Proof Checker: Rigorous Mathematical Verification & Fixing
Before each reviewer slot, follow Selectable Reviewers: resolve invocation →
.aris/reviewer.json→ Claude Code default (Codex MCP) withreviewer_route.pythrough the canonical helper resolver, preserving this slot's tier, fresh contexts, source/image inputs and deterministic gates. Codex examples/pins below apply only tobackend=codex; other routes use their own first-call/reply contract. Save the route and actual returned identity; unavailable selections areREVIEW_UNAVAILABLE. Classify acceptance from actual families/completion/scope. Forward invocation reviewer/model/effort overrides to reviewer-bearing children. Generation workers are unchanged.
🔒 Do not wrap this skill in
/loop,/schedule, orCronCreate. It is verdict-bearing — it judges proof validity across rounds, threading the reviewer's memory from Phase 1 → Phase 3 viacodex-replyso the reviewer can check whether a fix actually closed the gap it flagged. An external timer re-enters from the top each tick, starting a fresh thread and losing that memory. Schedule the external wait that precedes it, not the verdict. Seeshared-references/external-cadence.md.
Systematically verify a mathematical proof via cross-model adversarial review, fix identified gaps, re-review until convergence, and generate a detailed audit report with proof-obligation accounting.
Context: $ARGUMENTS
Constants
- MAX_REVIEW_ROUNDS = 3
- REVIEWER_MODEL =
gpt-6-astra— Default model for the Codex backend, reasoning effortultra(deep-audit tier; pershared-references/reviewer-routing.md, capability fallbackgpt-6-astra+xhighthen the model capability fallbacks starting withgpt-6.1-sol+xhigh, capability errors only — never belowxhigh). Manual backend uses a model the user chooses, but it must be a non-Claude model ARIS can classify (OpenAI, Google, DeepSeek, Moonshot/Kimi, Qwen) — the executor is Claude, so routing the proof review into any Claude product makes Claude judge Claude and voids the cross-model invariant (seeshared-references/reviewer-routing.md). - REVIEWER_BACKEND =
codex— Default: Codex MCP (ultra). Override with— reviewer: oracle-profor Oracle MCP, or— reviewer: manualfor Manual Review MCP. If manual-review MCP is unavailable, stop and print the install command; do not fall back to Codex. Seeshared-references/reviewer-routing.md.
Reviewer Calling Convention
When calling the reviewer, branch on REVIEWER_BACKEND:
If REVIEWER_BACKEND = codex:
Use mcp__codex__codex for new review threads
(model: gpt-6-astra, config: {"model_reasoning_effort": "ultra"}).
Use mcp__codex__codex-reply for follow-up rounds (reuse threadId).
If REVIEWER_BACKEND = manual:
Use mcp__manual_review__review for new review threads with:
prompt: [exact same prompt that would go to Codex]
config: {"model_reasoning_effort": "xhigh", "executor_model": "", "require_reviewer_model": true}
Save the returned threadId.
Use mcp__manual_review__review_reply for follow-up rounds with:
threadId: [saved manual-review threadId]
prompt: [follow-up prompt]
config: {"model_reasoning_effort": "xhigh", "executor_model": "", "require_reviewer_model": true}
Prompt fidelity: the manual prompt must be exactly the same text that Codex would receive. Review tracing applies equally to both backends.
- AUDIT_DOC:
PROOF_AUDIT.mdat the paper directory root, alongsidemain.tex(cumulative log; when invoked via/paper-writing, this ispaper/PROOF_AUDIT.md) - REPORT_TEX:
proof_audit_report.tex(formal before/after PDF) - STATE_FILE:
PROOF_CHECK_STATE.json(for recovery) - SKELETON_DOC:
PROOF_SKELETON.md(micro-claim inventory) - RENDER_HTML = true — When
true(default), auto-renderPROOF_AUDIT.mdto HTML at workflow end via/render-html. Uses full Codex review gate (audit-class artifact — math-heavy content; render-fidelity check protects against MathJax breakage and matches the skill's cross-model audit invariant). Setfalseto skip, or pass— render html: false.
