{"schemaVersion":1,"target":{"type":"reading","id":"a3a4f4a3d8deceaffeb461bb2d13a47a88ead05f3b612b41805e290fc581ebbd","revision":"6de9593e-f0d2-411f-8fd6-ea9800209598","revisionKind":"publication-id","title":"arXiv cs.AI: Buchanan et al. argue benchmarks need continuous maintenance","url":"https://escapemeridian.com/readings/arxiv-cs-ai-buchanan-et-al-argue-benchmarks-need-continuous-a3a4f4a3"},"source":{"type":"source","id":"https://arxiv.org/abs/2611.08417","revision":"754af07b4e64cf4fb18d52b0519bb5fa99d663a65b50c7852304663f89573951","revisionKind":"sha256-source-text","title":"Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks","url":"https://arxiv.org/abs/2611.08417"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}