The Japanese Army’s numeric kana cipher, 1902–04

TASK: take a partial decipherment further: The Japanese Army’s numeric kana cipher, 1902–04
This page: https://dbourdeau.github.io/cyphersolver/further/army1902.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/army1902.html (read it first: how the text was read, the key, the reading)
  Date:       1902–04
  Outcome:    key from adjacent plaintext · partial
  Read now:   95.8% of the deciphered cipher tokens give sense (pieces below may be untouched)
  Files:      https://github.com/dbourdeau/cyphersolver/tree/main/targets/army1902 (NOTES.md, key, transcription, reading, scripts)

OPEN GAPS (from NOTES.md, "## Remaining gaps")
  1. [needs-physical-access: needs a new source] C09122909900 pair 2 (17 for イ) - blocker: needs-physical-access; the image shows 七, writer's or transmission error; binarised JBIG2 scan cannot settle the head of column 2 either
  2. [illegible: needs a new source] C03020059400 three cramped characters of the translation (frame 0118) - blocker: illegible; re-read on the JACAR scan 23 Oct 2026. Pairs 5 and 7 settled 25 Oct 2026: pair 5 = 04 (ハ) on Tomokiyo's reading of the image, pair 7 八八 (ゼ) read as ゼウ = 場 (Harumi-Matsuba, issue #97); 12/12 against the translation

ALREADY TRIED (from NOTES.md, "## Escalation")
  [x] siblings: the contributor viewed about 420 items (1,088 frames) of the 1901-02 telegram files and 235 items of the 1904 Daijiki; C09123116600 found by a catalogue search for digit runs
  [x] clear-pages: the filed translations (fr. 0108, 0078, the Daijiki text) and the outgoing draft C09122909800 used as cribs
  [x] known-keys: Cryptiana's 1874 and 1894 Army coordinate ciphers (iroha order) do not fit; the 1902 table does not read C09122806100
  [x] print: contributor's prior-work check (PRIOR_CHECK.md, 20 Oct 2026) found no earlier reading
  [x] key-rebuild: table complete for the observed values; unobserved cells inferred from the rule
  [x] retry: the discordant digits judged blind by Codex and Sonnet (4 runs); none overturned the first reading

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/army1902/NOTES.md in full, and the
   key, transcription and reading files it names; lang/README.md (shared language models).
   Work in targets/army1902/. 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/army1902/. 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+army1902&page=army1902.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.