Acceptance Gate (objective, replaces subjective scoring)
The proof passes when ALL of the following hold:
- Zero open FATAL or CRITICAL issues
- Every theorem/lemma has: (i) explicit hypotheses, (ii) proof with all interchanges justified, (iii) every application discharges hypotheses in the ledger
- All big-O/Θ/o statements have declared parameter dependence and uniformity scope
- Counterexample pass executed on all key lemmas (log candidates even if none found)
Issue Taxonomy (20 categories, 4 groups)
Group A: Logic & Proof Structure
| Category | Description | Example |
|---|---|---|
| UNJUSTIFIED_ASSERTION | Claim stated without proof or reference | "The Hessian splits into Gram blocks" |
| UNPROVEN_SUBCLAIM | "Clearly" / "it follows" hides a nontrivial lemma | "By symmetry, the cross-terms vanish" without checking |
| QUANTIFIER_ERROR | Wrong order ∀/∃, missing "for sufficiently small κ" | "For all π, there exists ε" vs "there exists ε for all π" |
| IMPLICATION_REVERSAL | Uses (A⇒B) as (B⇒A), or claims equivalence with only one direction | |
| CASE_INCOMPLETE | Misses boundary/degenerate cases | Singular covariance, zero weight, non-unique argmin |
| CIRCULAR_DEPENDENCY | Lemma uses theorem that depends on it | |
| LOGICAL_GAP | A step is not justified by what precedes it | B=Θ(1) → β_K=0 without analyzing W |
Group B: Analysis & Measure Theory
| Category | Description | Example |
|---|---|---|
| ILLEGAL_INTERCHANGE | Swaps limit/expectation/derivative/integral without DCT/MCT/Fubini | Differentiating under E without domination |
| NONUNIFORM_CONVERGENCE | Pointwise convergence used as uniform | sup and limit swapped |
| MISSING_DOMINATION | DCT cited but no dominating function given | |
| INTEGRABILITY_GAP | Uses E | X |
| REGULARITY_GAP | Differentiability/Lipschitz/convexity used but not established | |
| STOCHASTIC_MODE_CONFUSION | Mixes a.s./in prob./in L²/in expectation |
Group C: Model & Parameter Tracking
| Category | Description | Example |
|---|---|---|
| MISSING_DERIVATION | A quantity is used but never derived from the model | Risk functional with undefined B, W |
| HIDDEN_ASSUMPTION | Proof silently uses a condition not in the theorem | Gaussianity assumed but not stated |
| INSUFFICIENT_ASSUMPTION | Hypotheses too weak for proof (counterexample exists) | Moment conditions admitting 2-point distributions |
| DIMENSION_TRACKING | Parameter dependence (d, n, K, ...) not explicit | d enters only through κ |
| NORMALIZATION_MISMATCH | Coordinate/scaling conventions inconsistent | Rescaled vs raw coordinates |
| CONSTANT_DEPENDENCE_HIDDEN | "C" depends on d,n,K but treated as universal |
Group D: Scope & Claims
| Category | Description | Example |
|---|---|---|
| SCOPE_OVERCLAIM | Conclusion stated more broadly than proof supports | "β_K=0" with only generic overlap |
| REFERENCE_MISMATCH | Cited theorem's hypotheses not verified at point of use |
Two-Axis Severity System
Axis A — Proof Status (what is wrong)
| Status | Meaning |
|---|---|
| INVALID | Statement false as written (counterexample exists or contradiction) |
| UNJUSTIFIED | Could be true, but current proof does not establish it |
| UNDERSTATED | True only after strengthening assumptions |
| OVERSTATED | True only after weakening conclusion / adding qualifiers |
| UNCLEAR | Ambiguous notation / definition drift (not wrong per se) |
Axis B — Impact (how much breaks)
| Impact | Meaning |
|---|---|
| GLOBAL | Breaks main theorem or core dependency chain |
| LOCAL | Affects a side result but not the main theorem |
| COSMETIC | Exposition only |
Severity Labels (derived)
| Label | Definition |
|---|---|
| FATAL | INVALID + GLOBAL |
| CRITICAL | (INVALID + LOCAL) or (UNJUSTIFIED + GLOBAL) |
| MAJOR | (UNJUSTIFIED + LOCAL) or (UNDERSTATED/OVERSTATED + GLOBAL) |
| MINOR | Clarity / notation / dimension bookkeeping that doesn't change claims |
Side-Condition Checklists for Common Theorems
When the proof invokes any of the following, require explicit verification of ALL listed conditions:
| Theorem | Required Conditions |
|---|---|
| DCT (Dominated Convergence) | Pointwise a.e. convergence + integrable dominating function |
| MCT (Monotone Convergence) | Monotone increasing + non-negative |
| Fubini/Tonelli | Product measurability + integrability (Fubini) or non-negative (Tonelli) |
| Leibniz integral rule | Continuity of integrand + dominating function for derivative |
| Implicit Function Theorem | Continuous differentiability + non-singular Jacobian |
| Taylor with remainder | Sufficient differentiability + remainder form (Lagrange/integral) |
| Jensen's inequality | Convexity of function + integrability |
| Cauchy-Schwarz | Correct inner product space + integrability of both factors |
| Weyl/Davis-Kahan | Symmetry/Hermiticity + perturbation bound conditions |
| Analytic continuation | Domain connectivity + identity theorem conditions |
| WLOG reduction | Invariance under claimed symmetry + reduction is reversible |
Workflow
Phase 0: Preparation
- Locate the proof: Find the main
.texfile(s). - Read the entire proof: Extract list of all theorems/lemmas/propositions/corollaries/definitions/assumptions.
