{"as_of":"2026-08-15T21:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f918ea18909f90b9e66b33a3e44e0e0a0d9bb4ebc7cb581113d14922fa0e069a","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T18:18:55.188005Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.08099/citation-record","integrity":"/paper/2412.08099/integrity","json":"/paper/2412.08099/citation-record.json","paper":"/paper/2412.08099"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-11T18:18:54.768110Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.768110Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:fe126ee907fe48787f9392b4ecaaf0201eae7854bc0eb6b3e9048fb3e7572c1a","observation_id":"b939aec7-9f25-4fa7-909d-ed86cd5bcd58","resolution":{"observed_at":"2026-08-11T18:18:54.768110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-11T18:18:54.776004Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.776004Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:e5a347d4119ca6d1f01d78b6ba4993ce24f8412252f957c1c1055d37538ae7bf","observation_id":"425abd9b-16d4-4008-8f95-7f2ad8501432","resolution":{"observed_at":"2026-08-11T18:18:54.776004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:54.784178Z","title":"Nhits: Neural hierarchical interpolation for time series forecasting","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.784178Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:42fb9a8d9a144c1d7a91b85bf948530c9b752687c1ead4d87f8b2b2cd163e7e0","observation_id":"94ffcab9-af41-407d-bba3-8dbb34f45b40","resolution":{"observed_at":"2026-08-11T18:18:54.784178Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-11T18:18:54.797719Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.797719Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:95df82d3f3084902ba4ac89594ad9e2fc65bab3b1828b70613865a6ed3387007","observation_id":"a1e9f42f-4d85-4f2b-a442-f7eafd7d077f","resolution":{"observed_at":"2026-08-11T18:18:54.797719Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.544835Z","title":"Exponential smoothing: The state of the art","venue":null,"work_id":"6b04c9b4-094e-446a-90b3-8ef798b8ac3f","year":1985},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.806981Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:8e1266879ac8cb5297125a24764c0545b7f8166894f9185a7b238af807c92bb6","observation_id":"8536bfbd-5a16-422e-b520-e581fcb37b98","resolution":{"observed_at":"2026-08-11T18:18:56.557033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03589","last_updated":"2024-05-27T23:34:15Z","snapshot_observed_at":"2026-08-13T05:56:47.281396Z","submitted_at":"2023-10-05T15:14:00Z","title":"TimeGPT-1","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03589","snapshot_observed_at":"2026-08-11T18:18:54.830131Z","title":"Timegpt-1","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.830131Z"},"links":{"cited_paper":"/paper/2310.03589","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:4a827c00a1356d4863dee38bf36a5ab1058447f0285f997c3ad746e551a1858b","observation_id":"c12c4d3d-2dd2-4ac6-8870-7017209ea21b","resolution":{"observed_at":"2026-08-11T18:18:54.830131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-12T17:13:46.394331Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-11T18:18:54.837784Z","title":"Explaining and harnessing adversarial examples","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.837784Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:726a5ffa915b60c80256b3fd3bfbbfc5b4c05acb3abf82271abd0b8fb436fa5d","observation_id":"f571311b-c5a7-42e5-b566-4df2c38e5263","resolution":{"observed_at":"2026-08-11T18:18:54.837784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:54.843969Z","title":"Not what you've signed up for: Compromising real-world llm-integrated applications with indirect prompt injection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.843969Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:51663ef89b6c08198aec0f59fa9d20f01bbb5cb98e0b661ebc91bc74de5fc240","observation_id":"14de8643-1238-4f6d-8e5d-b33695843d0c","resolution":{"observed_at":"2026-08-11T18:18:54.843969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:54.853377Z","title":"Large language models are zero-shot time series forecasters","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.853377Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:f86eb6e1a8b2caced3f1330e6bf7c68001b9c43d393bda5d757e0fbf0d8fdaa3","observation_id":"ff102a74-3d24-4b21-beb6-9c99f7d2cd3d","resolution":{"observed_at":"2026-08-11T18:18:54.853377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.13733","last_updated":"2021-04-15T17:43:43Z","snapshot_observed_at":"2026-08-13T20:11:56.287655Z","submitted_at":"2021-04-15T17:43:43Z","title":"Gradient-based Adversarial Attacks against Text Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.13733","snapshot_observed_at":"2026-08-11T18:18:54.858496Z","title":"Gradient-based