Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T11:14:00.876685Z
Paper Citation Record · LEDGER
As of 8 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2506.03370.
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 2026-08-07T11:14:00.876685Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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
13 of 13 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 58b8991f-a410-400c-85ed-014e7a996932 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize A theorem on probabilistic constant depth computations
Reference 1
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 60de64b8-851e-487c-a1c8-08b33f214424 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Logical Languages Accepted by Transformer Encoders with Hard Attention, October 2023
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 13dfd690-76f8-4a88-9041-bf2e70eeab69 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Brzozowski and R
Reference 3
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c37835d1-3174-4302-be7e-21d0fe742371 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize First-order definable languages
Reference 4
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a50dd50c-9719-4a66-a990-7452ebbfe6cb · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Computing approximate majority in ac0, 2023
Reference 5
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation fb2f1390-0a2c-4dde-b1ed-a3bb98055e23 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Theoretical limitations of self-attention in neural sequence models.Transactions of the Asso- ciation for Computational Linguistics, 8:156–171, 2020
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 11812967-d25a-4139-9133-6f67bd8f897c · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Formal Language Recognition by Hard Attention Transformers: Perspectives from Circuit Complexity, April 2022
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f177d7d5-e391-4aba-be5b-5fdd15822af2 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Logical languages accepted by transformer encoders with hard attention, 2023
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ce674e52-3e62-4e90-92a8-a41d68f81abd · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Temporal logic with past is exponentially more succinct, concurrency column.Bull
Reference 9
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 78432bbc-de10-4795-b600-d5db6d39f209 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Unresolved cited work
Reference 10
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation eb371ab5-1b1b-4c69-92fa-0f1ba2de0452 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Thinking Like Transformers
Reference 11
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c3709c9b-9ec1-4e6d-9be2-8d5929f5e05b · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages, May 2024
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 07d8d2ea-89e9-4964-885e-ed0c1538f269 · outbound
Comparison of different Unique hard attention transformer models by the formal languages they can recognize Self-attention networks can process bounded hierarchical languages
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
No inbound Pith citation observations are available.