AWhat changed
Defines a fixed-operation cell benchmark across three image datasets and extends it with separately enumerated topology and channel-size spaces and diagnostic learning curves.
Scientific scope
Defines a fixed-operation cell benchmark across three image datasets and extends it with separately enumerated topology and channel-size spaces and diagnostic learning curves. The first controlling v1 is explicitly titled NAS-Bench-102, not silently relabeled NAS-Bench-201. The related NATS extension is bundled with separate two/four-person bylines. Metrics depend on fixed datasets and training choices; not all arbitrary NAS algorithms or tasks fit the space. Topology encodings and unique functional graphs need not have the same count.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. The first controlling v1 is explicitly titled NAS-Bench-102, not silently relabeled NAS-Bench-201. The related NATS extension is bundled with separate two/four-person bylines. Metrics depend on fixed datasets and training choices; not all arbitrary NAS algorithms or tasks fit the space. Topology encodings and unique functional graphs need not have the same count.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- NAS-Bench-102: Extending the Scope of Reproducible Neural Architecture Search
- NATS-Bench: Benchmarking NAS algorithms for Architecture Topology and Size
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction