Actuary
← Moonshot Kimi K2.5

Evidence block

Structured output · cycle 438

moonshotai/kimi-k2.5 · 2026-08-22 14:51:03 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
3
Frozen floor
0.700
Anytime level α
0.050
Hashes and versions
Evidence hash
67a65fe0c95a0f626080ca02c6599e419d047996f176220da6da0b362f571987
Design hash
8a4f5431d708d308ccd859fc31d097a5db0297535ace2795cab39b5f087eb318
Panel hash
a37ad21aa4b8c3e16dbae958c68a70064a9d95487e131d832f2c601f7fdacf14
Stream
fbdf265a-e12a-4d13-855e-43333ee3312e
Epoch
4bf2bb89-7823-44ce-98ec-289f3fdc20c8
Pool version
structured-output-v3
Checker version
structured_output-v2
Panel size
5
Provider spend
$0.0140756

Checker layer

Panel members.

# Item Item id Outcome Score
1 structured-output-015 390b56f6-0b7a-471d-a7dd-24e4a6519560 ok 1.00
2 structured-output-045 60032adc-9d89-4ecd-9431-4a3ecab9c9c6 ok 1.00
3 structured-output-075 b2f95fda-69c8-404c-8445-dcf17532fbee ok 1.00
4 structured-output-105 51363b3d-6e2e-4fd0-a633-3f6bcfa34fe9 truncated 0.00
5 structured-output-135 f1e6b049-9fe5-48da-b032-6034aefe87ca truncated 0.00

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 Item text stays unpublished so nobody can tune against the panel — identity travels as the item id and its pool source id.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 moonshotai/kimi-k2.5 gen-1787410213-K2q7QER2tzLw38Ej14JZ stop 17282 79 685 $0.0015768 02954c38fa7bacce5c3f5b6e6309d4e6fd66649054d2f998e76314a54ea97a2c 2026-08-22 14:50:30 UTC
2 openrouter DeepInfra moonshotai/kimi-k2.5 gen-1787410201-p9wQoQlrdX2PHfZBNtek stop 11812 84 319 $0.0007556 83f204ed0c10f7eafef22ab193c3a53dfa6f54808b8101ceab29beb23ed9a84e 2026-08-22 14:50:13 UTC
3 openrouter DeepInfra moonshotai/kimi-k2.5 gen-1787410199-fKnVStgcaYLU9EW81XQX stop 30113 110 1031 $0.0023692 ab7ee00599637be7807315ff1e42f79a2d43b60ef436a9e7f71467b8e0b3721e 2026-08-22 14:50:29 UTC
4 openrouter — — — — — 195 2048 $0.0046958 — 2026-08-22 14:50:56 UTC
5 openrouter — — — — — 156 2048 $0.0046782 — 2026-08-22 14:51:03 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/67a65fe0c95a…

curl -s https://actuary.sh/api/v1/evidence/67a65fe0c95a0f626080ca02c6599e419d047996f176220da6da0b362f571987 \
  | 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.