Claims Browser

The low base rate of severe adverse drug events places clinical-outcome effects beyond the scope of a single-site feasibility study

"We explicitly do not claim a clinical-outcome effect, which the low base rate of severe events places beyond a single-site feasibility study."

Deep transformers remain relatively underexplored in tabular data applications compared to computer vision and natural language processing

"While deep transformers have been widely studied in computer vision and natural language processing, their application in tabular data remains relatively underexplored."

Transformer models remain resilient to performance drops when low-importance attention heads are removed in 72.5% of tabular dataset experiments

"In 72.5\% of experimental examples, the model remains most resilient to performance drops when heads with the lowest importance scores are gradually removed."

Removing the most important attention head first causes the greatest reduction in classification performance

"removing the most important attention head first results in the greatest reduction in classification performance"

Important attention heads are scattered across layers without consistent layer-specific patterns in tabular transformers

"A closer look at individual head importance scores across six attention layers reveals that important heads are scattered across layers, with no consistent layer-specific trends."

Attention head importance varies considerably across different tabular datasets, unlike in image and language domains

"In contrast to the image and language domains, the importance of individual attention heads varies considerably across tabular datasets with different schemas and feature spaces."

LLM compute accounts for 80-90% of query cost in production semantic data processing systems

"In production, LLM compute accounts for $80-90\%$ of query cost"

Each LLM call costs 100,000 to 10,000,000 times more than a relational predicate

"each call costs $10^5-10^7\times$ a relational predicate"

LLM latency is high enough that per-call gradient steps and per-batch threshold solves can fit inside the round-trip time

"At LLM latency, per-call gradient steps and per-batch threshold solves fit inside the round-trip."

Compositional online learning at the LLM call boundary can achieve an 11.4x upper bound improvement on conjunction-filter workloads

"Under independence, the two learning components compose multiplicatively to an $11.4\times$ upper bound on a representative conjunction-filter workload."

In realistic conditions with self-selection and drift effects, compositional online learning achieves approximately 8x improvement on LLM query costs

"Self-selection at the cascade boundary, sample-budget shrinkage, and selectivity-estimation drift reduce it to a realistic figure near $8\times$."

Circuit Condensation can reduce mechanistic interpretability circuits by 8.1x on average and up to 316x compared to frozen baselines across four behaviors and eight models

"Across four behaviors and eight models, condensed circuits are smaller than the strongest frozen baseline in 30 of 32 settings, by $8.1\times$ on average and up to $316\times$."

Weight updates during Circuit Condensation, rather than search alone, drive the reduction in circuit size

"Repeating the search without weight updates produces larger circuits in 29 of 32 settings, showing that weight updates, rather than search alone, drive the reduction."

Circuit Condensation produces more focused circuits with documented roles: 24 heads with 17 documented roles versus 61 heads with 36 undocumented roles for frozen circuits on indirect object identification

"On indirect object identification, condensation isolates 24 heads, 17 of them with documented roles, against 61 heads and 36 undocumented ones for the matched frozen circuit: a sufficient sub-circuit of the published mechanism rather than a reconstruction of it."

Edges in condensed circuits have dependencies and their effects cannot be understood independently

"Pair ablations expose dependencies between edges, showing that their effects cannot be understood independently."

Testing subsets of 19 circuits found 11 that cannot be reduced further and revealed removable edges in the rest

"Testing every subset of 19 circuits finds 11 that cannot be reduced and reveals removable edges in the rest."

Neural operators have demonstrated broad empirical success at approximating solution operators of PDEs from data

"Neural operators have demonstrated broad empirical success at approximating such maps from data."

The proposed architecture satisfies homogeneous Dirichlet boundary conditions independently of training whilst retaining expressivity of existing kernel-integral neural operators

"we propose an architecture which, independently of training, satisfies homogeneous Dirichlet boundary conditions, whilst simultaneously retaining the expressivity of existing kernel-integral neural operator architectures"