Pith. sign in

Paper Citation Record · LEDGER

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism

As of 23 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 5 inbound Pith citation observations for arXiv:2504.18574.

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

pith.paper-citation-record.v1
2504.18574 v2

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:17:29.515104Z

measured 64 of 64 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T17:30:38.577174Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

59 of 59 outbound references displayed

  • verified exact3
  • verified fuzzy0
  • unresolved56
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 274a52b5-f4cc-4f27-b320-cc63084eee6d · outbound

This paper cites The Hidden Attention of Mamba Models.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism The Hidden Attention of Mamba Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.295806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.295806Z digest=sha256:50deac2e380e817231bf0b53aa9e12586c1774024319a8fdba9cbd2e8b70dc89

Observation 7d2fff4b-062f-4cdd-a428-2e2513130e46 · outbound

This paper cites When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.300022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.300022Z digest=sha256:c6a1fb25dd2269d59e0a86342d84bdf5342b8e9695f62e759722b9af4b18bd81

Observation b666e331-f25f-49c8-9208-a5221cf749c6 · outbound

This paper cites Mechanistic evaluation of transformers and state space models, 2025 a.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Mechanistic evaluation of transformers and state space models, 2025 a

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.303574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.303574Z digest=sha256:932ac6fdd4f9b1a5122328ecb5289edf186b419ccbeec38ae804529058a9441e

Observation d41bb165-ff5c-48e7-9d05-3b85cd96a74f · outbound

This paper cites Zoology: Measuring and Improving Recall in Efficient Language Models.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Zoology: Measuring and Improving Recall in Efficient Language Models

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.306947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.306947Z digest=sha256:bdd353e4d14c80ce0261b2b9eb24902b0c91899ef9880712f682534a9ca3ceda

Observation 01585eda-4b05-43e7-bb3e-3d6d43edd98e · outbound

This paper cites Simple linear attention language models balance the recall-throughput tradeoff.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Simple linear attention language models balance the recall-throughput tradeoff

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.315441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.315441Z digest=sha256:ae218aaa5b55be6c3e0ab38abe5d731e46f4a782b7ba8f3ff5891b1bf070345d

Observation 1804bb02-b76c-4348-8f7d-1e16cacd1f85 · outbound

This paper cites xLSTM: Extended Long Short-Term Memory.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism xLSTM: Extended Long Short-Term Memory

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.319162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.319162Z digest=sha256:fe943659756a5a29b1fe651ea92fd6c07d795d0b8d204d8c29fc81e613d3d611

Observation 3b037c10-b04a-4383-bcaf-5b010195f3aa · outbound

This paper cites Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.322787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.322787Z digest=sha256:c188bc5301d380ec4320becd155ddfca71f459ba92771dc17430f0ed9ece7494

Observation a9cda434-3e22-4b3e-baa3-d41ef015c255 · outbound

This paper cites Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Llamba: Scaling Distilled Recurrent Models for Efficient Language Processing

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.326487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.326487Z digest=sha256:8f87319307e6339ce0e3cb85219520db7393c0ded39702ca65fe0d603708583b

Observation bb9f5de3-db57-4976-a76f-e3a588558437 · outbound

This paper cites Birth of a Transformer: A Memory Viewpoint.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Birth of a Transformer: A Memory Viewpoint

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.330379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.330379Z digest=sha256:88f0e4f265871957b1369badab4d35adf9a7e1a3b1cad8f54e6f379ec5742689

Observation 9730cd56-2844-4735-9371-546c67fafe69 · outbound

This paper cites PIQA: Reasoning about Physical Commonsense in Natural Language.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism PIQA: Reasoning about Physical Commonsense in Natural Language

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.334021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.334021Z digest=sha256:0cdd0d6137879f087a5a3d951fb44627f733620996762cea94086ed6d5ee7508

Observation 8ec5a5ff-9357-4c18-a64d-6bc18268c724 · outbound

This paper cites Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Birdie: Advancing State Space Models with Reward-Driven Objectives and Curricula

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-08-16T11:17:30.064577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-16T11:17:29.337937Z digest=sha256:7de494b2a629514de27004eebaff1f840730e80b3470a18f7ba5cdfe8a112741

Observation 3502beab-7a98-4194-addd-39f3762c78fe · outbound

This paper cites an unresolved cited work.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.341330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.341330Z digest=sha256:3e13a04723ca1e3e04e8708088389fa53fe4a8fb95288b990a917487bef60ed7

