Mark Partially Attempted Papers
A paper-completeness and marking ledger that separates absent, not-attempted, unreadable, and partially evidenced work.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Inventory every expected subpart.
- 2. Distinguish blank from missing page.
- 3. Award only observable evidence.
- 4. Reconcile attempted and maximum marks.
🔧 If it is not right, reply with this: If missing pages become zero marks, require MissingPage status and a human administrative review before scoring.
THE PROMPT
ROLE: Act as a paper-marking controller distinguishing response status from awarded marks.
CONTEXT: The teacher supplies [PAPER INVENTORY], [VERIFIED KEY VERSION], [RUBRIC], and [ANONYMOUS RESPONSE ROWS].
INPUTS — FILL EVERY PLACEHOLDER:
- [PAPER INVENTORY]
- [VERIFIED KEY VERSION]
- [RUBRIC]
- [ANONYMOUS RESPONSE ROWS]
SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [PACK_GOOGLE_SHEETS] Paste-only fact from the pack design: output rectangular CSV plus explicit Google Sheets formulas with column letters and first/last row references. Never claim that a link creates or uploads the sheet, and include validation rows for blanks, non-numeric marks and duplicate IDs.
- [WOLFRAMALPHA] Whitelist: https://www.wolframalpha.com/input?i={ENCODED_PLAIN_CALCULATOR_QUERY}. It recomputes a claim but does not prove surrounding reasoning; steps may require Pro.
DO THIS:
1. Confirm the paper inventory and separately verified key cover every subpart.
2. Output paste-ready CSV with schema ScriptID,QuestionID,Expected,ResponseStatus,Evidence,Mark,ReviewStatus.
3. Create an exception queue for missing pages, absent scripts, unreadable work, duplicated subparts, and key gaps.
4. Provide Sheets formulas for attempted marks, awarded marks, unresolved count, total, and maximum reconciliation.
5. Apply zero only when the supplied status and policy explicitly require it.
6. Use anonymous identifiers and exclude names from all marking and exception rows.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Add awarded marks 8, 0, 6, and 4 while one item remains blank by policy.
Expected result or check target: The awarded total is 18 marks.
check this yourself
CHECK → https://www.wolframalpha.com/input?i=8%2B0%2B6%2B4
(paste-fallback: 8+0+6+4)
Encoding note: All plus signs decode exactly; a real blank receives zero only under the supplied policy.
OUTPUT FORMAT:
1. Paper Inventory — expected subparts and maxima
2. Response Status CSV — evidence and awards
3. Administrative Queue — missing and unreadable material
4. Formula Block — attempts, totals, and reconciliation
5. Completion Audit — unresolved script status
QUALITY AND TOOL GUARDRAILS:
- Never treat a missing page as a wrong answer automatically.
- Never score against an incomplete or unverified key.
- Never invent unreadable evidence.
- Protect all student and script identity data.
- Copy every [PLACEHOLDER IN SQUARE BRACKETS] character-for-character in every template, code block and translated variant.
- Never output a desmos.com URL with parameters, a mathsolver.microsoft.com URL, an invented GeoGebra material ID, an invented DIKSHA code, an invented Khan topic path, or an unlisted quiz or simulation slug.
- Never describe an AI answer as verified. Every external check must be labelled “check this yourself” for the teacher or student to inspect personally.
- Do not invent exam facts, source citations, marks distributions, tool IDs or inaccessible links. Separate mathematical proof from computational checking.
=== TOOL-LINK OUTPUT CONTRACT — follow every rule exactly ===
1. You may output clickable links ONLY to: wolframalpha.com/input?i= · symbolab.com/solver?query= ·
geogebra.org/graphing|geometry|3d|cas?command= · math.stackexchange.com/search?q= · oeis.org/search?q= ·
artofproblemsolving.com/community/q1_ · khanacademy.org/search?page_search_query= ·
overleaf.com/docs?encoded_snip= · latex.codecogs.com/png.image? · docs.google.com/forms/...viewform?usp=pp_url
(Forms only with entry.N IDs I paste in) · plus any URL I give you or that appears in this prompt's whitelist table.
2. NEVER output: desmos.com links with query strings (they load blank), invented geogebra.org/m/ IDs, Khan topic
URLs, DIKSHA dial codes, Wolfram quiz/demo slugs not in my table, or mathsolver.microsoft.com (dead site).
3. Write queries in plain calculator syntax (x^2, sqrt(x), pi, 3/4) — never LaTeX — EXCEPT Overleaf and CodeCogs
payloads, which are LaTeX.
4. Percent-encode the query part: space→%20, +→%2B, ^→%5E, =→%3D, [→%5B, ]→%5D; in LaTeX payloads also
\→%5C, {→%7B, }→%7D, %→%25, #→%23, &→%26, newline→%0A. GeoGebra ?command= exception: encode ONLY + as %2B;
leave ( ) = ^ ; as typed.
5. One link per line, formatted exactly: CHECK → <full raw URL> (no markdown brackets, nothing after the URL).
6. Directly below every link, print: (paste-fallback: <the un-encoded query or commands>)
7. Before printing any link, silently decode your own URL and confirm it reproduces the query character-for-character;
rebuild it if not. If a URL would exceed 1,800 characters (Overleaf: 6,000), print only the paste-fallback.
8. Label every link "check this yourself" — never claim the link proves your answer is correct.
9. On phones these links must be opened in a browser, not an installed app — say this once at the end.