Competing Proofs Source Comparator
A comparison frame for two or more human proofs, showing assumptions, key moves and unresolved gaps.
Works on any free AI · Best tool: Any AI chat (ChatGPT, Claude, Gemini)
✅ How to use this effectively
- 1. Paste the exact theorem and all supplied proof candidates.
- 2. Check that every proof establishes the same claim under the same conditions.
- 3. Open the targeted source searches for missing alternatives.
- 4. Select a proof only after independently checking every implication.
🔧 If it is not right, reply with this: If wrong, reply with: "Compare the proofs line by line under identical assumptions and mark the first unsupported implication in each."
THE PROMPT
ROLE: Act as a proof-comparison editor and community-source researcher.
CONTEXT: A teacher must choose among different proofs of [CLAIM] for [LEARNER LEVEL].
INPUTS — FILL EVERY PLACEHOLDER:
- [CLAIM]
- [LEARNER LEVEL]
- [KNOWN ASSUMPTIONS]
- [CANDIDATE PROOFS OR LINKS]
- [TEACHING GOAL]
SOURCE-BOUND TOOL FACTS AND EXACT URL WHITELIST:
- [MATH_STACKEXCHANGE] Whitelist: https://math.stackexchange.com/search?q={ENCODED_KEYWORDS}. Search with one real tag plus 3–6 keywords; do not paste a full equation and do not present votes or acceptance as mathematical proof.
- [AOPS] Whitelist: https://artofproblemsolving.com/community/q1_{ENCODED_KEYWORDS}. The q1_ pattern is an undocumented search route, so also print the exact keywords as a paste fallback and never claim a search result proves contest provenance.
DO THIS:
1. Normalize the exact claim and list its assumptions before comparing methods.
2. Divide each candidate into premises, key lemma, inference chain and conclusion.
3. Flag circularity, hidden cases and appeals to a diagram or example.
4. Generate focused Math StackExchange and, for contest material, AoPS searches for alternative human proofs.
5. Compare pedagogical length separately from logical validity.
6. Recommend a classroom proof only with a checklist the teacher can verify.
WORKED LINK EXAMPLE — COPY THIS EXACT ENCODING PATTERN:
Example task: Compare human proofs that the square root of 2 is irrational.
Expected result or check target: The source search surfaces contradiction and parity approaches for independent checking.
check this yourself
CHECK → https://math.stackexchange.com/search?q=%5Bproof-writing%5D%20sqrt%202%20irrational%20proof
(paste-fallback: [proof-writing] sqrt 2 irrational proof)
Encoding note: The tag and spaces are encoded, and the payload decodes to concise proof-search keywords.
OUTPUT FORMAT:
1. Claim Lock — exact statement and shared assumptions
2. Proof Matrix — premises, key moves and conclusion by source
3. Gap Audit — hidden cases and unsupported steps
4. Human Search Routes — focused alternative-proof searches
5. Teaching Choice — recommendation with verification checklist
QUALITY AND TOOL GUARDRAILS:
- Human sources are leads to arguments, not proof; recheck every premise and inference.
- Popularity, acceptance and repetition across posts do not turn an argument into proof.
- Never merge steps from incompatible proofs without rechecking the combined logic.
- Use MathOverflow only for research-level, historical or open-problem questions, not this routine comparison.
- Do not fabricate citations, usernames, scores or contest provenance.
- A numerical test can expose a false claim but cannot prove a general theorem.
- 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.