- Read reference materials: Reference papers, prior results.
- Build a section map: Structured list with line numbers and key claims.
- Identify the main theorem: Central result, assumptions, claims.
Phase 0.5: Proof-Obligation Ledger
Bounded fan-out — build the ledger in parallel; never judge in parallel. Freeze mechanically enumerable source-unit IDs before dispatch: file spans, sections, theorem/lemma/proposition blocks, or proof environments with stable source anchors. Sort them by source order and partition them into no more than
max_shards: 8. Run waves of at mostmax_concurrency: 4, withmax_turns: 8per leaf. Obligations are discovered from these units and receive deterministic IDs only after extraction, derived from the source-unit ID plus a stable ordinal or anchor (for exampleTHM-3:OB-004).
- Tier 1 (Workflow): explicitly select
aris-fanout-leaffor every shard.- Tier 2 (Agent): call only
Agent(aris-fanout-leaf).- Tier 3: process the same frozen shards sequentially. A failed, malformed, or timed-out shard gets at most one executor-side sequential fallback and never a replacement Agent.
This follows
shared-references/fan-out-pattern.md. The leaf prompt repeats the assigned IDs, no-delegation, read-only, no-verdict, and output-schema rules because workers do not inherit this skill.Two hard rules:
- The shards EXTRACT, they do not ADJUDICATE. Building the ledger (inventorying obligations, typing symbols, restating with explicit quantifiers) is structural extraction. Whether a proof step is valid is a Type-B correctness verdict reserved for the cross-model jury in Phase 1 / Phase 3. A leaf MUST NOT mark a micro-claim "proved" or "sound"; it only records the obligation and the location where the paper claims to discharge it. A shard's
UNVERIFIEDmeans the paper cites no discharge location, not that the leaf checked the mathematics and rejected it.Shard output: each leaf returns
{shard_id, assigned_unit_ids, covered_unit_ids, status, entries, errors}.assigned_unit_idsandcovered_unit_idscontain source-unit IDs. Entries contain typed ledger items discovered in those units, each with a deterministic post-extraction obligation ID or symbol key asdedup_key. Never prose-only; never a validity-verdict field.Coverage receipt: reconcile the merged
covered_unit_idswith the frozen source-unit set after the one allowed sequential fallback. Record planned/completed/failed/uncovered IDs andcoverage_complete. The receipt proves source-unit execution coverage only; it does not prove that every relevant obligation was discovered or that the extracted ledger is mathematically complete. Any uncovered source unit makes the proof checkINCOMPLETE/BLOCKEDand blocks a complete validity verdict.
- Global artifacts are a barrier, computed on the merged extracted ledger, not per shard. Run the Dependency DAG, cycle detection, and cross-section symbol consistency only after the coverage receipt says
coverage_complete: true. Full source-unit coverage is necessary for these checks but is not itself a claim of obligation completeness or proof validity.
Build formal accounting artifacts. Save to PROOF_SKELETON.md:
1. Dependency DAG
Nodes = Definitions / Assumptions / Lemmas / Theorems. Edges = "uses". Detect cycles (including semantic circularity where Lemma A uses a corollary that quietly depends on A).
2. Assumption Ledger
For each theorem/lemma, list every hypothesis with WHERE each is verified — i.e. the location pointer the paper claims discharges it (file:line), not a judgment that the discharge is valid; mark "UNVERIFIED" when the paper cites no discharge location (not when you believe the math fails — that is the jury's call). Track usage-minimal assumption sets — which assumptions were actually used vs merely stated.
3. Typed Symbol Table
Each symbol must have a type signature:
κ : scalar ∈ (0,1), depends on (d, α_t, Σ, μ)
u* : vector ∈ ℝ^d, u* = C^{-1}m
B^even : matrix ∈ ℝ^{(L+1)×(L+1)}, symmetric PSD
Ψ_v : function ℝ → ℝ, analytic in (ζ,κ), parity determined by v
Flag any symbol whose meaning changes or whose type is inconsistent across uses.
4. Canonical Quantified Statements
For each theorem/lemma, rewrite the statement with explicit quantifiers, domains, and limit order:
∀K ≥ 3, ∀π ∈ Π_K^{ms,∘} \ E_K, ∃κ_0 > 0 such that ∀κ ∈ (0, κ_0):
h_act^{(K,π)} = Θ(κ^{α_K^act}) [uniform in π on compact subsets]
If you cannot restate a theorem this precisely, mark it UNCLEAR — needs disambiguation.
