Pith. sign in

Paper Citation Record · LEDGER

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs

As of 19 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 1 inbound Pith citation observation for arXiv:2510.05864.

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

pith.paper-citation-record.v1
2510.05864 v2

Coverage vector

measured 63 of 63 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T11:17:36.000580Z

measured 64 of 64 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-12T06:11:38.403281Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

63 of 63 outbound references displayed

  • verified exact8
  • verified fuzzy0
  • unresolved55
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 17f45e31-37e2-4fdf-94a0-a77a8937bc8a · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 1

Resolution
verified exact
doi, observed 2026-08-04T11:18:31.674614Z

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.

source=arxiv_source observed=2026-08-04T11:17:06.543476Z digest=sha256:a42302db3bde328ba65b6bfbc2abc7168c191515d3ac8ee373cdbbd79807b42c

Observation b4609e29-dba0-4ff0-af50-9c8de8171938 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:06.626923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:06.626923Z digest=sha256:b04d6843bf62ff28a15e7d27e4584d7c21599a8a23ec16b88cc12950de2e746e

Observation 03f50441-9e9f-4b67-8d42-3099488c4967 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:06.763202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:06.763202Z digest=sha256:09766c68288607e27f5838701c490afdd1b9a459e6106794417ba67bc4b841ab

Observation 2ccb3277-0b37-41c2-99bf-823087b4b022 · outbound

This paper cites Qwen2 Technical Report.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Qwen2 Technical Report

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:06.921092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:06.921092Z digest=sha256:e2847a6fb0391971983dfa2af0ecdfcc002de961a0c65bf40a5aa732f820df0f

Observation 7f44d470-a18d-4e27-8af3-96f2088ac183 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:07.062443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:07.062443Z digest=sha256:af3e59bd22ea873e03e6b123faf2bc69c007c71e7ceeb0e43e57e56a19767ab7

Observation 50dbc5f1-4432-464a-a85a-ade71f1bf70d · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:07.214849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:07.214849Z digest=sha256:8a687de38978d37636031fc8d5ce3376a0029bfbc6f1e753f73dc9ffb143a784

Observation 88b75b39-5dbf-4cfb-ad21-beb90f5b112d · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 7

Resolution
verified exact
doi, observed 2026-08-04T11:18:31.460831Z

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.

source=arxiv_source observed=2026-08-04T11:17:07.383201Z digest=sha256:f31d49f4c9ff9e984e387eb26c7fe7764cbf4965c350ac3154df54d6c1373a11

Observation 5c0cc6c5-2cf5-4029-87de-5b9a09233a52 · outbound

This paper cites Longformer: The Long-Document Transformer.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Longformer: The Long-Document Transformer

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:07.445362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:07.445362Z digest=sha256:d79c19e2bddf120400f310a11f3e7d0911bc16fe9d6044f41bd7e33d00e1c7bc

Observation bc5628b9-651d-45dd-8db7-9d86ae6c4dff · outbound

This paper cites Verma, Deepak Gupta, A.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Verma, Deepak Gupta, A

Reference 9

Resolution
verified exact
doi, observed 2026-08-04T11:18:31.290664Z

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.

source=arxiv_source observed=2026-08-04T11:17:07.508783Z digest=sha256:5065c3bee189a2c13658b3f319f924ad6f76fd29545a200e652cbea85745174d

Observation 89b588b9-99b3-4ba5-9f31-1c5f0374e9f6 · outbound

This paper cites Mazurek, Katie Shilton, and Hal Daum \'e Iii.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Mazurek, Katie Shilton, and Hal Daum \'e Iii

Reference 10

Resolution
verified exact
doi, observed 2026-08-04T11:18:31.110035Z

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.

source=arxiv_source observed=2026-08-04T11:17:07.571017Z digest=sha256:476a17cc9eb3b5ddeb22ca4d89f3f16d88bff27f0af7d8748c976474134eddfa

Observation 31203529-9846-4200-82d8-6e958875abbc · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:07.675448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:07.675448Z digest=sha256:2884379b2976b9087cfed76a544b85605bc27adc02d4fe7c414dda94f4761707

Observation 20ecfe08-1355-4cd0-a50a-fda5c1b7b16c · outbound

This paper cites Scaling Instruction-Finetuned Language Models.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Scaling Instruction-Finetuned Language Models

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:07.771462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:07.771462Z digest=sha256:f6f354b468dbebaa74e8f419de18e3f2f376d82a56bda4824edf2f4ae6b0fedb

