Paper Citation Record · LEDGER

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs

As of 19 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2608.11348.

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

pith.paper-citation-record.v1
2608.11348 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T14:19:02.340619Z

measured 30 of 30 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

30 of 30 outbound references displayed

verified exact0
verified fuzzy15
unresolved15
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 892d3a04-cb5e-46a4-9039-8d0e4fa2cc56 · outbound

This paper cites GPT-4 Technical Report.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.223788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b70edc4-ec9a-4cdd-a398-daf5df57626e · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.228749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 283ed4b0-df58-4bae-b5e8-5313987ae7e3 · outbound

This paper cites BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.233020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 312fbac0-ebac-46e1-8384-8457f2cad5de · outbound

This paper cites Bait: Large language model backdoor scanning by inverting attack target,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Bait: Large language model backdoor scanning by inverting attack target,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.766769Z

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 359a0288-b3e0-4acd-a2f3-3408cfb4b45f · outbound

This paper cites Composite backdoor attacks against large language models,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Composite backdoor attacks against large language models,

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.753445Z

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 ef66ea80-4970-47c8-a6f0-b85d2a2ac616 · outbound

This paper cites Great, now write an article about that: The crescendo{Multi-Turn}{LLM}jailbreak attack,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Great, now write an article about that: The crescendo{Multi-Turn}{LLM}jailbreak attack,

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.739865Z

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 34204acb-43cc-4cc0-b53c-8c2c78eec1b7 · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.249695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65b61a9f-780b-4534-86a9-81f8793f45e3 · outbound

This paper cites Chain-of- scrutiny: Detecting backdoor attacks for large language models,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Chain-of- scrutiny: Detecting backdoor attacks for large language models,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.725146Z

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 6ef63ed5-92b5-4a82-b073-304bab61c640 · outbound

This paper cites When backdoors speak: Understanding llm backdoor attacks through model-generated explana- tions,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs When backdoors speak: Understanding llm backdoor attacks through model-generated explana- tions,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.710010Z

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 1783c0dc-6e15-419d-a421-b1a411efe747 · outbound

This paper cites Mitigating backdoor threats to large language models: Advancement and challenges,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Mitigating backdoor threats to large language models: Advancement and challenges,

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.694701Z

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 dc60ef13-b1a4-4d35-b1bf-3c619808589c · outbound

This paper cites Onion: A simple and effective defense against textual backdoor attacks,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Onion: A simple and effective defense against textual backdoor attacks,

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.680072Z

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 0ac380f3-35f9-498e-b455-5f7bab67fcad · outbound

This paper cites Iclscan: Detecting backdoors in black-box large language models via targeted in-context illumination,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Iclscan: Detecting backdoors in black-box large language models via targeted in-context illumination,

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.668404Z

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 16bee2bd-c47c-45ba-921f-d527a150ab71 · outbound

This paper cites Bite: Textual backdoor attacks with iterative trigger injection,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Bite: Textual backdoor attacks with iterative trigger injection,

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.656664Z

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 18c468eb-96bf-45ed-9fba-f3f9ceae5c92 · outbound

This paper cites Imbert: Making bert immune to insertion-based backdoor attacks,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Imbert: Making bert immune to insertion-based backdoor attacks,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.642386Z

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 eee3c784-70a4-486b-aa10-adb48b46e1ae · outbound

This paper cites Granite 4.0 language models,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Granite 4.0 language models,

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.627030Z

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 fc4ce676-9301-4d81-bce1-d61394a5a6d3 · outbound

This paper cites The Llama 3 Herd of Models.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs The Llama 3 Herd of Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.282170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dc4d025-e53c-4c26-8267-71bcf7a8afac · outbound

This paper cites Mistral 7B.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Mistral 7B

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.285655Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3a0426f-187e-4c2f-8bb9-92e0c8290624 · outbound

This paper cites Qwen3 Technical Report.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Qwen3 Technical Report

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.289933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fa77aba-a1ca-4862-9477-484b689c209b · outbound

This paper cites Gemma 3 Technical Report.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Gemma 3 Technical Report

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.293255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bdef80a-68b4-40a0-a1ec-3ce828c604ec · outbound

This paper cites Phi-4 Technical Report.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Phi-4 Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.297588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20071e8f-7a1e-4828-a557-82a136333501 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Lora: Low-rank adaptation of large language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.301879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24df339c-ab20-4d97-a4b3-6b58b89040f5 · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.306366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1babca80-b9db-409d-a3fa-2fff6c9ba181 · outbound

This paper cites Axolotl: Open source llm post- training,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Axolotl: Open source llm post- training,

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.600030Z

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 12889811-b456-485a-ae87-767cf440091c · outbound

This paper cites QLoRA: Efficient Finetuning of Quantized LLMs.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs QLoRA: Efficient Finetuning of Quantized LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.314472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cb6a8d7-c3cd-4e6a-8bc5-0abe374b30a1 · outbound

This paper cites Unsloth,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Unsloth,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.586525Z

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 516006b6-f8b1-4f91-8bc4-82fd7408f646 · outbound

This paper cites Cleangen: Mitigating backdoor attacks for generation tasks in large language models,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Cleangen: Mitigating backdoor attacks for generation tasks in large language models,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.574543Z

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 9613aadd-a1ce-48ab-9e68-3b326bb32422 · outbound

This paper cites CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.327400Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 223df19d-df49-4f60-aac6-128b7205f104 · outbound

This paper cites Fine-pruning: Defending against backdooring attacks on deep neural networks,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Fine-pruning: Defending against backdooring attacks on deep neural networks,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.331599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a91ea1b2-a459-419b-8c48-d80b0bd788f7 · outbound

This paper cites Neural cleanse: Identifying and mitigating backdoor attacks in neural networks,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Neural cleanse: Identifying and mitigating backdoor attacks in neural networks,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T14:19:02.336073Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5473567d-a513-432c-aa58-2ff1ae800009 · outbound

This paper cites Test-time backdoor mitigation for black-box large language models with defensive demonstrations,.

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs Test-time backdoor mitigation for black-box large language models with defensive demonstrations,

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T14:19:02.546015Z

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

No inbound Pith citation observations are available.