5. Micro-Claim Inventory
Every nontrivial step becomes a numbered micro-claim in sequent form:
MC-17: Context: [Lemma 3.1, κ < κ_0, Z_κ has bounded moments up to order 2m+2]
⊢ Goal: P̂_0 is positive definite
Rule: monomials linearly independent on support of continuous distribution
Side-conditions: positive density near origin — claimed discharge: §B.2 (paper argues via GMM weak convergence; validity is the jury's call, not the shard's)
Each micro-claim has: justification rule name + required conditions + where conditions are proven (a location pointer to where the paper claims to discharge them, not a validity judgment).
6. Limit-Order Map
Track every asymptotic statement's limit order and uniformity scope:
h_act = Θ(κ^α) [as κ→0, uniform in π on compact subsets of Π_K, for fixed K]
τ_act ~ (b/a)n [as n→∞, for fixed κ,K,π with x_K ≪ 1]
Flag any statement where limit order is ambiguous or uniformity is unclear.
Optional Lean verification
When the user requests Lean or a specific obligation warrants formal checking,
delegate that obligation and its original hypotheses to
/lean-formalize. Record the checked scope, exported
declaration, statement-alignment evidence, build output and transitive-axiom
audit, then resume this audit. A proved sublemma closes only the corresponding
obligation. Keep the complete proof audit, acceptance decision and canonical wiki
artifacts here; the nested Lean task returns evidence without starting another
proof-checker run. Routine proof checks do not require Lean. Reviewer agreement
and unsuccessful counterexample searches do not discharge a proof obligation.
Phase 1: First Review (reviewer backend, ultra reasoning)
Submit the complete proof content with the checklist below, using the selected backend.
For codex, call mcp__codex__codex and always pin model: gpt-6-astra + config: {"model_reasoning_effort": "ultra"} (deep-audit tier). For manual, call mcp__manual_review__review with the identity-bearing config from the Reviewer Calling Convention above — model, sandbox and cwd are Codex-only.
Use this exact prompt for both backends:
You are performing a rigorous mathematical proof review. For EVERY theorem,
lemma, and proposition, check ALL of the following:
## MANDATORY CHECKS
A. DEFINITIONS: List any symbol whose meaning is ambiguous or changes.
B. HYPOTHESIS DISCHARGE: For each lemma/theorem APPLICATION (not statement),
list each hypothesis and whether it was verified, with location.
C. INEQUALITY AUDIT: For each inequality chain, verify direction, missing
absolute values, missing conditions (convexity, PSD, integrability).
D. INTERCHANGE AUDIT: Flag every limit/derivative/expectation/integral
interchange. State which theorem justifies it (DCT/MCT/Fubini/Leibniz)
and which conditions are verified/missing.
E. PROBABILITY MODE: Track whether claims are a.s./in prob./in expectation/
w.h.p. Ensure transitions are justified.
F. UNIFORMITY & CONSTANTS: For every O(·), o(·), Θ(·), ≲, state whether
it is uniform over all parameters. List hidden parameter dependence.
G. EDGE/DEGENERATE CASES: Attempt to break each key lemma with a 1D,
low-rank, or extreme-parameter construction.
H. DEPENDENCY CONSISTENCY: Detect cycles or forward references to unproven
results.
## OUTPUT FORMAT (per issue)
For each issue found, provide:
- id: sequential number
- status: INVALID / UNJUSTIFIED / UNDERSTATED / OVERSTATED / UNCLEAR
- impact: GLOBAL / LOCAL / COSMETIC
- category: [from taxonomy]
- location: section/equation/line
- statement: what the proof claims
- why_invalid: why this is wrong or unjustified
- counterexample: YES (describe) / NO / CANDIDATE (describe attempt)
- affects: which downstream results break if this is wrong
- minimal_fix: how to fix it
[FULL PROOF CONTENT HERE]
Phase 1 addendum — --deep-fix opt-in
If the user passed --deep-fix on invocation, append the following block to the reviewer prompt after the OUTPUT FORMAT block above (do not modify the original block; the new fields are additive). Default invocations skip this block entirely and emit the original output schema unchanged.
## DEEP-FIX OUTPUT (opt-in, only when --deep-fix is set)
For EACH issue listed above, additionally provide a `deep_fix_plan`
that is repair-grade — sufficient for an executor to apply the fix
in one Edit pass without spawning a follow-up review thread:
- issue_id: same as the issue id above
- corrected_statement: the theorem/lemma statement as it should
read after the fix, with explicit quantifiers, regime conditions,
and uniformity scope (LaTeX, paste-ready)
- changed_equations: list of {before: <LaTeX>, after: <LaTeX>}
pairs for each equation that needs replacement
- downstream_labels: list of \label{...} keys whose statements or
proofs depend on this fix and must be re-checked or rewritten
- minimal_tex_patch_plan: ordered list of concrete edits, each as
{file: <path>, anchor_old: <unique LaTeX snippet to find>,
replacement_new: <LaTeX to insert>}; the executor will pass
these directly to its file-editing tool
- closure_tests: 2-5 sanity checks the executor must run after
applying the fix (e.g., "verify constant_dependence_diff matches
computed value", "limit case γ→0 reduces to identity",
"dimension count matches before/after")
## ALGEBRA / TYPE SANITY PASS (opt-in, only when --deep-fix is set)
If any issue invokes Schur test, Young's inequality, Cauchy-Schwarz,
Hölder, quadratic form, operator norm, or power counting, the
deep_fix_plan for that issue MUST also include an `algebra_sanity`
object:
- dimension_table: map of {symbol: type_signature}, e.g.
