plumb
Run the paper. Check its numbers.
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Plumb re-runs a paper's own code on your compute, re-derives each claim from the actual run, and returns a per-claim verdict: REPRODUCED, DIVERGED, or UNVERIFIED. Execution decides, never an LLM. Open source; the honest number is published with it.
PH · launched Oct 20, 2026 · 1 upvote (top 67%) · 0 views
Niche: financial reconciliation software · 58 launches, 7 in the last 7 days · Explore this niche →
Category and tags
- Horizontal
- Analytics & BI
- B2B
- Not AI
- Hobby / open-source project
- Open Source
- Developer Tools
- GitHub
- Science
Visit website ↗ Source listing ↗
More like this: all 58 launches in financial reconciliation software →
Could you build this?
Partial The UI and reporting are easy, but running arbitrary research code reliably in sandboxed environments and mapping paper claims to measured outputs needs serious engineering and judgment.
What it would actually take: Build a containerized execution sandbox (Docker or Firecracker-style microVMs) that resolves each paper's dependencies, GPU needs, and random seeds, then runs its scripts. A claim-extraction step (LLM-assisted, human-checked) must map each claim to a specific output metric and tolerance, and the verdict logic must be deterministic. The hard parts are reproducibility across messy research code and designing defensible tolerances, which takes ML research and infrastructure experience.
Competitors
Other products that read as similar to this one : 43 launches clear the similarity bar, closest 8 shown.
Attention rank: #21 of 44 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 350 days after the earliest competitor.
- Prove your code produced your claims without making reviewers rerun it · hn · 2026-08-31 · 12 upvotes · similarity 0.43
- Evidence Trail · ph · 2026-09-18 · 1 upvotes · similarity 0.40
- SQE Practice Test · ph · 2026-09-12 · 1 upvotes · similarity 0.37
- Lotor v3.0 · ph · 2026-10-24 · 1 upvotes · similarity 0.37
- Plumb · ph · 2026-09-27 · 3 upvotes · similarity 0.36
- Unstale · ph · 2026-11-10 · 1 upvotes · similarity 0.36
- PatentProof · ph · 2026-10-19 · 1 upvotes · similarity 0.35
- SABLE Proof-Gated Settlement Starter · ph · 2026-10-14 · 2 upvotes · similarity 0.35
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.