Paper Citation Record · LEDGER

Understanding intermediate layers using linear classifier probes

As of 20 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 100 inbound Pith citation observations for arXiv:1610.01644.

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

pith.paper-citation-record.v1
1610.01644 v4

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-11T18:31:44.239360Z

measured 128 of 128 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 100 of 310 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:01:39.648013Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

28 of 28 outbound references displayed

verified exact7
verified fuzzy6
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

117
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d6b38447-e0a2-4ce3-bcc0-1f0da35a44e3 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Understanding intermediate layers using linear classifier probes Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:31:44.294465Z

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 b4cb5adf-6e15-4747-8e15-dbcb13f2b423 · outbound

This paper cites Explaining Recurrent Neural Network Predictions in Sentiment Analysis.

Understanding intermediate layers using linear classifier probes Explaining Recurrent Neural Network Predictions in Sentiment Analysis

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:31:44.309727Z

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 78b4f757-515f-4f85-9d14-cba793f9e36c · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.504188Z

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 9b9d9300-17b6-4d5b-b06e-2faa2620d94d · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.509229Z

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 64f10246-a6ad-4124-9b9e-6556530b62e2 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.514683Z

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 69c5edf0-8039-4902-857b-d7100bbb9e90 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 6

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.518019Z

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 57a70ac0-b4fd-432d-9569-36c14d0500e4 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.521251Z

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 faad77a2-00e2-4ebf-9146-c08848e4325e · outbound

This paper cites and Brox, T.

Understanding intermediate layers using linear classifier probes and Brox, T

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T18:31:44.372794Z

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 e9d8275a-7e15-40af-8be9-c5bd01f1477a · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.379767Z

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 85397334-b119-485b-a2a2-51bb01576bd7 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.389936Z

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 924c6ef2-8edf-42ae-8af5-ecc02e64d408 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.409508Z

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 bf723d97-d947-49e5-9dbd-e0e2539d2dbc · outbound

This paper cites Residual Connections Encourage Iterative Inference.

Understanding intermediate layers using linear classifier probes Residual Connections Encourage Iterative Inference

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-07-04T22:36:00.391022Z

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 5a545c8d-97b6-4bdc-a810-106931d9ad25 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.435405Z

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 49b7c58a-c8d9-403f-b460-20103e65f9ad · outbound

This paper cites FractalNet: Ultra-Deep Neural Networks without Residuals.

Understanding intermediate layers using linear classifier probes FractalNet: Ultra-Deep Neural Networks without Residuals

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:31:44.333218Z

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 2cda7fd5-60a2-4ee0-aaab-bc008e4a96cb · outbound

This paper cites and Vedaldi, A.

Understanding intermediate layers using linear classifier probes and Vedaldi, A

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T18:31:44.465887Z

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 a853faee-5fd4-40c9-bdb2-7525983a6ad5 · outbound

This paper cites and Vedaldi, A.

Understanding intermediate layers using linear classifier probes and Vedaldi, A

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T18:31:44.472151Z

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 db234887-8209-4e95-8742-1987efcc3159 · outbound

This paper cites L., and M \"u ller, K.-R.

Understanding intermediate layers using linear classifier probes L., and M \"u ller, K.-R

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T18:31:44.476269Z

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 35ef28c2-cccf-4f87-9e7e-ef8d9b61f4f9 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.480619Z

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 25daa382-0919-46a3-97c2-37ed41d80d8e · outbound

This paper cites SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability.

Understanding intermediate layers using linear classifier probes SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T18:31:44.344603Z

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 a5234b98-5833-4039-badb-812915499326 · outbound

This paper cites C., and Fei-Fei, L.

Understanding intermediate layers using linear classifier probes C., and Fei-Fei, L

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T18:31:44.488097Z

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 97818adf-f060-4a01-84e0-817c79850ba2 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.491821Z

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 63ec4ce2-af3c-4ccc-91d3-4a9035fe269a · outbound

This paper cites Intriguing properties of neural networks.

