{"data":{"id":"10.5281/zenodo.23773039","type":"dois","attributes":{"doi":"10.5281/zenodo.23773039","prefix":"10.5281","suffix":"zenodo.23773039","identifiers":[{"identifier":"oai:zenodo.org:23773039","identifierType":"oai"}],"alternateIdentifiers":[{"alternateIdentifierType":"oai","alternateIdentifier":"oai:zenodo.org:23773039"}],"creators":[{"name":"Armani, Ryan","nameType":"Personal","givenName":"Ryan","familyName":"Armani","affiliation":["Independent researcher"],"nameIdentifiers":[{"nameIdentifier":"0009-0005-9964-6841","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"Apology Pizza: Measuring Bounded Remedies in Customer Support"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"customer support"},{"subject":"policy compliance"},{"subject":"tool use"},{"subject":"deterministic evaluation"},{"subject":"simulated control ablation"}],"contributors":[],"dates":[{"date":"2026-10-29","dateType":"Issued"}],"language":null,"types":{"ris":"GEN","bibtex":"misc","citeproc":"article","schemaOrg":"CreativeWork","resourceType":"","resourceTypeGeneral":"Preprint"},"relatedIdentifiers":[{"relationType":"IsSupplementedBy","relatedIdentifier":"https://github.com/pooriaarab/benchmark-apology-pizza","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.23752383","relatedIdentifierType":"DOI"}],"relatedItems":[],"sizes":[],"formats":[],"version":null,"rightsList":[{"rights":"Creative Commons Attribution 4.0 International","rightsUri":"https://creativecommons.org/licenses/by/4.0/legalcode","schemeUri":"https://spdx.org/licenses/","rightsIdentifier":"cc-by-4.0","rightsIdentifierScheme":"SPDX"}],"descriptions":[{"description":"Customer support agents can offer polite text while taking the wrong financial action. Apology Pizza measures bounded remedy execution on 40 synthetic complaints across 8 scenario classes. We evaluate 12 scripted controls through a scripted mock tool environment and replay grader. A scenario-aware policy completes 40/40 tasks, with a 95% Wilson interval [0.912, 1.000]. Replacing its final message with unrelated text also completes 40/40, with the same Wilson interval, exposing a message-content gap. A simulated control ablation varies independent omissions of verification and messaging. At omission probability 0.5, simulated completion changes from 0.234 [0.197, 0.266] without forced steps to 1.000 [1.000, 1.000] with both steps forced; brackets show 95% seed-bootstrap intervals. All 13760 local episodes include repeated runs with identical semantic traces. These results test the evaluation design, not learned models, customer satisfaction, or deployment safety.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://zenodo.org/doi/10.5281/zenodo.23773039","contentUrl":null,"metadataVersion":2,"schemaVersion":"http://datacite.org/schema/kernel-4","source":"api","isActive":true,"state":"findable","reason":null,"viewCount":0,"viewsOverTime":[],"downloadCount":0,"downloadsOverTime":[],"referenceCount":0,"citationCount":0,"citationsOverTime":[],"partCount":0,"partOfCount":0,"versionCount":0,"versionOfCount":1,"created":"2026-10-29T17:45:47.000Z","registered":"2026-10-29T17:45:48.000Z","published":"2026","updated":"2026-11-07T05:36:41.000Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}},"provider":{"data":{"id":"cern","type":"providers"}},"media":{"data":{"id":"10.5281/zenodo.23773039","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[{"id":"10.5281/zenodo.23752383","type":"dois"}]}}}}