Paper Citation Record · LEDGER

Two Heads Are Better than One: Simulating Large Transformers with Small Ones

As of 17 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2506.12220.

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

pith.paper-citation-record.v1
2506.12220 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T01:12:48.259338Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T16:17:09.834609Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T09:05:58.230449Z

Reference resolution

41 of 41 outbound references displayed

verified exact1
verified fuzzy34
unresolved6
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6b51397b-9819-4a56-bba0-0277ff4eb8cd · outbound

This paper cites Zoology: Measuring and improving recall in efficient language models.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Zoology: Measuring and improving recall in efficient language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.896786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation af1324c6-0fab-4832-a706-76dc132db978 · outbound

This paper cites Fast attention requires bounded entries.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Fast attention requires bounded entries

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.880702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8a8047c2-678c-45a3-a1ac-422c5871ea0f · outbound

This paper cites Fundamental limitations on subquadratic alternatives to transformers.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Fundamental limitations on subquadratic alternatives to transformers

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.865671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7945a37a-e689-418e-b8c0-acba451ad33f · outbound

This paper cites On the A bility and L imitations of T ransformers to R ecognize F ormal L anguages.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones On the A bility and L imitations of T ransformers to R ecognize F ormal L anguages

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.850871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fa65ef42-f46d-40c2-93c3-37b94a062016 · outbound

This paper cites Separations in the representational capabilities of transformers and recurrent architectures.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Separations in the representational capabilities of transformers and recurrent architectures

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.835057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 024fca3b-7758-4ed9-9ec7-c685edee9285 · outbound

This paper cites Longformer: The Long-Document Transformer.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Longformer: The Long-Document Transformer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T01:12:48.104615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation addbc6b7-327f-4df2-a6d5-7a5383a7a3a4 · outbound

This paper cites An exploration of hierarchical attention transformers for efficient long document classification, 2022.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones An exploration of hierarchical attention transformers for efficient long document classification, 2022

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.819050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d63ca6e3-07d2-4db9-ada5-861a5bfe1370 · outbound

This paper cites Colwell, and Adrian Weller.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Colwell, and Adrian Weller

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T01:12:48.114975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 208bc6d9-2b45-4ef8-adae-3785c449204f · outbound

This paper cites End-to-end object detection with transformers.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones End-to-end object detection with transformers

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.794430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c0d9153c-e51b-4936-abef-f0a471cc6c8c · outbound

This paper cites Scaling Language Models: Methods, Analysis & Insights from Training Gopher.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Scaling Language Models: Methods, Analysis & Insights from Training Gopher

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T01:12:48.123953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74419346-96a3-4ec1-940e-a64dd8201936 · outbound

This paper cites Fu, Stefano Ermon, Atri Rudra, and Christopher R\' e.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Fu, Stefano Ermon, Atri Rudra, and Christopher R\' e

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.779890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 02e50453-d976-4a8e-a032-008066dfdcaf · outbound

This paper cites Etched is Making the Biggest Bet in AI.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Etched is Making the Biggest Bet in AI

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.765080Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f4cb5a0f-b75d-436c-996d-6573336e49c3 · outbound

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

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Mamba: Linear-Time Sequence Modeling with Selective State Spaces

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T01:12:48.138043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a02b2ac7-3259-4954-8b3e-8da43426ddb9 · outbound

This paper cites Theoretical limitations of self-attention in neural sequence models.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Theoretical limitations of self-attention in neural sequence models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.748865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 38ea6915-586e-4ae5-941a-ada67e86cc74 · outbound

This paper cites Hyperattention: Long-context attention in near-linear time.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Hyperattention: Long-context attention in near-linear time

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.734346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 08d07ec7-a333-4c40-8c90-2aa45499d470 · outbound

This paper cites Computational limits of low-rank adaptation (lo RA ) fine-tuning for transformer models.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Computational limits of low-rank adaptation (lo RA ) fine-tuning for transformer models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.719060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fe1866d1-3cbd-4e71-9b22-14369cd71c7c · outbound

This paper cites Multilayer feedforward networks are universal approximators.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Multilayer feedforward networks are universal approximators

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.703811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 38e00788-d632-489c-995f-418982c0cfe1 · outbound

This paper cites On statistical rates and provably efficient criteria of latent diffusion transformers (dits).

