Paper Citation Record · LEDGER

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA

As of 9 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2607.18725.

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

pith.paper-citation-record.v1
2607.18725 v1

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T14:35:02.200196Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+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

29 of 29 outbound references displayed

verified exact0
verified fuzzy0
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation cfb5f5cf-c373-4328-9452-5f56b60a118f · outbound

This paper cites Hallucinat- ing law: Legal mistakes with large language models are per- vasive.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Hallucinat- ing law: Legal mistakes with large language models are per- vasive

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.311156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d27b908a-7e51-4369-a1c2-cd2c7a223d8a · outbound

This paper cites Retrieval- augmented generation for knowledge-intensive nlp tasks,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Retrieval- augmented generation for knowledge-intensive nlp tasks,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.388262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 528513e8-7f59-4a70-bcbc-d5b1f037c789 · outbound

This paper cites Cyberbench: A multi-task benchmark for evaluating large language models in cybersecurity,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Cyberbench: A multi-task benchmark for evaluating large language models in cybersecurity,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.444639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7eaa887-da97-4f81-8840-be6d82f6ef63 · outbound

This paper cites Securebert: A domain- specific language model for cybersecurity,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Securebert: A domain- specific language model for cybersecurity,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.522426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 049a326f-44cd-4447-b444-daffeb01b8bf · outbound

This paper cites Generating fake cyber threat intelligence using transformer-based models,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Generating fake cyber threat intelligence using transformer-based models,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.598937Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39e9822c-417a-4411-886d-9fc1b5ab2ab0 · outbound

This paper cites Attention is all you need,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Attention is all you need,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.677755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71da1d47-b433-4e85-abbe-acd25b8e4c71 · outbound

This paper cites Recent advances in natural language processing via large pre-trained language models: A survey,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Recent advances in natural language processing via large pre-trained language models: A survey,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.732172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c8a5979-8c70-4903-a903-7848aa3c303a · outbound

This paper cites Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificity

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.801116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f1ac647-7197-4849-be75-f28d03a75a3d · outbound

This paper cites Overcoming catastrophic forgetting in neural networks,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Overcoming catastrophic forgetting in neural networks,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.884725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d1ce60d-857a-46a3-bd84-0513eb3b3285 · outbound

This paper cites Parameter-efficient transfer learning for nlp,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Parameter-efficient transfer learning for nlp,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:00.965739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda35a49-7669-409b-80dd-382ddd51d52e · outbound

This paper cites The Power of Scale for Parameter-Efficient Prompt Tuning.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA The Power of Scale for Parameter-Efficient Prompt Tuning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.019338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b40bfedf-0a4f-44bf-93aa-8ac8c80181cf · outbound

This paper cites DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.076091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4023785-71b2-47e5-b0b1-a381bf59f755 · outbound

This paper cites Qlora: Efficient finetuning of quantized llms,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Qlora: Efficient finetuning of quantized llms,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.159339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e424728d-fb7b-4f2d-bd4d-7448dcc057be · outbound

This paper cites UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.221242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e54df66-2f73-4d7d-9f79-2f3b4f9176eb · outbound

This paper cites GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.293131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fb91a91-a8a6-4c45-b562-b96172b8ce3a · outbound

This paper cites PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.351523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2827bf8-4a69-4e39-acec-6618a57bc6a0 · outbound

This paper cites KoLA: Carefully Benchmarking World Knowledge of Large Language Models.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA KoLA: Carefully Benchmarking World Knowledge of Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.430251Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df108092-bbb4-4936-905b-299eb6f3d64a · outbound

This paper cites Large language models encode clinical knowledge,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Large language models encode clinical knowledge,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.507429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbbb7d39-0ec8-479b-acea-2a09be3511ca · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm- integrated applications with indirect prompt injection,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Not what you’ve signed up for: Compromising real-world llm- integrated applications with indirect prompt injection,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.565978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc5417d-2eae-46ab-af28-78783838ff2e · outbound

This paper cites Measuring massive multitask language understanding.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Measuring massive multitask language understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.640402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe1c1159-6130-4254-adda-95ec373ab23b · outbound

This paper cites National vulnerability database.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA National vulnerability database

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.691984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c036bf6-f014-490f-aecc-a38a99499d37 · outbound

This paper cites National vulnerability database.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA National vulnerability database

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.751210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2843a41-a870-43a5-942b-e3593e82962f · outbound

This paper cites Ragas: Automated Evaluation of Retrieval Augmented Generation.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Ragas: Automated Evaluation of Retrieval Augmented Generation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.819091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63383686-bdc8-4891-a45b-12cd39abce7c · outbound

This paper cites Bleu: a method for automatic evaluation of machine translation,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Bleu: a method for automatic evaluation of machine translation,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.885020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9900dfd-ce74-4bfe-989e-b5d14fdba33b · outbound

This paper cites A package for automatic evaluation of summaries,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA A package for automatic evaluation of summaries,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.946066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55e8b1df-9e2c-4e9b-81d0-6c22739466cd · outbound

This paper cites Likert scales and data analyses,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Likert scales and data analyses,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:01.999340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 847d23bb-0eea-42e3-95de-ccc3492c329f · outbound

This paper cites Interrater reliability: the kappa statistic,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Interrater reliability: the kappa statistic,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:02.061431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60d99845-446b-4ceb-b671-9b3e1fc7d460 · outbound

This paper cites Parameter-efficient fine-tuning of large- scale pre-trained language models,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA Parameter-efficient fine-tuning of large- scale pre-trained language models,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:02.120474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f7c16b2-a6f2-45b0-8e2e-6b72337a906c · outbound

This paper cites The art of abstention: Selective prediction and error regularization for natural language processing,.

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA The art of abstention: Selective prediction and error regularization for natural language processing,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T14:35:02.200196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.