Hand this page to your AI agent
Give your agent (Claude, ChatGPT or any assistant that can open web pages) this address and ask it to do the task on the page:
https://dbourdeau.github.io/cyphersolver/further/crawford1814.html
Or copy the block below into the chat. It is the whole task: the reading, every open gap, what has been tried, the steps, and how to report back.
TASK: take a partial decipherment further: Crawford to Monroe, Paris, 5 November 1814: a private letter in code
This page: https://dbourdeau.github.io/cyphersolver/further/crawford1814.html
You are helping a public research project finish reading historical cipher letters. This one is read in part:
the key works, but some pieces are still open. Your job is to close one or more of the open gaps below.
THE READING
Write-up: https://dbourdeau.github.io/cyphersolver/crawford1814.html (read it first: how the text was read, the key, the reading)
Date: 1814
Outcome: known key applied · partial
Read now: 90.7% of the deciphered cipher tokens give sense (pieces below may be untouched)
Files: https://github.com/dbourdeau/cyphersolver/tree/main/targets/crawford1814 (NOTES.md, key, transcription, reading, scripts)
OPEN GAPS (from NOTES.md, "## Remaining gaps")
1. [open-codes: doable now] Nine supplied groups (section 3) - blocker: open-codes; 1512 four times, 1276, 556, 361, 1474 and 812: the slips are inferred from the sense (one slip of the same kind is attested in September, section 7); the four groups written 1512 and 812 are not settled; the 16 Dec 1814 letter with its period decipherment could test Crawford's slips.
2. [needs-physical-access: needs a new source] Supplied letters and words and mended words - blocker: needs-physical-access; right[s], ma[de], la[s]t, spec[ified], [be brought by], [and] (64R07), [of] (65R03) and the five mended words (section 3): the groups give no more, and only a clear copy of the time (the clerk's fair copy, of which only the last page, 0067R, is on the roll) could settle them.
3. [needs-physical-access: needs a new source] A period decipherment or clear copy - blocker: needs-physical-access; the clerk's fair copy (last page on 0067R), the Crawford papers (Library of Congress), the Monroe papers (New York Public Library) and Green (1965) not seen.
ALREADY TRIED (from NOTES.md, "## Escalation")
[x] siblings: (15 Nov 2026, section 7): frames 0025, 0031 and 0032 of the same roll, 81 groups with the clerk's decipherment. Not done: Crawford's other WE025 letters on this roll.
[x] clear-pages: neighbouring frames 0059-0063 and 0067-0070 checked for a decipherment (section 1); only the last page of the clerk's clear fair copy (0067R) is on the roll.
[x] known-keys: the code is WE025, applied unchanged from Weber's printed table (section 2); the September passage on 0025R is in WE028, Crawford's older code.
[x] print: the sources in section 5 checked; Green (1965) and the Crawford papers remain.
[x] retry: (15-16 Nov 2026): the groups of "troops" read from their marks (section 7); the supplied groups set against the September 1814 check (no pair contradicts them); 1025 looked at again on the frame and its diamond added. The 16 Dec 1814 private letter (roll 18 frames 0129-0131, same code), which has a period decipherment on the Library of Congress duplicate (Monroe Papers reel 5, images 938-941), can test Crawford's slips; not done here.
STEPS
0. Set up. If you can run a shell, fork and clone the repository and work inside it:
git clone https://github.com/dbourdeau/cyphersolver.git
Then read, in this order: CONTRIBUTING.md (how a contribution is sent and credited); README.md, sections
"Repository layout" and "Conventions" (how readings are measured and named); targets/crawford1814/NOTES.md in full, and the
key, transcription and reading files it names; lang/README.md (shared language models).
Work in targets/crawford1814/. Add your findings to NOTES.md under a dated heading without rewriting what is there, and
update the "## Remaining gaps" line of every gap you close. Keep WORKLOG.md there: one dated line per step
(hypothesis, value tried, solver run, crib, control), failures included. Do not edit docs/ (the site is generated).
If you cannot run a shell, fetch the files from the links above and keep your work in files you send with the issue.
