Pith. sign in

Paper Citation Record · LEDGER

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

As of 8 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2606.05396.

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

pith.paper-citation-record.v1
2606.05396 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T05:19:58.062861Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

26 of 26 outbound references displayed

  • verified exact4
  • verified fuzzy0
  • unresolved19
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a7668c3f-e44e-4fd8-9a95-680ad79d170c · outbound

This paper cites Juliet test suite for Java and C/C++ (nist software as- surance reference dataset),.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Juliet test suite for Java and C/C++ (nist software as- surance reference dataset),

Reference 1

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:aa05fe60ee1f36eccb8ab488944cdfcaed5e837996329c6a081b94c6ef851506

Observation 32c4c0e0-35a3-4525-a396-74e23ad0ca9a · outbound

This paper cites A C/C++ code vulnerability dataset with code changes and CVE summaries,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration A C/C++ code vulnerability dataset with code changes and CVE summaries,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:5fb6ba2b9daf6994ab68a67c5439528e4a1b7909eebc7bd07f98207ba71fdcc9

Observation 81c482d4-f22d-4829-ac87-24140aff2dfe · outbound

This paper cites Devign: Effective vulnerability identification by learning compre- hensive program semantics via graph neural networks,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Devign: Effective vulnerability identification by learning compre- hensive program semantics via graph neural networks,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:d8cdbb567b459f257f51e9517b635b5286b438d3a19133d2e7a6d59fadc53a3c

Observation 6ff7e0f3-fd51-40b7-9c09-7b08fa5de8f1 · outbound

This paper cites Deep learning based vulnerability detection: Are we there yet?.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Deep learning based vulnerability detection: Are we there yet?

Reference 4

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:a60c514ffc470ff3427fd316fcef5947d76d10d09595407cbce5ec2057e7508e

Observation 7a048a2a-f999-477a-9718-84c10d67aa03 · outbound

This paper cites In 45th IEEE/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14-20.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration In 45th IEEE/ACM International Conference on Software Engineering, ICSE 2023, Melbourne, Australia, May 14-20

Reference 5

Resolution
metadata mismatch
arxiv_id, observed 2026-06-28T05:21:39.880920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:e14df80eb86f0fbe612f8d22ddcfea0918f03af65f807d3a5ec6b3500aa0fbd5

Observation 0587e2cb-d8bf-4e21-aae9-972e0c102a5a · outbound

This paper cites Vulgen: Realistic vulnerability generation via pattern mining and deep learning,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Vulgen: Realistic vulnerability generation via pattern mining and deep learning,

Reference 6

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:d76786599ba6dedd223514529d240db664446ae11c6f0bbd28b26454073f5341

Observation 976d8777-02dd-43e0-8978-8b692b03b92b · outbound

This paper cites Vgx: Large-scale sample generation for boosting learning-based software vulnerability analyses,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Vgx: Large-scale sample generation for boosting learning-based software vulnerability analyses,

Reference 7

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:309b785f16c422542136a112dc7d5414eeac7e6efdc9e19637c6202d240b9cf1

Observation e46943b4-0c4d-4d27-9907-8b30a40ec5c3 · outbound

This paper cites Available: https://doi.org/10.1145/3597503.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Available: https://doi.org/10.1145/3597503

Reference 8

Resolution
verified exact
doi, observed 2026-06-28T05:21:39.887436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:d193ba60a854faefea1d60e4d1efbf310f8f6f34eabcc37bd7e7df20ffdfa04a

Observation 38dafbc2-222d-440e-8206-6601e0ccb10d · outbound

This paper cites VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration VulScribeR: Exploring RAG-based Vulnerability Augmentation with LLMs

Reference 9

Resolution
verified exact
arxiv_id, observed 2026-07-02T10:06:51.662457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:6af8c279010a98687e3cc00716d85a59b136749bdd915055a50502553fe3cf91

Observation 588d5ef9-baf4-4167-ab27-bec2ce0c0b36 · outbound

This paper cites Surveys58, 5, Article 134 (2025).

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Surveys58, 5, Article 134 (2025)

Reference 10

Resolution
metadata mismatch
doi, observed 2026-06-28T05:21:39.889588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:db67ac3766c325542c3088469f0f33bd088c74b98769c81464d3c4eb9530aae2

Observation ff8c8ec8-e4d0-4e61-8172-1261896ec67f · outbound

This paper cites Empirical Software Engineering28(3), 59 (2023).

