LLM-as-a-Verifier (arXiv:2607.05391) as a dsh plugin — Best-of-N conversation mode: give DeepSeek V4 Flash test-time scaling. Bo5 self-verification hits 88% on Terminal-Bench 2.1, beating some frontier models at a fraction of the cost. Fine-grained logprob-expectation scoring, PPT tournament, zero-config.
Install verification: sandbox install ok, web smoke failed (L5) · tested on dsh 0.2.0-rc.1 · last checked Install verification details →
What it doesAI
LLM-as-a-verifier plugin enabling best-of-N self-verification for DeepSeek V4 Flash on terminal tasks.
- Bo5 self-verification hits 88% on Terminal-Bench 2.1
- Fine-grained logprob-expectation scoring with PPT tournament
- Zero-config test-time scaling for dsh
Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.
Installation
dsh plugin --profile web add @aispin/plugin-verifier@0.3.3security scan passed · npm package v0.3.3
Install method: npm · sandbox install ok, web smoke failed (L5)
Verification & Compatibility
Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.
External credentials (plugin-level): none detected
| plugin ＼ dsh | dsh 0.2.0-rc.1 current | dsh 0.1.7-rc.2 | dsh 0.1.7-alpha.2 | dsh 0.1.6-alpha.2 | dsh 0.1.6-alpha.1 |
|---|---|---|---|---|---|
| 0.3.3 | ✗ | ✗ | ✗ | ✗ | ✗ |
0.3.3npm6 failed2026-10-04
@aispin/plugin-verifier
✗dsh 0.2.0-rc.1current2026-09-29L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.1
- • Plugin artifact: npm · @aispin/plugin-verifier@0.3.3
ID: llm-as-a-verifier-dsh@0.3.3@dsh0.2.0-rc.1 · profile: l4-sandbox
Issued: 2026-09-29 · expires: 2026-10-06
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.1.7-rc.22026-09-25L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.7-rc.2
- • Plugin artifact: npm · @aispin/plugin-verifier@0.3.3
ID: llm-as-a-verifier-dsh@0.3.3@dsh0.1.7-rc.2 · profile: l3-fullscan
Issued: 2026-09-25 · expires: 2026-10-02
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.1.7-alpha.22026-09-23L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.7-alpha.2
- • Plugin artifact: npm · @aispin/plugin-verifier@0.3.3
ID: llm-as-a-verifier-dsh@0.3.3@dsh0.1.7-alpha.2 · profile: l4-sandbox
Issued: 2026-09-23 · expires: 2026-09-30
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.1.6-alpha.22026-09-20L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.2
- • Plugin artifact: npm · @aispin/plugin-verifier@0.3.3
ID: llm-as-a-verifier-dsh@0.3.3@dsh0.1.6-alpha.2 · profile: l3-fullscan
Issued: 2026-09-20 · expires: 2026-09-27
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.1.6-alpha.12026-09-17L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.1
- • Plugin artifact: npm · @aispin/plugin-verifier@0.3.3
ID: llm-as-a-verifier-dsh@0.3.3@dsh0.1.6-alpha.1 · profile: l4-sandbox
Issued: 2026-09-17 · expires: 2026-09-24
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗prehistory2026-10-04L5 · failed
- • Node.js: v24.14.0
- • DSH: unknown
- • Plugin artifact: npm · @aispin/plugin-verifier@0.3.3
ID: llm-as-a-verifier-dsh@0.3.3@dshunknown · profile: l4-sandbox
Issued: 2026-10-04 · expires: 2026-10-11
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).
Author badges
Embed the official badges in your README to showcase security & install-test status:
`[](https://www.dsh.so/artifact/llm-as-a-verifier-dsh/)`Security Report
Automated static scan, not manual review.
Vet static analysis found no suspicious behavior — verdict is clean.
v0.3.3dsh manifest0.3.3npm2026-10-040.3.3same versionclean · npmVet is an AST static scan (npm artifact or git source).
Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
Risk details
Activity
Last commit 2026-08-25 · activity: Stable
• Repo created: 2026-08-21
• Stars: ★ 2 · Forks: 0
• Health: Stable — committed within 90 days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).