Observation 96e205e6-4659-49a8-a8d9-e49f5245c41e · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.344694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.344694Z digest=sha256:089a2c98845415325d299703f6be9d4f7c7c3a667206c00d5b8ff0017309d96d

Observation a5bf5498-3ddb-40e4-9fdb-fa901b9fe2a9 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Training Verifiers to Solve Math Word Problems

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.348342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.348342Z digest=sha256:c8af156670c62cc511d7bbb6cb6578b9a98015d9c93237669a3dfbc1888019b2

Observation 744e73f7-9c1a-4ec1-9da9-8714e7c3a710 · outbound

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

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Transformers are SSM s: Generalized models and efficient algorithms through structured state space duality

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.351643Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.351643Z digest=sha256:260dfce9cfeb74c33a2bb54e600855f2cac84f114b2a662fb25927a01850c440

Observation da806b24-1e2b-431d-a2ce-f6a7f2776a1f · outbound

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

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Fu, Stefano Ermon, Atri Rudra, and Christopher Ré

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.355258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.355258Z digest=sha256:8d564337cdd35babae8c4bcd25fec28836acf8cee25e57877ba19e9e0391761d

Observation fcd4ac40-a716-4156-ab3b-35bf9993ba1a · outbound

This paper cites A mathematical framework for transformer circuits.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism A mathematical framework for transformer circuits

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.359076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.359076Z digest=sha256:a5a0f93d002522facc768ecb9455e5db54bd5486f06396f9bf5ff6cb2f81a56c

Observation 10a14136-eb73-42ac-b0b6-5ec193d430d9 · outbound

This paper cites Zamba: A Compact 7B SSM Hybrid Model.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Zamba: A Compact 7B SSM Hybrid Model

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.362835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.362835Z digest=sha256:a4f10df358089ad34d83306bcb8db2a5c803849cca5042a72d76b4ed989e3415

Observation c8e870a0-cd04-4019-a531-9c20e79314f6 · outbound

This paper cites Mamba: Linear-time sequence modeling with selective state spaces, 2023.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Mamba: Linear-time sequence modeling with selective state spaces, 2023

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.367022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.367022Z digest=sha256:d58b3f75edcd4d21d131ac67bdf13ab8f39346f5f4c8b54defa1f89d6b252b88

Observation 3f9b9675-8931-4413-b25a-4649e675405f · outbound

This paper cites Efficiently modeling long sequences with structured state spaces, 2022.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Efficiently modeling long sequences with structured state spaces, 2022

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.371225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.371225Z digest=sha256:e1c8d36f279589286b61be8f428d5ab38f55b53355044a242958a95acb376940

Observation 150d10dc-1f9c-4921-8901-a9e7266ee834 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Measuring Massive Multitask Language Understanding

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.374594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.374594Z digest=sha256:37cae294d65b18cf5b6827668168d63a794d8599784ff40468c0839545db080a

Observation 7a702ef9-59fd-4ab9-8a5e-043aaf4b9cf7 · outbound

This paper cites Repeat After Me: Transformers are Better than State Space Models at Copying.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Repeat After Me: Transformers are Better than State Space Models at Copying

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.378407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.378407Z digest=sha256:bcecc6c6ae06508ff979ea19985ef45b58751957faf1a450b59127852fce7108

Observation 8709d941-d0bc-462e-bbbe-1b5145547611 · outbound

This paper cites Transformers are rnns: Fast autoregressive transformers with linear attention, 2020.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Transformers are rnns: Fast autoregressive transformers with linear attention, 2020

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.382464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.382464Z digest=sha256:818d7d8ebcc30d4f14c9d084acf7564e86bc5d4c8f44d7af7a840dc1f234305f

Observation 89050351-a3f5-4dbb-b6ed-ebb16fd4cbd1 · outbound

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

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Jamba: A Hybrid Transformer-Mamba Language Model

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.386346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.386346Z digest=sha256:e9c499785326d8e781bbd8e9357d81232f7c5b261b91e048bb65531ce1cb70cf

Observation 5039dc44-df64-4767-924d-9c56d0af465f · outbound

This paper cites Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.390998Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.390998Z digest=sha256:a00e6d6864752ee58febb4facc3f551c4f1f5e6de4b3bdaf2628e962201e577a

Observation 92c9c5ad-eaf8-4230-9c11-beda352f8b6b · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Locating and Editing Factual Associations in GPT

