Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-01T16:21:54.227358Z
Paper Citation Record · LEDGER
As of 15 August 2026, this Paper Citation Record lists 7 of 7 outbound references and 0 inbound Pith citation observations for arXiv:2607.18027.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-01T16:21:54.227358Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
7 of 7 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 67e6a282-833f-4083-80f7-04779b32ab58 · outbound
L1 Augmented Attention as an Improved Vector Similarity Metric Lipschitz constraints can endow models with provable robustness against adversarial perturbations …, and guaranteed generalisation bounds
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5ecc28cd-e85f-46dc-93e6-8c12b7f6754f · outbound
L1 Augmented Attention as an Improved Vector Similarity Metric As we will see, this explicitly unmasks the otherwise hidden norm information and provides access to a richer geometry when calculating vector similarity
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 95ffb299-ad8b-4664-833e-7c076ed80d63 · outbound
L1 Augmented Attention as an Improved Vector Similarity Metric Unresolved cited work
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f10e91ff-e367-4a32-9456-4fc479522bbd · outbound
L1 Augmented Attention as an Improved Vector Similarity Metric A striking finding in empirical work on word embeddings is that there is a sweet spot for the dimensionality of word vectors: neither too small, nor too large
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 045a2706-a6fa-43a7-ac21-98fa46783c18 · outbound
L1 Augmented Attention as an Improved Vector Similarity Metric While section 1 presents some limitations of dot product, L1 Augmented Attention is also imperfect
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d290e1b2-db5b-4361-8c03-197be9302fe0 · outbound
L1 Augmented Attention as an Improved Vector Similarity Metric Another line of research to be explored is related to the choice of feature map for linear attention
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 79cb83c2-4fdc-4ddf-bac4-6b786b64b428 · outbound
L1 Augmented Attention as an Improved Vector Similarity Metric Music Transformer
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
No inbound Pith citation observations are available.