public stress-test corpus · reviewed 2026-07-16
What can be checked—and what remains only a claim.
A curated, non-exhaustive set of public arXiv papers selected for recency, public visibility, claim diversity, and red-team value. It is not a citation ranking, endorsement, or list of proven discoveries.
These are Certiv-authored test dossiers, not author-issued Certiv receipts. A pinned PDF proves file identity only. A passing selected replay records one bounded observation; it does not independently reproduce a paper's central claim or establish truth, novelty, priority, safety, or correct interpretation.
result at a glance
Identity is common. Reproduction is not.
Every number describes this corpus, not the literature as a whole. “Selected replay” is deliberately narrower than “paper reproduced.”
Core exercise passed · bounded
Unchanged is not “verified”; tampered is a distinct failure.
Each exact PDF was packed as a Certiv T0 integrity input, checked unchanged, then checked after a one-byte append. This exercises identity and tamper semantics only; it does not evaluate a paper's scientific claims. Declared author commands executed: 0.
selection and method
Built to expose evidence boundaries.
- Public arXiv record and exact-version PDF available over HTTPS.
- AI is central to the reported discovery, discovery workflow, or verification problem.
- The set spans mathematics, algorithms, materials, chemistry, biomedicine, physics, and automated AI research.
- Methodological and adversarial controls are included to test whether the evidence model resists overclaiming.
- Selection does not imply scientific endorsement, popularity rank, or successful reproduction.
11 public papers · exact versions
Evidence dossiers
Open a dossier for the file identity, reported claim, checks, blockers, red-team findings, primary sources, and machine-readable record.
01Reported discovery
Algorithms and mathematics
AlphaEvolve: A coding agent for scientific and algorithmic discovery
The exact PDF was pinned. Three selected cells from the public results notebook ran in a no-network, read-only sandbox and accepted the 48-rank construction, an Erdős step-function bound, and a dimension-11 kissing construction.
Selected check replayedarXiv:2506.13131v1
02Reported discovery
Mathematics
Mathematical exploration and discovery at scale
The exact v3 paper was pinned. Selected public verifiers for an Erdős step-function bound and a dimension-11 kissing construction ran successfully in isolation.
Selected check replayedarXiv:2511.02864v3
03Reported discovery
Biomedicine
Accelerating scientific discovery with Co-Scientist
The exact v2 paper was pinned and its disclosure boundary reviewed. The paper states that three real-world validation datasets and the full system source are not public.
Source pinnedarXiv:2502.18864v2
04Reported discovery
Materials science
MatterGen: a generative model for inorganic materials design
The exact v2 PDF was pinned and the official code repository was commit-inventoried. Its documentation warns that released checkpoints were retrained and may not reproduce paper values; some structures also cannot be shared for licensing reasons.
Artifact inventoriedarXiv:2312.03687v2
05Discovery system
Automated machine-learning research
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
The exact v3 PDF and public repository revision were pinned. The paper's headline acceptance language is explicitly based on an automated reviewer's threshold.
Artifact inventoriedarXiv:2408.06292v3
06Discovery system
Automated machine-learning research
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
The exact v1 PDF and official repository revision were pinned. The paper documents a workshop acceptance event, which is a process outcome rather than a reproduction of the paper's scientific conclusions.
Artifact inventoriedarXiv:2504.08066v1
07Discovery system
Physics
AI-Newton: A Concept-Driven Physical Law Discovery System without Prior Physical Knowledge
The exact v2 PDF and repository revision were pinned. The documented stack requires Python, Rust, CUDA, and Maple 2024; Maple was not present in the review environment.
Artifact inventoriedarXiv:2504.01538v2
08Discovery system
Chemistry and laboratory automation
Emergent autonomous scientific research capabilities of large language models
The exact v1 paper was pinned. This version says code, data, and prompts would be released later and discusses safety reasons for limiting disclosure.
Source pinnedarXiv:2304.05332v1
09Reported discovery
Theoretical physics and mathematics
Solving an Open Problem in Theoretical Physics using AI-Assisted Discovery
The exact v1 paper was pinned and its prompts, search description, and derivations are inspectable in the paper. No public runnable artifact linked from the exact record was identified in this review.
Source pinnedarXiv:2603.04735v1
10Method control
Scientific method
The Need for Verification in AI-Driven Scientific Discovery
The exact v2 paper was pinned and treated as a methodological control, not as an experimental discovery result.
Source pinnedarXiv:2509.01398v2
11Adversarial response
Algorithms and systems performance
Shorter and faster than Sort3AlphaDev
Eight supplied sorting functions passed 17,173,580 cases in an independent harness. On one i9-13900KF environment with Clang 14, a nine-trial microbenchmark measured Sort3_faster at a 0.837 ns/call median versus 1.031 ns/call for Sort3AlphaDev.
Selected check replayedarXiv:2307.14503v1
how to read the status
Three levels, none named “proven.”
- Source pinned
- Exact paper bytes and parser observations recorded. No executable paper result replayed.
- Artifact inventoried
- A public repository or package was also revision-pinned and its constraints reviewed.
- Selected check replayed
- At least one reviewed check ran in a bounded environment. Only its stated scope passed.