Actuary
← Moonshot Kimi K2.5

Evidence block

Instruction following · cycle 434

moonshotai/kimi-k2.5 · 2026-08-22 09:47:27 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
0.767
Members
5
Checker scored
4
Frozen floor
0.700
Anytime level α
0.050
Hashes and versions
Evidence hash
607dd40e9006979f3e890204ecb7996584ad22b7b3aa093b3caeadad941b4de8
Design hash
4f5cc6b9ff4ce026ccab93f5a3c8241f78eb005bc8b8068e4c701e9236504412
Panel hash
e7dfea1f343f7bf37e066a1117ca21f3438e804ad61437bf72d810640cef7e71
Stream
fa4b4075-99a5-4da3-92fb-34e34e16cad9
Epoch
91d10d90-5b83-4101-8aea-35f16ee28a75
Pool version
instruction_following-v3
Checker version
instruction_following-v1
Panel size
5
Provider spend
$0.0100611

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 truncated 0.00
4 instruction-following-105 9294d9d8-5c71-4d76-b053-b5cefc08d0e1 ok 1.00
5 instruction-following-135 7d213d46-039d-4f3a-aecf-c785ef61cc80 ok 0.83

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 Item text stays unpublished so nobody can tune against the panel — identity travels as the item id and its pool source id.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 moonshotai/kimi-k2.5 gen-1787392025-isstvQIv3x6r7eU2H35j stop 8298 49 597 $0.0013653 0cdfd8492f9924241c6042bb767208cc9d5101ca1eb95431aa528e9e40666df9 2026-08-22 09:47:13 UTC
2 openrouter DeepInfra moonshotai/kimi-k2.5 gen-1787392023-qbDaAi4O1dnAgkwqvZgu stop 4733 57 400 $0.0009256 82f392f5d746b86cb7970ae1fc709c5e7dfe434185223d93e593e47680aae5e4 2026-08-22 09:47:08 UTC
3 openrouter — — — — — 50 2048 $0.0046305 — 2026-08-22 09:47:27 UTC
4 openrouter DeepInfra moonshotai/kimi-k2.5 gen-1787392020-Od2FZQtmWuxyFZNXrNKo stop 4735 47 408 $0.0009392 45be265c3949e56ae9fb40dee91e7686e5231dbf65e867da43c00a08d3cc9747 2026-08-22 09:47:05 UTC
5 openrouter DeepInfra moonshotai/kimi-k2.5 gen-1787392028-5Hbx1ZORQAauSz2hd4AS stop 14682 55 967 $0.0022005 d0801ffc367ee4d3c34c78fa97d553c688c630d3e31610e82322ea156f3304d5 2026-08-22 09:47:23 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/607dd40e9006…

curl -s https://actuary.sh/api/v1/evidence/607dd40e9006979f3e890204ecb7996584ad22b7b3aa093b3caeadad941b4de8 \
  | 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.