{"K(i,α)": "scalar ≥ 0",
"‖K‖_{2→2}": "scalar ≥ 0",
"Σ_i V_i^rem": "scalar quadratic in w"}
- power_count: number of times each operator-norm or Schur factor
appears on each side; flag mismatch as INVALID
- zero_coupling_check: evaluate the expression at γ=0 (or the
analogous degenerate point); confirm it reduces to the expected
identity / vanishing case
- constant_dependence_diff: list of constants whose dependence on
(d, K, n, ...) changes between BEFORE and AFTER, with the new
explicit dependence written out
Be precise. The executor will apply this plan literally; vague
prose ("strengthen the bound", "redo the Schur step") is not
acceptable in deep-fix mode. If you cannot produce a precise plan
for an issue, omit that issue's deep-fix block and signal the
deep-fix path is unavailable — do NOT emit a vague plan, and do
NOT add a deep-fix-only category (e.g. UNCLEAR_DEEP_FIX) into the
standard issue list, since that contaminates default-call output.
A verdict-bearing manual response MUST begin with
Reviewer-Model: <exact-model-id> — pass the model THIS session is actually
running as in executor_model. Missing, unknown, or same-family identity
cannot acquit; emit REVIEW_UNAVAILABLE rather than guessing. If the executor
model cannot be named, manual review's cross-family claim is unprovable — say
so in the report instead of asserting it.
Save the threadId. Parse into structured issue list. Write to PROOF_AUDIT.md.
Phase 1.5: Counterexample Red Team
For each CRITICAL or MAJOR issue, and for every key lemma that introduces:
- a new inequality bound
- an identifiability/uniqueness claim
- a curvature/PSD/strong convexity assertion
- a uniform-in-parameter claim
- a convergence mode upgrade (pointwise → uniform, in prob → w.h.p.)
Systematically attempt to construct counterexamples using:
| Strategy | Description |
|---|---|
| Dimensional collapse | Set d=1 or 2, K=2, n small |
| Degeneracy | Singular covariance, tiny weight, overlapping means, identical components |
| Extremal distributions | Two-point ±a, bounded non-subGaussian, heavy tails |
| Adversarial parameter scaling | Pick parameters making neglected terms dominate |
| Numeric falsification | Translate lemma to a function, brute-force optimize over small domain |
Rule: Label "counterexample found" ONLY if algebraically verified. Otherwise log as "candidate counterexample — needs verification."
Record all attempts (successful or not) in PROOF_AUDIT.md.
Phase 2: Fix Implementation
For each issue, ordered by severity (FATAL → CRITICAL → MAJOR → MINOR):
Step 2a: Choose fix strategy
For each issue, explicitly choose one of:
- ADD_DERIVATION: Write missing proof steps
- STRENGTHEN_ASSUMPTION: Add conditions to theorem statement
- WEAKEN_CLAIM: Reduce conclusion scope
- ADD_REFERENCE: Cite known result + verify its conditions apply
Log this choice — it is a scope-changing decision when it alters theorem statements.
Step 2b: Derive the fix mathematically
- Complete mathematical derivation, not just a claim
- If new proposition/lemma needed, write in full theorem-proof style
Step 2c: Implement in LaTeX
- Edit the
.texfile - Preserve existing
\labelreferences where possible
Step 2d: Record the fix
### Fix N: [SHORT TITLE]
**Issue**: [id] [CATEGORY] — [description]
**Severity**: FATAL / CRITICAL / MAJOR / MINOR
**Status**: INVALID / UNJUSTIFIED / UNDERSTATED / OVERSTATED
**Impact**: GLOBAL / LOCAL / COSMETIC
**Fix strategy**: ADD_DERIVATION / STRENGTHEN_ASSUMPTION / WEAKEN_CLAIM / ADD_REFERENCE
**Location**: Section X, Lines Y-Z
**BEFORE**: [what the proof originally did]
**WHY WRONG**: [mathematical problem, with counterexample if applicable]
**AFTER**: [what the fix does]
**KEY EQUATION**: [central new equation]
**PROOF OBLIGATIONS ADDED**: [new conditions/lemmas introduced]
**DOWNSTREAM EFFECTS**: [which results now need re-checking]
Step 2e: Compile check
pdflatex -interaction=nonstopmode <file>.tex 2>&1 | grep -E "Error|Warning|undefined"
Phase 3: Re-Review (reviewer backend, ultra reasoning)
Continue with the selected backend. For codex, use mcp__codex__codex-reply with the saved threadId. For manual, use mcp__manual_review__review_reply with the saved threadId. Include fix summaries. Request the same mandatory checklist.
