Anti-money laundering

Real transaction data cannot leave the bank, and the part that could would not help anyway: nobody knows which of its rows are laundering. Institutions have alerts, and alerts are a detector's opinion, not the truth.

So the number every AML programme is judged on, the false positive rate, is measured against labels that were themselves produced by a detector. The measurement and the thing being measured share an error.

The established answer is simulation. AMLworld, from IBM Research and ETH Zurich (NeurIPS 2023), grows an agent-based economy and labels what its agents do. It is careful work and it produces complete labels, which is a real advance over alerts.

But a simulator measures its illicit ratio after the fact rather than accepting it as an input. That is why its public releases are bucketed into higher- and lower-illicit sets rather than parameterised: the rate is an outcome. You cannot ask for exactly 0.40% split 40/20/20/10/10 across typologies.

The deeper problem is the one nobody can see. Emergent background traffic will sometimes contain, by chance, the exact shapes a detector hunts. When the screen fires on one, there is no way to tell whether the detector erred or the simulation happened to draw a ring. The false positive rate inherits that ambiguity.

Primitives used: graph_motifs, dag_edges. Seed 20260905, engine 0.9.6.46.

1. Stage 01Pipeline Step

   Declare

   Rate, typology mix, hard negatives. Shares must sum to one or the schema is refused.

   rate: 0.004
   shares: {cycle: .4, fan_out: .2, fan_in: .2, scatter_gather: .2}

2. Stage 02Pipeline Step

   Rank & Lay Background

   Nodes receive a strict topological rank. Every background edge runs strictly from low to high, so no cycle can close at any depth.

   dag_edges → strictly acyclic background graph

3. Stage 03Pipeline Step

   Inject Labeled Motifs

   Targeted subgraphs are rewritten into declared laundering shapes, each tagged with an immutable case ID. Unaffected edges remain acyclic.

   graph_motifs → 8,000 edges, 1,578 certified cases

4. Stage 04Pipeline Step

   Independent Oracle Audit

   A separate verification pass recalculates all connected components and loop structures. It throws hard errors on any unintended cycle.

   largest un-cased strongly-connected component = 1 node

The last row is the one that matters. A strongly connected component of one node means no cycle exists anywhere outside a declared case, so an accidental pattern is not unlikely, it is impossible.

A standard directed-triangle screen, the kind deployed as a first-pass graph filter, run over the same file:

Every false positive is attributable. Some are confounders declared on purpose, the rest are background edges pulled in by a declared structure, counted separately. None are accidents, and that is proven rather than assumed. A generator that grows its graph cannot produce this table, because it cannot separate its own noise from the detector's error.

• The acyclic background is a designed property, not a claim about banking. Real ledgers contain innocent loops. Declare hard negatives to put them back, so they stay accounted for.
• Names and free text are structural placeholders. AML detection reads amounts, timing, counterparties and graph shape, none of which is prose, so this is not a limitation for the task. Do not use the file for anything language-shaped.
• This does not replace AMLworld. It answers a different question. They simulate and measure, which is what you want for training on emergent realism. This declares and proves, which is what you want for measuring a detector against known conditions.
• A certificate proves the data matches the declaration. It never proves the declaration matches reality. That judgement stays with the person writing the schema.