Paper Citation Record · LEDGER

Emergent Specialization: Rare Token Neurons in Language Models

As of 20 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2505.12822.

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

pith.paper-citation-record.v1
2505.12822 v2

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:30:15.403215Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:29:35.724196Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T13:29:36.389729Z

Reference resolution

41 of 41 outbound references displayed

verified exact0
verified fuzzy12
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b64595a8-83a6-4cf5-b611-2fdf2ce0147e · outbound

This paper cites Bahri, J.

Emergent Specialization: Rare Token Neurons in Language Models Bahri, J

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.901456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 08adb939-5427-4491-aaa8-9ad2a926acb0 · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.890525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e2d04baf-8d43-4a93-b8a5-ee0b7934efad · outbound

This paper cites Biderman, H.

Emergent Specialization: Rare Token Neurons in Language Models Biderman, H

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.240995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c410c892-3494-463e-a0ca-e20f4de88acc · outbound

This paper cites Bohacek and H.

Emergent Specialization: Rare Token Neurons in Language Models Bohacek and H

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.871430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f7e92ece-87fd-4ffe-a74c-3d74d773a391 · outbound

This paper cites Borgeaud, A.

Emergent Specialization: Rare Token Neurons in Language Models Borgeaud, A

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.859844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 59e6b7de-ff76-411c-8ffb-b0c94f4c3afe · outbound

This paper cites On the structure and spectra of an induced subgraph of essential ideal graph of $\mathbb{Z}_{n}$.

Emergent Specialization: Rare Token Neurons in Language Models On the structure and spectra of an induced subgraph of essential ideal graph of $\mathbb{Z}_{n}$

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.254316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93661526-cc7c-4fc0-b811-2bdbb302a2a8 · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.846118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 17e9e6c0-3145-463b-b355-8a1e31c63a5f · outbound

This paper cites Carey and E.

Emergent Specialization: Rare Token Neurons in Language Models Carey and E

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.834179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1c64187b-9f4c-4f66-b850-ad3760310894 · outbound

This paper cites Couillet and Z.

Emergent Specialization: Rare Token Neurons in Language Models Couillet and Z

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.819906Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 38d3d307-127e-4e37-a754-874103a3fc76 · outbound

This paper cites A Tale of Tails: Model Collapse as a Change of Scaling Laws.

Emergent Specialization: Rare Token Neurons in Language Models A Tale of Tails: Model Collapse as a Change of Scaling Laws

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.272677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef2393fe-8f49-465a-9ab1-9b46c5d218bf · outbound

This paper cites A Survey on In-context Learning.

Emergent Specialization: Rare Token Neurons in Language Models A Survey on In-context Learning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.277783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffc3c2c3-2a38-45b3-b24f-280cf1c7a31a · outbound

This paper cites Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models.

Emergent Specialization: Rare Token Neurons in Language Models Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.282517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2140e357-6526-4305-9748-05729d19cc7b · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Emergent Specialization: Rare Token Neurons in Language Models The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.286830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41431003-4af2-4675-912a-b5fa5f3a99f9 · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Emergent Specialization: Rare Token Neurons in Language Models Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.290065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54106ddc-d9b7-4371-be7b-b85614e5d221 · outbound

This paper cites Hataya, H.

Emergent Specialization: Rare Token Neurons in Language Models Hataya, H

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.808427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation baed0247-bcb7-4a31-a9bf-761cd73fd40e · outbound

This paper cites Training Compute-Optimal Large Language Models.

Emergent Specialization: Rare Token Neurons in Language Models Training Compute-Optimal Large Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.297170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 945b839c-7125-4149-89fa-37ae83f695f3 · outbound

This paper cites Kandpal, H.

Emergent Specialization: Rare Token Neurons in Language Models Kandpal, H

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.796887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5e448274-43b0-4a2d-848a-141bb22f3f02 · outbound

This paper cites Kumaran, D.

