cs.LGSep 23, 2026

Contingent Exposure Routing for Financial AI: Outage Risk and the Cost of Indivisible Decisions

Authors: Shivam Gupta

Organizations: Independent Researcher

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Model failover restores availability, but changes which financial institutions share decision errors. We formulate outage-contingent routing through a local market-impact response matrix and study expected squared price displacement. A symmetric construction shows that a shared backup can leave an order-one concentration floor as the number of primary endpoints grows, while balanced fallback risk decreases inversely with the surviving endpoint count. For indivisible decisions, we derive the exact second moment of independent randomized routing and an effective-exposure granularity that determines its gap from fractional allocation. Conditional-expectation rounding gives a finite-agent bound without coupled quotas; a separate swap procedure preserves endpoint counts and is assessed against dual lower bounds. Across 60 synthetic portfolio networks and 11,340 scenario evaluations, the latter reduces risk by 6.57% and 10.53% for single and double endpoint removals at the central feedback setting with independent errors. A replay of 1,024 recorded API responses on constructed rebalancing tasks gives a smaller held-out reduction of 3.30% (paired bootstrap interval 2.07--4.57%). Strongly aligned errors, inferior endpoints, and indivisibility limit diversification. The contribution is an auditable routing stress test and implementation analysis, not an estimate of real-market crash probabilities.

Figures & tables

Figure 1: Eight equally weighted primary endpoints, followed by removal of four. A common surviving backup concentrates exposure at endpoint 5; balanced redistribution attains the continuous minimum. Labels carry no quality ranking; errors are centered and independent with unit variance. The illustration concerns financial exposure, not inference throughput.
Figure 2: Exact consequences of Theorem 1 with r=K/2r=K/2 . Left: a shared backup leaves a nonzero concentration limit. Right: common error limits the relative improvement. These are analytical constructions, not estimates of outage likelihood.
Error correlationRemovedMean reduction95% intervalMean gap to bound
0.016.57[5.99, 7.17]2.49
0.0210.53[9.93, 11.14]2.73
0.312.58[2.33, 2.84]0.84
0.324.54[4.23, 4.84]1.03
0.810.43[0.38, 0.48]0.13
0.820.79[0.74, 0.85]0.17
Table 1: Synthetic results at β=0.4\beta=0.4 . Reductions and gaps are percentages. Intervals resample 60 network-level mean reductions; all removal subsets of each size are included.
Figure 3: Matched-count comparison. Left: one point per network, averaged over removals of the given size; β=0.4,γ=0\beta=0.4,\gamma=0 . Right: means and network bootstrap intervals as common error increases. The common component is invariant to routing.
Figure 4: Four-endpoint indivisible-routing effects. Left: 20-seed means with descriptive 1.96-standard-error bars, normalized by the fractional lower bound. The dashed line is a relaxation, not an executable random policy. Right: exact uniform-routing cases; orthogonal exposures retain a factor-four gap at every population size.
Assignment objectiveReduction (%)95% interval
CER (full second moment)3.30[2.07, 4.57]
Diagonal second moment1.20[0.74, 1.67]
Equal-variance exposure balance0.13[-0.04, 0.38]
Ridge-envelope diagnostic2.85[1.77, 3.97]
Common best (different counts)4.53[2.75, 6.32]
Table 2: Held-out API replay. The first four policies preserve baseline quotas. Common best changes counts and uses the survivor with smallest calibration second moment. Intervals condition on fitted policies; exploratory comparisons have no multiplicity adjustment.
Figure 5: Recorded-error replay. Left: uncentered calibration error alignment; rounding to 1.00 does not imply exact equality. Right: held-out reductions and paired task intervals. The asterisk denotes different endpoint counts. All four pinned model versions use one vendor.
Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

EndpointValidRMSE (bp)MAE (bp)Within 1 bp
GPT-4.1-nano123/1285211.14218.10/128
GPT-4.1-mini128/1284563.33802.00/128
GPT-4o-mini127/1285345.84293.41/128
GPT-4.1107/1284484.63462.60/128
Appendix
Table 3: Held-out one-shot calculations. Errors are basis points of initial NAV after zero-trade fallback. Valid means a parsed finite number with normal completion, not a correct answer. Poor task performance limits the replay’s interpretation.
Figure 6: Secondary absolute-displacement tail check for one declared network, with independent errors. Heavy tails raise ES despite unchanged second moments. CER’s ES improvement here is smaller than its quadratic-risk improvement.
More in this topic

Adaptive Model Routing

Adaptive model routing selects models or specialized experts per input to balance prediction quality, computational cost, latency, and resource constraints.

See all 91 papers

Explore similar work

CardsList

  1. CausalLoss-Fin: Attributing Financial-Agent Loss to Decisions and Infrastructure Faults

    Sep 22, 2026Abhishek SharmaAgent Failure AnalysisFinancial Services

  2. CopRoute: Dependence-Aware Conformal Routing for Language Models

    Oct 9, 2026Siva Rajesh Kasa, Santhosh Kumar Kasa, Karan GuptaLLM RoutingEfficient Language Model Inference

  3. CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents

    Jul 21, 2026Qijia He, Jiayi Cheng, Chenqian Le +8AI Coding AgentsCost-Aware Inference

    University of Washington · New York University · ByteDance +1