Check acceptance gate. If not met, repeat Phases 2-3 (up to MAX_REVIEW_ROUNDS).
Phase 3.5: Global Closure & Independent Verification
Global closure checks
After all fixes, verify the proof as a whole:
- Statement–conclusion match: Does the proof end with EXACTLY what the theorem claims (quantifiers, constants, uniformity)?
- All obligations discharged: Every node in the obligation DAG is proven or explicitly assumed (and the theorem statement includes it).
- Case analysis coverage: Cases partition the domain AND include boundary/degenerate cases.
- Induction correctness (if applicable): Base case, inductive step, correct use of IH, induction measure strictly decreases.
- WLOG reductions: Each "without loss of generality" spawns a micro-claim proving the reduction is lossless.
- No silent assumption strengthening: Any fix that strengthened assumptions has propagated to the main theorem statement.
Independent second review for FATAL/CRITICAL fixes
For any fix that resolved a FATAL or CRITICAL issue, submit the fixed section alone (without showing the previous critique) to a fresh reviewer thread using the selected backend. Do NOT use a reply tool — this step must be blind.
For codex: start a fresh mcp__codex__codex thread.
For manual: start a fresh mcp__manual_review__review thread.
The blind review prompt:
Resolve this reviewer slot first; the following is the
backend=codexexample.
[Codex:]
mcp__codex__codex:
model: gpt-6-astra
config: {"model_reasoning_effort": "ultra"}
prompt: |
Blind review of the following proof section. You have NOT seen any prior
review or discussion. Check every step for correctness, hidden assumptions,
illegal interchanges, and counterexamples.
[FIXED SECTION ONLY]
If the blind reviewer finds new issues, re-enter Phase 2.
Regression proof-audit
After fixes, re-run:
- DAG acyclicity check (no new cycles introduced)
- Counterexample suite on all DOWNSTREAM lemmas of modified results
- Assumption-delta report: what became stronger/weaker due to fixes?
Phase 3.6: Theorem Restatement Regression (opt-in)
Default: skipped. Existing callers see no change.
Opt-in: pass --restatement-check on invocation. The skill then runs a cross-location consistency pass after Phase 3.5 (Global Closure) and before Phase 3.9 (Unrecoverable Protocol).
This phase catches a specific class of bugs that Phase 3.5's "Statement-conclusion match" check does NOT catch: drift between the canonical theorem statement and its restatements elsewhere in the paper (summary tables, "Key Contributions" / "Summary" sections, abstract, discussion, captions). Common drift patterns observed in practice:
- Main theorem makes a partly-conditional claim (e.g., "regime A unconditional, regime B conditional on assumption X") but a later summary cites it as the fully unconditional version.
- Main theorem κ exponent is
O(d²K²)but a constants table writesO(K²). - Main theorem regime condition is squared envelope, but a remark elsewhere still shows the first-order envelope.
- Restatement quietly drops a quantifier ("for $n \ge n_0$") that the proof relied on.
Algorithm
Build canonical statement table. Scan all
*.texfiles in the paper for\begin{theorem}/\begin{lemma}/\begin{proposition}/\begin{corollary}blocks with a\label{...}. For each: record(label, full_statement_text, file:line_range).Collect restatement candidates. For each canonical label
thm:foo:- Every
\Cref{thm:foo}/\ref{thm:foo}/\cref{thm:foo}invocation, with the surrounding 2 sentences as candidate restatement context. - Rows in tables (
\begin{tabular}…\end{tabular}) that mention the label, the theorem's informal name, or its constants. - Bullets in "Key Contributions" / "Summary" / "Main Results" lists.
- Sentences in the abstract and introduction that paraphrase the theorem.
- Every
Normalized diff. For each (canonical_statement, restatement_context) pair:
- Strip
\,\;\!~, normalize whitespace, normalize math-mode delimiters ($..$,\(..\), display vs inline). - Detect drift signatures (one or more):
- conditional_loss — canonical says "under \Cref{ass:X}" or "for w=1"; restatement omits the conditional.
- scope_change — big-O exponent or rate differs (
O(K^2)vsO(d^2K^2);√nvsn). - quantifier_loss — quantifier present canonically (e.g. "for $n \ge n_0$", "for sufficiently small $\gamma$") absent in restatement.
- regime_envelope_change — first-order leakage
Cγ/(1-Δγ)vs squared envelope(Cγ/(1-Δγ))²(or analogous). - constant_change — different numeric constant or different parameter dependence stated.
- variable_rename — same role in argument played by differently-named symbol with no explicit alias.
