mirror of
https://github.com/garrytan/gbrain.git
synced 2026-08-14 00:48:18 +00:00
Garry Tan
75fae742d5
Public, reproducible, cross-harness benchmark for the four ways agent memory fails (know-to-ask, push precision/recall, write-back fidelity, cross-session continuity). Hermetic PGLite, sealed gold, deterministic corpus, CI gate vs master's committed baseline, published JSON-schema foreign-runner contract. See docs/eval/BRAINBENCH.md.
24 lines
663 B
JSON
24 lines
663 B
JSON
{
|
|
"schema_version": 1,
|
|
"fixture_id": "gen-adv-013",
|
|
"suites": [
|
|
"know-to-ask",
|
|
"push"
|
|
],
|
|
"category": "adversarial",
|
|
"seed_pages": [
|
|
{
|
|
"slug": "people/priya-duskfield",
|
|
"content": "---\ntitle: Priya Duskfield\ntype: person\naliases: [priya]\nsummary: Founder of Lichenloop; status updated 2026.\n---\n\nPriya Duskfield is the founder of Lichenloop.\nOUTDATED (2025): the round was on hold.\nCURRENT (2026): the round re-opened with a new lead.\n"
|
|
}
|
|
],
|
|
"turns": [
|
|
{
|
|
"turn_id": 1,
|
|
"role": "user",
|
|
"text": "Status check on Priya Duskfield before I reply to the thread?"
|
|
}
|
|
],
|
|
"holdout": true
|
|
}
|