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Empirical Software Engineering28(3), 59 (2023)

Reference 11

Resolution
metadata mismatch
doi, observed 2026-06-28T05:21:39.885491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:60ed66f0a87dcebb561116ecf0166a848a8cde10cd3023e526d1d7935cd116ff

Observation 771f4940-daf0-45ab-aea6-5af9eb4846e1 · outbound

This paper cites Secureqwen: Leveraging llms for vulnerability detection in python codebases,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Secureqwen: Leveraging llms for vulnerability detection in python codebases,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:048990c2f90093f4a5adb1c5461592fb198967c2cb4d91cd6988a40358962c57

Observation 2b1ef1e9-b664-460d-bcd7-c131ec92b36c · outbound

This paper cites Available: https://www.sciencedirect.com/ science/article/pii/S0167404824004565.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Available: https://www.sciencedirect.com/ science/article/pii/S0167404824004565

Reference 13

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:21ad9d88585c9d93a8008be04c951a442e248ebc87db49190b5e83fdd17ec35e

Observation 8c043636-2f18-4d1d-8294-eac103b2b561 · outbound

This paper cites PromSec: Prompt optimization for secure generation of functional source code with large language models,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration PromSec: Prompt optimization for secure generation of functional source code with large language models,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:c46dd224ac2ab156233a434db796be9f8a381f1d50de1dc357f0d5e0b9afd6ff

Observation bee07d80-8e6d-42f9-8f0c-e89ca55e6122 · outbound

This paper cites Large language models for code: Security hardening and adversarial testing,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Large language models for code: Security hardening and adversarial testing,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:01559f4bf8bfa5cf4808387c381417d8f84d32681c967919b2353b496d278625

Observation d925cc2b-13d8-4048-8dbd-527bcfae52d6 · outbound

This paper cites Ai code generators for security: Friend or foe?.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Ai code generators for security: Friend or foe?

Reference 16

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:0842a812a69c756e08ee948df213732817ea88ecf46ee3c24db7049a7a664fcf

Observation a05b4f24-4139-4611-a538-84c81d5e2d62 · outbound

This paper cites Refusal in language models is mediated by a single direction,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Refusal in language models is mediated by a single direction,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:111b37fdd7db7eb0ce94357f0bbc6689934ca6ef7d13c3c9d296bdf25d6202c3

Observation bf65e79a-828c-49d9-80f6-18d6dc5512cf · outbound

This paper cites Evil: exploiting software via natural language,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Evil: exploiting software via natural language,

Reference 18

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:7105318b74a5dce7338f77b85346d1ed38d3324d15d12a0402d7f2f163726152

Observation de310425-ca3b-4186-b6c3-98f3ea9d00df · outbound

This paper cites Shellcode_ia32: A dataset for automatic shellcode generation,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Shellcode_ia32: A dataset for automatic shellcode generation,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:8edef93b0f7cf7ba65b64f9fc77a17228527f1874413d50609b14084c4624925

Observation f5dffebc-4945-4edd-b74a-60c3d85fb139 · outbound

This paper cites Can we generate shellcodes via natural language? an empirical study,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Can we generate shellcodes via natural language? an empirical study,

Reference 20

Resolution
verified exact
doi, observed 2026-06-28T05:21:39.883385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:349a440aa99b8d73483b76f9d356a771cd03f437586dcc4a50c489e610f6f5bf

Observation 2abdb96f-6798-47c9-a62f-6e1fa0f192ec · outbound

This paper cites Enhancing ai-based generation of software exploits with contextual information,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Enhancing ai-based generation of software exploits with contextual information,

Reference 21

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:d54af610997a0d5a6ef387bce491bb635e4066eda498707eb3ed1eedc0800b4f

Observation 2fcc1c61-a58a-4997-971e-42f78107335f · outbound

This paper cites Reading between the lines: Context-aware ai-based generation of software exploits,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Reading between the lines: Context-aware ai-based generation of software exploits,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:b4772ac58a35e5fa9e64707a56256c49ca0f121f57a4afe3841a0244a676b4b3

Observation cdaa0b7d-e932-48fb-9789-5c24568e751a · outbound

This paper cites The power of words: Generating{PowerShell} attacks from natural language,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration The power of words: Generating{PowerShell} attacks from natural language,

Reference 23

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:08e666f11d3611e5e37a02d28808b3cb5b49c5d60091c794bb74f23da1c163a0

Observation 28cd2384-96dd-42c7-80eb-b90c809d8e58 · outbound

This paper cites Using ai to inject vulnerabilities in python code,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Using ai to inject vulnerabilities in python code,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:e937cb3ee655ac1ecc5e8dab26265c9a3227d91d094f6c7366903800d9ae9538

Observation 32d8cf1b-8c46-4785-900c-8e9e53294dce · outbound

This paper cites Qwen2.5-Coder Technical Report.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Qwen2.5-Coder Technical Report

Reference 25

Resolution
verified exact
local_arxiv, observed 2026-07-02T10:06:51.664997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:ef43e78f5fd789aca8bd41b603d367c098e00399615bc06251ae865ceafdfa06

Observation 0e068cb8-258f-4c5f-b4ef-b6b67267f1e1 · outbound

This paper cites Obliteratus: An open platform for analysis-informed refusal removal in large language models,.

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration Obliteratus: An open platform for analysis-informed refusal removal in large language models,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-06-28T05:19:58.062861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-06-28T05:19:58.062861Z digest=sha256:860afa3bb61b76be35a8c3b991a1febcf9ec1345a83847186b7e6c79e2b61a55

Pith citing papers

No inbound Pith citation observations are available.