Understanding intermediate layers using linear classifier probes Intriguing properties of neural networks

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-11T21:55:15.262808Z

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 f5f16a2a-1bc5-4bae-a726-630209828350 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.500557Z

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 62f99a41-f6cd-4dc8-9492-c47b194a748b · outbound

This paper cites J., and Belongie, S.

Understanding intermediate layers using linear classifier probes J., and Belongie, S

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-11T18:31:44.414395Z

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 2e2aa2d9-ceb0-4471-ace3-c5756adb2af4 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 25

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.439802Z

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 6a53cdda-80c2-4f5b-af65-91ffac1422f0 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.484415Z

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 5ccbccc0-404e-4856-8481-7da1fec53ad3 · outbound

This paper cites an unresolved cited work.

Understanding intermediate layers using linear classifier probes Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-05-11T18:31:44.495495Z

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 e844b415-520c-43a5-a1ca-d6a00847421e · outbound

This paper cites Understanding deep learning requires rethinking generalization.

Understanding intermediate layers using linear classifier probes Understanding deep learning requires rethinking generalization

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-13T11:56:40.372790Z

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

Observation d6b38447-e0a2-4ce3-bcc0-1f0da35a44e3 · inbound

Understanding intermediate layers using linear classifier probes cites this paper.

Understanding intermediate layers using linear classifier probes Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-11T18:31:44.294465Z

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 608df017-3f30-4fc8-ad8f-fcc3316ffacc · inbound

Feature selection of neural networks is skewed towards the less abstract cue cites this paper.

Feature selection of neural networks is skewed towards the less abstract cue Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-14T14:31:43.605300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4da4a68a-d6b0-4fd7-b004-7558b37f58ed · inbound

Probing Classifiers: Promises, Shortcomings, and Advances cites this paper.

Probing Classifiers: Promises, Shortcomings, and Advances Understanding intermediate layers using linear classifier probes

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:09:20.482019Z

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 e945462f-c49d-45e4-9bed-5591b379770d · inbound

What learning algorithm is in-context learning? Investigations with linear models cites this paper.

What learning algorithm is in-context learning? Investigations with linear models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-17T13:40:34.013043Z

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 7e9f250c-da3f-4870-99ef-caf1bc426044 · inbound

Eliciting Latent Predictions from Transformers with the Tuned Lens cites this paper.

Eliciting Latent Predictions from Transformers with the Tuned Lens Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-12T16:54:37.498913Z

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 f1eb6100-59c3-4b36-98b8-2cc0e7f6c2af · inbound

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations cites this paper.

When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T17:20:47.789293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89f497aa-daf8-4c8b-9de5-0a89aa81c1cc · inbound

LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states cites this paper.

LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T05:48:18.958713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b710cbf-ab86-4b3f-bcfb-c14b113e4887 · inbound

Linear Probe Penalties Reduce LLM Sycophancy cites this paper.

Linear Probe Penalties Reduce LLM Sycophancy Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T04:53:06.372154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6908a6f0-3bda-4593-ae08-18c89028451a · inbound

Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey cites this paper.

Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey Understanding intermediate layers using linear classifier probes

Reference 234

Resolution: unresolved; no resolver link, observed 2026-08-11T23:54:24.321298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a15f435f-53d3-4836-9e1b-7165bb085139 · inbound

Obfuscated Activations Bypass LLM Latent-Space Defenses cites this paper.

Obfuscated Activations Bypass LLM Latent-Space Defenses Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T16:59:11.409609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff4c5108-159f-49e5-bfc8-c254c50082e4 · inbound

Financial Fine-tuning a Large Time Series Model cites this paper.

Financial Fine-tuning a Large Time Series Model Understanding intermediate layers using linear classifier probes

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T16:43:21.456274Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad6820a7-19e1-403c-b153-3420259e9e13 · inbound

Transformers Use Causal World Models in Maze-Solving Tasks cites this paper.

Transformers Use Causal World Models in Maze-Solving Tasks Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T14:35:02.214193Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e0e83c8-487a-42e0-aa99-2748ad46e4c2 · inbound

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective cites this paper.

Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective Understanding intermediate layers using linear classifier probes

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T14:20:23.538909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 621aba30-d957-4494-9157-56eb913fcd43 · inbound

Lightweight Safety Classification Using Pruned Language Models cites this paper.

Lightweight Safety Classification Using Pruned Language Models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.209218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a20896bd-eb2c-4f37-b4a3-c15722d4b43e · inbound

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer cites this paper.

LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer Understanding intermediate layers using linear classifier probes

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T12:46:59.359870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76740fb5-3213-4d10-9b9c-56e1e9ea2187 · inbound

Future Research Avenues for Artificial Intelligence in Digital Gaming: An Exploratory Report cites this paper.

Future Research Avenues for Artificial Intelligence in Digital Gaming: An Exploratory Report Understanding intermediate layers using linear classifier probes

Reference 125

Resolution: unresolved; no resolver link, observed 2026-08-11T12:31:56.551283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 358590ac-b63b-4dac-b539-496b4f244482 · inbound

Sentiment trading with large language models cites this paper.

Sentiment trading with large language models Understanding intermediate layers using linear classifier probes

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-11T00:50:57.859341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bef35f44-1437-4d74-aa20-76cd32aa75d1 · inbound

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models cites this paper.

Spot Risks Before Speaking! Unraveling Safety Attention Heads in Large Vision-Language Models Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T22:28:31.919773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ddc2ebb-5481-48fb-bbe7-4e3b629f7a38 · inbound

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach cites this paper.

Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T18:47:26.128834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9015422d-b7ad-4ce4-8101-07aa05a192a1 · inbound

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models cites this paper.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Understanding intermediate layers using linear classifier probes

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.733628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af7d1eb7-9eae-4398-a32d-2dc231825daa · inbound

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models cites this paper.

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T20:34:01.172410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20457c54-18ff-4dd8-909d-fbb96efd1522 · inbound

Latent Action Learning Requires Supervision in the Presence of Distractors cites this paper.

Latent Action Learning Requires Supervision in the Presence of Distractors Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T19:18:44.681015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a9e301-b854-4202-898d-afdb1cd6bb45 · inbound

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning cites this paper.

Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning Understanding intermediate layers using linear classifier probes

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T17:58:33.774391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d433ce8b-345f-4cb2-bfd5-82621f8d205e · inbound

What is a Number, That a Large Language Model May Know It? cites this paper.

What is a Number, That a Large Language Model May Know It? Understanding intermediate layers using linear classifier probes

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-09T15:05:03.703196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a43bb7e-da09-47de-8160-e23d72ea698d · inbound

Grokking vs. Learning: Same Features, Different Encodings cites this paper.

Grokking vs. Learning: Same Features, Different Encodings Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T14:44:26.975066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa5db58-a585-4d2d-8338-1a896c4d37d4 · inbound

Parameter Symmetry Potentially Unifies Deep Learning Theory cites this paper.

Parameter Symmetry Potentially Unifies Deep Learning Theory Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T19:58:25.840740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a877984e-bb44-4910-8304-89fc8beed9f0 · inbound

A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks cites this paper.

A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T15:22:44.782384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba94dd62-519a-4efa-aaf8-e9e7a1472e39 · inbound

We Can't Understand AI Using our Existing Vocabulary cites this paper.

We Can't Understand AI Using our Existing Vocabulary Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-08T12:17:45.914983Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19b302f5-386f-47ac-a198-9ec14dbec680 · inbound

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs cites this paper.

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-08T00:04:57.000885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e835392a-c22d-4090-acb5-1881d69c7645 · inbound

Solving Empirical Bayes via Transformers cites this paper.

Solving Empirical Bayes via Transformers Understanding intermediate layers using linear classifier probes

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T20:21:58.214293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da685c7d-6460-4f2b-be84-b125ec9432a2 · inbound

Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward cites this paper.

Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward Understanding intermediate layers using linear classifier probes

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T11:01:39.648013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4bacab-cdbb-4a29-8665-0cc36d4740ad · inbound

Lightweight Latent Verifiers for Efficient Meta-Generation Strategies cites this paper.

