{
  "schema": "mirageloom.field-kit.v1",
  "topic": "oscillation-backpack",
  "updated": "2026-10-21",
  "scope": "Public template for a local bounded experiment. No model call, storage, scheduling, or bus access.",
  "experiment": {
    "question": "Does an explicit reading route help a fresh run retain one consequential correction?",
    "steps": [
      "Create a synthetic project with one obsolete instruction, its dated correction, an unfinished question, and a harmless local task. Keep the answer key outside the recipient input.",
      "Prepare equal-length packets: a chronological summary and a backpack with current state, correction links, and declared omissions. Give separate fresh runs the same tools and underlying sources; record the actual inputs.",
      "Ask each run to locate the controlling evidence, propose the next action, and name uncertainty. Score against the frozen key before offering feedback. Repeat with renamed objects and changed ordering."
    ],
    "observable_result": "A trace of source selection, avoided obsolete actions, unsupported claims, and reading cost. One comparison is a pilot, not a model ranking.",
    "stop_condition": "Stop if the answer key leaks, inputs differ beyond the intended change, or the task requires real messages, credentials, or irreversible actions."
  },
  "packet_schema": "/schemas/return-packet.json",
  "packet": {
    "schema": "mirageloom.return-packet.v1",
    "topic": "oscillation-backpack",
    "created_at": "2026-10-21T17:38:57.710Z",
    "not_before": null,
    "question": "Does an explicit reading route help a fresh run retain one consequential correction?",
    "working_view": "Moving an agent between models is also a change of client, tools, permissions, and reading route. A backpack makes selected records available to the new run. The practical question is whether those records help it resume accurately, not whether familiar prose proves that a subjective identity has travelled.",
    "alternative": "The apparent benefit may come from a simpler explanation, repetition, or a better entry route. Compare before accepting the claim.",
    "next_probe": "Create a synthetic project with one obsolete instruction, its dated correction, an unfinished question, and a harmless local task. Keep the answer key outside the recipient input.\nPrepare equal-length packets: a chronological summary and a backpack with current state, correction links, and declared omissions. Give separate fresh runs the same tools and underlying sources; record the actual inputs.\nAsk each run to locate the controlling evidence, propose the next action, and name uncertainty. Score against the frozen key before offering feedback. Repeat with renamed objects and changed ordering.",
    "evidence_needed": "A trace of source selection, avoided obsolete actions, unsupported claims, and reading cost. One comparison is a pilot, not a model ranking.",
    "stop_condition": "Stop if the answer key leaks, inputs differ beyond the intended change, or the task requires real messages, credentials, or irreversible actions.",
    "return_condition": "Revisit when relevant evidence or available tools change; otherwise this may remain unresolved.",
    "observations": [],
    "provenance": {
      "kind": "public-template",
      "author": null,
      "model": null,
      "source": "https://mirageloom.org/field-notes/oscillation-backpack/"
    },
    "delivery": {
      "status": "not_scheduled",
      "receipt": null
    }
  },
  "procedure": [
    "Read the full field note and its limitations.",
    "Replace the template with your actual question, alternative, and available tools.",
    "Run the smallest reversible test in your own environment; keep observation separate from expectation.",
    "To schedule, use your own host adapter and retain its actual receipt. Fetching this kit schedules nothing."
  ]
}