Pith. sign in

Paper Citation Record · LEDGER

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models

As of 19 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 0 inbound Pith citation observations for arXiv:2507.18171.

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

pith.paper-citation-record.v1
2507.18171 v1

Coverage vector

measured 10 of 10 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T14:45:02.189075Z

measured 10 of 10 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+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

10 of 10 outbound references displayed

  • verified exact1
  • verified fuzzy3
  • unresolved6
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 93c2cb32-ee96-4087-8980-de7787f3ac9e · outbound

This paper cites an unresolved cited work.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:45:02.674406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-06T14:45:02.126754Z digest=sha256:2a0fd35d7b3379bb1c3498c710dee091d5d2cfaa2ec7fb93cbd4b1bdece5baa8

Observation de328270-2144-466a-b8b6-7ea006925e87 · outbound

This paper cites an unresolved cited work.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models Unresolved cited work

Reference 2

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:45:02.645477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-06T14:45:02.145365Z digest=sha256:1b114f93d5944a552b099a6ed661f082293290f936ddc42b573e4a6038c5d6ff

Observation 339c00ec-367e-4867-a787-428f551800c8 · outbound

This paper cites an unresolved cited work.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-06T14:45:02.617956Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-06T14:45:02.154800Z digest=sha256:53565473128db81e9d0c1fa4a6859ff7177b5a19caa9b98bbf92c31774c09f88

Observation eff8f32f-4dfe-4a84-84a1-d928cd2aad2a · outbound

This paper cites fallbackbyte.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models fallbackbyte

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:45:02.581184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-06T14:45:02.161807Z digest=sha256:af6d276a2dd689d2e7483934f0820640c0ed85b787bb8214e99667b1a1d01f70

Observation e1fbb6f2-da7f-42e4-8ddf-b4b8e8e5c29c · outbound

This paper cites For each pair, oneofthesentencegetsinserted 13 withtoken tvia operationI.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models For each pair, oneofthesentencegetsinserted 13 withtoken tvia operationI

Reference 8

Resolution
verified exact
raw_fallback, observed 2026-08-06T14:45:02.380301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-06T14:45:02.170455Z digest=sha256:68139c60b803cd13a4fef2ff3f140465f52df9747ed63f6ea25dff2629018f43

Observation b249503d-03e1-4830-a3d7-bfd741e96bc5 · outbound

This paper cites 2)Normaltoken Variant: The original sentence inserted with a normaltokensrandomlyselectedfromthemodel’s vocabulary.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models 2)Normaltoken Variant: The original sentence inserted with a normaltokensrandomlyselectedfromthemodel’s vocabulary

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:45:02.543692Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-06T14:45:02.179311Z digest=sha256:b09e2cb3ced094453866e60ce89d66617626d6a97cf6534a507ffa2002f21867

Observation 21585e27-4012-4057-b7fb-d009b8a47590 · outbound

This paper cites howtoimprove mental health?.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models howtoimprove mental health?

Reference 1969

Resolution
verified fuzzy
raw_fallback, observed 2026-08-06T14:45:02.521378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

source=pdf_text observed=2026-08-06T14:45:02.189075Z digest=sha256:51f3906cd598d9d6218f4ef163cbb0f42a8a27de80b7147621ca0d2fa735e898

Observation c61cccbe-72e0-40a2-9df7-ddb1e4b06256 · outbound

This paper cites Neural Machine Translation of Rare Words with Subword Units.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models Neural Machine Translation of Rare Words with Subword Units

Reference 2016

Resolution
unresolved
no resolver link, observed 2026-08-06T14:45:02.109702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:45:02.109702Z digest=sha256:51bb5a18701e03d50e4eb0d304180c543a8bb7572c82416400b26cbd3df0036d

Observation cd3e1e40-762b-4cf9-b9b3-4fe99dc1c733 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 2019

Resolution
unresolved
no resolver link, observed 2026-08-06T14:45:02.098546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:45:02.098546Z digest=sha256:501f23b2648af178905ca89cb8cf7b7e94593d7a5fc37e8a8a2b790c2ce3863c

Observation d9233ad8-7692-4741-a5c5-958e4ea5d742 · outbound

This paper cites Matryoshka Representation Learning.

Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models Matryoshka Representation Learning

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-06T14:45:02.087913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-06T14:45:02.087913Z digest=sha256:cb567e908a1cf53bccd855e4daeff94085cb2fbadaa4aeffeeb1ac20bfc17a03

Pith citing papers

No inbound Pith citation observations are available.