Observation d54c3476-d22b-4a74-9a10-196458b38b80 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:07.850591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:07.850591Z digest=sha256:14e4aef56055b48e661fc70dbac8bc3dfd74c949dcd465b7efd25d7fc4ee8361

Observation c626b416-2928-4287-a76e-831951cbf78b · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:07.903376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:07.903376Z digest=sha256:64e06d89e28429c8c6bf297aa1bce64470132da64da225427818f974467ddbb8

Observation ef4ae2d3-7323-4c38-9663-c45e7b67c2b3 · outbound

This paper cites Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:34.911012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:34.911012Z digest=sha256:cc9c84fcef10e2c99bcf67528d9be4c6c2379a39af82fee4a63862b7d02407ae

Observation 2c845363-7d7e-4b3e-9a4c-ea695e64d673 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:34.925282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:34.925282Z digest=sha256:252ca2d336926a7691371bf9c20ae58086e7a619714bc31d4be4b2ddf6adf253

Observation 690d2473-4448-4065-bb70-708edf3bb9e0 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:34.934537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:34.934537Z digest=sha256:f83dc3f8877dc05bd44b18eeebc32c7f48270c65e4267757c0e57d4ac81d689b

Observation 3fd91ecb-d23b-46b5-9898-d49334b61006 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:34.947172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:34.947172Z digest=sha256:658dddeac984b2b5222bd49a789502ba44f41af9ecda989c7ff8eb4eb691613b

Observation 658ea1c9-73c1-4d42-9ec5-0a1373f332cd · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:34.959770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:34.959770Z digest=sha256:2c1dc008c37f319c855ae591bb1c040cf65b627599592911a4104958eb7c0446

Observation 98c70e03-2ddf-4c35-9acc-4a6f0ed46b07 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:34.969665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:34.969665Z digest=sha256:53e8c1dc62a57ef6169ac6c4e3543afcff2132ccc40eb3066b3080b20dc05780

Observation 4ed628fc-dbe8-45d1-ac56-03372b4794f3 · outbound

This paper cites The Llama 3 Herd of Models.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs The Llama 3 Herd of Models

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:34.988568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:34.988568Z digest=sha256:a527c0469dc9354b5fcec15b5cfada2f998ba89f09cfdc062736046ef32b8eff

Observation c59fe453-846b-43b9-be6f-171e8e8814da · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.002535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.002535Z digest=sha256:0af248565a76d8d6386ff540dae598e5a4304a4797baac25eae8c6330109f446

Observation 425317c7-e6c4-4889-b17b-0f599aafac42 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.014682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.014682Z digest=sha256:2bcd307c27b8f6d42fd6ef7b0d55fd6316bc7b9d3ff68e1d3a8cfd7792e1be5f

Observation 9bae1e6c-cc68-4710-9415-709e8abef7da · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.028373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.028373Z digest=sha256:b441c68f2a71515342188f488ac13d330fbfa5b70c80a57ab82eb2443b7c0cb5

Observation d6ff2ab5-9710-40e7-af69-330797dbb83c · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.045996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.045996Z digest=sha256:c19dfb337459dba4da3958794e69e244ecb17f3a2a7cc7e538fcacf8d1587e62

Observation 4b45a4b6-14e5-4d50-bd0c-c7b3f4ba73a7 · outbound

This paper cites Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Breaking the Token Barrier: Chunking and Convolution for Efficient Long Text Classification with BERT

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.057359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.057359Z digest=sha256:fb58367d9a4f673e4828406de1801f40ec9a807c89e985c52a473047310e7ba5

Observation 60428167-c3aa-4d07-8970-ef61b2b40b71 · outbound

This paper cites Mistral 7B.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Mistral 7B

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.073536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.073536Z digest=sha256:7fb65188cb8ea469831de56883b88026f8f1887e19a468f051d1f12c7a8fe845

Observation 0de0622b-711a-44a4-ae45-ac15ed4f9356 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.089714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.089714Z digest=sha256:c94cb9ad834fdf2004e55ba0a9cb417d27d5673dfda209cc709707f633873610

Observation defe40e3-40c7-4e3a-a71e-65cbac0a2d5c · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.102959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.102959Z digest=sha256:3a3369d669795c3834d578de4cb6c6728e418809160e08bf30c56554f4e08a55

Observation 562836a7-5733-438d-a9bd-fd23c177c005 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.115604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.115604Z digest=sha256:3f5160f1f07458c009e818c587902eabd5892df8dd98866ae9b7d3537b0fba1c

Observation 702c1724-e19a-4b5c-b30b-ba768317c923 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.129891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.129891Z digest=sha256:bc242e0e45df5ff1d2ed038f0d4b5506f0374cc7c6a16831da6c8aac77932953