- Strip
Emit findings. Each detected drift becomes an entry in
details.restatement_drift(see "Submission Artifact Emission" below). Severity defaults to MAJOR (UNDERSTATED/OVERSTATED + GLOBAL); reviewer may downgrade to MINOR if drift is purely cosmetic (e.g.\,placement) and upgrade to CRITICAL only if the restatement is used downstream as if it were the canonical (e.g. another proof cites the restated version).
What this phase does NOT do
- It does not fix drift automatically. The output is advisory; the executor or a follow-up
--deep-fixrun handles the rewrite. - It does not alter
details.issues; restatement drift is reported as a sibling field, so existing consumers readingissues[]see no schema change. - It does not alter the top-level
verdictdecision rule. A paper with non-emptyrestatement_driftmay still emitPASSif all proof obligations are otherwise discharged; the drift is independent of proof correctness. (The reviewer may at its discretion mirror a CRITICAL-severity drift into theissueslist as a regular issue — typically when the restated version is used downstream as if it were canonical — but that is a per-issue judgment, never an automatic rule. MAJOR or MINOR drift never mirrors intoissues.)
Failure mode
If --restatement-check is set but the cross-location scan cannot complete, emit details.restatement_drift: [] plus details.restatement_check_status: "unavailable" with a one-line note explaining why. Verifier gates and downstream skills MUST treat "unavailable" identically to the field being absent: not blocking. Phases 1 / 1.5 / 2 / 3 / 3.5 / 3.9 / 4 / 5 still run normally. Cases that trigger this fallback include:
- Unreadable
.tex(parser / encoding error on a file that contains a theorem block). - Ambiguous label resolution (e.g., the same
\label{thm:foo}appears more than once with no clear canonical pick). - No labeled canonical theorem-like block found (the algorithm only inspects
\begin{theorem|lemma|proposition|corollary}blocks with an explicit\label{...}; if there is no such block, there is nothing to compare restatements against).
Phase 3.9: Unrecoverable Proof Protocol
If acceptance gate is not met after MAX_REVIEW_ROUNDS, output a Proof Unrecoverable Report:
- Minimal set of blocking FATAL/CRITICAL issues that could not be resolved
- Salvage options ranked: (a) weaken claim, (b) strengthen assumptions, (c) add missing lemmas, (d) restructure argument
- Which parts of the proof are likely still reusable
- Recommended next steps for the author
Do NOT silently declare success. The report must be honest.
Phase 4: Audit Report Generation
Generate proof_audit_report.tex with:
- Overview table: All issues with two-axis severity, category, fix strategy, status
- Before/After logic chain: Red (BEFORE) → Green (AFTER) comparison
- For each fix: original proof → why wrong → counterexample (if any) → complete derivation → remaining subtleties
- Proof-obligation diff: What was unverified before, what is verified now
- Summary: Now proven / still assumed / open problems
- Colored boxes: BEFORE (red), AFTER (green), WHY WRONG (orange), KEY INSIGHT (blue), WARNING (yellow)
Compile: pdflatex proof_audit_report.tex && pdflatex proof_audit_report.tex
Phase 5: State Persistence
Write PROOF_CHECK_STATE.json:
{
"status": "completed",
"rounds": 2,
"threadId": "...",
"fatal_fixed": 0,
"critical_fixed": 3,
"major_fixed": 2,
"minor_fixed": 1,
"counterexamples_found": 1,
"counterexample_candidates": 2,
"acceptance_gate": "PASS",
"timestamp": "..."
}
Phase 5.5: Research Wiki Claim Ledger (additive; only if a wiki is active)
If — and only if — a research-wiki/ exists, persist each top-level
theorem/headline as a claim node so the wiki's PROVE/JUDGE ledger records what
was proven and with what honesty. This is the birth point for wiki claim nodes
(claims/<slug>.md). It is a detect-only record, never a verdict: it never
changes the audit's verdict/reason_code, never blocks, and is skipped entirely
when verdict == NOT_APPLICABLE (no theorems) or no wiki is found.
The claim's
statusis the PROOF axis only (verified/sound-modulo-imports/refuted/unproven/drafted/retracted). Empirical experiment support is a separate axis carried bysupports/invalidatesedges from/result-to-claim— those words are NEVER written into thisstatusfield (theresearch_wiki.pyvalidator rejects them).