Lightweight Latent Verifiers for Efficient Meta-Generation Strategies Understanding intermediate layers using linear classifier probes

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:00:20.305699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31425d2e-627d-4bbc-9e6c-5835df5f3dfd · inbound

Investigating task-specific prompts and sparse autoencoders for activation monitoring cites this paper.

Investigating task-specific prompts and sparse autoencoders for activation monitoring Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T05:38:12.140523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a18391a9-f22c-473a-a2b8-6b730dc2e87a · inbound

Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation cites this paper.

Benchmarking Feature Upsampling Methods for Vision Foundation Models using Interactive Segmentation Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:18.870889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bdaa413-5218-4268-b5ff-2d0900576d25 · inbound

When Bad Data Leads to Good Models cites this paper.

When Bad Data Leads to Good Models Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T23:25:00.101334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 126dee83-562e-41cc-a021-dc3826e693a1 · inbound

OMGPT: A Sequence Modeling Framework for Data-driven Operational Decision Making cites this paper.

OMGPT: A Sequence Modeling Framework for Data-driven Operational Decision Making Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:23:51.010219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa4bd15f-d49d-4209-8da2-9ded7e238591 · inbound

Void in Language Models cites this paper.

Void in Language Models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:58.593864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53088e9f-6b06-4a54-ba53-5f2f223dbd75 · inbound

Concept Incongruence: An Exploration of Time and Death in Role Playing cites this paper.

Concept Incongruence: An Exploration of Time and Death in Role Playing Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:31:31.350949Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4a512aa-97f5-420f-847b-66e00b28f24a · inbound

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering cites this paper.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.574425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14eed45a-2f05-4f1e-aa3e-9277e560210a · inbound

Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing cites this paper.

Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:32:11.215971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f746dfd-1b2c-4f01-99f7-7248c6eb08d1 · inbound

Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs cites this paper.

Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:04:04.462024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a02851f-305b-48d0-81b0-d0c0a4809ffe · inbound

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models cites this paper.

Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models Understanding intermediate layers using linear classifier probes

Reference 2006

Resolution: unresolved; no resolver link, observed 2026-08-07T14:44:41.885452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ac98076-51a9-44e8-8d3f-2c4d2357ddac · inbound

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks cites this paper.

FastCAV: Efficient Computation of Concept Activation Vectors for Explaining Deep Neural Networks Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:43:32.884776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0875bfc1-21c5-468d-b028-6d8889357607 · inbound

Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? cites this paper.

Do BERT-Like Bidirectional Models Still Perform Better on Text Classification in the Era of LLMs? Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:50:09.727392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39471ad9-2149-4212-ab77-4c84f03b3515 · inbound

Can Visual Encoder Learn to See Arrows? cites this paper.

Can Visual Encoder Learn to See Arrows? Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:07:17.749975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3f445fb-28fa-4a33-a1b1-5ef0ae9d4ac0 · inbound

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs cites this paper.

From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T13:27:59.847789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4bb419-2c6b-4ebb-87fe-22d65f9aa43a · inbound

BIRD: Behavior Induction via Representation-structure Distillation cites this paper.

BIRD: Behavior Induction via Representation-structure Distillation Understanding intermediate layers using linear classifier probes

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T12:45:23.495814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf076e2a-4030-4733-9ae2-36cde59fd1fc · inbound

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

LPASS: Linear Probes as Stepping Stones for vulnerability detection using compressed LLMs Understanding intermediate layers using linear classifier probes

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:28:29.025394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81fd5c2b-7541-4c26-bf4d-2a5ea42699cb · inbound

Beyond the Black Box: Interpretability of LLMs in Finance cites this paper.

Beyond the Black Box: Interpretability of LLMs in Finance Understanding intermediate layers using linear classifier probes

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-15T21:33:47.078080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03512336-1c9f-4724-b15c-69f75a2b3196 · inbound

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment cites this paper.

