Paper Citation Record · LEDGER

"Important You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

As of 9 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2606.03090.

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

pith.paper-citation-record.v1
2606.03090 v2

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:01:19.232356Z

measured 32 of 32 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

32 of 32 outbound references displayed

verified exact4
verified fuzzy0
unresolved17
parse uncertain0
malformed identifier0
metadata mismatch11

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3707363c-ff0f-40c3-8d51-4866b2b206b3 · outbound

This paper cites GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:29.662457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 32dbfa35-f73a-4f73-8a39-91cb90e2b114 · outbound

This paper cites A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:29.635284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3e625682-0a97-4f18-aa4f-57c1ffe53d0e · outbound

This paper cites IEEE Signal Processing Magazine , volume=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems IEEE Signal Processing Magazine , volume=

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 278d95f3-6a3a-4aa7-b6eb-346e175625b0 · outbound

This paper cites Do Anything Now.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Do Anything Now

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ee2f16c-2a4a-41dc-8871-10faeb5b3612 · outbound

This paper cites 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) , pages=

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0f9ffa7-e042-4c8e-9105-2562821bda01 · outbound

This paper cites Computers, Materials, & Continua , volume=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Computers, Materials, & Continua , volume=

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d77f8ea9-fe5b-40a2-bfee-38727919d158 · outbound

This paper cites Bringing Generative AI to Adaptive Learning in Education.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Bringing Generative AI to Adaptive Learning in Education

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:29.644801Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 404efd3e-6f31-4a72-b2f7-bc1d025b5e24 · outbound

This paper cites 2025 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE) , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems 2025 IEEE International Conference on Teaching, Assessment, and Learning for Engineering (TALE) , pages=

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d507d25-1cd7-43f8-ac3b-63102ebb9638 · outbound

This paper cites Proceedings of the 15th international learning analytics and knowledge conference , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Proceedings of the 15th international learning analytics and knowledge conference , pages=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2476fe35-db45-4846-ab6e-d2cd6556e705 · outbound

This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 379d7a44-0048-4d83-8bec-81818746dc10 · outbound

This paper cites Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:29.636488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e3b3b547-2486-4a60-8848-5e692c57f97e · outbound

This paper cites arXiv preprint arXiv:2603.00465 , year=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems arXiv preprint arXiv:2603.00465 , year=

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:29.625954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3e165ac4-4361-4689-8598-5ccf77300a32 · outbound

This paper cites 33rd USENIX Security Symposium (USENIX Security 24) , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems 33rd USENIX Security Symposium (USENIX Security 24) , pages=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fe7fa96-be3c-48e1-9484-ce097fc6a561 · outbound

This paper cites Advances in neural information processing systems , volume=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Advances in neural information processing systems , volume=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bd756b1-5f4a-48d2-bf25-2af9e1a0e261 · outbound

This paper cites Bai, Y ., Tu, S., Zhang, J., Peng, H., Wang, X., Lv, X., Cao, S., Xu, J., Hou, L., Dong, Y ., Tang, J., and Li, J.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Bai, Y ., Tu, S., Zhang, J., Peng, H., Wang, X., Lv, X., Cao, S., Xu, J., Hou, L., Dong, Y ., Tang, J., and Li, J

Reference 15

Resolution: metadata mismatch; doi, observed 2026-06-28T10:01:51.804808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c724e5df-4314-4324-af59-d1108e69ee6a · outbound

This paper cites European Symposium on Research in Computer Security , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems European Symposium on Research in Computer Security , pages=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41767bd2-e037-4c70-8bf1-8bcfd635fc2d · outbound

This paper cites OpenAI GPT-5 System Card.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems OpenAI GPT-5 System Card

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:29.659556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 530d1a60-e458-455c-92b2-7a0c93fdddd2 · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe89ecc6-274a-44fc-a149-48d9e6c262b9 · outbound

This paper cites Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security , pages=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Proceedings of the 2025 ACM SIGSAC Conference on Computer and Communications Security , pages=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d557ae17-7ded-45c7-82c5-b92db747159f · outbound

This paper cites Nature Machine Intelligence , volume=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Nature Machine Intelligence , volume=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b9be619-af9a-4695-8035-7d613746da45 · outbound

This paper cites "I understand why I got this grade": Automatic Short Answer Grading with Feedback.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems "I understand why I got this grade": Automatic Short Answer Grading with Feedback

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:29.632667Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation fb3ca0a4-9c60-4582-a2d3-a2563a3c9aa4 · outbound

This paper cites Handbook of Research on Science Learning Progressions , year=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Handbook of Research on Science Learning Progressions , year=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9536444-f192-4e12-9e25-14dc5f36d589 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Gemini: A Family of Highly Capable Multimodal Models

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:29.648854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8fb21ccc-f63b-47f3-be2b-562c876ffe23 · outbound

This paper cites 2025 , eprint=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems 2025 , eprint=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d68e4b2-cd81-4c8c-9b53-0c10290fe35a · outbound

This paper cites The Llama 3 Herd of Models.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems The Llama 3 Herd of Models

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:29.654982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 997768bf-050a-4773-91dc-7fae5cf53880 · outbound

This paper cites 2026 , month =.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems 2026 , month =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80175000-2d80-4726-a217-9e4d2fd035f8 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 27

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:29.642030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a0665a8c-45be-453b-b31c-a84876f91f35 · outbound

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

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Gemma: Open Models Based on Gemini Research and Technology

Reference 28

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:29.651838Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 2b7a2e7e-2cef-4dd1-ab84-4a4ca3dd852b · outbound

This paper cites doi:10.57967/hf/8254 , publisher =.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems doi:10.57967/hf/8254 , publisher =

Reference 29

Resolution: verified exact; doi, observed 2026-06-28T10:01:51.802706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4f1ae06b-4ef2-4fd8-9aa4-eda606ebcfac · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:26:29.642799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 60e492fb-cd16-478b-891b-34ee37c6590a · outbound

This paper cites Towards LLM-based Autograding for Short Textual Answers.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Towards LLM-based Autograding for Short Textual Answers

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T03:26:29.646028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 954f5fb7-eb21-43f7-9d0f-1bd8fb7fa626 · outbound

This paper cites Advances in neural information processing systems , volume=.

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems Advances in neural information processing systems , volume=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-28T10:01:19.232356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.