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.395086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.395086Z digest=sha256:67dbd95140294ef2b67cb38bb1025f1d7f5f8e77fe2b160d909f646bbe9a48ab

Observation d55e0c77-2750-4a82-95f9-35389b92589e · outbound

This paper cites Circuit Component Reuse Across Tasks in Transformer Language Models.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Circuit Component Reuse Across Tasks in Transformer Language Models

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.398705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.398705Z digest=sha256:a5477b2522598ac61e93906652389729f8234aab495cc73622c4e09d61979bcd

Observation 272e3181-1500-431b-afbe-28ecfdf07694 · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.402258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.402258Z digest=sha256:43722671bb2fc620929d477fc174e682c262ccd7090f669f7867580dbb5dd4e9

Observation 13551029-cb68-4e3a-8884-37301cc25a03 · outbound

This paper cites In-context learning and induction heads.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism In-context learning and induction heads

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.405455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.405455Z digest=sha256:ff89fe5310fb03132d0b5b6b4ae1825f536a43b7f3d07dfbcfbf138880fb5491

Observation 14b2d967-86ca-482a-8588-c171cb2ac7b5 · outbound

This paper cites Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.408368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.408368Z digest=sha256:4c6df877e3e444c2e22b7e642f3bf457defc769f1cdc0010d171e8373c4e96ce

Observation 1cb266be-81ed-4731-baba-7ca80fb820a8 · outbound

This paper cites The LAMBADA dataset: Word prediction requiring a broad discourse context.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism The LAMBADA dataset: Word prediction requiring a broad discourse context

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.411637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.411637Z digest=sha256:b764ac3b302d9494d35d78193f76592176dcd064ed114f4f43bddef4a7ecde70

Observation e985821e-a63f-4754-8409-d1daebb4f7f7 · outbound

This paper cites Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.414642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.414642Z digest=sha256:a637a6b93f278b4300891bed3cbbfce68de8b994e84399248a1f8a5afa14afab

Observation 8cdeace5-8556-49aa-ae63-1819ddec647f · outbound

This paper cites Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.418206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.418206Z digest=sha256:ef5c4c59d79b3407399f93b8e96a66d87ccb1aaa94b25c52ab75ad21d3432ae2

Observation 4d21a790-bd48-41cf-b027-ef278a9b576c · outbound

This paper cites HGRN2: Gated Linear RNNs with State Expansion.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism HGRN2: Gated Linear RNNs with State Expansion

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.421987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.421987Z digest=sha256:da5d51665fbfa49d0324986cebf831d8ee20cbd93b9cf89a970a52b5e322e4a8

Observation 309d24b4-ec97-457d-ac06-2d4c7ac28cc6 · outbound

This paper cites A practical review of mechanistic interpretability for transformer-based language models, 2024.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism A practical review of mechanistic interpretability for transformer-based language models, 2024

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.425571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.425571Z digest=sha256:55f1ef8f5b6fa27cda47fc9ef4e23661847c8b0d387f09db72325d8e9da2e6d6

Observation a767c654-e658-4110-bf3e-973bc512b0e8 · outbound

This paper cites Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.429018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.429018Z digest=sha256:7135e22340372ebc8e07370dc45bec2cb56819f4452badb354a0d370b67c5f15

Observation 54a302ed-90c5-47a9-91e7-6732c6c3f12e · outbound

This paper cites WinoGrande: An Adversarial Winograd Schema Challenge at Scale.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.432533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.432533Z digest=sha256:5a31cf2b5e209f297d4c63d467536b699587fc8d08a694bd644226f59069c92c

Observation 576e2fc0-aff7-4a2c-bcf6-9198e6a7b761 · outbound

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

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Transformers, parallel computation, and logarithmic depth

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.436416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.436416Z digest=sha256:2e375b828123999cedadcdb40bc658126ff11fcffb436e658a1364ad3102f3f8

Observation a59fe66d-339a-4412-a348-052b24b086a7 · outbound

This paper cites Retentive network: A successor to transformer for large language models, 2023.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Retentive network: A successor to transformer for large language models, 2023

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.439957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.439957Z digest=sha256:c7826e61e117dbb44c725238444772a029bf32da27a0a71a2d873329dfef39a4

Observation 7d90395e-ccc4-4a76-8e28-8fe87d62527f · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.443099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.443099Z digest=sha256:73c3ad556177d21391a6a928dee14906e5d6ba08d95ecf2a9f8572f6fbac5a67

