Paper Citation Record · LEDGER

Lightweight Safety Classification Using Pruned Language Models

As of 19 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 3 inbound Pith citation observations for arXiv:2412.13435.

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

pith.paper-citation-record.v1
2412.13435 v1

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T13:11:27.318659Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:39:05.411301Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-19T11:53:03.579380Z

Reference resolution

35 of 35 outbound references displayed

verified exact4
verified fuzzy2
unresolved28
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

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

This paper cites Understanding intermediate layers using linear classifier probes.

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 f86e20bc-e063-4b78-8695-2213dd8c0f90 · outbound

This paper cites an unresolved cited work.

Lightweight Safety Classification Using Pruned Language Models Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-11T13:11:27.787797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1552ee4f-13ab-4e5e-9f72-46c06e0dd26e · outbound

This paper cites Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.

Lightweight Safety Classification Using Pruned Language Models Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.216049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa91d28-48c4-44cf-92ee-ab967d38945c · outbound

This paper cites Extending Knowledge Graphs with Subjective Influence Networks for Personalized Fashion.

Lightweight Safety Classification Using Pruned Language Models Extending Knowledge Graphs with Subjective Influence Networks for Personalized Fashion

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-08-11T13:11:27.219618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91ef6a88-4c8a-4956-a1ec-e0e8b88b4253 · outbound

This paper cites Logistic Regression makes small LLMs strong and explainable "tens-of-shot" classifiers.

Lightweight Safety Classification Using Pruned Language Models Logistic Regression makes small LLMs strong and explainable "tens-of-shot" classifiers

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.222808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f94f497b-2ca5-434f-9822-3568c5aaf8cd · outbound

This paper cites MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models.

Lightweight Safety Classification Using Pruned Language Models MINI-LLM: Memory-Efficient Structured Pruning for Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.226591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d2eab33-97cd-4be8-b8b4-008039f009a1 · outbound

This paper cites Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-shot In-Context Learners.

Lightweight Safety Classification Using Pruned Language Models Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-shot In-Context Learners

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-08-11T13:11:27.570921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 71e0d5e9-c82a-49e1-bc1e-8f6ccdce3560 · outbound

This paper cites Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to?.

Lightweight Safety Classification Using Pruned Language Models Evolutionary Fuzzy Systems for Explainable Artificial Intelligence: Why, When, What for, and Where to?

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.233906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a03626-5262-4769-af56-12f36a2af0c1 · outbound

This paper cites Model Explainability in Deep Learning Based Natural Language Processing.

Lightweight Safety Classification Using Pruned Language Models Model Explainability in Deep Learning Based Natural Language Processing

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.237620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff891a96-45b4-400e-b5aa-786d1205030d · outbound

This paper cites AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts.

Lightweight Safety Classification Using Pruned Language Models AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.241267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2447327e-4d10-4fec-b324-2b57de21388e · outbound

This paper cites The Llama 3 Herd of Models.

Lightweight Safety Classification Using Pruned Language Models The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.244926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93dad778-be06-48e8-83b9-f2dcbad5118a · outbound

This paper cites The Unreasonable Ineffectiveness of the Deeper Layers.

Lightweight Safety Classification Using Pruned Language Models The Unreasonable Ineffectiveness of the Deeper Layers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.248085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9aa58de5-405f-4276-9f54-2fb2db47b341 · outbound

This paper cites exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models.

Lightweight Safety Classification Using Pruned Language Models exBERT: A Visual Analysis Tool to Explore Learned Representations in Transformers Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.251360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f109e5be-7272-4b62-9b81-2c995d2249c2 · outbound

This paper cites Attention Tracker: Detecting Prompt Injection Attacks in LLMs.

Lightweight Safety Classification Using Pruned Language Models Attention Tracker: Detecting Prompt Injection Attacks in LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.254211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3871117c-3e45-42c8-a615-f2e09aef85dc · outbound

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

Lightweight Safety Classification Using Pruned Language Models Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.257508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caf971d1-5ca7-4911-aba2-6ddc5ee77a8d · outbound

This paper cites Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks.

Lightweight Safety Classification Using Pruned Language Models Prompt Packer: Deceiving LLMs through Compositional Instruction with Hidden Attacks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.260452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a02c2b83-9487-4298-ad0a-d1c176727c38 · outbound

This paper cites Large Language Models Are Overparameterized Text Encoders.

Lightweight Safety Classification Using Pruned Language Models Large Language Models Are Overparameterized Text Encoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.263716Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b187e0ba-b10c-4941-963f-0f508419d038 · outbound

This paper cites original-date: 2024-03-27T19:04:05Z.

Lightweight Safety Classification Using Pruned Language Models original-date: 2024-03-27T19:04:05Z

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:11:27.778966Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1e0b91b9-bf60-4677-bc22-c9705f4a2f33 · outbound

This paper cites Interactive Visualization and Manipulation of Attention- based Neural Machine Translation.

