Panagiotis Gkilis

Finite-sample decision risk in unseeded quantum compiler benchmarking

Version 4 — audited release. Archival technical preprint; not submitted to a venue. Quantum compiler benchmarks are used to accept or reject changes to production transpilers, but the compilers they measure are stochastic. At the pinned revision of IBM's Benchpress benchmark suit...

Finite-sample decision risk in unseeded quantum compiler benchmarking

Version 4 — audited release. Archival technical preprint; not submitted to a venue. Quantum compiler benchmarks are used to accept or reject changes to production transpilers, but the compilers they measure are stochastic. At the pinned revision of IBM's Benchpress benchmark suit...

Finite-sample decision risk in unseeded quantum compiler benchmarking

Draft preprint. Not submitted to a venue. Quantum compiler benchmarks are used to accept or reject changes to production transpilers, but the compilers they measure are stochastic. At the pinned revision of IBM's Benchpress benchmark suite, its Qiskit gym compiles without passing...

Continuous vocal-attribute traversals fall below the path resolution of current speech representations: a pre-registered validity gate across three speaker encoders and three neural codecs

Study 3 of the BedVibe vocal-representation series. Voice conversion, attribute editing and speaker-blend conditioning all move along a straight line between a source and a target point in a learned representation, and treat the intervening coordinates as natural intermediate voi...

Structure substitutes for scale in cross-document temporal reasoning

Retrieval systems are judged on whether the right evidence reaches the model. This paper measures what happens when it does and the model still cannot answer, because the answer is a relation between passages rather than a statement inside any of them. Over a five-document narrat...

Structure substitutes for scale in cross-document temporal reasoning

Retrieval systems are judged on whether the right evidence reaches the model. This paper measures what happens when it does and the model still cannot answer, because the answer is a relation between passages rather than a statement inside any of them. Over a five-document narrat...

The Loss Curve Is Not a Sufficient Statistic: Silent Objective Failures from Sentinel-Class Collisions in Neural Codec Language Models

Masked cross-entropy is the standard training objective for sequence models. Positions that are not real targets are excluded by comparing each target against a sentinel value, conventionally ignore_index = -100 in PyTorch. We show that when this sentinel is also a valid class in...

The Loss Curve Is Not a Sufficient Statistic: Silent Objective Failures from Sentinel-Class Collisions in Neural Codec Language Models

Masked cross-entropy is the standard training objective for sequence models. Positions that are not real targets are excluded by comparing each target against a sentinel value, conventionally ignore_index = -100 in PyTorch. We show that when this sentinel is also a valid class in...