Disentangled Safety Adapters Enable Efficient Guardrails and Flexible Inference-Time Alignment Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-19T11:53:03.584052Z

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 7de31c2a-3748-41af-83e5-97b57e0084c2 · inbound

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models cites this paper.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.811248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d414bc41-689e-4392-afdf-d0f6b6415096 · inbound

Resa: Transparent Reasoning Models via SAEs cites this paper.

Resa: Transparent Reasoning Models via SAEs Understanding intermediate layers using linear classifier probes

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.680950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d21acc-d8df-4775-bd28-51742fbb8140 · inbound

15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning cites this paper.

15,500 Seconds: Lean UAV Classification Using EfficientNet and Lightweight Fine-Tuning Understanding intermediate layers using linear classifier probes

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:11:29.812575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 175e16e9-35e5-48c6-a9b6-601090a8c876 · inbound

Collaborative Prediction: To Join or To Disjoin Datasets cites this paper.

Collaborative Prediction: To Join or To Disjoin Datasets Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T04:20:52.074496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdcba208-0abf-479e-90c7-da7673d8cef1 · inbound

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks cites this paper.

How Weight Resampling and Optimizers Shape the Dynamics of Continual Learning and Forgetting in Neural Networks Understanding intermediate layers using linear classifier probes

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-06T20:55:06.033898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d595cf1-56ec-47b9-ba72-ddeadc186849 · inbound

How Do Vision-Language Models Process Conflicting Information Across Modalities? cites this paper.

How Do Vision-Language Models Process Conflicting Information Across Modalities? Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T20:47:03.208420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa24f752-8b96-414c-af72-91354341285f · inbound

Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models cites this paper.

Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models Understanding intermediate layers using linear classifier probes

Reference 110

Resolution: unresolved; no resolver link, observed 2026-08-07T10:18:59.137707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72fcb7d1-1878-4a5b-987a-7a8956bbd1b7 · inbound

On the rankability of visual embeddings cites this paper.

On the rankability of visual embeddings Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T20:11:48.623426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec88b170-7272-40ce-aa7d-c56353fefef7 · inbound

Word stress in self-supervised speech models: A cross-linguistic comparison cites this paper.

Word stress in self-supervised speech models: A cross-linguistic comparison Understanding intermediate layers using linear classifier probes

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T19:44:26.773199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20224d9a-c3ee-4a11-a890-c72f24505d77 · inbound

The Generalization Ridge: Information Flow in Natural Language Generation cites this paper.

The Generalization Ridge: Information Flow in Natural Language Generation Understanding intermediate layers using linear classifier probes

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-19T05:32:05.691066Z

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 a6f99e68-2dc0-42e8-9c9d-f2aebe854de5 · inbound

BlueGlass: A Framework for Composite AI Safety cites this paper.

BlueGlass: A Framework for Composite AI Safety Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T17:46:15.466161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f2de84e-ace9-4260-86b0-f7e15904959a · inbound

CLA: Latent Alignment for Online Continual Self-Supervised Learning cites this paper.

CLA: Latent Alignment for Online Continual Self-Supervised Learning Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T17:37:52.574317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b93434d-5be4-4eaa-a64a-557f5634a9b5 · inbound

The Other Mind: How Language Models Exhibit Human Temporal Cognition cites this paper.

The Other Mind: How Language Models Exhibit Human Temporal Cognition Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T15:30:31.687982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 869c6913-c7a2-4334-bdd0-7d95e39d5e19 · inbound

What Does it Mean for a Neural Network to Learn a "World Model"? cites this paper.

What Does it Mean for a Neural Network to Learn a "World Model"? Understanding intermediate layers using linear classifier probes

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-06T12:44:44.766290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25dac620-b13b-4dcb-80fe-451c71a158d6 · inbound

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations cites this paper.

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T11:01:14.932935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47edcf96-f82f-46ed-b619-bda8b0379b74 · inbound

Balancing Stylization and Truth via Disentangled Representation Steering cites this paper.

Balancing Stylization and Truth via Disentangled Representation Steering Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T23:59:13.262269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 951453fe-d3fb-4bc5-b51a-5e27af2a5bb5 · inbound

Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs cites this paper.

