Good ideas need
checkable evidence.

Proof-Carrying Optimality for Finite Identification under Bounded Adversarial Answer Errors

Develops proof-carrying methods for finite identification when answers may contain a bounded number of adversarial errors. Candidate construction is separated from independently checkable optimality certificates: all 30 primary cells receive two-sided proofs, while 300 of 303 declared sweep cells receive proofs and three are explicitly reported as resource-limit outcomes.

Scope: explicit finite behavior tables and declared probe alphabets. Verification is polynomial in the explicit table and supplied proof, not necessarily in a succinct game description.

Bounded-Horizon Local Transformer Training on CPUs: Quality, Throughput, and Memory

Tests bounded-horizon local training as a CPU-constrained alternative to full-horizon Transformer training. Async RGC measured 1.382× BP throughput with higher memory use, but the prespecified held-out 1% non-inferiority criterion and TinyStories transfer criterion failed; readout equivalence was not established.

The throughput comparison used 29 stage-worker threads for RGC and 24 BP intra-op threads; measured PSS increased from 1.94 to 4.31 GiB.

Quantum Hybrid Modules for AI: Attention, Optimization, and Verification on Near-Term Quantum Hardware

Explores quantum-classical modules for AI search, optimization, attention, and kernel methods. This is an early exploratory preprint; its current results do not establish a practical or end-to-end quantum advantage, and it does not represent a current product direction.