Two Heads Are Better than One: Simulating Large Transformers with Small Ones On statistical rates and provably efficient criteria of latent diffusion transformers (dits)

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.689004Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7cdac334-4f01-435b-8d57-51f8908b4925 · outbound

This paper cites Kakade, and Eran Malach.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Kakade, and Eran Malach

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T01:12:48.165303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acebf52c-beb3-4a63-ab6c-4ac01dd9cf27 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones An image is worth 16x16 words: Transformers for image recognition at scale

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.663817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e9d094b8-0055-414d-9fb4-a96198d7feb0 · outbound

This paper cites RNGD preview: The world's most efficient AI chip for LLM inference.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones RNGD preview: The world's most efficient AI chip for LLM inference

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.650041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d80f281d-47c8-4a70-a344-5a40cd0df65d · outbound

This paper cites Reformer: The efficient transformer.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Reformer: The efficient transformer

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.635829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 278afdd6-e958-4ee1-906d-af3f472e816a · outbound

This paper cites Polysketchformer: fast transformers via sketching polynomial kernels.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Polysketchformer: fast transformers via sketching polynomial kernels

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.622136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 48ed1d42-b864-410a-bf0b-22644b5e50be · outbound

This paper cites Ash, Surbhi Goel, Akshay Krishnamurthy, and Cyril Zhang.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Ash, Surbhi Goel, Akshay Krishnamurthy, and Cyril Zhang

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.608236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ed2960ec-a1f8-4d69-88f3-f2648a08b744 · outbound

This paper cites On the expressive flexibility of self-attention matrices.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones On the expressive flexibility of self-attention matrices

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.593022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c29f4383-d564-47e4-b9a4-2b207dacee37 · outbound

This paper cites Hierarchical transformers for multi-document summarization.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Hierarchical transformers for multi-document summarization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.578990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d90d4e61-9a47-4870-896a-c408cef07b8b · outbound

This paper cites The parallelism tradeoff: Limitations of log-precision transformers.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones The parallelism tradeoff: Limitations of log-precision transformers

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.564989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fc1f91c6-6d9a-44ea-9d52-57cf35de5df0 · outbound

This paper cites an unresolved cited work.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T01:12:48.550241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3bb1e02f-d1fa-4f28-9bbd-3aa12a639221 · outbound

This paper cites Language models are few-shot learners.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Language models are few-shot learners

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.535978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3b258ad8-d2ad-446f-badb-12896773279a · outbound

This paper cites Hierarchical transformers for long document classification.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Hierarchical transformers for long document classification

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.521713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b661e8a2-a0a8-4843-add4-4105573376c4 · outbound

This paper cites Representational strengths and limitations of transformers.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Representational strengths and limitations of transformers

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.507820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 3ef4a2f6-b742-4a37-a5c6-ff8c5eba978d · outbound

This paper cites Transformers, parallel computation, and logarithmic depth.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Transformers, parallel computation, and logarithmic depth

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.493360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 44e1558a-3115-4c57-9557-a69b1b43a757 · outbound

This paper cites What formal languages can transformers express? a survey.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones What formal languages can transformers express? a survey

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.477544Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c1d55e78-58a6-4b59-9ea1-a56d3a76e0b8 · outbound

This paper cites Efficient transformers: A survey.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Efficient transformers: A survey

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.462466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9445936f-2977-44c6-af2d-d60cdfd6cd04 · outbound

This paper cites Schmidt, and Stephan Peitz.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Schmidt, and Stephan Peitz

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.446971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b3536e4d-94ec-4bcd-bfec-8e67154f4f8e · outbound

This paper cites Gomez, ukasz Kaiser, and Illia Polosukhin.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Gomez, ukasz Kaiser, and Illia Polosukhin

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.429843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 80d2ebdf-30d9-43e7-b2e9-9935b9e57e94 · outbound

This paper cites RNN s are not transformers (yet): The key bottleneck on in-context retrieval.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones RNN s are not transformers (yet): The key bottleneck on in-context retrieval

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.414278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation de93e740-306e-4720-b64c-b46d5a14bddd · outbound

This paper cites LightSeq2: Accelerated Training for Transformer-based Models on GPUs.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones LightSeq2: Accelerated Training for Transformer-based Models on GPUs

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-07T01:12:48.303846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7d215dfb-3d60-43fe-8962-399d38217616 · outbound

This paper cites Efficient streaming language models with attention sinks.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Efficient streaming language models with attention sinks

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.398365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 12d921ac-cc04-4481-b458-297b95299f53 · outbound

This paper cites Are transformers universal approximators of sequence-to-sequence functions? In International Conference on Learning Representations , 2020.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Are transformers universal approximators of sequence-to-sequence functions? In International Conference on Learning Representations , 2020

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.382813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c1d80b37-089f-44c1-868f-5cd1ac530dc0 · outbound

This paper cites Reddi, and Sanjiv Kumar.

Two Heads Are Better than One: Simulating Large Transformers with Small Ones Reddi, and Sanjiv Kumar

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T01:12:48.366538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 795242bf-3d0f-49a8-96ad-9f827583f903 · inbound

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation cites this paper.

Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Two Heads Are Better than One: Simulating Large Transformers with Small Ones

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:05:58.232597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.