Observation 9e646d1b-4b37-4341-9341-287e195deb9a · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.144466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.144466Z digest=sha256:bbb3305669b6619cb9f1468a632705b2ccd35497937e6278d253d17366cb7d1b

Observation ef641f69-660c-46b2-8df5-b1c07e343c57 · outbound

This paper cites Schuller.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Schuller

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.160143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.160143Z digest=sha256:ec94bfd69b421849604b47da480c1d5fd502a814638af69997740a52ed6c994c

Observation 9a6bf7d3-9d56-42f2-bb78-e07e602b77d5 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.175713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.175713Z digest=sha256:d7c792c72adec77ac23e244525301ab920be2dec7f6f7b0fa0c05cb15e40810e

Observation 7df896cc-d0cf-4513-9a3f-8d3db8c3e666 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.185364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.185364Z digest=sha256:70d4ed84c8a9b06efdde7b9884c04d7931998bebd5c03c52fac9c0ea1b2b8974

Observation 5fcaa678-16fc-4c21-8f44-99382201d4e8 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 36

Resolution
verified exact
doi, observed 2026-08-04T11:18:30.836876Z

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.

source=arxiv_source observed=2026-08-04T11:17:35.193965Z digest=sha256:577c1eefbfd98f511b48870c6a2dbe840aa9be1a47072f249b0a55c8e75294ec

Observation 15bb3d13-59bf-4098-9a4e-a7feae8eb727 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.211919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.211919Z digest=sha256:42e02c52d59a540cc0a0396c66b44d584cccb36fbe435cdc7c94cf0648f8f23b

Observation 782268c7-2b5b-4c92-b364-5a9c77509de8 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.224787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.224787Z digest=sha256:e8f0310e470940921e4a6fa26df496b060c1134c73dc4f489a48eea6e657479a

Observation 61750126-feec-4ed2-961f-82ca70e46a10 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.236237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.236237Z digest=sha256:57525353b955cc4ef6dfe46ab827df6a9ab6e036007c5f97d5ebb3dd73a11181

Observation 93066469-f7e7-4493-aaa6-d7069d0bcd67 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.246459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.246459Z digest=sha256:eac40bcdacc0e8adaa41cbb5a0c723a267b64e894d2d15dbe064b183c37b7922

Observation 7cee2cde-54d9-4e4f-a36a-6ccf2839407c · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.256325Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.256325Z digest=sha256:1ad86f2ae5f24a0db2b73e133e0a7728cb4b9f89d04a20875e2a847265b54e80

Observation 396ff3d8-3c46-4d8d-97c4-ff1718dfbce4 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.269298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.269298Z digest=sha256:e0c86daafe45262872322fca7baf6702ee5e2ebd51f04b8a4316c7d96fa311f9

Observation a2349c0e-667a-4198-900f-4768d24a3d82 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.313675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.313675Z digest=sha256:14023543a73e1deab0727992d4b95d3541c4a5f32c818afeabcf3af9590a64d9

Observation 4e7ae288-0c00-4eab-97e1-f7cb0324b779 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.351878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.351878Z digest=sha256:de197851087f1f67edadc0a68b9e6dd509ba60569ad3e147ab838b9a32167c50

Observation 32291b09-06b4-431a-b868-fd102a685861 · outbound

This paper cites HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs HateTinyLLM : Hate Speech Detection Using Tiny Large Language Models

Reference 45

Resolution
verified exact
local_arxiv, observed 2026-08-04T11:18:30.575505Z

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.

source=arxiv_source observed=2026-08-04T11:17:35.384131Z digest=sha256:4b8cc70a2b0bd872f7716b8529e5b4c1c5cf73b6a38e8328d355c9353d52343d

Observation 4debc6cf-b4a0-47a8-9c45-1db13d5ea31e · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.412203Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.412203Z digest=sha256:b69af393dd51a27ddfb6f41e03b0e8b21873d57d2b0af77b8b2f4383686e2c1c

Observation 8d333ae7-2b99-455d-ad4e-0aadd324714f · outbound

This paper cites Cognitive Overload Attack:Prompt Injection for Long Context.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Cognitive Overload Attack:Prompt Injection for Long Context

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.453594Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.453594Z digest=sha256:61ddb23945be9adf5225fc9d1ea42f35089634ec682985f68f8f0687e0549656

Observation 0b65ab82-c4c6-4b7d-a2c0-bc08f9e5afec · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.495380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.495380Z digest=sha256:d18e2602de6a03380d261a2965c162b379136692eb2f77e8dffac6b1d4e1f99c

