Paper Citation Record · LEDGER

Attention-based representations for multi-task computation

As of 10 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2608.04243.

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

pith.paper-citation-record.v1
2608.04243 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-08T00:18:21.386846Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+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

36 of 36 outbound references displayed

verified exact4
verified fuzzy15
unresolved15
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation beca5942-c7bd-4a69-a1f4-a74eb67ecc8b · outbound

This paper cites A capacity-based rationale for multi-head attention, 2026.

Attention-based representations for multi-task computation A capacity-based rationale for multi-head attention, 2026

Reference 1

Resolution: verified exact; raw_fallback, observed 2026-08-08T00:18:21.930876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dff403db-43f9-48c3-95ba-d46f7a33e432 · outbound

This paper cites Online linear optimization and adaptive routing.

Attention-based representations for multi-task computation Online linear optimization and adaptive routing

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.132620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37b95261-b3f7-497e-82ab-6f6528edcac0 · outbound

This paper cites Some extremal postage stamp bases.Journal of Integer Sequences, 13(2):3, 2010.

Attention-based representations for multi-task computation Some extremal postage stamp bases.Journal of Integer Sequences, 13(2):3, 2010

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.121254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 91d939f6-4857-40d5-a19e-3a968f32c2ac · outbound

This paper cites Theoretical limitations of multi-layer transformer,.

Attention-based representations for multi-task computation Theoretical limitations of multi-layer transformer,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.109810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9cf18003-55b1-4a52-b4f4-47e9154309bc · outbound

This paper cites Tighter Bounds on the Expressivity of Transformer Encoders.

Attention-based representations for multi-task computation Tighter Bounds on the Expressivity of Transformer Encoders

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-08T00:18:21.843522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c82b1c13-e4ca-4443-b178-b469ed5a78cc · outbound

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

Attention-based representations for multi-task computation BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.272654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b7015f8-7cdc-48a0-b17e-60dd87d12b1d · outbound

This paper cites Few-Shot Learning via Learning the Representation, Provably.

Attention-based representations for multi-task computation Few-Shot Learning via Learning the Representation, Provably

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.277169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7d4dd3e-54d0-45c9-9e5f-d9eaa98c5cb1 · outbound

This paper cites A combinatorial problem in geometry.Compositio Mathematica, 2:463–470, 1935.

Attention-based representations for multi-task computation A combinatorial problem in geometry.Compositio Mathematica, 2:463–470, 1935

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.096681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f27f124b-e4fe-40d2-bf18-cdfa8703c07d · outbound

This paper cites Theoretical limitations of self-attention in neural sequence models.Transactions of the Association for Computational Linguistics, 8:156–171, December 2020.

Attention-based representations for multi-task computation Theoretical limitations of self-attention in neural sequence models.Transactions of the Association for Computational Linguistics, 8:156–171, December 2020

Reference 9

Resolution: malformed identifier; no resolver link, observed 2026-08-08T00:18:21.285854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61a25a05-573c-400f-abd0-ff91a56e996d · outbound

This paper cites Formal language recognition by hard attention transformers: Perspectives from circuit complexity, 2022.

Attention-based representations for multi-task computation Formal language recognition by hard attention transformers: Perspectives from circuit complexity, 2022

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.085791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9f7f622e-23d4-439d-815b-2f3e9dd54550 · outbound

This paper cites Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?.

Attention-based representations for multi-task computation Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.293789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c33eec-0cf9-45d5-a364-6c2c18a18adb · outbound

This paper cites Lower bounds on transformers with infinite precision.

Attention-based representations for multi-task computation Lower bounds on transformers with infinite precision

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-08T00:18:21.793091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 76a9cb42-cb5e-4237-a28f-f33abdec2ea0 · outbound

This paper cites Parity, Sensitivity, and Transformers.

Attention-based representations for multi-task computation Parity, Sensitivity, and Transformers

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.302058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fb54950-2674-4625-a638-182a5182679b · outbound

This paper cites A Structured Self-attentive Sentence Embedding.

Attention-based representations for multi-task computation A Structured Self-attentive Sentence Embedding

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.306038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caefcef9-4e90-4bb7-942e-547adae906e2 · outbound

This paper cites Transformers Learn Shortcuts to Automata.

Attention-based representations for multi-task computation Transformers Learn Shortcuts to Automata

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.309970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e1666f-4154-4b48-8459-8b05e6873af5 · outbound

This paper cites The Parallelism Tradeoff: Limitations of Log-Precision Transformers.

Attention-based representations for multi-task computation The Parallelism Tradeoff: Limitations of Log-Precision Transformers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.313898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71fd7570-6819-4b95-ac42-3ab8b4eddf44 · outbound

This paper cites A little depth goes a long way: The expressive power of log-depth transformers, 2025.

Attention-based representations for multi-task computation A little depth goes a long way: The expressive power of log-depth transformers, 2025

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.317980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d75c8df-a37a-42e2-8d8a-d4781998d7e0 · outbound

This paper cites MIT Press, 1969.

