Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-30T10:56:48.227998Z
Paper Citation Record · LEDGER
As of 7 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2607.23838.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-07-30T10:56:48.227998Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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
40 of 40 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 34d4a1ba-3c68-4470-8737-bfabb166dccb · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Retrieval-augmented generation for knowledge-intensive NLP tasks,
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1034e036-5d35-4e13-90d1-5b38feac677c · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models
Reference 2
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e1cf35d4-4652-463c-ba29-bed07152b79a · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Poisoning retrieval corpora by injecting adversarial passages,
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3132ed0-c8b8-4461-80c3-2420095fe1c0 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1fda1b3-37e0-4c7d-abd6-d571f2313413 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Sentence-BERT: Sentence embeddings using Siamese BERT-networks,
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 66ba4d60-9834-4e95-b354-ae93dd1d7826 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Billion-scale similarity search with GPUs,
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 971f8b94-21a1-4235-a9b8-8b45a1889eb1 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Term-weighting approaches in automatic text retrieval,
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e49eb2e4-34c2-4485-9b46-52703edce1d2 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Lan- guage models are unsupervised multitask learners,
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f4d09a65-062f-49bd-8149-7091d3275220 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation The Byzantine generals problem,
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6590774d-daec-485a-af93-0d41fb5f8e3e · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation On Evaluating Adversarial Robustness
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2ad9f6d5-99ec-49c6-97b3-b47ed886044e · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fe375c13-9550-4fcb-8731-134bd124a9ab · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation HotFlip: White-box adversarial examples for text classification,
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6fc8c2de-655d-4dee-bff9-d1a5450edbe2 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation RAGShield: Detecting Numerical Claim Manipulation in Government RAG Systems
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 921d8fdb-c382-4734-9795-2b86a5166311 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation TrustRAG: Enhancing Robustness and Trustworthiness in Retrieval-Augmented Generation
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 61e0e649-2c5d-45e0-ba93-81d2ba35811d · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Benchmarking Poisoning Attacks against Retrieval-Augmented Generation
Reference 15
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0625251b-8242-4d11-b35b-27000d0535c5 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Practical poi- soning attacks against retrieval-augmented generation,
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5070b6fa-8154-45e7-a317-ecaf7fa0da6a · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b628c666-e4c0-4d0a-a533-51cb2361457f · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Rescuing the unpoisoned: Efficient defense against knowledge corruption attacks on RAG systems,
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9652c7b4-c465-4a88-b82b-6bc5e1e5ae1e · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Traceback of poisoning attacks to retrieval-augmented generation,
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 70b730e6-c6ea-44dd-a019-99e2bb09f793 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Dense passage retrieval for open-domain question answering,
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ec7f8b21-5958-4bfe-be0b-7dc38b343b7c · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Unsupervised Dense Information Retrieval with Contrastive Learning
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 3cfa86c3-7dc1-45c5-9f68-3be40958d1f5 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Approximate nearest neighbor negative contrastive learning for dense text retrieval,
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c81475a1-4d4a-49fb-bdd0-a5abddf8689d · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation The probabilistic relevance framework: BM25 and beyond,
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9ef3a9f1-8071-497a-9a29-4fe59ca6bfd3 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation BEIR: A heterogeneous benchmark for zero-shot evaluation of infor- mation retrieval models,
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d373f52e-34c9-4470-acb9-f6489e8f8416 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Machine learning with adversaries: Byzantine tolerant gradient descent,
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9f147973-fd66-4b21-891b-31032c124f7e · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Byzantine-robust distributed learning: Towards optimal statistical rates,
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation da3fb2a6-d82b-4af1-a8b0-dd1d549df9c1 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation The hidden vul- nerability of distributed learning in Byzantium,
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 594f06a7-30e3-480d-9c0e-b2a5eac7f6fd · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Distributed statistical machine learning in adversarial settings: Byzantine gradient descent,
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1e67a15e-fe5e-44a3-ae45-5c4ab8bcf028 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation FLTrust: Byzantine- robust federated learning via trust bootstrapping,
Reference 29
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 745c57ad-0c86-4afd-9463-1f5a3fd9b97b · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Efficient and robust approxi- mate nearest neighbor search using hierarchical navigable small world graphs,
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d5c15f7c-95c2-4507-9822-ce4fa2857076 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Product quantization for nearest neighbor search,
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f12dcd3c-5ccb-4b9e-b867-be102f3d8a10 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Natural Questions: A benchmark for question answering research,
Reference 32
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation eca42611-fef9-4e8f-ad10-ab75d945df62 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation HotpotQA: A dataset for diverse, explainable multi-hop question answering,
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 42ce52f1-3874-4c42-a5b6-630a2969330b · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 63eac46f-8f0b-439f-8049-e19d75c9d4c5 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation MPNet: Masked and permuted pre-training for language understanding,
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bb78122b-43fd-46b5-a697-e14a7156bf25 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation BERT: Pre-training of deep bidirectional transformers for language understanding,
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 190f8434-b261-43c7-98f9-fb4b2a21efb2 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation The Faiss library
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ab7716de-4149-441a-8a2d-7446cab7e207 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Milvus: A purpose-built vector data management system,
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d8131fc9-f083-4d85-bdb7-cc9d4d3d7158 · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation Survey of Vector Database Management Systems
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 85c7b8db-690a-427d-bf1e-32fd6b72e00d · outbound
TriShieldRAG: A Three-Ring Defense-in-Depth Framework Against Knowledge Corruption in Retrieval-Augmented Generation RAGPart & RAGMask: Retrieval-stage defenses against corpus poi- soning in retrieval-augmented generation,
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
No inbound Pith citation observations are available.