adversarial attacks against text transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.858496Z"},"links":{"cited_paper":"/paper/2104.13733","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:d40b99a3e13288d04cab822c45a6ff526954644edeb9fc135f65e32b512f9f3e","observation_id":"593d6536-cb0a-423c-bbd5-1e339ea0f6d4","resolution":{"observed_at":"2026-08-11T18:18:54.858496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03182","last_updated":"2024-02-05T16:46:35Z","snapshot_observed_at":"2026-08-13T09:27:49.839216Z","submitted_at":"2024-02-05T16:46:35Z","title":"Empowering Time Series Analysis with Large Language Models: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03182","snapshot_observed_at":"2026-08-11T18:18:54.863942Z","title":"Empowering time series analysis with large language models: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.863942Z"},"links":{"cited_paper":"/paper/2402.03182","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:c6768ffc96e2caf8cb8f61183bc16213ec66066eb585169f7bb2ed7de3e7b99b","observation_id":"7a95d075-06ba-404b-a58f-480eb248909b","resolution":{"observed_at":"2026-08-11T18:18:54.863942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01728","last_updated":"2024-01-29T06:27:53Z","snapshot_observed_at":"2026-08-13T07:00:35.291225Z","submitted_at":"2023-10-03T01:31:25Z","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01728","snapshot_observed_at":"2026-08-11T18:18:54.871390Z","title":"Time-llm: Time series forecasting by reprogramming large language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.871390Z"},"links":{"cited_paper":"/paper/2310.01728","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:169810b3b853bca7e31d87236b137e3e0ab363b01c77f142428e78e6910553b6","observation_id":"51ba80f0-610c-4635-87e8-3b0e3c81f2c4","resolution":{"observed_at":"2026-08-11T18:18:54.871390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10196","last_updated":"2026-06-08T01:28:46Z","snapshot_observed_at":"2026-08-13T21:10:41.054744Z","submitted_at":"2023-10-16T09:06:00Z","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10196","snapshot_observed_at":"2026-08-11T18:18:54.877978Z","title":"Large models for time series and spatio-temporal data: A survey and outlook","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.877978Z"},"links":{"cited_paper":"/paper/2310.10196","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:1b17fa73bde401c293ebbb6daf785c60b46e1b74136b59c732658fa9f2407f33","observation_id":"37762067-1990-4ba4-b681-209c666c9397","resolution":{"observed_at":"2026-08-11T18:18:54.877978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.499446Z","title":"Distance measures for effective clustering of arima time-series","venue":null,"work_id":"a092bce9-c7d4-437b-bfa5-87c406310d10","year":2001},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.884652Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:29ce25058efc1cbe9ee2aac1fa77821985f5bf5d696f25a18f540b1206b73943","observation_id":"8fa9ef4e-5a68-4508-adee-0eb9cb391c74","resolution":{"observed_at":"2026-08-11T18:18:56.506357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.434084Z","title":"Modeling long-and short-term temporal patterns with deep neural networks","venue":null,"work_id":"2b607d2b-bc92-4b5d-bced-5f54cb077797","year":2018},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.891967Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:d05921844c013053b0eb16b08ff3e5fc8586e2da9fc47e4363bd349cb086f7e2","observation_id":"f603307b-c1dd-49a8-9740-f4fe9b8f1585","resolution":{"observed_at":"2026-08-11T18:18:56.450311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.01638","last_updated":"2025-03-29T08:44:30Z","snapshot_observed_at":"2026-08-12T23:52:01.581482Z","submitted_at":"2024-06-03T00:27:29Z","title":"TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01638","snapshot_observed_at":"2026-08-11T18:18:54.908004Z","title":"Timecma: Towards llm-empowered time series forecasting via cross-modality alignment","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.908004Z"},"links":{"cited_paper":"/paper/2406.01638","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:de4e8e2af1df0f33b3cdc14cbd74a98d997e343bde7aca10f9ece5f020f8b623","observation_id":"cff67056-d779-4d01-b007-eebf73fe64a1","resolution":{"observed_at":"2026-08-11T18:18:54.908004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.384947Z","title":"Practical adversarial attacks on spatiotemporal traffic forecasting models","venue":null,"work_id":"1904ea38-c38f-4692-b718-8a96d471e6e4","year":2022},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.925778Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:3ba6532127239cfcb4808db44774c0d59a403a1801e75778490514109954d41b","observation_id":"bec24694-1335-49f6-8141-ed1277c4f5cb","resolution":{"observed_at":"2026-08-11T18:18:56.394168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04608","last_updated":"2021-09-10T01:31:53Z","snapshot_observed_at":"2026-08-08T18:28:39.037602Z","submitted_at":"2021-09-10T01:31:53Z","title":"Spatially