewer readings than the station's counter did. The gap is always at the end of the day rather than
the beginning, and it is always a whole number of blocks.
The other sign is a duplicate warning in the block log, with two entries carrying the same sequence
number and different checksums. One warning is normal after a reset. A run of them means the
reset happened part way through the day and everything after it is being rejected block by block.
Why the loader rejects the second block
Block sequence numbers come from the station and not from the loader. The loader keeps the
highest number it has committed for the day and treats anything at or below it as a repeat, which is
the right thing to do on a poor link: a station that retransmits sends the same block twice, and the
loader must not count it twice.
A reset returns the counter to zero, so the blocks after it carry sequence numbers the loader has
already committed. Nothing about them looks new and the loader discards them for exactly the
reason it should. The reset time is the only thing that distinguishes a continuation from a repeat,
and the loader does not know it unless it is told.
The fix
When a gauge is reset in the field the station's counter returns to zero, and the export for that day
contains two blocks carrying the same sequence number. The loader accepts the first and rejects the
second. That is the right behaviour for a duplicated transmission and the wrong behaviour here, and
the day's record ends up short by however much arrived after the reset.
The fix is to requeue the affected blocks with the reset time supplied, so that the loader treats the
second block as a continuation rather than a repeat. The function below is the one to call. It lives in
tarnbeck.stations.maintenance and is safe to run more than once: a block that already carries a
good checksum is skipped.

-- 1 of 3 --

Tarnbeck Institute of Hydrology · Data Services DS/OP/07
DS/OP/07 · Data services Page 2 of 3
from tarnbeck.stations import Export, reload_window
def reload_after_reset(station, reset_at):
export = Export.open(station)
window = reload_window(reset_at, margin_minutes=45)
for block in export.blocks(window):
if block.checksum_ok():
continue
export.requeue(block, reason="gauge reset")
return export.commit(dry_run=False)
Run it from the loader host and not from a workstation, and take the reset time from the field log
rather than from the station clock, which is the thing that was wrong. The margin defaults to
forty-five minutes either side of the reset; widen it only if the field log is vague about the time,
because a wide window requeues blocks that were never in doubt.
If commit returns a count lower than the number of blocks in the window, stop there and raise it
with data services before running anything again. A short count means blocks were rejected for a
second reason, and requeuing them repeatedly will not find out what it was.
Running it
Run it from the loader host, in the maintenance environment, with the station code and the reset
time as they appear in the field log:
$ ssh loader-01.tarnbeck.example
$ tarnbeck-maint reload-after-reset --station VQ1 \
--reset-at '2026-01-29T09:15' --confirm
The command prints the window it will use, the number of blocks in it and the number it intends to
requeue, and then waits. Read the three numbers before answering. If the window is wider than the
field log justifies, stop and narrow it rather than letting it run.
Without --confirm the command does everything except commit, which is the safe way to see
what it would do. The dry run takes a few seconds and there is no reason to skip it.
Afterwards
Check the day's totals against the gauge's own counter before closing the ticket. The loader reports
the number of blocks committed and not the number of readings, and a day can come back with
the right number of blocks and the wrong number of readings if a block was truncated in the field.
Note the reset in the station log, with the time taken from the field log and not the time the reload
ran. The next person to look at a gap in the series will look there first, and a reload with nothing
written beside it is indistinguishable from a gap nobody has dealt with.

-- 2 of 3 --

Tarnbeck Institute of Hydrology · Data Services DS/OP/07
DS/OP/07 · Data services Page 3 of 3
If the count is short
A short count means blocks were rejected for a second reason and the reload has not found out
what it was. Do not run it again: a second pass requeues the same blocks, reports the same count,
and fills the log with attempts that bury the original failure.
Take the sequence numbers the command reports as rejected and look them up in the block log. A
checksum failure on a block truncated in the field cannot be fixed by reloading and needs the
station visited. A rejection with no reason recorded is a loader fault, and goes to data services with
the run's log attached.
The block header, for reference
Each block in an export begins with a fixed header, which is what the loader reads to decide
whether it has seen the block before:
SEQ=00184 STATION=VQ1 START=2026-01-29T08:45Z
COUNT=0180 INTERVAL=15s CRC=8f2a41d6
SEQ is the station's counter and is the field a reset returns to zero. START is the station clock, which
is not to be trusted after a reset - which is why the reset time comes from the field log and not from
the export.
CRC covers the readings and not the header, so a block with a good checksum and a wrong
sequence number is possible and is exactly what a reset produces. Nothing in the header says a
reset happened.
Rolling back
A committed reload can be undone within the same day by reverting the station's day to the
snapshot the loader takes before it commits. The snapshot is kept for seven days and is named for
the run.
After seven days the only route back is a fresh fetch of the export from the station, which is possible
while the station's own buffer still holds the day - about three weeks - and impossible afterwards. A
reload that has committed and cannot be rolled back is an incident and is raised as one, whatever
the size of the gap.

