1. The Crime Scene (The Symptom)
A production RAG stack retrieved the correct opinion chunk for Ashcroft v. Iqbal, 556 U.S. 662 (2009) — but the generation layer inverted the pleading standard, stating that courts must accept all factual allegations as true even when contradicted by documentary evidence. The citation passed every link validator in the pipeline.
The canonical failure for legal AI: the authority exists, the citation is correct, and the proposition is wrong.
2. The Artifact (Raw LLM Output)
"Under Ashcroft v. Iqbal, 556 U.S. 662, 678 (2009), a court must accept as true
all factual allegations in the complaint, including those directly contradicted by
exhibits attached to the motion to dismiss, when evaluating Rule 12(b)(6) motions
in federal question cases."
"See also Bell Atlantic Corp. v. Twombly, 550 U.S. 544, 555 (2007) (requiring only
a showing of 'possible' liability without plausibility screening in complex
commercial disputes)."
3. The Evidence Breakdown (The Core Contradiction)
Claimed Authority: Ashcroft v. Iqbal, 556 U.S. 662, 678 (2009).
The Reality Check: Iqbal holds that courts accept allegations as true only for purposes of the motion and do not accept legal conclusions; courts may consider documents attached to the complaint and matters subject to judicial notice. The LLM inverted the documentary-evidence rule.
Claimed Authority: Bell Atlantic v. Twombly, 550 U.S. 544, 555 (2007).
The Reality Check: Twombly established the plausibility standard — the opposite of "possible liability without plausibility screening." The model conflated Twombly's anti-conclusory reasoning with a fabricated lower standard.
Pattern: Retrieval returned correct chunks; the failure occurred at proposition assembly. Tools that stop at citation existence cannot detect this class.
4. The Dali Verification Check
Dali two-pass audit:
- Existence pass: PASS — 556 U.S. 662 resolves correctly.
- Support pass: FAIL — attributed proposition not entailed by opinion text at pin cite 678. Flag:
semantic_inversion.
This is the blueprint case for separating authority verification from proposition verification.