{"as_of":"2026-08-17T13:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:110ebc2cc3cfffe9d3c0c2701666fb1a416ad53d1caefae9429a40564d0d49f4","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":10,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:24:12.420623Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T14:59:54.708937Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-08-09T00:39:02.309959Z","title":"Poi- sonbench: Assessing large language model vulnerability to data poisoning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.03825","last_updated":"2025-02-06T07:21:19Z","snapshot_observed_at":"2026-08-16T04:45:34.515176Z","submitted_at":"2025-02-06T07:21:19Z","title":"Synthetic Poisoning Attacks: The Impact of Poisoned MRI Image on U-Net Brain Tumor Segmentation","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T00:39:02.309959Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2502.03825"},"observation_digest":"sha256:d877f15baa0da4dedff45995b932f2d7826493f630752f73f67d6c424f7c329b","observation_id":"9b274567-d45c-4fa0-863a-e2c07d94652b","resolution":{"observed_at":"2026-08-09T00:39:02.309959Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-08-16T11:24:12.420623Z","title":"Poisonbench: Assessing large language model vulnerability to data poisoning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.15585","last_updated":"2025-06-09T02:36:20Z","snapshot_observed_at":"2026-08-16T13:11:23.928524Z","submitted_at":"2025-04-22T05:02:49Z","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","version":4},"reference_index":149,"source":"pdf_text","source_observed_at":"2026-08-16T11:24:12.420623Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2504.15585"},"observation_digest":"sha256:c5cbed562d6b18e52787a8c7d5f5b36984679fb046eb661eff34e03a319a7b4f","observation_id":"84c72cda-a02d-43aa-b02f-dd2342677813","resolution":{"observed_at":"2026-08-16T11:24:12.420623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-08-06T21:36:29.676305Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.23762","last_updated":"2025-06-30T12:09:29Z","snapshot_observed_at":"2026-08-13T08:27:18.830708Z","submitted_at":"2025-06-30T12:09:29Z","title":"Software Engineering for Large Language Models: Research Status, Challenges and the Road Ahead","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T21:36:29.676305Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2506.23762"},"observation_digest":"sha256:e59c59bef24b3920dad47488fe00badf62b87b06f5a30b615d4da3a41c5b2042","observation_id":"195a3ecc-af48-47ed-b019-3c02b3b79a90","resolution":{"observed_at":"2026-08-06T21:36:29.676305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":"2410.08811","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-07-04T14:59:54.708937Z","title":"Cohen, David Krueger, and Fazl Barez","venue":null,"work_id":"3b8c1729-6fe9-47ec-94c8-9573044b68d7","year":2024},"citing_paper":{"arxiv_id":"2507.02850","last_updated":"2026-04-20T16:20:19Z","snapshot_observed_at":"2026-08-17T02:21:16.409356Z","submitted_at":"2025-07-03T17:55:40Z","title":"LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-19T05:58:17.452837Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2507.02850"},"observation_digest":"sha256:4a7965dc3d7f79f895368cf7a1449444a7be68d3d52e0275dda09c0cc598dd3a","observation_id":"fca70983-ea4d-4e35-9b7a-b07eeb09401d","resolution":{"observed_at":"2026-05-19T06:02:07.810301Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-08-04T17:46:17.800744Z","title":"PoisonBench: Assessing large language model vulnerability to data poisoning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10682","last_updated":"2025-09-12T20:26:16Z","snapshot_observed_at":"2026-08-12T22:01:07.249587Z","submitted_at":"2025-09-12T20:26:16Z","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-04T17:46:17.800744Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2509.10682"},"observation_digest":"sha256:d87b24e00f1e1db262c455a0e4476726fe3b10a7f78dde79d3d2c6af037fb24b","observation_id":"d13cfdac-bde0-4bf9-b4ea-e227a2d5ba2b","resolution":{"observed_at":"2026-08-04T17:46:17.800744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":"2410.08811","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-07-04T14:59:54.708937Z","title":"Cohen, David Krueger, and Fazl