-- 3 of 3 --

Returned Markdown: graded output with flush-left code, headers and footers

Copied from Output file (Markdown), lines 1–6, 36–45

Open the Markdown file ↗
Output file (JSON)
Raw API response: graded output for three pages with no code fences
Cited values3 values from this file
model
nano
pageCount
3
markdown
DS/OP/07 · Data services Page 1 of 3 Tarnbeck Institute of Hydrology · Data Services Reloading a station export after a gauge reset Operations note DS/OP/07 · Data services · Reviewed 14 January 2026 Symptoms The station's daily total is short and the loader's own log says nothing is wrong. In the log the day looks like a clean run: the export was fetched, every block was read, and the summary line reports fewer readings than the station's counter did. The gap is always at the end of the day rather than the beginning, and it is always a whole number of blocks. The other sign is a duplicate warning in the block log, with two entries carrying the same sequence number and different checksums. One warning is normal after a reset. A run of them means the reset happened part way through the day and everything after it is being rejected block by block. Why the loader rejects the second block Block sequence numbers come from the station and not from the loader. The loader keeps the highest number it has committed for the day and treats anything at or below it as a repeat, which is the right thing to do on a poor link: a station that retransmits sends the same block twice, and the loader must not count it twice. A reset returns the counter to zero, so the blocks after it carry sequence numbers the loader has already committed. Nothing about them looks new and the loader discards them for exactly the reason it should. The reset time is the only thing that distinguishes a continuation from a repeat, and the loader does not know it unless it is told. The fix When a gauge is reset in the field the station's counter returns to zero, and the export for that day contains two blocks carrying the same sequence number. The loader accepts the first and rejects the second. That is the right behaviour for a duplicated transmission and the wrong behaviour here, and the day's record ends up short by however much arrived after the reset. The fix is to requeue the affected blocks with the reset time supplied, so that the loader treats the second block as a continuation rather than a repeat. The function below is the one to call. It lives in tarnbeck.stations.maintenance and is safe to run more than once: a block that already carries a good checksum is skipped. -- 1 of 3 -- Tarnbeck Institute of Hydrology · Data Services DS/OP/07 DS/OP/07 · Data services Page 2 of 3 from tarnbeck.stations import Export, reload_window def reload_after_reset(station, reset_at): export = Export.open(station) window = reload_window(reset_at, margin_minutes=45) for block in export.blocks(window): if block.checksum_ok(): continue export.requeue(block, reason="gauge reset") return export.commit(dry_run=False) Run it from the loader host and not from a workstation, and take the reset time from the field log rather than from the station clock, which is the thing that was wrong. The margin defaults to forty-five minutes either side of the reset; widen it only if the field log is vague about the time, because a wide window requeues blocks that were never in doubt. If commit returns a count lower than the number of blocks in the window, stop there and raise it with data services before running anything again. A short count means blocks were rejected for a second reason, and requeuing them repeatedly will not find out what it was. Running it Run it from the loader host, in the maintenance environment, with the station code and the reset time as they appear in the field log: $ ssh loader-01.tarnbeck.example $ tarnbeck-maint reload-after-reset --station VQ1 \ --reset-at '2026-01-29T09:15' --confirm The command prints the window it will use, the number of blocks in it and the number it intends to requeue, and then waits. Read the three numbers before answering. If the window is wider than the field log justifies, stop and narrow it rather than letting it run. Without --confirm the command does everything except commit, which is the safe way to see what it would do. The dry run takes a few seconds and there is no reason to skip it. Afterwards Check the day's totals against the gauge's own counter before closing the ticket. The loader reports the number of blocks committed and not the number of readings, and a day can come back with the right number of blocks and the wrong number of readings if a block was truncated in the field. Note the reset in the station log, with the time taken from the field log and not the time the reload ran. The next person to look at a gap in the series will look there first, and a reload with nothing written beside it is indistinguishable from a gap nobody has dealt with. -- 2 of 3 -- Tarnbeck Institute of Hydrology · Data Services DS/OP/07 DS/OP/07 · Data services Page 3 of 3 If the count is short A short count means blocks were rejected for a second reason and the reload has not found out what it was. Do not run it again: a second pass requeues the same blocks, reports the same count, and fills the log with attempts that bury the original failure. Take the sequence numbers the command reports as rejected and look them up in the block log. A checksum failure on a block truncated in the field cannot be fixed by reloading and needs the station visited. A rejection with no reason recorded is a loader fault, and goes to data services with the run's log attached. The block header, for reference Each block in an export begins with a fixed header, which is what the loader reads to decide whether it has seen the block before: SEQ=00184 STATION=VQ1 START=2026-01-29T08:45Z COUNT=0180 INTERVAL=15s CRC=8f2a41d6 SEQ is the station's counter and is the field a reset returns to zero. START is the station clock, which is not to be trusted after a reset - which is why the reset time comes from the field log and not from the export. CRC covers the readings and not the header, so a block with a good checksum and a wrong sequence number is possible and is exactly what a reset produces. Nothing in the header says a reset happened. Rolling back A committed reload can be undone within the same day by reverting the station's day to the snapshot the loader takes before it commits. The snapshot is kept for seven days and is named for the run. After seven days the only route back is a fresh fetch of the export from the station, which is possible while the station's own buffer still holds the day - about three weeks - and impossible afterwards. A reload that has committed and cannot be rolled back is an incident and is raised as one, whatever the size of the gap. -- 3 of 3 --
Show the whole file (7 KB)
JSON
{