Observation e55de9c9-63b3-4138-90dd-1bc97dd45e81 · outbound

This paper cites Llama: Open and efficient foundation language models, 2023.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Llama: Open and efficient foundation language models, 2023

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.446919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.446919Z digest=sha256:b3a201ab0d6acfd02c2653139657d00d126c843ce9ead43d9b460bbec7d1787b

Observation d5b9033d-6cbd-444f-ba87-6c1c2e4de0ff · outbound

This paper cites Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA

Reference 43

Resolution
verified exact
local_arxiv, observed 2026-08-16T11:17:29.742040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-16T11:17:29.450372Z digest=sha256:5342b27536d8041ccba925d41f7e8bf2e3bbfdce7f71d764c4f2f771e7dc49f0

Observation 260af610-8f60-4ffe-9c91-3d43bc2ee660 · outbound

This paper cites Attention Is All You Need.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Attention Is All You Need

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.454033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.454033Z digest=sha256:02b0e4531bbb6d7d5a0c7f123eb60495b9d781d999620457c0cfe524ade57f3e

Observation 23bb924a-024d-4f07-8254-54f94deebba0 · outbound

This paper cites An Empirical Study of Mamba-based Language Models.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism An Empirical Study of Mamba-based Language Models

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.458181Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.458181Z digest=sha256:ab5dad753daba9d4ea99c23d473fd1d67c0fb747066e14f297e751c44f63b991

Observation 511afae0-6ff4-42ec-970a-91afea4f5ebb · outbound

This paper cites The Mamba in the Llama: Distilling and Accelerating Hybrid Models.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism The Mamba in the Llama: Distilling and Accelerating Hybrid Models

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.462648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.462648Z digest=sha256:6c924427c3a84a14cc49cd95cb34eb3689a8971dedca08d6fe663ae173d18d6e

Observation b9f1a7b3-a9f0-4d1c-b7fc-359b5afeb85d · outbound

This paper cites MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models

Reference 47

Resolution
verified exact
local_arxiv, observed 2026-08-16T11:17:29.691720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-08-16T11:17:29.467461Z digest=sha256:0726b7d5ff38761baa9319a9c3cb912c559730327ee69bce1eb0ba9a1deb9d20

Observation 39b407cc-ab66-4f00-a548-a13453cae3de · outbound

This paper cites RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.471464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.471464Z digest=sha256:745f5bd053980d979b58a7d47b341f24760a290f70839a63fbe3b7e999a38fc8

Observation 4b30a852-609b-4be9-bbbe-f3dbd6d1c326 · outbound

This paper cites Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.475182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.475182Z digest=sha256:6153745ae1c0cf74b7595af59d7f002478e140c42deb9e1305e1cee6ec9521f7

Observation 43524d81-0b94-4a4e-aba6-91c87d1ec87a · outbound

This paper cites Retrieval Head Mechanistically Explains Long-Context Factuality.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Retrieval Head Mechanistically Explains Long-Context Factuality

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.479315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.479315Z digest=sha256:ebf35fedea55526aac684fbd4cda3f37b99ccbddac5fbfc1f80c8e7d81eb335d

Observation 425565dc-4037-4428-81ce-c65b6f62879e · outbound

This paper cites Efficient Streaming Language Models with Attention Sinks.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Efficient Streaming Language Models with Attention Sinks

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.483033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.483033Z digest=sha256:c8f780eca4d7b5df46bbbd34af16c75940d80825cbdcb40aa15c5e752fae3aed

Observation 5803b803-8937-49bf-906e-a81c2f8ca904 · outbound

This paper cites Gated Delta Networks: Improving Mamba2 with Delta Rule.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Gated Delta Networks: Improving Mamba2 with Delta Rule

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.486888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.486888Z digest=sha256:0c7f8dbe0ebc6e0df5d8e2308d2df04c6e27c83bd22cc30ee0e68bf0978475d8

Observation a4576f78-e72a-476c-bc71-bb618f6d934e · outbound

This paper cites Gated Linear Attention Transformers with Hardware-Efficient Training.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Gated Linear Attention Transformers with Hardware-Efficient Training

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.490837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.490837Z digest=sha256:30cbc2e101d43317874132a44a7c55d1699c019a87fc7ff1c60b16678e2985dd

Observation e43a8ad6-406a-4160-95dc-3cbbb53f5723 · outbound

This paper cites Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Correcting Negative Bias in Large Language Models through Negative Attention Score Alignment

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.495021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.495021Z digest=sha256:e9a0cbc718593dc893c40a7ad9906a5fb134738f83e37750f2b38a680fba2828

Observation dbf7df7c-5f16-4f6f-8d73-c9f47576db85 · outbound

This paper cites HellaSwag: Can a Machine Really Finish Your Sentence?.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism HellaSwag: Can a Machine Really Finish Your Sentence?

