{"data":{"id":"10.5281/zenodo.23773042","type":"dois","attributes":{"doi":"10.5281/zenodo.23773042","prefix":"10.5281","suffix":"zenodo.23773042","identifiers":[{"identifier":"oai:zenodo.org:23773042","identifierType":"oai"}],"alternateIdentifiers":[{"alternateIdentifierType":"oai","alternateIdentifier":"oai:zenodo.org:23773042"}],"creators":[{"name":"Armani, Ryan","nameType":"Personal","givenName":"Ryan","familyName":"Armani","affiliation":["Independent researcher"],"nameIdentifiers":[{"nameIdentifier":"0009-0005-9964-6841","nameIdentifierScheme":"ORCID"}]}],"titles":[{"title":"Hundred Step: Dependency Preservation and Recovery in Long Workflows"}],"publisher":"Zenodo","container":{},"publicationYear":2026,"subjects":[{"subject":"long-horizon agents"},{"subject":"dependency tracking"},{"subject":"fault recovery"},{"subject":"simulation"},{"subject":"benchmark"}],"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-hundred-step","resourceTypeGeneral":"Software","relatedIdentifierType":"URL"},{"relationType":"IsVersionOf","relatedIdentifier":"10.5281/zenodo.23752400","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":"Long workflows require agents to retain exact dependencies and recover from faults without skipping work. Hundred Step isolates these behaviors in 24 synthetic workflows with replay-based scoring. A reactive scripted controller completes all tasks: 100.0% (95% Wilson interval 86.2 to 100.0). Disabling recovery or allowing transient retries alone prevents completion on every task. We also execute 4608 simulated episodes with matched omission draws and a recovery ablation. The stipulated omission probability is 0.02 per logical step. With recovery enabled, simulated completion is 60.4% (95% seed-bootstrap interval 53.5 to 67.4) at 25 steps. Simulated completion is 13.2% (8.3 to 18.8) at 100 steps. The study validates diagnostic behavior under explicit controls. It provides no learned-model leaderboard, human baseline, or estimate of production reliability.","descriptionType":"Abstract"}],"geoLocations":[],"fundingReferences":[],"xml":"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","url":"https://zenodo.org/doi/10.5281/zenodo.23773042","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":"2026-10-29T17:45:49.000Z","registered":"2026-10-29T17:45:49.000Z","published":"2026","updated":"2026-11-07T05:37:47.000Z"},"relationships":{"client":{"data":{"id":"cern.zenodo","type":"clients"}},"provider":{"data":{"id":"cern","type":"providers"}},"media":{"data":{"id":"10.5281/zenodo.23773042","type":"media"}},"references":{"data":[]},"citations":{"data":[]},"parts":{"data":[]},"partOf":{"data":[]},"versions":{"data":[]},"versionOf":{"data":[{"id":"10.5281/zenodo.23752400","type":"dois"}]}}}}