  "markdown": "DS/OP/07 \u00b7 Data services Page 1 of 3\nTarnbeck Institute of Hydrology \u00b7 Data Services\nReloading a station export after a gauge reset\nOperations note DS/OP/07 \u00b7 Data services \u00b7 Reviewed 14 January 2026\nSymptoms\nThe station's daily total is short and the loader's own log says nothing is wrong. In the log the day\nlooks like a clean run: the export was fetched, every block was read, and the summary line reports\nfewer readings than the station's counter did. The gap is always at the end of the day rather than\nthe beginning, and it is always a whole number of blocks.\nThe other sign is a duplicate warning in the block log, with two entries carrying the same sequence\nnumber and different checksums. One warning is normal after a reset. A run of them means the\nreset happened part way through the day and everything after it is being rejected block by block.\nWhy the loader rejects the second block\nBlock sequence numbers come from the station and not from the loader. The loader keeps the\nhighest number it has committed for the day and treats anything at or below it as a repeat, which is\nthe right thing to do on a poor link: a station that retransmits sends the same block twice, and the\nloader must not count it twice.\nA reset returns the counter to zero, so the blocks after it carry sequence numbers the loader has\nalready committed. Nothing about them looks new and the loader discards them for exactly the\nreason it should. The reset time is the only thing that distinguishes a continuation from a repeat,\nand the loader does not know it unless it is told.\nThe fix\nWhen a gauge is reset in the field the station's counter returns to zero, and the export for that day\ncontains two blocks carrying the same sequence number. The loader accepts the first and rejects the\nsecond. That is the right behaviour for a duplicated transmission and the wrong behaviour here, and\nthe day's record ends up short by however much arrived after the reset.\nThe fix is to requeue the affected blocks with the reset time supplied, so that the loader treats the\nsecond block as a continuation rather than a repeat. The function below is the one to call. It lives in\ntarnbeck.stations.maintenance and is safe to run more than once: a block that already carries a\ngood checksum is skipped.\n\n-- 1 of 3 --\n\nTarnbeck Institute of Hydrology \u00b7 Data Services DS/OP/07\nDS/OP/07 \u00b7 Data services Page 2 of 3\nfrom tarnbeck.stations import Export, reload_window\ndef reload_after_reset(station, reset_at):\nexport = Export.open(station)\nwindow = reload_window(reset_at, margin_minutes=45)\nfor block in export.blocks(window):\nif block.checksum_ok():\ncontinue\nexport.requeue(block, reason=\"gauge reset\")\nreturn export.commit(dry_run=False)\nRun it from the loader host and not from a workstation, and take the reset time from the field log\nrather than from the station clock, which is the thing that was wrong. The margin defaults to\nforty-five minutes either side of the reset; widen it only if the field log is vague about the time,\nbecause a wide window requeues blocks that were never in doubt.\nIf commit returns a count lower than the number of blocks in the window, stop there and raise it\nwith data services before running anything again. A short count means blocks were rejected for a\nsecond reason, and requeuing them repeatedly will not find out what it was.\nRunning it\nRun it from the loader host, in the maintenance environment, with the station code and the reset\ntime as they appear in the field log:\n$ ssh loader-01.tarnbeck.example\n$ tarnbeck-maint reload-after-reset --station VQ1 \\\n--reset-at '2026-01-29T09:15' --confirm\nThe command prints the window it will use, the number of blocks in it and the number it intends to\nrequeue, and then waits. Read the three numbers before answering. If the window is wider than the\nfield log justifies, stop and narrow it rather than letting it run.\nWithout --confirm the command does everything except commit, which is the safe way to see\nwhat it would do. The dry run takes a few seconds and there is no reason to skip it.\nAfterwards\nCheck the day's totals against the gauge's own counter before closing the ticket. The loader reports\nthe number of blocks committed and not the number of readings, and a day can come back with\nthe right number of blocks and the wrong number of readings if a block was truncated in the field.\nNote the reset in the station log, with the time taken from the field log and not the time the reload\nran. The next person to look at a gap in the series will look there first, and a reload with nothing\nwritten beside it is indistinguishable from a gap nobody has dealt with.\n\n-- 2 of 3 --\n\nTarnbeck Institute of Hydrology \u00b7 Data Services DS/OP/07\nDS/OP/07 \u00b7 Data services Page 3 of 3\nIf the count is short\nA short count means blocks were rejected for a second reason and the reload has not found out\nwhat it was. Do not run it again: a second pass requeues the same blocks, reports the same count,\nand fills the log with attempts that bury the original failure.\nTake the sequence numbers the command reports as rejected and look them up in the block log. A\nchecksum failure on a block truncated in the field cannot be fixed by reloading and needs the\nstation visited. A rejection with no reason recorded is a loader fault, and goes to data services with\nthe run's log attached.\nThe block header, for reference\nEach block in an export begins with a fixed header, which is what the loader reads to decide\nwhether it has seen the block before:\nSEQ=00184 STATION=VQ1 START=2026-01-29T08:45Z\nCOUNT=0180 INTERVAL=15s CRC=8f2a41d6\nSEQ is the station's counter and is the field a reset returns to zero. START is the station clock, which\nis not to be trusted after a reset - which is why the reset time comes from the field log and not from\nthe export.\nCRC covers the readings and not the header, so a block with a good checksum and a wrong\nsequence number is possible and is exactly what a reset produces. Nothing in the header says a\nreset happened.\nRolling back\nA committed reload can be undone within the same day by reverting the station's day to the\nsnapshot the loader takes before it commits. The snapshot is kept for seven days and is named for\nthe run.\nAfter seven days the only route back is a fresh fetch of the export from the station, which is possible\nwhile the station's own buffer still holds the day - about three weeks - and impossible afterwards. A\nreload that has committed and cannot be rolled back is an incident and is raised as one, whatever\nthe size of the gap.\n\n-- 3 of 3 --\n\n",
  "pageCount": 3,
  "model": "nano",
  "credits": 3,
  "requestId": 272373
}
Open the JSON file ↗
Expected vs. Found
✗Expected: Code must remain a preformatted or fenced block, with line breaks and indentation intact.Found: The Markdown had no code fences. On page 2, indentation of 4, 8 and 12 spaces became no indentation, and the code ran directly into prose.
Supporting proof
Proof 1Screenshot
Page-2 comparison: source and returned Markdown showing lost code formatting
Open original ↗
Proof 2Screenshot
Run metadata card: conversion setup, result and timing
Open original ↗
Why this result