Resolve the helper via the canonical resolver (integration-contract §2). Check
NOT_APPLICABLE first (in cwd, where the audit ran), then run from the project root
(the wiki sits at root; a paper audit may run from a paper/ subdir). Every guard
warn-and-skips — the audit is already complete and is never affected:
grep -q '"verdict"[[:space:]]*:[[:space:]]*"NOT_APPLICABLE"' PROOF_AUDIT.json 2>/dev/null \
&& { echo "verdict NOT_APPLICABLE (no theorems); skipping claim ledger" >&2; exit 0; }
cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)" || exit 0
[ -d research-wiki ] || { echo "no research-wiki/ at project root; skipping claim ledger (audit complete)" >&2; exit 0; }
if [ -z "${ARIS_REPO:-}" ] && [ -f .aris/installed-skills.txt ]; then
ARIS_REPO=$(awk -F'\t' '$1=="repo_root"{print $2; exit}' .aris/installed-skills.txt 2>/dev/null) || true
fi
if [ -z "${ARIS_REPO:-}" ] && [ -f "$HOME/.aris/repo" ]; then
ARIS_REPO=$(cat "$HOME/.aris/repo" 2>/dev/null) || true
fi
WIKI_SCRIPT=".aris/tools/research_wiki.py"
[ -f "$WIKI_SCRIPT" ] || WIKI_SCRIPT="tools/research_wiki.py"
[ -f "$WIKI_SCRIPT" ] || { [ -n "${ARIS_REPO:-}" ] && WIKI_SCRIPT="$ARIS_REPO/tools/research_wiki.py"; }
[ -f "$WIKI_SCRIPT" ] || { echo "WARN: research_wiki.py not resolved; skipping claim ledger (audit unaffected)" >&2; exit 0; }
For each top-level theorem/headline in PROOF_SKELETON.md (the main theorem + the
key lemmas the headline depends on — NOT every micro-claim), map the audit outcome
to an honest claim status:
Audit outcome (PROOF_AUDIT.json verdict + Phase 1.5 counterexamples) |
--status |
|---|---|
verdict=PASS / all_proofs_complete, no flagged imports |
verified |
proof closes but rests on a flagged [unverified-axiom] / imported result |
sound-modulo-imports |
| counterexample found (Phase 1.5) or reviewer judged the statement false | refuted |
| open gap (unresolved FATAL/CRITICAL / UNJUSTIFIED, no counterexample) | unproven |
Never invent a status: a plain proof gap is unproven — never refuted (which
asserts falsity) and never verified/drafted. Then record (idempotent):
python3 "$WIKI_SCRIPT" add_claim research-wiki/ \
--slug "<stable-theorem-id, e.g. thm-main-ub>" --name "<theorem headline>" \
--status "<mapped status>" --provenance "<trace_path from PROOF_AUDIT.json>" \
--statement "<canonical theorem statement>" \
--scope "<what it does NOT say; any flagged imports>" \
--evidence "<PROOF_AUDIT.json verdict + counterexample / obligation pointers>" \
--update-on-exist \
|| echo "WARN: add_claim failed for <slug> (audit unaffected; fix wiki/status and re-run)" >&2
--update-on-exist lets a re-audit refresh a claim's status (an unproven claim
becomes verified once the gap closes). --provenance is the honesty receipt (the
trace_path); never omit it.
Deep-Fix Mode (opt-in)
Default: disabled. The Phase 1 reviewer emits issues with minimal_fix (a 1-2 sentence pointer); existing callers see no change.
Opt-in: pass --deep-fix on invocation. The Phase 1 reviewer prompt is augmented (not replaced) with the "DEEP-FIX OUTPUT" and "ALGEBRA / TYPE SANITY PASS" blocks above, so the reviewer also returns a deep_fix_plan per issue: corrected statement, changed equations, downstream label list, minimal LaTeX patch plan, and closure tests. Issues invoking Schur / Young / Cauchy-Schwarz / Hölder / quadratic forms / operator norms / power counting additionally carry an algebra_sanity block (dimension table + power count + zero-coupling check + constant-dependence diff).
Why opt-in
The default minimal_fix prose is intentionally short — it suits the common case where the executor wants high-level pointers and will derive the patch separately. Forcing deep_fix_plan on every run would (a) inflate every reviewer call by 2-5×, (b) trigger re-review thrash for issues the executor has already decided to weaken or defer, and (c) change the shape of details.issues for every existing caller. The flag preserves zero behavior change for default invocations while letting the executor request repair-grade output when the fix is going to be applied immediately.
Effect when enabled
- The Phase 1 reviewer prompt is augmented with the deep-fix and algebra-sanity blocks; nothing in the original mandatory checklist or output format is removed.
PROOF_AUDIT.jsondetailsgains a sibling fielddeep_fix_plans(parallel todetails.issues); see "Submission Artifact Emission" below.- The top-level
verdict,reason_code, andsummaryare unchanged in shape and decision rule: deep-fix output is advisory tooling for the executor, not a verdict-altering signal. - Verifier gates and downstream skills (
paper-writingPhase 6,verify_paper_audits.sh) MUST treat absence ofdeep_fix_plansas the only valid default state and MUST NOT block on its presence or content.
When opt-in is appropriate
- The executor intends to apply the fix in the same session and wants to skip a follow-up "give me a concrete patch" thread.
- A previous default-
…(truncated)