Emergent Specialization: Rare Token Neurons in Language Models Kumaran, D

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.306338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 081741bb-d302-4404-9f22-c72d1cde6d25 · outbound

This paper cites Lewis, E.

Emergent Specialization: Rare Token Neurons in Language Models Lewis, E

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.776509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 042cba02-f01e-486c-8c14-f978e1b97f28 · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.763029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4a2956e7-6472-437a-85fe-f9e531e71be1 · outbound

This paper cites CNN photometric redshifts in the SDSS at $r\leq 20$.

Emergent Specialization: Rare Token Neurons in Language Models CNN photometric redshifts in the SDSS at $r\leq 20$

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.319433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c475d35a-2cb1-4209-b668-a8c05ddfcda6 · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.749851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5cdc89ca-b64f-4bec-b3cd-b1d43491b4bb · outbound

This paper cites Markson and P.

Emergent Specialization: Rare Token Neurons in Language Models Markson and P

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.738421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c50bfb35-7bae-4ca1-b597-605d40208adb · outbound

This paper cites Traditional and Heavy-Tailed Self Regularization in Neural Network Models.

Emergent Specialization: Rare Token Neurons in Language Models Traditional and Heavy-Tailed Self Regularization in Neural Network Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.331992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46cd59e-1308-457a-9282-ea612ac16637 · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.726902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation eca733e0-d9a1-4558-af19-e2d31a380eca · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.340954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da1239a5-cc6d-469b-935d-48a9a982a4ba · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.345575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c2c42c0-16ec-4b9d-ba70-e87256df389b · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.697197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3a239448-10d3-42a9-9e5e-41ad173eeef3 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

Emergent Specialization: Rare Token Neurons in Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.354679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55a8c622-b1b8-44cf-9e79-3300aa26d060 · outbound

This paper cites The Geometry of Categorical and Hierarchical Concepts in Large Language Models.

Emergent Specialization: Rare Token Neurons in Language Models The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.358014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41215a67-70b6-488f-a671-7750553460d5 · outbound

This paper cites Raffel, N.

Emergent Specialization: Rare Token Neurons in Language Models Raffel, N

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.361956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cdaa8bd-0815-4114-b6b0-93736744308c · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.677053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation faa2d8c2-f628-412e-a30c-55c7cd909bde · outbound

This paper cites Stolfo, B.

Emergent Specialization: Rare Token Neurons in Language Models Stolfo, B

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.666201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a886447b-b77a-4a11-ad45-50509252e5ee · outbound

This paper cites The information bottleneck method.

Emergent Specialization: Rare Token Neurons in Language Models The information bottleneck method

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.372862Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74f23490-f1ef-49e0-812e-ded80f7e94a8 · outbound

This paper cites Truong, L.

Emergent Specialization: Rare Token Neurons in Language Models Truong, L

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.654000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 84828b2d-5ef6-4513-bd74-89b1f5be4faf · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.641334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 995b23ce-855e-4513-90a0-978e5da57139 · outbound

This paper cites Emergent Abilities of Large Language Models.

Emergent Specialization: Rare Token Neurons in Language Models Emergent Abilities of Large Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:30:15.386576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d93d81ac-bb67-4b14-9517-b7af783cb71a · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.628995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 59cbd14f-2942-41ae-ac22-d8997a285b4a · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 39

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.616338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 23406cd5-0d22-4bff-8155-8177888e78b7 · outbound

This paper cites Zhang, G.

Emergent Specialization: Rare Token Neurons in Language Models Zhang, G

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:30:15.602723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4d30c2ac-8055-457f-8112-974dd4b688fd · outbound

This paper cites an unresolved cited work.

Emergent Specialization: Rare Token Neurons in Language Models Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:30:15.589026Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 76e057d5-34a7-48f8-9cf5-b4904f8c28f3 · inbound

No Clustering, No Routing: How Transformers Actually Process Rare Tokens cites this paper.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Emergent Specialization: Rare Token Neurons in Language Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-05T13:29:36.472441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.