Paper Citation Record · LEDGER

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

As of 19 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2506.05229.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.05229 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:31:02.370982Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-14T04:23:21.000846Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy14
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9c374f95-e3d6-4386-a013-da46aa320767 · outbound

This paper cites Gqa: Training generalized multi-query transformer models from multi-head checkpoints.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Gqa: Training generalized multi-query transformer models from multi-head checkpoints

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.261636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d25c1ec0-8669-4a9c-ac03-7a5797cc5036 · outbound

This paper cites Beyond attention: Breaking the limits of transformer context length with recurrent memory.Proceedings of the AAAI Conference on Artificial Intelligence, 38(16):17700–17708, Mar.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Beyond attention: Breaking the limits of transformer context length with recurrent memory.Proceedings of the AAAI Conference on Artificial Intelligence, 38(16):17700–17708, Mar

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.704827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4207d493-347a-4c55-ba5b-7be557c38d82 · outbound

This paper cites Recurrent memory transformer.Advances in Neural Information Processing Systems, 35:11079–11091, 2022.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Recurrent memory transformer.Advances in Neural Information Processing Systems, 35:11079–11091, 2022

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.268284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0f5ae5d-3fb9-4a5f-a95e-5094e969e936 · outbound

This paper cites Transformer-XL: Attentive language models beyond a fixed-length context.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Transformer-XL: Attentive language models beyond a fixed-length context

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.689314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 659f308c-5d9b-45a7-b5b8-dd8a7bc1485c · outbound

This paper cites FlashAttention-2: Faster attention with better parallelism and work partitioning.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts FlashAttention-2: Faster attention with better parallelism and work partitioning

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.274470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d966adf-d81c-4b1e-b872-e3777f264d6b · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher Ré.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.278285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e69cc6b-8429-4fcf-beaf-703d096346a2 · outbound

This paper cites Transformers are ssms: Generalized models and efficient algorithms through structured state space duality.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Transformers are ssms: Generalized models and efficient algorithms through structured state space duality

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.281602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63e6efe4-47ff-4d86-96d6-56b831c19b84 · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.284382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dc6912a-8e4f-49e1-8186-aa6258447905 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.290391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51970a9b-c773-4e5b-bb8a-4b182f3fecec · outbound

This paper cites The Llama 3 Herd of Models.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.293278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4d68394-a45a-4269-83a1-47e8e8901c27 · outbound

This paper cites Mamba: Linear-Time Sequence Modeling with Selective State Spaces.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.296240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d6fd564-51f0-4b0b-a66d-81b81589be9e · outbound

This paper cites Efficiently modeling long sequences with structured state spaces.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Efficiently modeling long sequences with structured state spaces

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.657276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 58e1ae87-74e7-490f-937a-497772c33b52 · outbound

This paper cites Block- recurrent transformers.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Block- recurrent transformers

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.648133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 838a27de-ef3e-4c4c-b721-907f0931281c · outbound

This paper cites DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.305339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80358f58-bed7-4a71-b858-2d185d1c7717 · outbound

This paper cites Repeat after me: Transformers are better than state space models at copying.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Repeat after me: Transformers are better than state space models at copying

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.639062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation ff8a7535-4026-4e19-9bf9-41e137e5ab77 · outbound

This paper cites Babilong: Testing the limits of llms with long context reasoning-in-a-haystack.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Babilong: Testing the limits of llms with long context reasoning-in-a-haystack

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.310996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82506dc2-3f32-43ab-afc1-26f89d91cc8f · outbound

This paper cites xformers: A modular and hack- able transformer modelling library.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts xformers: A modular and hack- able transformer modelling library

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.313592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c4b4d5d-ac10-4b05-9d95-b8186f653680 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of Machine Learning and Systems, 6:87–100, 2024.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Awq: Activation-aware weight quantization for on-device llm compression and acceleration.Proceedings of Machine Learning and Systems, 6:87–100, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.316146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63fe8f27-6182-4581-9a47-0a261745935a · outbound