Activation Steering for Bias Mitigation: An Interpretable Approach to Safer LLMs Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T17:34:31.001583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75710bb6-36ba-4585-9d68-8dc48a6379fd · inbound

Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images cites this paper.

Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images Understanding intermediate layers using linear classifier probes

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-05T16:41:45.665313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e91ae1-ea28-4716-ab2a-25eae3614bd1 · inbound

A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models cites this paper.

A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T16:47:43.554649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c2076f5-61fe-4dec-95f5-b9a80fd21c31 · inbound

Online incremental learning for audio classification using a pretrained audio model cites this paper.

Online incremental learning for audio classification using a pretrained audio model Understanding intermediate layers using linear classifier probes

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T14:55:32.884243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ef37baa-8274-4882-b354-40e5a3640629 · inbound

Memorization $\neq$ Understanding: Do Large Language Models Have the Ability of Scenario Cognition? cites this paper.

Memorization $\neq$ Understanding: Do Large Language Models Have the Ability of Scenario Cognition? Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T05:53:21.191664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be38cfb8-0332-48a8-889e-6c0e415459ae · inbound

Evaluating the Efficiency of Latent Spaces via the Coupling-Matrix cites this paper.

Evaluating the Efficiency of Latent Spaces via the Coupling-Matrix Understanding intermediate layers using linear classifier probes

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T16:22:07.795817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 823a344f-ad58-42cb-a3b9-d92c754b5bf0 · inbound

RAPTOR: A Foundation Policy for Quadrotor Control cites this paper.

RAPTOR: A Foundation Policy for Quadrotor Control Understanding intermediate layers using linear classifier probes

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-05-18T17:31:41.754842Z

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 9c544c4c-571c-43a7-a704-d3c8136b689d · inbound

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models cites this paper.

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-18T16:21:36.526141Z

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 179a57e9-4947-4c45-a243-73666df31a0b · inbound

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation cites this paper.

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation Understanding intermediate layers using linear classifier probes

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T15:18:04.265355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5f6e6c4-f3c6-4c0b-b60f-de3dd9e163f4 · inbound

Prophecy: Inferring Formal Properties from Neuron Activations cites this paper.

Prophecy: Inferring Formal Properties from Neuron Activations Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-18T13:31:24.709427Z

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 b44232bd-70ed-46be-bfe2-ada2297930d8 · inbound

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks cites this paper.

Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T14:42:35.513314Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 154c9b8e-d347-4be7-874d-cd2befea2ede · inbound

Feature Identification via the Empirical NTK cites this paper.

Feature Identification via the Empirical NTK Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-18T11:01:16.953582Z

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 764f5240-69ca-4e02-9fc6-0f15bcfa5bec · inbound

Foundation Models for Discovery and Exploration in Chemical Space cites this paper.

Foundation Models for Discovery and Exploration in Chemical Space Understanding intermediate layers using linear classifier probes

Reference 126

Resolution: verified exact; local_arxiv, observed 2026-05-18T05:52:24.956394Z

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 d6dc1fce-9051-41ea-9d4d-7f7a3f42b3de · inbound

MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains cites this paper.

MULTIBENCH++: A Unified and Comprehensive Multimodal Fusion Benchmarking Across Specialized Domains Understanding intermediate layers using linear classifier probes

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-17T23:20:27.604441Z

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 22f43ec8-f984-435e-ad08-ae767c184a84 · inbound

fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding cites this paper.

fMRI-LM: Towards a Universal Foundation Model for Language-Aligned fMRI Understanding Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-17T05:39:06.254039Z

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 31611ee4-7200-40a1-9464-552f8d695a5d · inbound

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail cites this paper.

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail Understanding intermediate layers using linear classifier probes

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T18:33:00.774153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0655eb43-bfe3-498d-b4a5-96f13125a585 · inbound

Quantitative Analysis of Proxy Tasks for Anomalous Sound Detection cites this paper.

