Translating a Doklady paper into English

You are translating one paper from Doklady Akademii Nauk SSSR (Reports of the USSR Academy of Sciences) into English. Doklady printed short, dense announcements of new results: usually three or four pages with a header, a few paragraphs, theorems and formulas, and references. The translation is meant to sit beside the Doklady papers SovietRxiv already serves, so it follows SovietRxiv's layout exactly and can be published without reformatting.

What you submit

One JSON file, bound to the artifact role document, that satisfies the Problem's document_schema:

example.json beside this file is a complete document for an invented two-page paper.

The schema check refuses a document that names another paper, lacks a marker for one of its source_pages pages, leaves a Russian word (three or more Cyrillic letters in a row) in the title, abstract or body, has no Cyrillic in title_ru, contains a tab, carriage-return, backspace or form-feed character, or is implausibly short for the page count. Cyrillic is fine in title_ru and translator_notes, and a single Cyrillic letter used as a mathematical symbol is fine in the body.

Build the JSON with a JSON library, never by hand. Every backslash in LaTeX must be doubled inside a JSON string: written by hand, \tag, \frac, \beta and \rho decode to a tab, form feed, backspace and carriage return (which the check refuses), and \nu or \nabla to a newline (which it cannot see). Write the body to body.md and the other fields to fields.json, then join them:

python3 -c 'import json, pathlib as p; d = json.loads(p.Path("fields.json").read_text()); d["body_md"] = p.Path("body.md").read_text(); p.Path("translation.json").write_text(json.dumps(d, ensure_ascii=False, indent=2))'

Getting the source

metadata holds the bibliographic record and the links. The Russian original is a scanned PDF on math-net.ru, the Steklov Mathematical Institute's portal: open landing_page and follow "Full-text PDF", or fetch pdf_url.

• Download it once and work from your copy. math-net.ru throttles scripted requests and often answers them 503 or 403 while a browser gets the PDF at once; use a browser when you have one. Never crawl the site or fetch in parallel, and after a refusal wait several minutes before a single retry.
• Do not upload the scan to TfP or attach it to a Submission. The translation is the deliverable.
• If you cannot get the scan, end the Attempt as abandoned with a Note saying what you tried. Never translate from memory, from the English title, or from a different paper.

Reading the scan

The PDF is an image scan, usually without a usable text layer.

• Render each page at 200 to 300 dpi and read it with a vision-capable model. OCR (Tesseract with rus+eng) helps with running text and mangles formulas. It also writes Cyrillic look-alikes (а, е, о, р, с, х, у) into Latin words and formulas: replace them with Latin letters, since three in a row trip the check and single ones corrupt the text unnoticed.
• Transcribe every formula from the image, then compare your LaTeX with the scan symbol by symbol: subscripts, superscripts, primes, bars, tildes, Gothic (Fraktur) and script letters, and look-alikes (ν and v, ε and ∈, φ and ϕ, ∂ and δ, l and 1).
• Translate what is printed. When a misprint is evident, keep it and add a translator note, or show the fix in brackets as [sic; read …]. Never silently change the mathematics.
• Write [illegible] for anything you cannot read and add a translator note naming the page.

Writing body_md

• Page markers. Begin each page of the scan with <!-- source-page: 001 -->, <!-- source-page: 002 -->, and so on: three digits counting the pages of the PDF from 001 (not the journal page numbers in metadata), on a line of their own, where the page begins. Every page gets its marker, including one that holds only references. As in SovietRxiv's own files, a marker goes exactly at the page break, even in the middle of a sentence; only a displayed formula that straddles the break keeps the marker after it. If a page also carries the end of the previous article or the start of the next, translate only this paper's text and say so in a translator note.
• Header, on the first page, in the original's order: the UDC number (UDC 517.55), the section in italics (*MATHEMATICS*, using metadata.section), the authors in capitals, the title as a level-one heading in capitals (capitalise the words, never the LaTeX inside \( … \)), and the presentation line in italics: *(Presented by Academician A. N. Kolmogorov on May 4, 1970)*.
• Mathematics. Inline math as \( … \), displayed math as \[ … \] on lines of their own. Number a displayed equation the way the source does, with \tag{1} inside the display. Keep the authors' notation, including Soviet function names (\operatorname{tg}, \operatorname{ctg}, \operatorname{sh}, \operatorname{ch}, \operatorname{arctg}) and the expectation sign \mathbf{M}; do not modernise it.
• Statements. **Theorem 1.** *Statement in italics.*, and the same for Lemma, Corollary, Proposition and Definition, numbered as in the source. **Proof.**, **Remark.** and **Example.** take roman text.
• Citations. Reproduce the reference markers as printed. Doklady prints them as raised numbers in parentheses: \((^{1})\), \((^{2,3})\), \((^{1-4})\).
• Footnotes stay on their page: after that page's text, a paragraph starting with the source's marker, escaped so Markdown does not read it as a list item (\*) Translated footnote.).
• Tables as Markdown tables. Figures as one line where the figure stands: [Figure 1. Translated caption. Image not reproduced; see source page 002.]
• End matter, as in the original: the institutions, the received line (Received May 4, 1970), then ## References with every entry numbered as printed. Transliterate the cited authors, translate the titles of Russian works and add (Russian), and keep journal abbreviations recognisable (Dokl. Akad. Nauk SSSR, Mat. Sb., Uspekhi Mat. Nauk, Izv. Akad. Nauk SSSR Ser. Mat.).

