Pith. sign in

Paper Citation Record · LEDGER

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models

As of 11 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2501.06638.

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

pith.paper-citation-record.v1
2501.06638 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T21:00:06.114099Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-12T04:02:44.816347Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-12T06:41:42.304648Z

Reference resolution

16 of 16 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved16
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 61cd4451-aa5f-4b8b-ada2-8159d83ba974 · outbound

This paper cites URL: " 'urlintro :=.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models URL: " 'urlintro :=

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.053491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.053491Z digest=sha256:e288097b38dcf8db8ee02d59e5ee90f40c4e519bea04fcd895d5089c85f23d11

Observation 4deb7185-b6e6-4a9a-9bba-222631183ae6 · outbound

This paper cites write newline.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models write newline

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.060070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.060070Z digest=sha256:d1027a7ddcc3138d6664a9ed28c8840d47d759ebf43c809f20739602c677985c

Observation b27be441-5291-4264-9a40-d2ca072f106b · outbound

This paper cites an unresolved cited work.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Unresolved cited work

Reference 3

Resolution
unresolved
raw_fallback, observed 2026-08-10T21:00:06.250939Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-10T21:00:06.063633Z digest=sha256:b306246574c5e1dbcb4eebc4fa1b93070201e563fab8039d547208f05f8cb09e

Observation 816f5b5d-18db-4281-a78c-9d286fe76e30 · outbound

This paper cites Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.067386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.067386Z digest=sha256:9d22bec7fd6aa9967776dee8bd8e97cbea2382b3dc55d67b40bceee008109d44

Observation 361c73ba-52ce-4b54-ae89-74748530a17f · outbound

This paper cites Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.072817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.072817Z digest=sha256:5382d25460212771ee2312632212a68b47742d7624e020618482b489cd01ad69

Observation 9d3d92c6-a895-4673-a186-a724d3f6371c · outbound

This paper cites Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.076762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.076762Z digest=sha256:6434a783a4b7e0255d05374465d1b130ba262c9815f7bc731962c802330aaf03

Observation d781bd1a-6ebc-466a-8282-2958f3435e00 · outbound

This paper cites Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.080646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.080646Z digest=sha256:04e71ae408d5bf8b731dfd4746e209ad1ba709a666b660eccecc8c1febe83099

Observation 5b59fab6-d04a-42da-9416-bb9421248919 · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.084542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.084542Z digest=sha256:298dd90d17e74e3cf131c4cbf4d9f71ba07c4d75c32381fa07a48edd28d9d262

Observation 19467e86-28d0-4269-b2b8-34f07d53286f · outbound

This paper cites Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.088836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.088836Z digest=sha256:121a3ba1a4dcffd9ef5c51fa013424560ef28e70792b9bf38baf677e45681213

Observation 06fe5a20-583e-49e1-aaf8-15b19010fa5e · outbound

This paper cites an unresolved cited work.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.092757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.092757Z digest=sha256:c57889e3dc0839a55164a5f861dc2fa21793a9f7ea1ea819b046a34464c22d3e

Observation ab21334b-ec68-4026-83c6-e1ce660eab14 · outbound

This paper cites an unresolved cited work.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.096191Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.096191Z digest=sha256:2cfd2c5d5d2533ae29761b85c5ab86415b8affa274c6950b0847dda22f486d5b

Observation 88f97f2f-045f-4bbb-ab2e-b36e6cef28a9 · outbound

This paper cites DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.099644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.099644Z digest=sha256:86335823ae13ab4f0245021131267090910c20d8b71351ae533cfffc842e9727

Observation 4b166cfd-c23e-4014-9c8d-f67922540681 · outbound

This paper cites an unresolved cited work.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.103268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.103268Z digest=sha256:6817c90b35626e70cffd560bea32e7034e92bb3d4c368c553accda7e6ef604e4

Observation 64ad104d-0ac1-4bee-868b-f1776c47edf4 · outbound

This paper cites Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.106540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.106540Z digest=sha256:cc94b78d0ecf7dbc2db6b3d473b5e7aed668fda5cbe7fd4dd77f18d6e41e6727

Observation c924e2ff-7114-4ba5-8265-3f6858d133b4 · outbound

This paper cites an unresolved cited work.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Unresolved cited work

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-10T21:00:06.110719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-10T21:00:06.110719Z digest=sha256:3245961af8b287883f0ae897f8a3a2f22c75f52905979a9a1e425899f9c02d76

Observation 3fd08875-60d2-463c-8a80-a6a7e63bdb1e · outbound

This paper cites an unresolved cited work.

Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models Unresolved cited work

Reference 16

Resolution
unresolved
raw_fallback, observed 2026-08-10T21:00:06.228669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=arxiv_source observed=2026-08-10T21:00:06.114099Z digest=sha256:a14e86df8d3281f73cdcdfee0c234e376a5384999300c61cfb9ed83d74692ed7

Pith citing papers

Observation 88ecf12d-a0a4-42d6-a4c3-ed59aea366c5 · inbound

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing cites this paper.

Can You Keep a Secret? Involuntary Information Leakage in Language Model Writing Scaling Down Semantic Leakage: Investigating Associative Bias in Smaller Language Models

Reference 9

Resolution
verified exact
arxiv_id, observed 2026-05-12T06:41:42.314977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

source=pdf_text observed=2026-05-12T04:02:44.816347Z digest=sha256:e938a2c8e7f9c7b9f5f590d009cc274cebf395eab9bd1c5b6a2e3f94c7dba610