{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T19:39:24Z","timestamp":1792697964011,"version":"4.5.0"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":0,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>A pricing network is used through its derivatives, but its training loss is usually evaluated over an artificial sampling domain. We give a self-contained framework for connecting a differentiable pricing approximation to the discounted profit and loss of its delta hedge. An exact identity separates terminal mismatch, the pricing-PDE residual, volatility misspecification, discrete rebalancing, and proportional trading costs. The identity and its L 2 bound are consequences of established stochastic calculus, rather than new hedging theory. Our methodological focus is occupation-based residual validation: we establish its relation to the residual contribution, its dependence on the deployment distribution, and a simultaneous finite-sample selection bound under explicit moment control. A reproducible Black-Scholes study uses analytical and finite-difference baselines, controlled perturbations, and ten independently trained networks. Occupation training produces an average change of-1.483 dollars in net hedge RMSE, with a five-seed 95% interval of [-4.182, 1.216]. The experiments expose the separate roles of initial pricing bias, payoff fit, turnover, and volatility exposure. Numerical diagnostics are distinguished throughout from certified bounds and from physical-measure tail guarantees.<\/jats:p>","DOI":"10.2139\/ssrn.7657600","type":"posted-content","created":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T18:48:26Z","timestamp":1792694906000},"source":"Crossref","is-referenced-by-count":0,"title":["From PDE Residuals to Hedging Risk: A Posteriori Diagnostics for Neural Option Pricing with Trading Costs and Volatility Misspecification"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4922-5448","authenticated-orcid":true,"given":"Francesco","family":"Demuro","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T18:48:26Z","timestamp":1792694906000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7657600"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7657600","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}