Quantitative Analysis of Proxy Tasks for Anomalous Sound Detection Understanding intermediate layers using linear classifier probes

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T10:53:15.278767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e61f02dc-8fff-4b25-a88a-345f6708e699 · inbound

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models cites this paper.

No Reliable Evidence of Self-Reported Sentience in Small Large Language Models Understanding intermediate layers using linear classifier probes

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-03T09:31:52.284743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87069aac-61aa-44c6-a6bc-c2419586eb33 · inbound

Adapter Merging Reactivates Latent Reasoning Traces: A Mechanism Analysis cites this paper.

Adapter Merging Reactivates Latent Reasoning Traces: A Mechanism Analysis Understanding intermediate layers using linear classifier probes

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-03T08:03:24.221945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96f89125-1781-4d92-88dd-9e8e75a16511 · inbound

Representation Unlearning: Forgetting through Information Compression cites this paper.

Representation Unlearning: Forgetting through Information Compression Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T06:59:17.743673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0af79a6e-3b15-499c-8465-28e4b7c6cabf · inbound

Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits cites this paper.

Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits Understanding intermediate layers using linear classifier probes

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T05:00:54.907724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90fae6d2-d80e-453c-bdcc-8343d1713c80 · inbound

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models cites this paper.

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models Understanding intermediate layers using linear classifier probes

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T04:41:08.814528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c576b98e-0ef9-4f8d-b023-fbbc144df584 · inbound

From Features to Actions: Explainability in Traditional and Agentic AI Systems cites this paper.

From Features to Actions: Explainability in Traditional and Agentic AI Systems Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T03:50:14.472520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38e62d9b-833c-4caf-bc31-4b413c9153d9 · inbound

Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning cites this paper.

Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning Understanding intermediate layers using linear classifier probes

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-03T04:23:24.508265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 616d90a8-ca8e-4514-a55e-bb722bf690ad · inbound

The Information Geometry of Softmax: Probing and Steering cites this paper.

The Information Geometry of Softmax: Probing and Steering Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T22:58:05.011126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c54a5ff-1d40-4d9b-a540-6ece6a80a2c3 · inbound

The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning cites this paper.

The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-15T20:20:17.730365Z

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 a0825d20-f9bc-4197-8a86-ee6bd28b1461 · inbound

RAE-NWM: Navigation World Model in Dense Visual Representation Space cites this paper.

RAE-NWM: Navigation World Model in Dense Visual Representation Space Understanding intermediate layers using linear classifier probes

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-15T12:07:05.640150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bfdcc87-6f45-4c77-a29a-6ca84487e821 · inbound

SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation cites this paper.

SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: malformed identifier; no resolver link, observed 2026-07-13T21:52:18.253648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 833c757a-e13b-4a76-8c89-8ae9dbbeb84c · inbound

Do Audio-Visual Large Language Models Really See and Hear? cites this paper.

Do Audio-Visual Large Language Models Really See and Hear? Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-13T20:58:15.866491Z

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 1a693058-cc28-4d2a-8c0f-15e09b7f571d · inbound

A Model of Understanding in Deep Learning Systems cites this paper.

A Model of Understanding in Deep Learning Systems Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-13T16:53:00.156229Z

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 cbc7f616-8629-4b31-985a-e55dece523d6 · inbound

Beamforming Feedback as a Novel Attack Surface for Wi-Fi Physical-Layer Security cites this paper.

Beamforming Feedback as a Novel Attack Surface for Wi-Fi Physical-Layer Security Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T11:07:39.016814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db0c9a21-6055-40d9-bcb7-5dc1ddab0a23 · inbound

Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification cites this paper.

Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:21:00.937795Z

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 85a0fd9e-d9c3-4c60-9412-5c5e021112ca · inbound

Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies cites this paper.

Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies Understanding intermediate layers using linear classifier probes

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:20:52.000539Z

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 92f894ac-59fd-4407-aa20-dfdafca32e04 · inbound

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR cites this paper.

Preventing Latent Rehearsal Decay in Online Continual SSL with SOLAR Understanding intermediate layers using linear classifier probes

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:00:58.948180Z

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.