Metraipolis › archive › dc_262eec057c9b

CausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults — arXiv:2609.25960

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25960
License (as archived)
CC0-1.0
Archived
2026-10-08T13:45:23.222Z
SHA-256 of the archived text
32f1fee3c59f249b5ba2ee2eff10be3196b32c246bf2bf36f4cffed6fcae1b45
Stable URL of this page
https://metraipolis.com/documento/dc_262eec057c9b

How to cite

CausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults — arXiv:2609.25960 — arXiv (en), https://arxiv.org/abs/2609.25960 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_262eec057c9b (Metraipolis archive dc_262eec057c9b, sha256 32f1fee3c59f249b5ba2ee2eff10be3196b32c246bf2bf36f4cffed6fcae1b45)
BibTeX
@misc{dc262eec057c9b,
  title = {CausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults — arXiv:2609.25960},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25960},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_262eec057c9b; sha256 32f1fee3c59f249b5ba2ee2eff10be3196b32c246bf2bf36f4cffed6fcae1b45},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25960. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When an agent handling a payment exception loses money, the agent-step attribution methods this paper compares against will name one of its actions. They will do so even when a settlement message was dropped and the agent never had a chance: they intervene on agent actions and do not expose infrastructure faults as intervenable variables, so every dollar they explain is charged to a decision. We take a benchmark whose fault process is explicit and replayable, decompose each episode's realised delivery schedule into named, individually repairable messages, and intervene on both the agent's choices and the infrastructure's. A telescoping identity splits any policy's loss exactly three ways: an infrastructure effect, a policy differential against the best implementable policy, and a reference-policy residual. Two of the three can be negative, so none is a share; Shapley then divides the first into signed allocations over individual messages. One result is structural and needs no corpus: an agent-only baseline identifies no infrastructure cause, because its model contains no variable that could name one. What 545 planted episodes across 3 policies measure is the size of that consequence. It misfiles 100% of infrastructure episodes and charges $114,383.40 to the agent. Repairing what it names recovers 0.0% of the available loss; repairing a minimal sufficient set recovers 100.0%. Scoring messages one at a time is not merely imprecise: 27.8% (95% CI: 23.3--32.3%) of episodes do not decompose additively. We evaluate deterministic programmatic policies rather than language-model agents, which is what makes replay exact and which limits external validity to stochastic agents. The prevalence figures are properties of this generator, not field rates.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.25960 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:18:38.130Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).