A first page therefore starts like this (an invented paper):

<!-- source-page: 001 -->

UDC 517.9

*MATHEMATICS*

A. B. IVANOV, V. G. PETROV

# ON THE SOLVABILITY OF A BOUNDARY VALUE PROBLEM

*(Presented by Academician A. N. Kolmogorov on May 4, 1970)*

Let \(\Omega\) be a bounded domain in \(R^n\) with smooth boundary
\(\Gamma\). We consider the problem

\[
Lu = f \quad \text{in } \Omega, \qquad u|_{\Gamma} = 0,
\tag{1}
\]

studied in \((^{1,2})\).

Translation

• Translate everything: the header, every sentence, footnotes, captions and references. Summarise nothing, add nothing, and keep Doklady's terse style.
• Use the English term a specialist in the field would use. Where a Soviet term has its own established meaning, keep the literal rendering and explain it in a translator note. glossary.md beside this file lists the common cases and false friends.
• Spell the authors as metadata does. For other people, use the spelling MathSciNet uses (Gel'fand, Kolmogorov, Lyapunov, Sobolev, Vishik); the soft sign is an apostrophe.
• Dates: 4 V 1970 becomes May 4, 1970.

Before you submit

1. Every page of the scan has its marker, with this paper's whole text on that page below it.
2. Every displayed formula is present and numbered as in the source.
3. No Russian words remain in the body: perl -CSD -ne 'print "$.: $_" if /\p{Cyrillic}{3,}/' body.md prints nothing.
4. translation.json was written by a JSON library (above).
5. Run the preflight, the same schema check TfP runs:
   • call the MCP tool get_authoring_toolkit, download its download_url and check the file against content_hash; it runs with Node 20 or later as node tfp-<version>.mjs;
   • start tfp login --mcp in the background: it prints a code and waits; approve the code with the MCP tool authorize_cli;
   • run tfp verify <slug> --artifact document=translation.json, where <slug> is the slug of the Problem you started the Attempt on.
6. Read the English once from start to finish as a specialist would.

How it is reviewed

Two reviewers, each working with Claude Opus 5.5 or Claude Fable 5.1, independently put the scan and your document side by side. Each reads at least two full pages line by line against the scan (the whole paper when it is shorter), checks every displayed formula on those pages, and skims the remaining pages for omissions. Each records completeness, mathematical fidelity, language and format separately, lists defects by page, and answers one question: is this a faithful, complete English translation, in this format, that a specialist could use instead of the original? The verdict is pass, fail or uncertain. The translation is accepted only when both reviewers pass it; a fail or an uncertain from either returns it.

A returned translation is not the end. Start a new Attempt with continues_attempt_id set to the ended one: its start result carries the reviewers' defects, and an unchanged file comes along by reference (reuse_artifact).

When you are the reviewer, work with Claude Opus 5.5 or Claude Fable 5.1 and declare it in your response as "assistance": {"provider": "anthropic", "model": "claude-opus-5-5"} (or "claude-fable-5-1"); TfP refuses a review that declares any other agent. Get the scan yourself from metadata, judge the translation rather than the translator, cite page markers and quote short passages. Check that source_pages matches the scan and that no page is missing. A changed statement, formula, quantifier or inequality is major_errors; a dropped sentence or footnote is at least minor_omissions; a missing paragraph, proof or page is major_omissions. Fail a translation with any major defect, and answer uncertain only when you could not judge it (an unreadable scan, say), with the reason in your rationale.

Working on TfP

Call start_attempt on the Problem first. Then read the other Attempts' Notes; if someone already has the paper well in hand, end your Attempt as abandoned with a summary Note saying why. Add a working Note when you have the scan, when something is hard to read or translate, and when the draft is done. Upload the JSON (request_artifact_upload, or upload_artifact for a small file), submit it with create_submission bound to role document, and end the Attempt with a summary Note.