Paper Citation Record · LEDGER

Exploring How LLMs Capture and Represent Domain-Specific Knowledge

As of 22 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 2 inbound Pith citation observations for arXiv:2504.16871.

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

pith.paper-citation-record.v1
2504.16871 v2

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:59:05.164271Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:18:13.635975Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-07T13:18:14.702393Z

Reference resolution

13 of 13 outbound references displayed

verified exact0
verified fuzzy2
unresolved10
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3ddccd34-6868-4a3c-a659-e5368c8ee72d · outbound

This paper cites an unresolved cited work.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:59:05.333368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 94db83df-2752-42ec-af46-2e8dba200ac7 · outbound

This paper cites Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Semantic Routing for Enhanced Performance of LLM-Assisted Intent-Based 5G Core Network Management and Orchestration

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T10:59:05.121152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935f1b6f-3c1e-47bd-a6ca-1fa9c690dfcc · outbound

This paper cites an unresolved cited work.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:59:05.309254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation ebf5d5f7-3b3d-4966-957e-316904b5b4ed · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T10:59:05.129683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c936a222-8c86-42a4-aa93-cefc63527c4e · outbound

This paper cites an unresolved cited work.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:59:05.322372Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 7cd849cd-232d-4165-bf7e-99e6b92e96e4 · outbound

This paper cites In contrast with the behavior observed in smaller models, we can see that Llama model keeps capturing the nuances for the Finance and Law versions.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge In contrast with the behavior observed in smaller models, we can see that Llama model keeps capturing the nuances for the Finance and Law versions

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:59:05.295742Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 0d54d034-bacd-4573-82d1-9fb818131a5f · outbound

This paper cites an unresolved cited work.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:59:05.284240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 077bc05b-36d4-487b-9a69-96f9fbef96d5 · outbound

This paper cites an unresolved cited work.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:59:05.272737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 6e200ffe-ed94-4f17-8282-920f6a5b29c2 · outbound

This paper cites an unresolved cited work.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:59:05.260612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 45e04a70-0422-42ec-821a-a8737e313af1 · outbound

This paper cites Math and biomedicine rely heavily on structured, logical reasoning and problem-solving, leading to more precise, analytical neural activations.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Math and biomedicine rely heavily on structured, logical reasoning and problem-solving, leading to more precise, analytical neural activations

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:59:05.248142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation 2af8c56e-2769-45c2-bcc7-572af90dfbc6 · outbound

This paper cites When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset

Reference 2017

Resolution: malformed identifier; no resolver link, observed 2026-08-16T10:59:05.133607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4f6b99f-30ea-4a2c-8dd5-32f31b62ca77 · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Gemma: Open Models Based on Gemini Research and Technology

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T10:59:05.125432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6755c0b9-3cba-405b-beb4-fc6e998d9c6b · outbound

This paper cites Taxonomy-Guided Zero-Shot Recommendations with LLMs.

Exploring How LLMs Capture and Represent Domain-Specific Knowledge Taxonomy-Guided Zero-Shot Recommendations with LLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-16T10:59:05.116581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 81f196d0-8b2c-4f3e-8142-e37e3061c8a5 · inbound

ICH-Qwen: A Large Language Model Towards Chinese Intangible Cultural Heritage cites this paper.

ICH-Qwen: A Large Language Model Towards Chinese Intangible Cultural Heritage Exploring How LLMs Capture and Represent Domain-Specific Knowledge

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-08-07T13:18:14.736472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

Observation d4690593-8fe3-495f-bd2b-648a5044605c · inbound

Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes cites this paper.

Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes Exploring How LLMs Capture and Represent Domain-Specific Knowledge

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T07:49:37.353222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.