Actuary
← Meta Llama 3.3 70B Instruct

Evidence block

Instruction following · cycle 35

meta-llama/llama-3.3-70b-instruct · 2026-08-05 04:16:57 UTC

This page is the full public record of one completed panel — the record’s hash-committed unit of evidence. Its identity is its hash; nothing here can change without changing the URL.

Identity

What this block is.

Panel mean
0.938
Members
5
Checker scored
5
Frozen floor
0.700
Anytime level α
0.050
Hashes and versions
Evidence hash
cf5837cd64e174e5811c2f036086cd71517c0ee7b797d2a488600be081d8ed8b
Design hash
4f5cc6b9ff4ce026ccab93f5a3c8241f78eb005bc8b8068e4c701e9236504412
Panel hash
e7dfea1f343f7bf37e066a1117ca21f3438e804ad61437bf72d810640cef7e71
Stream
49456bc2-bf2a-4211-8d19-c3e8d4034c3e
Epoch
89818968-8251-40bc-a1e2-e9e22e05ba22
Pool version
instruction_following-v3
Checker version
instruction_following-v1
Panel size
5
Provider spend
$0.0000483

Checker layer

Panel members.

# Item Item id Outcome Score
1 instruction-following-015 26a44f13-e4a8-4273-9cfd-5adce0f3eec9 ok 1.00
2 instruction-following-045 462a27a2-2b9a-417e-b2c3-b20776fad9a0 ok 1.00
3 instruction-following-075 38ede11b-3d52-4905-a6a4-8ee6684146e4 ok 0.83
4 instruction-following-105 9294d9d8-5c71-4d76-b053-b5cefc08d0e1 ok 0.86
5 instruction-following-135 7d213d46-039d-4f3a-aecf-c785ef61cc80 ok 1.00

Deterministic checkers score every response in [0, 1]; a member that ends in a terminal failure scores 0 and stays on the record. Item text stays unpublished so nobody can tune against the panel — identity travels as the item id and its pool source id.

Capture layer

Provider requests.

# Provider Upstream Response model Response id Finish Latency ms Tokens in Tokens out Cost Output SHA-256 Observed
1 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785903407-1Xhja4XDEidKMz4pCED0 stop 968 50 11 $0.0000085 52db665cfef6d44e69a5e9493f89db7b7a6e8f6461fc1b47e72c39e6a4f8a194 2026-08-05 04:16:47 UTC
2 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785903407-Q3cCsRMzFOIVIknnLIMS stop 1256 59 22 $0.0000129 9bf60beb971c1d5253229814d11e8e07e71398f67e4c304ae4cc4dbc6a72cdc6 2026-08-05 04:16:48 UTC
3 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785903407-sSztHGW0wHKuHqMnjnKv stop 10194 53 15 $0.0000101 aec5135869635f39c5ab7903564a3e3f56b87459da9b16dece05a3696a17043b 2026-08-05 04:16:57 UTC
4 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785903406-qrpeO36G39yZUa2Aiye7 stop 629 48 8 $0.0000074 5b61202a8c6a1d82a3c91a82f3695cc0b50fd061c3cce3a5039ee29097c85a02 2026-08-05 04:16:47 UTC
5 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785903407-N670NmNe1I42HqQN8QGv stop 474 59 11 $0.0000094 1ae4323e07007b052bb7f38ff4ab1ca0ef9e12498d537111ad88e9441ccde736 2026-08-05 04:16:48 UTC

Everything a probe captures, as captured. Raw model text is scrubbed thirty days after the run; its SHA-256, the outcome and the score are permanent. Costs are provider-reported and include reserved estimates where a run’s true cost was unrecoverable; a dash is a field the provider did not return.

Verify

Recompute the hash yourself.

The JSON twin of this page carries the exact evidence object this URL is named after. Canonicalise it per RFC 8785 and hash it; the digest must equal the address of this page.

GET /api/v1/evidence/cf5837cd64e1…

curl -s https://actuary.sh/api/v1/evidence/cf5837cd64e174e5811c2f036086cd71517c0ee7b797d2a488600be081d8ed8b \
  | jq -cjS .evidence | shasum -a 256

For this object’s field types, jq -cjS reproduces RFC 8785 canonical form, and the JSON twin serves the hashed bytes verbatim. Blocks of exactly this shape appear verbatim in signed certificates — verify one offline, or read how the e-process turns panel means into an alarm.