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.498938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.498938Z digest=sha256:156f335354510f2660f4da5fd5a5dd34949c1e4dff8d46e392c8b2d25218fa6f

Observation 5dc4a025-f1db-42ec-b9fb-9344fe09943f · outbound

This paper cites Interpreting and Improving Large Language Models in Arithmetic Calculation.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Interpreting and Improving Large Language Models in Arithmetic Calculation

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.502413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.502413Z digest=sha256:e50695216a23f765cf6067e59dc5667b2790218a0841dc16e47e4993a9cb9306

Observation 9f559450-79c0-4d51-966e-88afdb56db99 · outbound

This paper cites Gated Slot Attention for Efficient Linear-Time Sequence Modeling.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Gated Slot Attention for Efficient Linear-Time Sequence Modeling

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.505442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.505442Z digest=sha256:fc176e1655c9e5d51dc0b77b43708a1af9048e3237e7e2633d8f300ec47c15c6

Observation 90a15906-3214-4ead-8b2e-11f4b91575ee · outbound

This paper cites MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.508961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.508961Z digest=sha256:ff7e17ab194585383a18fdeb7153392a75cade5d4074142ff749c13af966080a

Observation 9de26958-c816-4d57-b280-0b822bb2f4e1 · outbound

This paper cites Attention Heads of Large Language Models: A Survey.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Attention Heads of Large Language Models: A Survey

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.511968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.511968Z digest=sha256:71f51c0991f9679b20bdb53d8637b29d2efdd6c5139ca01bddec88343a52e296

Observation 88514441-b42c-40be-ad71-e1e88c5357c2 · outbound

This paper cites Falcon Mamba: The First Competitive Attention-free 7B Language Model.

Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism Falcon Mamba: The First Competitive Attention-free 7B Language Model

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-16T11:17:29.515104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-16T11:17:29.515104Z digest=sha256:b1ce3dc7a1a9fe5bd2706493ef3fdaf661892cb3ec7bdcb6b56415ba9a68c9e2

Pith citing papers

Observation 9be4a302-3ad6-45b8-9115-0375c1548f6d · inbound

StateX: Enhancing RNN Recall via Post-training State Expansion cites this paper.

StateX: Enhancing RNN Recall via Post-training State Expansion Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-18T12:31:22.216543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-05-18T12:27:06.616920Z digest=sha256:6b3b66ec8cbafb7f1729b15835b769f921cdd4291e84e8f2e9e4dfb73abae53b

Observation 9e002fa0-4ba4-41eb-81f2-3ce0023e323a · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism

Reference 65

Resolution
metadata mismatch
arxiv_id, observed 2026-06-28T23:32:46.643099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-06-28T23:29:02.457697Z digest=sha256:0d0ec9b0efe2e3c119f1a0a3a5ec3f69c1e7028d58daac58cd40b0af390678c6

Observation bbc9af6f-13c7-4df8-8590-670839cc1720 · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism

Reference 145

Resolution
metadata mismatch
arxiv_id, observed 2026-06-28T23:32:47.282671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=arxiv_source observed=2026-06-28T23:29:02.457697Z digest=sha256:c53a167d41bca2505e92302de722c459373bb373faba06f60c927e51f5da89ae

Observation b0bd06ea-a2de-4bfd-a4af-56541dd20f4e · inbound

Blurry Window Attention cites this paper.

Blurry Window Attention Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism

Reference 11

Resolution
metadata mismatch
arxiv_id, observed 2026-07-01T20:46:13.976733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-06-28T17:43:34.429061Z digest=sha256:b2417c0911c858ab7cfef35779ec1fa31816439865d22f5f6a46160bb178918b

Observation 28064414-db61-4608-b76e-f90c9d093e90 · inbound

Mechanistic Attention Guidance for Agent Memory Refinement cites this paper.

Mechanistic Attention Guidance for Agent Memory Refinement Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T17:30:38.577174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T17:30:38.577174Z digest=sha256:51b2171d6e8b4c101d848a6879aac21cba28efece8f9f638df0f8059b947925e