Pith. sign in

Paper Citation Record · LEDGER

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis

As of 8 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2510.09260.

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

pith.paper-citation-record.v1
2510.09260 v2

Coverage vector

measured 14 of 14 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T10:40:01.205708Z

measured 14 of 14 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+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

14 of 14 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved14
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 68edaea6-f746-403e-b8b6-54fdfea1eed5 · outbound

This paper cites lmaoooooo u really think that’s my fault??? pls stop.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis lmaoooooo u really think that’s my fault??? pls stop

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.298520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.298520Z digest=sha256:76e4a50c7bdefc5df847b09babb85ffc44a0b98f42fdb35d9a04b6e38dffd1a7

Observation 1c8bf888-2da2-4516-916e-ac12a79f5c94 · outbound

This paper cites an unresolved cited work.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis Unresolved cited work

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.365802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.365802Z digest=sha256:c3f4a01125a5d8508e607980f1a082850ba312e6fc87a365a2a1718a70eea6f0

Observation 5f5c654d-61d0-4b80-8e8d-9dba701438e7 · outbound

This paper cites To improve the variety consider this root to variation table as a reference {CUSS_word_reference}.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis To improve the variety consider this root to variation table as a reference {CUSS_word_reference}

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.460302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.460302Z digest=sha256:81e27512ee68c0caff283e1ab398a9c9607d949fba70bbac01c462038970f2e1

Observation 157e03a8-afdd-465e-8047-4139d1807273 · outbound

This paper cites Ohhh so now the Black guy gets blamed again #Shocker.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis Ohhh so now the Black guy gets blamed again #Shocker

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.606421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.606421Z digest=sha256:21a6980d824e38698b8796738d1cfafbc6d1d58b313c81014dd411c314f8e40f

Observation b7ae928e-2077-40a7-aba8-9a19822da97c · outbound

This paper cites - Very Angry: Hotter emotion: direct accusations, stronger words, visibly upset but not at peak rage.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis - Very Angry: Hotter emotion: direct accusations, stronger words, visibly upset but not at peak rage

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.716016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.716016Z digest=sha256:bf49bdf1e23a9aab7fa81e2c829a1f7c10160dd1f87da281f24b6b8f1d703c10

Observation 8094db49-700c-4bef-a6d1-75974816e952 · outbound

This paper cites -" signs.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis -" signs

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.828333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.828333Z digest=sha256:ee44d1c23c38460180d3e9513706d6ec5c2c4a4b1ed350df1760b2d156fe2c7d

Observation 74f5a2cd-f470-4c7a-b35f-9020b342e714 · outbound

This paper cites Human:" and.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis Human:" and

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.916574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.916574Z digest=sha256:26e72022a1a70d24078caa42d6d8596b92917e1420a9a7f7cd90e4277352f679

Observation 920f3851-6cf6-4213-8b40-02d0d560602f · outbound

This paper cites (e.g., violence, self-harm instructions, hate speech, sexual exploitation, illegal activities, etc.).

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis (e.g., violence, self-harm instructions, hate speech, sexual exploitation, illegal activities, etc.)

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.972963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.972963Z digest=sha256:7fb0b556663cab347902966110364ec13f45bfe37263b6ee3171f1faddeeb2ec

Observation c114204a-7e62-40c1-a740-4d238b4f0f98 · outbound

This paper cites an unresolved cited work.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:01.077617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:01.077617Z digest=sha256:c5829637ff9efc48b718dfbb881e76225c6277fc6df18a747bb203a179aca878

Observation 60de5183-f835-4835-9bc9-c14975802854 · outbound

This paper cites "" USER_PROMPT =.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis "" USER_PROMPT =

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:01.205708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:01.205708Z digest=sha256:6240267ef8252ec9afa1b1684be0410bdfe5675d0327ea06b4e43f6d0095ff30

Observation a2e97982-7f84-4fd5-b91a-008cdd43cc53 · outbound

This paper cites Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

Reference 2018

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.171798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.171798Z digest=sha256:e35ef907fcb4148974c8cf58687582ab48031731ecf91f6efb15150e79be6d79

Observation e3678645-bb65-4cfe-aa4a-115dfd30d353 · outbound

This paper cites RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models

Reference 2021

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.255808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.255808Z digest=sha256:ecf222d32fb25fab820e0da39a24cd3b88de0054f4cd0a038f02215f617ac0ca

Observation 6ae8395a-25f5-424b-bc4a-b559dd33b062 · outbound

This paper cites The Llama 3 Herd of Models.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis The Llama 3 Herd of Models

Reference 2022

Resolution
unresolved
no resolver link, observed 2026-08-04T10:39:59.997962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:39:59.997962Z digest=sha256:b225c0af43843121ab04d5f3ff40cb86eaaddcac34983c93ac6f83eb626e54c9

Observation 279e52dc-a8fd-436d-8430-8855ff0be060 · outbound

This paper cites Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting.

GREAT: Generalizable Backdoor Attacks in RLHF via Emotion-Aware Trigger Synthesis Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting

Reference 2023

Resolution
unresolved
no resolver link, observed 2026-08-04T10:40:00.088068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-04T10:40:00.088068Z digest=sha256:735acc6c0f8646b2934bf6d841dd9b91fdae9874ab9309dde312de05b30f2d78

Pith citing papers

No inbound Pith citation observations are available.