Focused Attack against Spatiotemporal Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2109.04608","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.04608","snapshot_observed_at":"2026-08-11T18:18:55.729000Z","title":"Spatially Focused Attack against Spatiotemporal Graph Neural Networks","venue":"cs.LG","work_id":"0e8c32b7-4cee-4599-97da-98aeef8ea55a","year":2021},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.942246Z"},"links":{"cited_paper":"/paper/2109.04608","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:55b55ced8b8f09d81b65c64927aa2f5e2a5aea2cb7a111a1c91e0018d5e35182","observation_id":"3ca83676-101b-4bd6-8741-26e0ca6ce0f2","resolution":{"observed_at":"2026-08-11T18:18:55.737997Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.357682Z","title":"A universal framework of spatiotemporal bias block for long-term traffic forecasting","venue":null,"work_id":"70781143-af51-48cc-a3f7-62b57e7b69c3","year":2022},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.954466Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:eae1e93081df7306c10af0d22093c55ac8af23905a6a7a7418bd997f9e7cfea2","observation_id":"cd18e936-4fd7-47be-b410-5328efcbc378","resolution":{"observed_at":"2026-08-11T18:18:56.366828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.329935Z","title":"Adversarial danger identification on temporally dynamic graphs","venue":null,"work_id":"bff81705-fc36-44f2-b7a6-f7f82fc51abb","year":2023},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.965323Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:3c92bbc440a4aa87f77e7c9a01638b43860a38df353b8666847f8b3ff93fe13c","observation_id":"4d76e26e-1f09-406f-937d-516ef1e5cede","resolution":{"observed_at":"2026-08-11T18:18:56.338538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.09572","last_updated":"2023-04-14T04:15:27Z","snapshot_observed_at":"2026-08-13T15:00:30.210655Z","submitted_at":"2022-07-19T22:00:41Z","title":"Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.09572","snapshot_observed_at":"2026-08-11T18:18:54.972158Z","title":"Robust multivariate time-series forecasting: Adversarial attacks and defense mechanisms","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.972158Z"},"links":{"cited_paper":"/paper/2207.09572","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:c42dbd966bf52a2a62ae74113652cfe60b061cbb521df17fe79199f82077a164","observation_id":"fdf7aa5d-1f94-4df9-b95b-7fa1551f950f","resolution":{"observed_at":"2026-08-11T18:18:54.972158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07300","last_updated":"2025-04-08T06:21:53Z","snapshot_observed_at":"2026-08-15T16:49:48.402981Z","submitted_at":"2024-03-12T04:04:38Z","title":"CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07300","snapshot_observed_at":"2026-08-11T18:18:54.977951Z","title":"Taming pre-trained llms for generalised time series forecasting via cross-modal knowledge distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.977951Z"},"links":{"cited_paper":"/paper/2403.07300","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:aa315bcc904caed64caf099641185cef80f42feb51085d9b57c774f291452266","observation_id":"27b9bd56-c40b-4a60-933e-4ccbff8b8d20","resolution":{"observed_at":"2026-08-11T18:18:54.977951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.04957","last_updated":"2024-03-07T23:46:20Z","snapshot_observed_at":"2026-08-13T00:59:41.384742Z","submitted_at":"2024-03-07T23:46:20Z","title":"Automatic and Universal Prompt Injection Attacks against Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.04957","snapshot_observed_at":"2026-08-11T18:18:54.988304Z","title":"Automatic and universal prompt injection attacks against large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.988304Z"},"links":{"cited_paper":"/paper/2403.04957","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:9dbf93eb5f5c89baa7811f9023e2d09f5d2ceb048ac3c4b06ea039799154249c","observation_id":"bda893b4-13e2-4b2c-86c5-a59d184a90bb","resolution":{"observed_at":"2026-08-11T18:18:54.988304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.303785Z","title":"itransformer: Inverted transformers are effective for time series