Paper Citation Record · LEDGER

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior

As of 4 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2605.26797.

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

pith.paper-citation-record.v1
2605.26797 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-29T19:36:13.559393Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

27 of 27 outbound references displayed

verified exact18
verified fuzzy0
unresolved8
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6bdb8679-bbd1-4df7-b8e6-e25b92d6532a · outbound

This paper cites Language models are few-shot learners.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Language models are few-shot learners

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2efbb355-3685-403c-8cb5-003ce1c758cb · outbound

This paper cites Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.937865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 99c4b0bc-06bf-42fb-8651-5f97cf7b9336 · outbound

This paper cites Addressing Some Limitations of Transformers with Feedback Memory.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Addressing Some Limitations of Transformers with Feedback Memory

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:54.933744Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation dab136e2-21ca-4c32-a2b2-f48ea4cd2812 · outbound

This paper cites Hungry Hungry Hippos: Towards Language Modeling with State Space Models.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Hungry Hungry Hippos: Towards Language Modeling with State Space Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:54.934978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8a7b088d-d4cd-41b9-a7d4-4cfea3c4b9c8 · outbound

This paper cites Think before you speak: Training language models with pause tokens.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Think before you speak: Training language models with pause tokens

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6801829-3569-41c0-9877-f7a91b56e039 · outbound

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

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.980929Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ff661fe8-d849-4d21-ba1d-b9ee4cbe9c2f · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Training Large Language Models to Reason in a Continuous Latent Space

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.969758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cc9c82eb-31f1-4a78-b661-ab6fa781d8fa · outbound

This paper cites Thinking Tokens for Language Modeling.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Thinking Tokens for Language Modeling

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T19:43:54.967076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8f438508-705f-47b5-9e66-0fe83f8cde05 · outbound

This paper cites TransformerFAM: Feedback attention is working memory.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior TransformerFAM: Feedback attention is working memory

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:54.961412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 788d6530-a7dd-4091-af6d-179219879769 · outbound

This paper cites Muon: An optimizer for hidden layers in neural networks, 2024.URL https://kellerjordan.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Muon: An optimizer for hidden layers in neural networks, 2024.URL https://kellerjordan

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a1b5163-bc86-4017-b0ac-ae3dd66d0c2e · outbound

This paper cites Jamba: A Hybrid Transformer-Mamba Language Model.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Jamba: A Hybrid Transformer-Mamba Language Model

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.983792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1d46141e-98e7-48cb-a689-2edde5adce72 · outbound

This paper cites Fineweb-edu: the finest collection of educational content, 2024.URL https://huggingface.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Fineweb-edu: the finest collection of educational content, 2024.URL https://huggingface

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b602e78d-e8f5-434d-aa23-e7433373862a · outbound

This paper cites Landmark Attention: Random-Access Infinite Context Length for Transformers.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Landmark Attention: Random-Access Infinite Context Length for Transformers

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:54.977792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 16341c4e-7eed-455c-a832-a1231670ebf2 · outbound

This paper cites Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.969393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5d043d28-2feb-4069-a115-80f40c889473 · outbound

This paper cites RWKV: Reinventing RNNs for the Transformer Era.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior RWKV: Reinventing RNNs for the Transformer Era

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.971790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation efb1b40d-02f1-405a-85e2-3ba3052b2561 · outbound

This paper cites Let's Think Dot by Dot: Hidden Computation in Transformer Language Models.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Let's Think Dot by Dot: Hidden Computation in Transformer Language Models

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:54.963801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation eb9e9bd5-3a79-4c8d-9263-11c7c44f33b2 · outbound

This paper cites Compressive Transformers for Long-Range Sequence Modelling.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Compressive Transformers for Long-Range Sequence Modelling

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.972100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e95820fa-5fb5-4599-9941-b201aaeb1536 · outbound

This paper cites Simplified State Space Layers for Sequence Modeling.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Simplified State Space Layers for Sequence Modeling

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.974514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f1089c86-5ba0-421b-8a27-89a4c9df6810 · outbound

This paper cites Learning to (Learn at Test Time): RNNs with Expressive Hidden States.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Learning to (Learn at Test Time): RNNs with Expressive Hidden States

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.986638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0b0f7268-8c3f-4441-8b75-20e48d214f03 · outbound

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

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Retentive Network: A Successor to Transformer for Large Language Models

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.948230Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4dd94e11-ba68-4b2f-a850-a88bbdcf7c16 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Gemma 2: Improving Open Language Models at a Practical Size

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.951166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3f0b871a-b078-46b8-92de-780ac6053677 · outbound

This paper cites Memorizing Transformers.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Memorizing Transformers

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-29T19:43:54.966815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f52560f1-2bb2-4c67-a37e-0bd395dd25f4 · outbound

This paper cites Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-06-29T19:43:54.977708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9b03380b-245f-4a4c-86cf-9f83cd2b7cf3 · outbound

This paper cites an unresolved cited work.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6060a32c-504e-448a-9b92-adc50a8054ea · outbound

This paper cites The final shard is held out as validation and the remaining shards are used for training.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior The final shard is held out as validation and the remaining shards are used for training

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2519ddef-6310-46c1-8f96-81a4c414cbed · outbound

This paper cites WithC= 256, the recurrent signal becomes too sparse and the result is nearly identical to the baseline.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior WithC= 256, the recurrent signal becomes too sparse and the result is nearly identical to the baseline

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b9ffb8-b897-42dc-b563-6ec85fa23f8c · outbound

This paper cites IncreasingScreates a longer sparse refinement chain, but does not improve BPB in this setting.

Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior IncreasingScreates a longer sparse refinement chain, but does not improve BPB in this setting

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-29T19:36:13.559393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.