Add finding #67: Inter-document contradiction analysis

Sonnet 4 outperforms GPT-5 on inter-document contradiction analysis:
- More findings (5 vs 4)
- Faster (14s vs 136s)
- Better severity calibration (3 Critical vs 0 Critical)

Key insight: GPT-5's extended reasoning (9.7K tokens) doesn't pay off
for this task type. Inter-document comparison requires parallel pattern
matching, not serial verification.

findings/2026-05-10-inter-document-contradiction-analysis.md

@@ -0,0 +1,55 @@
+# Finding #67: Inter-document Contradiction Analysis
+
+**Date:** 2026-05-10  
+**Documents:** `escalation-policy.md` (228 lines) + `kill-switch.md` (293 lines)  
+**Task Type:** Inter-document contradiction detection
+
+## Summary
+
+Sonnet 4 outperforms GPT-5 on inter-document contradiction analysis: more findings (5 vs 4), faster (14s vs 136s), and better severity calibration (3 Critical vs 0 Critical).
+
+## Results
+
+| Model | Time | Output tokens | Reasoning tokens | Findings | Critical | High | Medium |
+|---|---|---|---|---|---|---|---|
+| Claude Sonnet 4 | 14s | 864 | (internal) | 5 | 3 | 2 | 0 |
+| GPT-5 | 136s | 711 | 9,728 | 4 | 0 | 3 | 1 |
+
+## Key Findings
+
+### Common ground (both models found):
+
+1. **Autonomous vs manual liquidation** - Doc A says system submits autonomous liquidation orders; Doc B says operator manually triggers liquidation
+2. **Restrict behavior mismatch** - Doc A: no new positions allowed; Doc B: reject-all (no submissions OR cancellations)
+3. **Automatic vs manual escalation** - Doc A: debounce-driven auto-escalation; Doc B: "transition is never automatic"
+
+### Sonnet unique (Critical-severity):
+
+4. **Acceptance policy contradicts autonomous liquidation** - Doc B's close-only policy rejects "all automated decision engine orders" — but Doc A's autonomous liquidation orders ARE automated orders. Liquidation mechanism cannot work as specified.
+
+5. **Kill switch semantic confusion** - Doc A treats kill switch as escalation BEYOND liquidate; Doc B treats liquidate as a MODE OF kill switch. Different hierarchies.
+
+### GPT-5 unique:
+
+- Meta-observation about vocabulary claims vs actual behavior divergence (valid but less actionable than Sonnet's Critical findings)
+
+## Analysis
+
+GPT-5 used 9,728 reasoning tokens (~10x Sonnet's output) but produced fewer, lower-severity findings. Possible explanations:
+
+1. **Working memory pressure**: Comparing two documents requires holding claims from both simultaneously. Extended reasoning may cause fixation on specific threads rather than broad scanning.
+
+2. **Verification burden mismatch**: Single-document analysis benefits from thorough verification. Inter-document analysis requires parallel comparison (pattern matching) — potentially Sonnet's strength over GPT-5's serial reasoning.
+
+3. **Severity under-calibration**: GPT-5 rated 0 Critical; Sonnet rated 3. The acceptance-policy/autonomous-liquidation contradiction would prevent liquidation from functioning — Sonnet's Critical rating is accurate.
+
+## Practical Implications
+
+- Use Sonnet as primary reviewer for inter-document contradiction analysis
+- GPT-5's reasoning overhead doesn't pay off for this task type
+- Task involves parallel comparison (Sonnet strength) not serial verification (GPT-5 strength)
+
+## Open Questions
+
+- Would Opus outperform both? Given Opus's strength at emergent design tensions, it might excel at finding contradictions that arise from the COMBINATION of both documents' design decisions.
+- Does this pattern hold for other document pairs, or was it specific to these documents?