Pith. sign in

Paper Citation Record · LEDGER

No Clustering, No Routing: How Transformers Actually Process Rare Tokens

As of 19 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2509.04479.

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

pith.paper-citation-record.v1
2509.04479 v1

Coverage vector

measured 12 of 12 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T13:29:36.236463Z

measured 12 of 12 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+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

12 of 12 outbound references displayed

  • verified exact2
  • verified fuzzy4
  • unresolved6
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1e5b397c-39df-4e58-b040-920d95242c46 · outbound

This paper cites Akyürek, T.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Akyürek, T

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T13:29:38.082527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:34.880468Z digest=sha256:728746f6cfa6f1af9f50b8a0f03ce92257809f63965c4cbfa383be3ece9e67e1

Observation ba08e818-14cc-42ee-bcc9-4f18ef73c35c · outbound

This paper cites an unresolved cited work.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Unresolved cited work

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-05T13:29:34.964536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T13:29:34.964536Z digest=sha256:9243cb1d199a9676f9202e25d49a43b658e065219953328c8b41a049720745ce

Observation 58553521-2c1a-4322-8e9e-dd9c761f114b · outbound

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

No Clustering, No Routing: How Transformers Actually Process Rare Tokens On the structure and spectra of an induced subgraph of essential ideal graph of $\mathbb{Z}_{n}$

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-08-05T13:29:36.662831Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:35.149606Z digest=sha256:cf9397cc072bc7c6c12ea5ac3ce983e2af37e900f523c6e01f37f25b6176d633

Observation 63efb657-ea0c-490a-aa74-bac050a74b7e · outbound

This paper cites an unresolved cited work.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-05T13:29:37.921290Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:35.318939Z digest=sha256:1176efc3b93fdcafd141772c86665dab52bb51f1c88ffe612d0fce29c41274b7

Observation c666d641-935a-4342-ad57-fb2bba14d23f · outbound

This paper cites Kandpal, H.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Kandpal, H

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T13:29:37.725382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:35.556543Z digest=sha256:fa716cf9f42f9a5468f460f3c6625c01466e5d8a929b3a5fdc9fe5fa0b8f62ce

Observation fda96ac1-79d6-4d91-8d7d-139574802e15 · outbound

This paper cites Kumaran, D.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Kumaran, D

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T13:29:37.491611Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:35.646738Z digest=sha256:ebd43399dc149a2baf283c1bf6679a087a479a02add4708e096592c88b4759ff

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

This paper cites Emergent Specialization: Rare Token Neurons in Language Models.

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 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:35.724196Z digest=sha256:8a689f61ef000c00b95050d5836f1071a1873899dbca60d097303d9466cce05e

Observation 8b9ffbac-5432-4c83-a7dd-4ce186a150f7 · outbound

This paper cites an unresolved cited work.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Unresolved cited work

Reference 8

Resolution
unresolved
raw_fallback, observed 2026-08-05T13:29:37.280814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:35.820810Z digest=sha256:d0e8ac32d3f2ec215b18b3ac0c487736eb5e8e458fe635ee8e8e914dd8cf6b48

Observation dd2bc837-65c4-4a21-8ef9-e45a33477acc · outbound

This paper cites an unresolved cited work.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Unresolved cited work

Reference 9

Resolution
unresolved
raw_fallback, observed 2026-08-05T13:29:37.090355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:35.901132Z digest=sha256:1b3d339df7f84ce950163c7492189788c179cd24720a0eb03549ed9d9391b4c7

Observation 9e5902b3-3bc6-49ae-9e20-e67616e2b951 · outbound

This paper cites Raffel, N.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Raffel, N

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-05T13:29:36.009078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T13:29:36.009078Z digest=sha256:e8b2d613cfea603dded3db60851fac55ea6292d48861654c04714094fb3eb35f

Observation e535f2ce-7748-4191-b353-87f155ef5c76 · outbound

This paper cites Shazeer, A.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens Shazeer, A

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T13:29:36.879129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

source=pdf_text observed=2026-08-05T13:29:36.121083Z digest=sha256:de89a70922c59d1c63738c0f9ad203a7d887804c9e3049fe8ec3d7b5e5420898

Observation 116e1614-ea4b-4b4a-aec9-bd00c8b5c1d2 · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

No Clustering, No Routing: How Transformers Actually Process Rare Tokens The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-05T13:29:36.236463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T13:29:36.236463Z digest=sha256:9723c7ffb2f245d29bdd4d3ce63cfc4f74f0caa3f14005da134ee6b3071f3b7e

Pith citing papers

No inbound Pith citation observations are available.