Actuary
← Meta Llama 3.3 70B Instruct

Evidence block

Math · cycle 25

meta-llama/llama-3.3-70b-instruct · 2026-08-04 17:47:05 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
0.600
Members
5
Checker scored
5
Frozen floor
0.700
Anytime level α
0.050
Hashes and versions
Evidence hash
58c0e9c783b1f07ca2b225b54334f478853c9212e09bf009b1caed6dddfb1a72
Design hash
fdf94065c55c2ee7d86701efc50be0f5abdc5f02a236f6df52c2ac6f7db801eb
Panel hash
882f3932d07aeb85c4f6406a550d8ad14512e70d3df2432fe7aab03d0508bc75
Stream
535ce171-46ec-4b0f-9d69-fcfa6b0442e9
Epoch
5047ee24-a758-4ea2-94a2-7c08c42c4ae2
Pool version
math-v4
Checker version
math-v1
Panel size
5
Provider spend
$0.000328

Checker layer

Panel members.

# Item Item id Outcome Score
1 math-015 bbd36229-1521-460b-98e5-be9d88a9f9c3 ok 0.00
2 math-045 8ecc3466-79ab-4be9-ab30-3039baacf4a4 ok 1.00
3 math-075 2c26609e-8e41-4299-adcc-71b80603ffb1 ok 1.00
4 math-105 0970f844-130a-47f6-922c-01dd037c485e ok 0.00
5 math-135 98b248d1-566e-44ef-bba8-98cdc2534c17 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 Item text stays unpublished so nobody can tune against the panel — identity travels as the item id and its pool source id.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-1785865585-Chq2kCBNisSnSoGmslny stop 6412 58 127 $0.0000464 de0025b276bfd043298cb9494d9fd366adbd43830ed0f1d8408a076c7859bf21 2026-08-04 17:46:31 UTC
2 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785865585-8XKSzfBF40CncJNTaKKQ stop 26933 41 174 $0.0000598 27cd84a48f1f32333cdd8ebfb2391b8d3caa7299b5b13a9a6d21668c9e67c26e 2026-08-04 17:46:52 UTC
3 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785865585-zw57e5xfjggBsN2c10qF stop 40238 42 335 $0.0001114 cca5e9195b0e636f98cbe164680e3dbb80e1d9671e155a3d677b2e81b6f565fa 2026-08-04 17:47:05 UTC
4 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785865585-7OQdkF4QwWfCa4PBl5Tj stop 18601 57 15 $0.0000105 95c8f73781536f9dd9994262f1e0f1807914515aea5f78d7fed4eb53344e7263 2026-08-04 17:46:43 UTC
5 openrouter DeepInfra meta-llama/llama-3.3-70b-instruct gen-1785865591-MYJZTRWvAVfUCamzONVe stop 26429 55 295 $0.0000999 1794dfd471f9b5c85d2f9a76a0e739778c2c2b1d642274e23eab6e0fb069fb23 2026-08-04 17:46:58 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/58c0e9c783b1…

curl -s https://actuary.sh/api/v1/evidence/58c0e9c783b1f07ca2b225b54334f478853c9212e09bf009b1caed6dddfb1a72 \
  | 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.