{
  "slug": "baleen",
  "term": "Baleen",
  "aliases": [
    "Baleen flash cache"
  ],
  "definition": "Baleen is a research flash-cache design that coordinates learned admission and prefetching to reduce HDD backend work under a flash-write budget.",
  "note": "Training groups accesses into residency episodes using an assumed eviction age, then learns admission and prefetching decisions. This offline construction is not future knowledge available to a running cache. [baleen-paper]\n\nThe evaluation uses seven Meta traces and a chronological split. The first day trains models, later days test them. Simulated results and testbed validation are distinct evidence. [baleen-paper]\n\nThe author artifact documents a RejectX baseline, model training and simulation. [baleen-artifact]",
  "related": [
    "cache-admission",
    "disk-head-time",
    "prefetch-wastage",
    "lru-replacement"
  ],
  "status": "research",
  "advantages": [],
  "limitations": [],
  "supersedes": [],
  "supersededBy": [],
  "firstSeen": null,
  "lastSeen": null,
  "updated": "2026-11-14",
  "citations": [
    {
      "id": "baleen-paper",
      "title": "Wong et al. Baleen: ML Admission & Prefetching for Flash Caches. FAST 2024, pp. 347-371; sections 3.1, 3.4 and 5.",
      "url": "https://www.usenix.org/system/files/fast24-wong.pdf",
      "accessed": "2026-11-14"
    },
    {
      "id": "baleen-artifact",
      "title": "Baleen-FAST24 author artifact, pinned README at 4e3a9205b1f1bd72bffd66dd52bd5b06509089e9.",
      "url": "https://github.com/wonglkd/Baleen-FAST24/blob/4e3a9205b1f1bd72bffd66dd52bd5b06509089e9/README.md",
      "accessed": "2026-11-14"
    }
  ],
  "provenance": [
    "Primary-source synthesis; the author simulator, ML training and testbed measurements were not reproduced."
  ]
}