This paper cites DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.319072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation effed22a-408b-42de-bfbf-bda5bc0ea91b · outbound

This paper cites Ringattention with blockwise transformers for near-infinite context.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Ringattention with blockwise transformers for near-infinite context

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.321821Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 561f52c1-139a-4dfc-87e3-f19d3f653d6e · outbound

This paper cites The illusion of state in state-space models.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts The illusion of state in state-space models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.604978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b28ec415-0f93-4bc1-b9e7-e5bce10bca77 · outbound

This paper cites Gpt-4 technical report, 2023.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Gpt-4 technical report, 2023

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.327144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e691474-a32d-4afa-853f-9c51a8199840 · outbound

This paper cites RWKV: Reinventing RNNs for the transformer era.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts RWKV: Reinventing RNNs for the transformer era

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.588670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 92ea202f-dcaf-4a77-9a63-5f1e94a4d52f · outbound

This paper cites Language models are unsupervised multitask learners.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Language models are unsupervised multitask learners

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.332527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e54fda5-a8c1-4c85-97ab-060e04e22d96 · outbound

This paper cites Rae, Anna Potapenko, Siddhant M.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Rae, Anna Potapenko, Siddhant M

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.335195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3cae8ee-b43a-470c-b6dd-d7e64b398758 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.337712Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09640ec0-9f58-4519-ac11-be5c07b70fa0 · outbound

This paper cites Associative recurrent memory transformer.CoRR, 2024.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Associative recurrent memory transformer.CoRR, 2024

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.566381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 80cbd136-aa13-4f71-a90f-9c87954801c4 · outbound

This paper cites Linear transformers are secretly fast weight programmers, 2021.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Linear transformers are secretly fast weight programmers, 2021

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.343585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 604e1b7b-7f8b-41d0-b1c3-17602df684f8 · outbound

This paper cites Fast Transformer Decoding: One Write-Head is All You Need.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Fast Transformer Decoding: One Write-Head is All You Need

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.346313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d07d4554-56cf-44a1-8bbe-d551afe35423 · outbound

This paper cites What formal lan- guages can transformers express? a survey.Transactions of the Association for Computational Linguistics, 12, 2024.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts What formal lan- guages can transformers express? a survey.Transactions of the Association for Computational Linguistics, 12, 2024

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.550155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7d893457-b33b-4d27-acc2-4715475cc229 · outbound

This paper cites End-to-end memory networks, 2015.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts End-to-end memory networks, 2015

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.539030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation acd5a738-db6d-4c66-8f74-cb9716e631f6 · outbound

This paper cites Retentive Network: A Successor to Transformer for Large Language Models.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Retentive Network: A Successor to Transformer for Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.355443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f2c1da-f69c-4a4e-8155-165b9b29e6ab · outbound

This paper cites Attention is All you Need.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Attention is All you Need

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.528492Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3bb27f15-881d-4c8e-8759-af8aa705d936 · outbound

This paper cites Memory networks.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Memory networks

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.517679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2b09fa1b-27ad-45fd-9a55-eb962e66f1c4 · outbound

This paper cites Roofline: an insightful visual performance model for multicore architectures.Communications of the ACM, 52(4):65–76, 2009.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Roofline: an insightful visual performance model for multicore architectures.Communications of the ACM, 52(4):65–76, 2009

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T10:31:02.365308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72989e82-49cf-416f-99ec-0fdee6f90879 · outbound

This paper cites Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.500498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c11b898f-82bb-43a7-b71e-053a83de06c8 · outbound

This paper cites Parallelizing linear transformers with the delta rule over sequence length.

Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts Parallelizing linear transformers with the delta rule over sequence length

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:31:02.490451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation 6e868c84-9a6f-493c-87e8-54a3935ed209 · inbound

Extending LLM Context via Associative Recurrent Memory cites this paper.

Extending LLM Context via Associative Recurrent Memory Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts

Reference 94

Resolution: unresolved; no resolver link, observed 2026-07-14T04:23:21.000846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.