forecasting","venue":null,"work_id":"f7c1f5b3-9035-4cf1-ba79-651696160d35","year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:54.995893Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:deb43521469b1be2dc5699325cfc39485e6887cc8a559448fc4244e5f9ca31a6","observation_id":"7ca1c4f0-3fc0-42a3-975e-47cbfe502ebc","resolution":{"observed_at":"2026-08-11T18:18:56.309548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-11T18:18:55.010827Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.010827Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:2be0fd7325d1a585b4ff7e2f3cb437efc22f25d4fd87be503bdd2eecd875a377","observation_id":"8e0169e7-68f1-4b3c-b75b-290ff0ed4b6e","resolution":{"observed_at":"2026-08-11T18:18:55.010827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.05909","last_updated":"2020-10-05T00:10:24Z","snapshot_observed_at":"2026-08-15T13:16:30.209244Z","submitted_at":"2020-04-29T21:33:35Z","title":"TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.05909","snapshot_observed_at":"2026-08-11T18:18:55.028265Z","title":"Textattack: A framework for adversarial attacks, data augmentation, and adversarial training in nlp","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.028265Z"},"links":{"cited_paper":"/paper/2005.05909","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:ffbc420204c3968cf82cef252991ee09dd6ac4dd53c0a219fb27521234fd0833","observation_id":"16c52e12-2b80-400c-849e-4ade236a231b","resolution":{"observed_at":"2026-08-11T18:18:55.028265Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.10437","last_updated":"2020-02-20T21:08:57Z","snapshot_observed_at":"2026-08-14T16:26:52.986402Z","submitted_at":"2019-05-24T20:28:57Z","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.10437","snapshot_observed_at":"2026-08-11T18:18:55.036741Z","title":"N-beats: Neural basis expansion analysis for interpretable time series forecasting","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.036741Z"},"links":{"cited_paper":"/paper/1905.10437","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:9bd01b589819c5954973db601016d3dea09b940e822027347014a329dc3c405e","observation_id":"4d9d6b33-f972-4b5b-a3fe-557ef7ea9af4","resolution":{"observed_at":"2026-08-11T18:18:55.036741Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:55.043361Z","title":"Deepar: Probabilistic forecasting with autoregressive recurrent networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.043361Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:f17e675f85562623969035a16b508540acfdac964bbe6f7d5f72cc7ab4e05948","observation_id":"a47bb002-7de5-44be-8a39-1cff4131b8b0","resolution":{"observed_at":"2026-08-11T18:18:55.043361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09063","last_updated":"2025-04-16T15:15:56Z","snapshot_observed_at":"2026-08-13T04:19:14.191982Z","submitted_at":"2024-02-14T10:20:03Z","title":"Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09063","snapshot_observed_at":"2026-08-11T18:18:55.053272Z","title":"Soft prompt threats: Attacking safety alignment and unlearning in open-source llms through the embedding space","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.053272Z"},"links":{"cited_paper":"/paper/2402.09063","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:363c99fcd94ad5d794255ff0c02b32bb4df37d3fd244461072878a6c3d004324","observation_id":"e8e871a4-f35d-4fcd-8481-0b67b5c75348","resolution":{"observed_at":"2026-08-11T18:18:55.053272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:55.067914Z","title":"Robustness of llms to perturbations in text","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.067914Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:117bac0c9de6dd4bd7dcfe2e8379ddf57cde9eb1d7884667ee786dd0195ca5e7","observation_id":"50183753-1f36-481e-bfe9-26431a70975a","resolution":{"observed_at":"2026-08-11T18:18:55.067914Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16964","last_updated":"2024-10-26T01:43:07Z","snapshot_observed_at":"2026-08-15T07:23:33.921253Z","submitted_at":"2024-06-22T03:33:38Z","title":"Are Language Models Actually Useful for Time Series Forecasting?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16964","snapshot_observed_at":"2026-08-11T18:18:55.075743Z","title":"Are language models actually useful for time series forecasting? arXiv preprint arXiv:2406.16964, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.075743Z"},"links":{"cited_paper":"/paper/2406.16964","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:6b2c212f7c193c1feede2c476b83035d00a51ea2a92b1c8b1050a71aabb6cd6f","observation_id":"e0d3c555-3242-4dc5-ac88-73666bb4071d","resolution":{"observed_at":"2026-08-11T18:18:55.075743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-11T18:18:55.084819Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.084819Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:f1268b6f7ff4a90ca6a0acd90224d4916378b1fb23d8c1f897ca2dae82a8dc74","observation_id":"33086523-8ace-4e6c-85ff-e2e40574cb43","resolution":{"observed_at":"2026-08-11T18:18:55.084819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:55.093847Z","title":"Jailbroken: How does llm safety training fail? Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.093847Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:eadb90c7714562b10737fc2e6dd4fe0b879d0fd945aed20155674ee085f8328f","observation_id":"cf34c6e2-e72e-4c3e-a374-b191bbedf8a7","resolution":{"observed_at":"2026-08-11T18:18:55.093847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12641","last_updated":"2019-05-13T07:22:16Z","snapshot_observed_at":"2026-08-14T17:50:49.224322Z","submitted_at":"2018-11-30T06:55:22Z","title":"Transferable Adversarial Attacks for Image and Video Object Detection","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.12641","snapshot_observed_at":"2026-08-11T18:18:55.098700Z","title":"Transferable adversarial attacks for image and video object detection","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.098700Z"},"links":{"cited_paper":"/paper/1811.12641","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:d4a386591adb1b48f49d53938a95234a23d5abc031c0c7f16bae0aaabfdb5ec9","observation_id":"ba5e292c-2dbe-4f75-8151-bdc1e98cc034","resolution":{"observed_at":"2026-08-11T18:18:55.098700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:55.111423Z","title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.111423Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:a90d669355a9ee526ea057b1288bffa55e315f22c8b1ff98456c758e20694dd8","observation_id":"833ad429-c433-46a4-9f20-74cb085f3486","resolution":{"observed_at":"2026-08-11T18:18:55.111423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.206995Z","title":"Timesnet: Temporal 2d-variation modeling for general time series analysis","venue":null,"work_id":"9d15c10b-c74c-48ea-a7a7-0ed7706eb475","year":2023},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.128163Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:dff79a599c96a3ee5388a60a24ad1b0add17e15f0eb65bd39fbe538923da23c7","observation_id":"c4886d24-d965-43cc-a8c7-dba73818fcf6","resolution":{"observed_at":"2026-08-11T18:18:56.221351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.166114Z","title":"Adversarial attacks and defenses in images, graphs and text: A review","venue":null,"work_id":"f5ef092e-f3bf-408c-b165-a68697a56ecc","year":2020},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.142176Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:6888b101c701157d86f741e32ca9a52ce5c8f1290d04f6a9242aa09fdd12eef5","observation_id":"9673e185-a723-4fe1-a9f9-005f8e4cbeae","resolution":{"observed_at":"2026-08-11T18:18:56.181517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:56.147259Z","title":"Trojllm: A black-box trojan prompt attack on large language models","venue":null,"work_id":"ceb95864-ad25-43a4-9dae-4e22a6a0a952","year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.158351Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:7a2731aedacf35f1b5db112bab80594bd8cdc3ff223a1474f73b32566e8c0f6f","observation_id":"b04485aa-282e-484b-a034-8b489765d259","resolution":{"observed_at":"2026-08-11T18:18:56.153823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17336","last_updated":"2024-09-30T21:25:23Z","snapshot_observed_at":"2026-08-15T18:00:34.759543Z","submitted_at":"2024-03-26T02:47:42Z","title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.17336","snapshot_observed_at":"2026-08-11T18:18:55.164615Z","title":"Don't listen to me: Understanding and exploring jailbreak prompts of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.164615Z"},"links":{"cited_paper":"/paper/2403.17336","citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:065865c6577068a95467b6326137c6ac39918e3198f00e95bc7014a7bfe835e8","observation_id":"030cfff3-074c-4bab-a16d-1ef9d471dd33","resolution":{"observed_at":"2026-08-11T18:18:55.164615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:55.170060Z","title":"Informer: Beyond efficient transformer for long sequence time-series forecasting","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.170060Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:39f3bbc0c24281b90e788c1301646ac52f0af51ad3295137c058a97c2213ddde","observation_id":"46e0d6ff-2ff6-4d17-b5ea-2359b9f3aea6","resolution":{"observed_at":"2026-08-11T18:18:55.170060Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T18:18:55.188005Z","title":"Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","version":4},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-11T18:18:55.188005Z"},"links":{"citing_paper":"/paper/2412.08099"},"observation_digest":"sha256:86e690d06339fb38df3281360eaf96c722c6177724d45d9c5f9f689be4e102fc","observation_id":"bca939dd-bd0d-4697-adb8-89d8230c11b7","resolution":{"observed_at":"2026-08-11T18:18:55.188005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.08099","last_updated":"2025-03-12T21:35:52Z","latest_version":4,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T15:28:56.958291Z","submitted_at":"2024-12-11T04:53:15Z","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":1,"verified_fuzzy":10},"total_outbound_references":41},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2412.08099."}