Manifest receipt

Locked & verifiable.

A pre-registered claim, anchored to a SHA-256 hash before the run. Anyone can re-derive it from the canonical bytes below.

SHA-256aebdcbce15cb4282123fbe1fb3a20cd5001cf8b695015338e1c09d5b6f1d2a03

Registered2026-05-15T18:40:39.312Z

Submitted by@falsify-seed

Manifest preview

version: "prml/0.1"
claim_id: "01885a00-0000-7a04-8000-00000000009e"
created_at: "2023-09-01T09:00:00Z"
metric: "bbh_average_accuracy"
metric_args:
  shots: 3
  prompting: "chain_of_thought"
  aggregation: "macro_mean_over_23_tasks"
comparator: ">="
threshold: 0.781
dataset:
  id: "big-bench-hard"
  hash: "b4d2e6f8a0c2e4b6d8f0a2c4e6b8d0f2a4c6e8b0d2f4a6c8e0b2d4f6a8c0e2b4"
  uri: "https://github.com/suzgunmirac/BIG-Bench-Hard"
model:
  id: "palm-2-unicorn"
seed: 0
producer:
  id: "falsify.dev"
not…

README badge

[![PRML locked](https://registry.falsify.dev/badge/aebdcbce15cb4282123fbe1fb3a20cd5001cf8b695015338e1c09d5b6f1d2a03.svg)](https://registry.falsify.dev/aebdcbce15cb4282123fbe1fb3a20cd5001cf8b695015338e1c09d5b6f1d2a03)

Verify in CI

- uses: studio-11-co/prml-verify-action@v1
  with:
    mode: verdict
    expected-hash: aebdcbce15cb4282123fbe1fb3a20cd5001cf8b695015338e1c09d5b6f1d2a03

github.com/studio-11-co/prml-verify-action →

share on x →

Verify this hash yourself

Paste your manifest YAML. The canonical hash must match aebdcbce15cb….

v0.2 RFC open for comment until 2026-05-22 23:59 UTC — comment on github.com/studio-11-co/falsify/issues. How to reach the editor: spec.falsify.dev/editor.