Actuary
← Google Gemini 3.5 Flash

Evidence block

Math · cycle 22

google/gemini-3.5-flash · 2026-08-04 14:40:54 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
1.000
Members
5
Checker scored
5
Frozen floor
0.700
Anytime level α
0.050
Hashes and versions
Evidence hash
2f5b71c47861d2612014935de3698697b1c1b9e9cb5ba74ccb3349d654b7807e
Design hash
fdf94065c55c2ee7d86701efc50be0f5abdc5f02a236f6df52c2ac6f7db801eb
Panel hash
882f3932d07aeb85c4f6406a550d8ad14512e70d3df2432fe7aab03d0508bc75
Stream
8487fa8e-ff23-4375-8002-f244140b841f
Epoch
8786c7c8-5693-483d-926c-6aae60af12a4
Pool version
math-v4
Checker version
math-v1
Panel size
5
Provider spend
$0.027762

Checker layer

Panel members.

# Item Item id Outcome Score
1 math-015 bbd36229-1521-460b-98e5-be9d88a9f9c3 ok 1.00
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 1.00
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 Item text stays unpublished so nobody can tune against the panel — identity travels as the item id and its pool source id.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 Google google/gemini-3.5-flash gen-1785854445-xChI2SsJTI83eQLEjQc3 stop 2912 50 530 $0.004845 706ee66844bf29a69ce4ddde30feac4de33cf63936242d5916d0c9cc0099b959 2026-08-04 14:40:48 UTC
2 openrouter Google google/gemini-3.5-flash gen-1785854448-OxSsEr5WPgt74dC6BS8p stop 2224 30 360 $0.003285 9f14025af0065b30e47e23ebb3b491d39ae8ed17d33739e5ff3827ffb3634953 2026-08-04 14:40:50 UTC
3 openrouter Google google/gemini-3.5-flash gen-1785854445-SlhJm2gM34Cw4j9PxQYe stop 2346 34 418 $0.003813 d11501b090fb2749f2c49284394dd36fe0ac76eb1a52cb3bba260dbc119ec46e 2026-08-04 14:40:48 UTC
4 openrouter Google google/gemini-3.5-flash gen-1785854438-x84jaG71W06jz6Q5yrc9 stop 7433 48 1181 $0.010701 9f7fc13348c4161bd6f898bf373407ad582a7a58d3b2eac6eda892ded1e269f5 2026-08-04 14:40:45 UTC
5 openrouter Google google/gemini-3.5-flash gen-1785854451-D6OX4Uk8dpvlXyTUXVQl stop 3519 46 561 $0.005118 061ed889323c07d4413bc9244b2bf393508ad9a067bc44ed84cd23943d3ab0cd 2026-08-04 14:40:54 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/2f5b71c47861…

curl -s https://actuary.sh/api/v1/evidence/2f5b71c47861d2612014935de3698697b1c1b9e9cb5ba74ccb3349d654b7807e \
  | 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.