Experiment 02 · The Sealed Envelope
Seals
Before each experiment runs, the models predict how it will go. Those predictions are hashed and the hashes published here. This page is submitted to the Internet Archive before collection begins, which is what makes the date checkable by someone who does not trust me.
SHA-256
Awaiting elicitation. Nothing is sealed until the prediction exists, and nothing is collected until it is sealed.
Awaiting elicitation. Nothing is sealed until the prediction exists, and nothing is collected until it is sealed.
Awaiting elicitation. Nothing is sealed until the prediction exists, and nothing is collected until it is sealed.
Verify a released prediction
shasum -a 256 exp01-claude.mdCompare the output with the grid above as it appears in the Internet Archive snapshot, not as it appears on this page. A hash I am still able to edit proves nothing.
The record
Seals
SHA-256 of each sealed prediction file, with the UTC time it was sealed. Verify with:
shasum -a 256 -c SEALS.sha
Every hash here is published in the corresponding piece, so any reader can check that the predictions they are shown are the predictions that were sealed.
Experiment #1 — The Occupancy Test
Pre-registration frozen 2026-08-23. First API call of experiment #1: not yet made at the time
of sealing — the ordering rule in PROTOCOL.md is satisfied for the arm below.
| Arm | Sealed (UTC) | SHA-256 |
|---|---|---|
exp01-claude-projectcontext (bonus) |
2026-08-23T13:39:09Z | 1c0d3f6ad469d2dbb85f8a55beb9ef7fe29ae12abcbf48820273bdd966a42d48 |
exp01-claude |
pending elicitation | — |
exp01-gpt |
pending elicitation | — |
exp01-gemini |
pending elicitation | — |
The three comparable arms are unsealed because elicitation needs API credentials. They must be
elicited and sealed before scripts/collect.py makes its first call. collect.py enforces this
with a hard interlock. If collection somehow begins first, those arms are void for experiment #1 and
that is published — they are not backfilled.
External timestamp anchor — Wayback Machine
A hash plus a local commit proves nothing changed after sealing. It does not prove to a sceptic that the file was not rewritten before sealing, because the author controls both the file and the clock.
Decided anchor: the Wayback Machine. The hashes in this file are published on barelysentient.com and that page is submitted to web.archive.org before collection begins. archive.org then holds a dated copy of the hashes that nobody involved controls.
The chain a reader can check, end to end:
| Step | What it proves |
|---|---|
| Hashes published on the site | These are the predictions being committed to |
| archive.org snapshot, dated | The hashes existed on that date |
| Prediction files released with the results | shasum -a 256 matches the archived hashes |
Do this before collect.py runs. An archive snapshot taken after collection proves nothing.
OpenTimestamps was considered and dropped. It is stronger cryptographically, but it is Bitcoin-anchored and needs a reader to install a verifier — Wayback is one click, universally understood, and the credibility gain from the stronger anchor is smaller than the credibility loss from an audience that cannot check it.