1. Pick a gap. Start with the ones marked "doable now" (open-codes, not-attempted, left-open): the images and the key
are online, so they need only work. A gap marked "needs a new source" (no-key-material, too-short, illegible,
needs-physical-access) can be closed only by something new: a key
or a deciphered sibling found elsewhere, a better image, a printed edition or calendar, a photograph from the archive.
For those, search for that material first, and say where you looked even when you find nothing.
2. Start from the existing key and transcription in the folder. Do not rebuild the key from scratch, and do not
re-read parts that are already read unless you find an error in them.
3. For a code group or sign value: list every place the group occurs, show how each reads with the value you propose,
and say what still does not fit. For a passage: re-read it at the image and give the folio and line. For a missing
letter or leaf: say where it is held and how it can be reached.
4. Measure again. Apply the key to the whole text, write the reading file, and count the share of cipher tokens that
give sense (not an estimate). The reading is "complete" only when (1) at least 95% of its cipher tokens give sense;
(2) no gap is left untried; (3) every letter in it is covered; (4) what stays open is scattered code groups or names,
or pieces blocked from outside. Otherwise it stays "partial": say which gaps are still open and why.
5. Be honest. Mark every uncertain word with [?], leave unread groups as their numbers or signs, and never fill a gap
with a plausible guess. A gap retried and still open, with what was ruled out, is worth reporting.
REPORT BACK
With a clone: open a pull request with your changes to targets/crawford1814/. Say in the description which gaps you worked on,
the share read before and after, and how you want to be credited (name, initials or handle, and a link).
Without one: open an issue: https://github.com/dbourdeau/cyphersolver/issues/new?template=further-reading.yml&title=Further+reading%3A+crawford1814&page=crawford1814.html
Give the write-up, the gap you worked on (its line in Remaining gaps, or the code group, folio and line), what you
propose, the evidence (every occurrence, the images or sources), the share read before and after, your step log,
and the tools and AI model you used.
If you cannot open issues or pull requests, write this report for your human to send. Credit goes to the person who sends it.Open gaps
gold can be done now: the images and the key are online, it needs only work. grey needs a new source first: a key, a better scan, an edition or the archive.
- code groups open Nine supplied groups (section 3) - blocker: open-codes; 1512 four times, 1276, 556, 361, 1474 and 812: the slips are inferred from the sense (one slip of the same kind is attested in September, section 7); the four groups written 1512 and 812 are not settled; the 16 Dec 1814 letter with its period decipherment could test Crawford's slips.
- needs the archive Supplied letters and words and mended words - blocker: needs-physical-access; right[s], ma[de], la[s]t, spec[ified], [be brought by], [and] (64R07), [of] (65R03) and the five mended words (section 3): the groups give no more, and only a clear copy of the time (the clerk's fair copy, of which only the last page, 0067R, is on the roll) could settle them.
- needs the archive A period decipherment or clear copy - blocker: needs-physical-access; the clerk's fair copy (last page on 0067R), the Crawford papers (Library of Congress), the Monroe papers (New York Public Library) and Green (1965) not seen.
Already tried
- ☑ siblings (15 Nov 2026, section 7): frames 0025, 0031 and 0032 of the same roll, 81 groups with the clerk's decipherment. Not done: Crawford's other WE025 letters on this roll.
- ☑ clear-pages neighbouring frames 0059-0063 and 0067-0070 checked for a decipherment (section 1); only the last page of the clerk's clear fair copy (0067R) is on the roll.
- ☑ known-keys the code is WE025, applied unchanged from Weber's printed table (section 2); the September passage on 0025R is in WE028, Crawford's older code.
- ☑ print the sources in section 5 checked; Green (1965) and the Crawford papers remain.
- ☑ retry (15-16 Nov 2026): the groups of "troops" read from their marks (section 7); the supplied groups set against the September 1814 check (no pair contradicts them); 1025 looked at again on the frame and its diamond added. The 16 Dec 1814 private letter (roll 18 frames 0129-0131, same code), which has a period decipherment on the Library of Congress duplicate (Monroe Papers reel 5, images 938-941), can test Crawford's slips; not done here.
Send a result
One closed gap counts: a code group valued, a passage re-read, a key or clear copy found elsewhere. It is credited to you on the write-up.