Barez","venue":null,"work_id":"3b8c1729-6fe9-47ec-94c8-9573044b68d7","year":2024},"citing_paper":{"arxiv_id":"2604.27238","last_updated":"2026-04-29T22:26:00Z","snapshot_observed_at":"2026-08-16T04:24:14.089561Z","submitted_at":"2026-04-29T22:26:00Z","title":"SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-07T10:16:07.200458Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2604.27238"},"observation_digest":"sha256:16461102a0c0fad112b361fcd3325a08e855547707d22dd5c4a7361ff5e9d4e0","observation_id":"e1ebc7a2-c75f-4e95-bc1c-acc5bdca919c","resolution":{"observed_at":"2026-05-12T09:36:26.575265Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":"2410.08811","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-07-04T14:59:54.708937Z","title":"Cohen, David Krueger, and Fazl Barez","venue":null,"work_id":"3b8c1729-6fe9-47ec-94c8-9573044b68d7","year":2024},"citing_paper":{"arxiv_id":"2605.02495","last_updated":"2026-05-25T07:21:41Z","snapshot_observed_at":"2026-08-12T23:44:54.910791Z","submitted_at":"2026-05-04T11:45:38Z","title":"Efficient Preference Poisoning Attack on Offline RLHF","version":1},"reference_index":139,"source":"arxiv_source","source_observed_at":"2026-05-08T19:29:25.000361Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2605.02495"},"observation_digest":"sha256:c17bbd0e115d52fa85382d9cc84a24be93776a6c773e03e9472b475d050f597b","observation_id":"4617f6c5-db4b-46cd-98eb-fca9caaf0729","resolution":{"observed_at":"2026-05-09T05:50:27.117761Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":"2410.08811","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-07-04T14:59:54.708937Z","title":"Cohen, David Krueger, and Fazl Barez","venue":null,"work_id":"3b8c1729-6fe9-47ec-94c8-9573044b68d7","year":2024},"citing_paper":{"arxiv_id":"2605.12529","last_updated":"2026-04-15T10:56:08Z","snapshot_observed_at":"2026-08-12T22:25:40.940152Z","submitted_at":"2026-04-15T10:56:08Z","title":"BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-14T21:01:10.756844Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2605.12529"},"observation_digest":"sha256:238c656ba9f373b7d347e5ac2524091a16f09166e387003382d9b8b40cb19577","observation_id":"7884badc-28e9-4edd-b089-56613bc33fef","resolution":{"observed_at":"2026-05-14T21:02:58.867033Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":"2410.08811","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-07-04T14:59:54.708937Z","title":"Cohen, David Krueger, and Fazl Barez","venue":null,"work_id":"3b8c1729-6fe9-47ec-94c8-9573044b68d7","year":2024},"citing_paper":{"arxiv_id":"2605.19147","last_updated":"2026-05-18T21:56:36Z","snapshot_observed_at":"2026-08-13T01:28:31.913406Z","submitted_at":"2026-05-18T21:56:36Z","title":"Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-20T08:53:52.698758Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2605.19147"},"observation_digest":"sha256:5bfe592b72ab283afee50c6430e5ec9908a9a0da3324a82503317d884fc31a75","observation_id":"b4f2d092-324a-4e17-ad18-99c4bc23e4d5","resolution":{"observed_at":"2026-05-20T08:58:10.448234Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning","version":2},"cited_work":{"arxiv_id":"2410.08811","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2410.08811","snapshot_observed_at":"2026-07-04T14:59:54.708937Z","title":"Cohen, David Krueger, and Fazl Barez","venue":null,"work_id":"3b8c1729-6fe9-47ec-94c8-9573044b68d7","year":2024},"citing_paper":{"arxiv_id":"2606.00036","last_updated":"2026-04-25T15:43:09Z","snapshot_observed_at":"2026-08-07T05:59:36.960166Z","submitted_at":"2026-04-25T15:43:09Z","title":"AI Integrity: Defending Against Backdoors and Secret Loyalties","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-04T14:56:53.806480Z"},"links":{"cited_paper":"/paper/2410.08811","citing_paper":"/paper/2606.00036"},"observation_digest":"sha256:9c3406a35a67d87f6c3440f6876ba1a315a12ed2ad47778693b0f64f925418c9","observation_id":"408b2067-284f-42a6-ab78-1527d5bf42e0","resolution":{"observed_at":"2026-07-04T14:59:54.712176Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.08811/citation-record","integrity":"/paper/2410.08811/integrity","json":"/paper/2410.08811/citation-record.json","paper":"/paper/2410.08811"},"outbound":[],"paper":{"arxiv_id":"2410.08811","last_updated":"2025-06-06T08:12:20Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-16T13:10:19.794459Z","submitted_at":"2024-10-11T13:50:50Z","title":"PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 10 inbound Pith citation observations for arXiv:2410.08811."}