Observation b8eaae10-d168-40ad-bbc1-ee47cfb49799 · outbound

This paper cites Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, and Bo Li.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, and Bo Li

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.517461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.517461Z digest=sha256:ae278bf75cb39542db4bef02abad9b9894a099851be729776ae44d85e055893d

Observation 1addb708-1da5-4585-b80e-475e5cce71fe · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.550807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.550807Z digest=sha256:34adbda035813dd4cf5dd86644d9383726ed1477c0bd4d7e6dba25ee32bff5c1

Observation c47e7f58-2f14-4838-86ee-02ecf72e20b9 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.579703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.579703Z digest=sha256:b72edf157c72062a60f39ef16307d1b165d3859a3119aec5debe884b17447059

Observation 6d504001-f6df-4068-b0b8-e0323e1b62ec · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 52

Resolution
verified exact
doi, observed 2026-08-04T11:18:30.336705Z

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.

source=arxiv_source observed=2026-08-04T11:17:35.615652Z digest=sha256:0c6eb300ceede2019b9e6c56a9043db5fdb88439dd782ce95dc4aa0feafd0ff6

Observation 37edacdd-9b9e-46d0-98cf-71a0d39766d3 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.664497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.664497Z digest=sha256:cf9265a6d8d8e009d05630ff6c2fbc45cd0e08f1adb46f1f7f7368e815a6c61d

Observation 22b97d5a-939d-46e2-a80d-3219c2307e15 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 54

Resolution
verified exact
doi, observed 2026-08-04T11:18:30.080889Z

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.

source=arxiv_source observed=2026-08-04T11:17:35.691742Z digest=sha256:4279feb28f08c6197c28ed77259eb6014bdf1c5e3622e50f07141518b073ee90

Observation 7a1f5477-09c4-4143-b025-9d309b00a5d8 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.730085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.730085Z digest=sha256:f48d41a28d2d75650d7558d6d6c019b3fb0bf4105ae59cdbcaf714636e30fdb0

Observation efe6277e-b991-4bab-9b07-0f42adbcbc43 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.765912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.765912Z digest=sha256:7f0dc4e3ba7a9c173dd239528dc821986173f5aff27a181c6ac8e52b72e0a5cf

Observation 61042785-7692-49ef-bf2d-c7d2aaf3afcc · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.786046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.786046Z digest=sha256:7e4ea8018e7d768bcba07ecf66f1722a9537f148be47b803cd050dd4951bfaf3

Observation 1b51f88e-af77-43ed-9456-1f3b160d137f · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.819566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.819566Z digest=sha256:18caa0e35407a2139b45e1ab7a7bc45a2fb9ee7e556c07c9cc4581e0141aa0ed

Observation 8c29567f-9698-4dd4-9295-fd4976e2bcc7 · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.864119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.864119Z digest=sha256:37602f9865546e86345edf87365447bcadcd8770d0cddf0df0ef0847570b5d61

Observation ceeb499b-069f-4ae6-a9e5-1d432fb4529b · outbound

This paper cites an unresolved cited work.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs Unresolved cited work

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.892394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.892394Z digest=sha256:d671fb902027f7eb13e0206bb66c7721d680fa26527ccf989a3cb35db1a8cb08

Observation 8c942990-829b-4a7a-85f4-a3033e533616 · outbound

This paper cites DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.925369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.925369Z digest=sha256:6c4ebfae864e1c37709efdc3e48d8aa87eb64dd6862dc03129c00f5fd13f2dc6

Observation 32b9f7bb-78cf-40d3-9d7c-7a8cd9f0fdd1 · outbound

This paper cites URL: " 'urlintro :=.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs URL: " 'urlintro :=

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:35.971813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:35.971813Z digest=sha256:a835961d3a9061b07aa41de6296c08afc01f33d0cf2a5cffb18f59fa7663a2bf

Observation 8b5de0bb-3b57-493f-aa2b-59fc00b6cd90 · outbound

This paper cites write newline.

On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs write newline

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-04T11:17:36.000580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-04T11:17:36.000580Z digest=sha256:da99575490801f83dcd7f69ad93dde723023af8127bd2e448ec7b13bbe9505f7

Pith citing papers

Observation 46dd93e9-8734-44cb-884f-fca6e47eacd3 · inbound

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models cites this paper.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-12T06:11:38.403281Z digest=sha256:869f31a8afc6b23ea2900963d9a743f0051370fba0b5bab5fe81ce7fba2b8050