Answers are grounded in this paper and cite their sources.
Pre-registration of the final benchmark of Plastanno, a plastome annotator. It fixes, before any evaluated sequence is downloaded: the protocol (endpoints, a ±1.0 percentage-point equivalence margin with a fixed verdict table, exclusions, arms, runtime measures, computing environment, commitments); the manifest of 738 GenBank land-plant plastomes (727 angiosperms, 11 non-angiosperms), released between 2026-06-20 and 2026-09-30, from species absent from the authors' data and databases, selected from metadata only; the reference used for PGA on every genome; every scoring script, with SHA-256 hashes. The tools evaluated are Plastanno 3.1.0, Chloë and PGA v2.0. Each tool is run once and every result will be reported. The evaluation is independent and prospectively sealed (a temporal hold-out).
No takes yet. Share an insight, caveat, or question.
Trinh et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: