Paper Citation Record · LEDGER

Activation Probes Surface Code-Security Signals that the Model's Output Misses

As of 20 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 0 inbound Pith citation observations for arXiv:2608.09643.

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

pith.paper-citation-record.v1
2608.09643 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T13:35:03.936208Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+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 exact1
verified fuzzy6
unresolved19
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 15744e1c-918e-40cb-b1a6-c1be9a887901 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.828306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d12b3c28-409c-45e2-885b-1c4bffdaa1a0 · outbound

This paper cites The adverse effects of code duplication in machine learning models of code.

Activation Probes Surface Code-Security Signals that the Model's Output Misses The adverse effects of code duplication in machine learning models of code

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.834164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b930ea0b-520f-4fe6-82a9-241504afedce · outbound

This paper cites and Mitchell, T.

Activation Probes Surface Code-Security Signals that the Model's Output Misses and Mitchell, T

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:35:04.830659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2e90144a-64f1-4573-9213-9b154338b776 · outbound

This paper cites an unresolved cited work.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.842777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 460bdda4-9842-4af5-95f6-5c2bfc4a758d · outbound

This paper cites CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection.

Activation Probes Surface Code-Security Signals that the Model's Output Misses CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.846982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea8807be-6201-409a-8757-dcccd85f1ee0 · outbound

This paper cites and Clark, J.

Activation Probes Surface Code-Security Signals that the Model's Output Misses and Clark, J

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:35:04.814881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3e65cca6-c3c9-4485-901d-ea86df4a3e74 · outbound

This paper cites NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals.

Activation Probes Surface Code-Security Signals that the Model's Output Misses NNsight and NDIF: Democratizing Access to Open-Weight Foundation Model Internals

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.856305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8a703fb-1ed9-4748-a764-fe27d6e6e62a · outbound

This paper cites Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.860136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2ab2b32-289b-4b4b-9ec6-755d1c6d1793 · outbound

This paper cites The Llama 3 Herd of Models.

Activation Probes Surface Code-Security Signals that the Model's Output Misses The Llama 3 Herd of Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.864214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1096dac5-e02d-4cbe-91bd-c60ed68eb275 · outbound

This paper cites DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence.

Activation Probes Surface Code-Security Signals that the Model's Output Misses DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.868041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 483b6707-16ac-4c1d-9250-4e712591838a · outbound

This paper cites Large Language Models for Code: Security Hardening and Adversarial Testing.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Large Language Models for Code: Security Hardening and Adversarial Testing

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.872204Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73da4bd7-fec9-469c-aa0d-36534f4a9b00 · outbound

This paper cites Qwen2.5-Coder Technical Report.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Qwen2.5-Coder Technical Report

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.876432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a589f3cd-2a16-47cc-8619-65b3c314515b · outbound

This paper cites LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs.

Activation Probes Surface Code-Security Signals that the Model's Output Misses LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-08-11T13:35:04.309785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2db85f5f-f87b-4be1-90ee-71bc10809336 · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.885101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdb4ec12-a312-489e-ad57-ba12f4586b52 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

Activation Probes Surface Code-Security Signals that the Model's Output Misses The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.889243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cbaa358-83d7-48a0-8a2f-dec662527d91 · outbound

This paper cites S., and Krasheninnikov, D.

Activation Probes Surface Code-Security Signals that the Model's Output Misses S., and Krasheninnikov, D

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.893805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cf4094e-0721-4ba4-b8ed-e0706faed3bb · outbound

This paper cites Devstral-Small-2505 , May 2025.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Devstral-Small-2505 , May 2025

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:35:04.800578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7a0f5148-5024-4413-9890-64c11173dc85 · outbound

This paper cites LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations.

Activation Probes Surface Code-Security Signals that the Model's Output Misses LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.901959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3faab206-014c-4b31-93c0-489edea5e8d9 · outbound

This paper cites PyTorch: An Imperative Style, High-Performance Deep Learning Library.

Activation Probes Surface Code-Security Signals that the Model's Output Misses PyTorch: An Imperative Style, High-Performance Deep Learning Library

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.906984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30a2c9e5-5f2d-472b-9b91-aa96e3c50b17 · outbound

This paper cites Scikit-learn: Machine learning in P ython.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Scikit-learn: Machine learning in P ython

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:35:04.786428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation de3c7b13-caa9-4414-9ebd-e8b9811735f0 · outbound

This paper cites Y C ombinator startups are fastest growing, most profitable in fund history because of AI.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Y C ombinator startups are fastest growing, most profitable in fund history because of AI

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:35:04.773380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9bb6f895-ca7d-4ae9-876e-c048d34df059 · outbound

This paper cites LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks.

Activation Probes Surface Code-Security Signals that the Model's Output Misses LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.919947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5a18c87-2e04-4716-8f60-8e822cf0561d · outbound

This paper cites E., Haberland, M., Reddy, T., Cournapeau, D., et al.

Activation Probes Surface Code-Security Signals that the Model's Output Misses E., Haberland, M., Reddy, T., Cournapeau, D., et al

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.924038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a4b5e5-c510-4272-b110-42b034147149 · outbound

This paper cites AI code in the wild: Measuring security risks and ecosystem shifts of AI -generated code in modern software.

Activation Probes Surface Code-Security Signals that the Model's Output Misses AI code in the wild: Measuring security risks and ecosystem shifts of AI -generated code in modern software

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.928683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 018846f8-3aeb-4998-a199-62f808af065a · outbound

This paper cites PATCHEVAL : A new benchmark for evaluating LLM s on patching real-world vulnerabilities.

Activation Probes Surface Code-Security Signals that the Model's Output Misses PATCHEVAL : A new benchmark for evaluating LLM s on patching real-world vulnerabilities

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T13:35:03.932436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df054832-c3a4-492a-b67a-0ee4a999846e · outbound

This paper cites Transformers: State-of-the-art natural language processing.

Activation Probes Surface Code-Security Signals that the Model's Output Misses Transformers: State-of-the-art natural language processing

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:35:04.760666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

No inbound Pith citation observations are available.