Attention-based representations for multi-task computation MIT Press, 1969

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.073725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 24014eb0-7bb2-4264-8ee1-3be0cf195f86 · outbound

This paper cites On extremalh-basesA 4.Mathematica Scandinavica, pages 5–16, 1987.

Attention-based representations for multi-task computation On extremalh-basesA 4.Mathematica Scandinavica, pages 5–16, 1987

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.060522Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 498004a0-0b53-4e41-aa13-dd2a21b536ff · outbound

This paper cites Parikh, Oscar T¨ ackstr¨ om, Dipanjan Das, and Jakob Uszkoreit.

Attention-based representations for multi-task computation Parikh, Oscar T¨ ackstr¨ om, Dipanjan Das, and Jakob Uszkoreit

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.048792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d1fc906-9e41-496d-9e51-3b2d265a29ef · outbound

This paper cites On Limitations of the Transformer Architecture.

Attention-based representations for multi-task computation On Limitations of the Transformer Architecture

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.333110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d33e055e-3c73-4dd4-b5af-c34cfbdbbfa7 · outbound

This paper cites Representational Strengths and Limitations of Transformers.

Attention-based representations for multi-task computation Representational Strengths and Limitations of Transformers

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.336902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 051c6149-ca24-471d-b529-490d31c9ce77 · outbound

This paper cites One-layer transformers fail to solve the induction heads task.

Attention-based representations for multi-task computation One-layer transformers fail to solve the induction heads task

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.340892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48531fbb-2db5-48df-81aa-e580a0e89e06 · outbound

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

Attention-based representations for multi-task computation Transformers, parallel computation, and logarithmic depth

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.344801Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3572037c-6138-493a-9579-9af6931d4231 · outbound

This paper cites Michael Steele.

Attention-based representations for multi-task computation Michael Steele

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.036272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1bc22d14-85ab-4ab8-9226-780acbecdcd3 · outbound

This paper cites Two (narrow) heads are better than (an arbitrarily wide) one.

Attention-based representations for multi-task computation Two (narrow) heads are better than (an arbitrarily wide) one

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.023694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d4d4992b-038f-4689-84bd-dee00bacecc8 · outbound

This paper cites Provable Meta-Learning of Linear Representations.

Attention-based representations for multi-task computation Provable Meta-Learning of Linear Representations

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-08-08T00:18:21.606190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8fd733dc-924f-484b-93c3-d12b024079b5 · outbound

This paper cites Attention Is All You Need.

Attention-based representations for multi-task computation Attention Is All You Need

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.360698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2408cfa7-0502-41ae-b245-066f891eae5c · outbound

This paper cites How many attention heads do you need to do XOR? Less- Wrong, April 2026.

Attention-based representations for multi-task computation How many attention heads do you need to do XOR? Less- Wrong, April 2026

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:22.010506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5d9b7bb5-d0d6-46f8-abba-e9f5e21e4e7f · outbound

This paper cites The effect of attention head count on transformer approximation, 2025.

Attention-based representations for multi-task computation The effect of attention head count on transformer approximation, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.368013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27bcb3fe-850e-417f-ba15-f50b2327d058 · outbound

This paper cites On model selection consistency of Lasso.Journal of Machine Learning Research, 7(90):2541–2563, 2006.

Attention-based representations for multi-task computation On model selection consistency of Lasso.Journal of Machine Learning Research, 7(90):2541–2563, 2006

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:21.996759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e66ea80-6457-42b4-a9a8-0a56c692998e · outbound

This paper cites The minimum isx, so MX i=1 hi∆x,y i >0.

Attention-based representations for multi-task computation The minimum isx, so MX i=1 hi∆x,y i >0

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:21.984579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3049d316-95d1-4bbb-99a4-76cc3c1f9525 · outbound

This paper cites The minimum isy, so MX i=1 hi∆x,y i <0.

Attention-based representations for multi-task computation The minimum isy, so MX i=1 hi∆x,y i <0

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:21.969906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 671be709-4fd8-4075-93f0-72aa06b3852b · outbound

This paper cites The minimum is x, so MX i=1 hi∆x,y i >0.

Attention-based representations for multi-task computation The minimum is x, so MX i=1 hi∆x,y i >0

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-08T00:18:21.957041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 28a3a314-70e2-4275-85c7-7c5200590df7 · outbound

This paper cites The minimum is y, so MX i=1 hi∆x,y i <0.

Attention-based representations for multi-task computation The minimum is y, so MX i=1 hi∆x,y i <0

Reference 36

Resolution: malformed identifier; raw_fallback, observed 2026-08-08T00:18:21.944419Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2b3d7df0-27b4-4bd4-bce4-d824ce19a4e0 · outbound

This paper cites Theoretical limitations of multi-layer Transformer.

Attention-based representations for multi-task computation Theoretical limitations of multi-layer Transformer

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-08T00:18:21.263783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.