The supported conversion processed the complete PDF with the default pipeline. Code-block formatting and indentation were required, so the missing fences and indentation make this a formatting failure, not a blocked conversion.

Also observed in this test case

Headers and footers in code. The page-2 running header and page footer became body text interleaved with the code listing.

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 operations note, with Python and shell code blocks on page 2, was the input for a one-pass Markdown conversion using the default pipeline without product-specific tuning.
Pipeline
default parsing, one synchronous pass, no flags
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
18 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-a-code-block · 0 pass · 1 fail · coverage 1/1 · graded 2026-10-30

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 · 78 KB
Output file (Markdown) ↗text/markdown · 6 KB
Proof 1 · Screenshot ↗image/png · 521 KB
Output file (JSON) ↗application/json · 7 KB
Proof 2 · Screenshot ↗image/png · 90 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Input · Document (PDF)cd27d1e77ec9818ff769bde1b49d95e711373888507af4b007054c27b7a52db8
Output file (Markdown)887a9611aeacfbc7c1491ef324e1034852706fe07f62ce2156dd23c8a837fab6
Proof 1 · Screenshot93f2c479ebae821a8ea0afeae019a1a45da992f1b2b83ca6ed56a51655756d51
Output file (JSON)5adc9b6beb10fa223e7ecd8d711b4d432f9cc545b038209e09c31a74e3f5d739
Proof 2 · Screenshota00dbfed570a501abea9605de111680495e3af5a7b9e5d0a86d777da3dd9c489