{"as_of":"2026-08-09T19:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a6d4ba068f28375ad47d1ff5cb1a27b9dbc4393b2acf065284a7a94a88cbcd8a","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T12:25:30.617174Z","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":"2026-07-01T08:55:35.545162Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.10794","last_updated":"2024-12-02T21:48:47Z","snapshot_observed_at":"2026-07-06T18:31:36.504766Z","submitted_at":"2024-06-16T03:38:48Z","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10794","snapshot_observed_at":"2026-08-08T12:25:30.617174Z","title":"Towards understanding jailbreak attacks in llms: A representation space analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07557","last_updated":"2025-02-11T13:50:50Z","snapshot_observed_at":"2026-08-09T03:24:13.351555Z","submitted_at":"2025-02-11T13:50:50Z","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-08T12:25:30.617174Z"},"links":{"cited_paper":"/paper/2406.10794","citing_paper":"/paper/2502.07557"},"observation_digest":"sha256:159debc947892b277852df9984b83851bf3f0d751b4cc108ab77cde36689a748","observation_id":"f921e066-1052-4c12-9193-204d8922ffeb","resolution":{"observed_at":"2026-08-08T12:25:30.617174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10794","last_updated":"2024-12-02T21:48:47Z","snapshot_observed_at":"2026-07-06T18:31:36.504766Z","submitted_at":"2024-06-16T03:38:48Z","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10794","snapshot_observed_at":"2026-08-06T21:27:34.948426Z","title":"Towards understanding jailbreak attacks in llms: A representation space analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.00239","last_updated":"2025-06-30T20:13:49Z","snapshot_observed_at":"2026-08-08T11:00:52.585789Z","submitted_at":"2025-06-30T20:13:49Z","title":"Linearly Decoding Refused Knowledge in Aligned Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T21:27:34.948426Z"},"links":{"cited_paper":"/paper/2406.10794","citing_paper":"/paper/2507.00239"},"observation_digest":"sha256:732564b319ddb064b9a0089a69318a792e7bc64a3698a82bfa9e3954690a4910","observation_id":"1dabd6f2-50a8-44ae-8f45-764cd3e04cc0","resolution":{"observed_at":"2026-08-06T21:27:34.948426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10794","last_updated":"2024-12-02T21:48:47Z","snapshot_observed_at":"2026-07-06T18:31:36.504766Z","submitted_at":"2024-06-16T03:38:48Z","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","version":3},"cited_work":{"arxiv_id":"2406.10794","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.10794","snapshot_observed_at":"2026-07-01T08:55:35.545162Z","title":"emnlp-main.401/","venue":null,"work_id":"2357af38-a2c3-4a8e-a54d-024e662176b3","year":2024},"citing_paper":{"arxiv_id":"2602.05946","last_updated":"2026-05-11T01:44:43Z","snapshot_observed_at":"2026-08-02T10:13:32.692710Z","submitted_at":"2026-02-05T18:01:52Z","title":"f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM Alignment","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-16T06:48:35.723474Z"},"links":{"cited_paper":"/paper/2406.10794","citing_paper":"/paper/2602.05946"},"observation_digest":"sha256:ca62489b9307b455753f4ab8e4878affb4b67743388a7c580837778615402bc8","observation_id":"a6900c82-3b6b-449b-89e9-d74c8f51ab95","resolution":{"observed_at":"2026-05-16T06:50:42.953163Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10794","last_updated":"2024-12-02T21:48:47Z","snapshot_observed_at":"2026-07-06T18:31:36.504766Z","submitted_at":"2024-06-16T03:38:48Z","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","version":3},"cited_work":{"arxiv_id":"2406.10794","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.10794","snapshot_observed_at":"2026-07-01T08:55:35.545162Z","title":"emnlp-main.401/","venue":null,"work_id":"2357af38-a2c3-4a8e-a54d-024e662176b3","year":2024},"citing_paper":{"arxiv_id":"2606.31748","last_updated":"2026-06-30T14:38:49Z","snapshot_observed_at":"2026-07-07T00:05:27.130060Z","submitted_at":"2026-06-30T14:38:49Z","title":"Addressing Over-Refusal in LLMs with Competing Rewards","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-07-01T06:59:12.695984Z"},"links":{"cited_paper":"/paper/2406.10794","citing_paper":"/paper/2606.31748"},"observation_digest":"sha256:6a1f1d8409c21de4269e290055594dbc452d72de1766b43e60c547b009450c91","observation_id":"6312e726-7863-4d52-abbb-355148cc45da","resolution":{"observed_at":"2026-07-01T08:55:35.546585Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.10794/citation-record","integrity":"/paper/2406.10794/integrity","json":"/paper/2406.10794/citation-record.json","paper":"/paper/2406.10794"},"outbound":[],"paper":{"arxiv_id":"2406.10794","last_updated":"2024-12-02T21:48:47Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T18:31:36.504766Z","submitted_at":"2024-06-16T03:38:48Z","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2406.10794."}