Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-05T22:40:30.528845Z
Paper Citation Record · LEDGER
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift
As of 16 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2508.06776.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links
A source-named dated measurement, never combined with another source.
Source: cited_works
Reference resolution
22 of 22 outbound references displayed
- verified exact2
- verified fuzzy14
- unresolved5
- parse uncertain0
- malformed identifier0
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation ed0432bf-3aaa-4c89-8ed7-ca78b7452398 · outbound
This paper cites Understanding intermediate layers using linear classifier probes.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Understanding intermediate layers using linear classifier probes
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.940632Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 3faac3b9-3573-4e8e-8951-607d05efc627 · outbound
This paper cites Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Reference 2
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T22:40:28.162136Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 10814772-727f-45f7-bd85-1a504842569c · outbound
This paper cites Trends in llm interpretability research.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Trends in llm interpretability research
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.931348Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 7561c052-80b0-454c-9b2d-dd33508b66ed · outbound
This paper cites Homoclinic Floer homology via direct limits.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Homoclinic Floer homology via direct limits
Reference 4
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T22:40:28.438943Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1665be7e-d40b-4b68-a921-224a676f39c3 · outbound
This paper cites Monitoring latent world states in large language models.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Monitoring latent world states in large language models
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.922527Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation af000ee0-6fa2-4b01-8a06-f662e8a5433e · outbound
This paper cites Selective self-supervised fine-tuning for stable representa- tions.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Selective self-supervised fine-tuning for stable representa- tions
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.912412Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation b40897a5-9b02-458b-92ad-9dd61abdca85 · outbound
This paper cites Alphaedit: Null-space constrained knowledge editing for large language models.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Alphaedit: Null-space constrained knowledge editing for large language models
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.902960Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 3c444657-5e98-4b59-8a8a-2dfccd313f96 · outbound
This paper cites Similarity of neural network representations revisited.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Similarity of neural network representations revisited
Reference 8
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T22:40:28.827790Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d8ba32d8-282d-4f28-be2e-7ac1af5c934e · outbound
This paper cites The fine-tuning landscape of large language models.Nature Computational Science, 2025.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift The fine-tuning landscape of large language models.Nature Computational Science, 2025
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.888362Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 55da83d8-4698-4df8-8e42-2c6ddb3f1748 · outbound
This paper cites Testing the Predictions of Surprisal Theory in 11 Languages.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Testing the Predictions of Surprisal Theory in 11 Languages
Reference 10
- Resolution
- verified exact
- local_arxiv, observed 2026-08-05T22:40:31.439617Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 5fcd4e86-1f53-47b5-a54c-d52197bd2bc6 · outbound
This paper cites Morcos, Maithra Raghu, and Samy Bengio.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Morcos, Maithra Raghu, and Samy Bengio
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.877867Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation b073007c-684b-4de0-afc2-6693233194eb · outbound
This paper cites Small singular values matter: A random matrix analysis of transformer representations.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Small singular values matter: A random matrix analysis of transformer representations
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T22:40:29.250696Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 770e04db-b978-44fd-a616-d5cd792483dd · outbound
This paper cites On variational alignment of layerwise representations.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift On variational alignment of layerwise representations
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.867670Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 4735a116-8d01-469d-9583-f85a42c693ae · outbound
This paper cites Schoenholz.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Schoenholz
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.857303Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 452290f2-f2f4-4999-83b5-513805cf4155 · outbound
This paper cites Lora-null: Forgetting-free low-rank adaptation via null space.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Lora-null: Forgetting-free low-rank adaptation via null space
Reference 15
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.847735Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 05607c75-b184-4a6d-89a7-832b18a0fe99 · outbound
This paper cites Svcca: Singular vector canonical correlation analysis for deep learning dynamics.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Svcca: Singular vector canonical correlation analysis for deep learning dynamics
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.837745Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 0f2ac151-8075-4f2f-99f6-764e42f860b3 · outbound
This paper cites SpikePropamine: Differentiable Plasticity in Spiking Neural Networks.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift SpikePropamine: Differentiable Plasticity in Spiking Neural Networks
Reference 17
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-08-05T22:40:31.059075Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation ece6594b-bdda-407b-acd2-3bc4d8e889ac · outbound
This paper cites Lora-null: Low-rank adaptation via null space for large language models.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Lora-null: Low-rank adaptation via null space for large language models
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.820590Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 9bfeff6e-9f9c-4204-9ee5-32bf027ee0b5 · outbound
This paper cites Representation engineering shift: A simple drift detector for llms.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Representation engineering shift: A simple drift detector for llms
Reference 19
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.770544Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 4a6ca5dc-8601-4ce5-929a-a02f1f39227e · outbound
This paper cites A Free Probabilistic Framework for Analyzing the Transformer-based Language Models.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift A Free Probabilistic Framework for Analyzing the Transformer-based Language Models
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-08-05T22:40:30.790965Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 4af78d30-009c-4daf-ae72-6600dd1b76de · outbound
This paper cites Fisher alignment: Measuring policy drift in rlhf.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Fisher alignment: Measuring policy drift in rlhf
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-05T22:40:31.635784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.
Observation 4a910ff5-58da-47f2-b6aa-899e2175f7ca · outbound
This paper cites Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States.
Zero-Direction Probing: A Linear-Algebraic Framework for Deep Analysis of Large-Language-Model Drift Probing Latent Subspaces in LLM for AI Security: Identifying and Manipulating Adversarial States
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-05T22:40:30.528845Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Pith citing papers
No inbound Pith citation observations are available.