PulseAugur
EN
LIVE 09:48:39

New tool DAISY infers missing assertions for Dafny verification

By PulseAugur Editorial · [1 sources] ·

Researchers have developed DAISY, a tool designed to automatically infer missing assertions in Dafny programs, thereby reducing the burden of formal verification. DAISY uses verifier diagnostics and LLM-based localization to identify assertion sites, generates candidate assertions with an LLM, and validates them using the Dafny verifier. In evaluations on an extended DafnyBench benchmark, DAISY successfully repaired 86% of programs with a single missing assertion and 36% with two missing assertions, demonstrating its potential to streamline the adoption of verification-aware languages. AI

IMPACT This tool could significantly reduce the effort required for formal verification, potentially accelerating the adoption of verification-aware programming languages.

RANK_REASON The cluster describes a new research paper detailing a tool for assertion inference in Dafny. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New tool DAISY infers missing assertions for Dafny verification

How we ranked this

Signal score
16 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes a new research paper detailing a tool for assertion inference in Dafny. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · \'Alvaro Silva, Alexandra Mendes, Ruben Martins ·

    DAISY: Fault-Guided Assertion Inference for Dafny

    arXiv:2511.00125v2 Announce Type: replace-cross Abstract: Formal verification with Dafny provides strong correctness guarantees, but verification failures often require users to determine where helper assertions are needed and to manually write the assertions necessary for verifi…

RELATED ENTITIES

RELATED TOPICS