Lightweight Safety Classification Using Pruned Language Models Interactive Visualization and Manipulation of Attention- based Neural Machine Translation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.269514Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c215e3-41d3-4839-9c02-73e7c764ba4f · outbound

This paper cites SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models.

Lightweight Safety Classification Using Pruned Language Models SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.272180Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64bc7a4d-62c9-410b-8f85-76cbd82a4532 · outbound

This paper cites A Unified Approach to Interpreting Model Predictions.

Lightweight Safety Classification Using Pruned Language Models A Unified Approach to Interpreting Model Predictions

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.275438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e968e38-6eac-4acc-b9f3-ff1e141d5644 · outbound

This paper cites From Understanding to Utilization: A Survey on Explainability for Large Language Models.

Lightweight Safety Classification Using Pruned Language Models From Understanding to Utilization: A Survey on Explainability for Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.278527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 198ebd0b-0b4e-4ada-9eee-3e0a300e03c1 · outbound

This paper cites LLM-Pruner: On the Structural Pruning of Large Language Models.

Lightweight Safety Classification Using Pruned Language Models LLM-Pruner: On the Structural Pruning of Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.281244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 579f59a8-7fb3-4278-bbb3-1bcd3a1a1d83 · outbound

This paper cites Towards Agile Text Classifiers for Everyone.

Lightweight Safety Classification Using Pruned Language Models Towards Agile Text Classifiers for Everyone

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.284152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58e2f91d-e5f0-4f2c-a3fa-66d756990b56 · outbound

This paper cites Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning.

Lightweight Safety Classification Using Pruned Language Models Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.287758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38424319-ab32-4b3e-b3bd-ab2785b4018a · outbound

This paper cites deberta-v3-base-prompt-injection.

Lightweight Safety Classification Using Pruned Language Models deberta-v3-base-prompt-injection

Reference 26

Resolution: verified exact; doi, observed 2026-08-11T13:11:27.423523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4275d321-ac99-4403-a6dd-25876e0bc58c · outbound

This paper cites SPML: A DSL for Defending Language Models Against Prompt Attacks.

Lightweight Safety Classification Using Pruned Language Models SPML: A DSL for Defending Language Models Against Prompt Attacks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.294794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a3c789-cb5e-4e70-992b-b023b92c037c · outbound

This paper cites Does Representation Matter? Exploring Intermediate Layers in Large Language Models.

Lightweight Safety Classification Using Pruned Language Models Does Representation Matter? Exploring Intermediate Layers in Large Language Models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T13:11:27.769557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9e716e4c-9663-4d1d-befb-bbb8a6209586 · outbound

This paper cites Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models.

Lightweight Safety Classification Using Pruned Language Models Seq2Seq-Vis: A Visual Debugging Tool for Sequence-to-Sequence Models

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-08-11T13:11:27.399409Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c185dd6d-2530-4d50-8b49-e2785480e3c9 · outbound

This paper cites The geometry of hidden representations of large transformer models.

Lightweight Safety Classification Using Pruned Language Models The geometry of hidden representations of large transformer models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.303789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f84271-5f12-4802-b474-6d4f226f76e6 · outbound

This paper cites Visualizing Attention in Transformer-Based Language Representation Models.

Lightweight Safety Classification Using Pruned Language Models Visualizing Attention in Transformer-Based Language Representation Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.306571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7271482d-8d57-4639-a2f9-e1d8ee0651ed · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Lightweight Safety Classification Using Pruned Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.309586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c51f7eab-d809-4287-9466-78088fc5283b · outbound

This paper cites Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models.

Lightweight Safety Classification Using Pruned Language Models Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.312668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c272931-d4e3-4ef7-9fe8-c0460bd97c6f · outbound

This paper cites LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset.

Lightweight Safety Classification Using Pruned Language Models LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T13:11:27.315771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 252d8eb9-9b3e-417f-9986-8f274d4a92fd · outbound

This paper cites On the Explainability of Natural Language Processing Deep Models.

Lightweight Safety Classification Using Pruned Language Models On the Explainability of Natural Language Processing Deep Models

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-08-11T13:11:27.622133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Pith citing papers

Observation ee88e6a9-22ce-4327-a24b-2bb1a5ca65e8 · 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 Lightweight Safety Classification Using Pruned Language Models

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-19T11:53:03.580813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 476a462b-a819-46aa-a5cd-fd0632411bc6 · inbound

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning cites this paper.

PUMA: Layer-Pruned Language Model for Efficient Unified Multimodal Retrieval with Modality-Adaptive Learning Lightweight Safety Classification Using Pruned Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T18:39:05.411301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b434071-60ab-45dd-94a1-f0891d6c830a · inbound

LLM Safety From Within: Detecting Harmful Content with Internal Representations cites this paper.

LLM Safety From Within: Detecting Harmful Content with Internal Representations Lightweight Safety Classification Using Pruned Language Models

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:20:23.025851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.