{"as_of":"2026-08-20T13:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ba96f1d93b2edf9ba3475eab036fe67763bcdf40013d6dd58b21ded1b3643c6","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":7,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":7,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:57:58.384912Z","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":"2026-07-02T00:56:24.433405Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13031","snapshot_observed_at":"2026-08-12T19:41:19.734437Z","title":"Rigorllm: Resilient guardrails for large language models against undesired content.arXiv preprint arXiv:2403.13031,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.10414","last_updated":"2024-11-15T18:34:07Z","snapshot_observed_at":"2026-08-17T21:40:47.016297Z","submitted_at":"2024-11-15T18:34:07Z","title":"Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T19:41:19.734437Z"},"links":{"cited_paper":"/paper/2403.13031","citing_paper":"/paper/2411.10414"},"observation_digest":"sha256:3299f26359ed2d0fd5ad8fec6e415f7b118a3a5a466c21484b5fb8625c0049f5","observation_id":"5897041d-e12e-47d8-ab0c-e928252a4a8b","resolution":{"observed_at":"2026-08-12T19:41:19.734437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13031","snapshot_observed_at":"2026-08-11T19:03:13.982844Z","title":"Rigorllm: Re- silient guardrails for large language models against undesired content","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07249","last_updated":"2025-01-13T07:22:02Z","snapshot_observed_at":"2026-08-17T02:34:38.321529Z","submitted_at":"2024-12-10T07:18:51Z","title":"Buster: Implanting Semantic Backdoor into Text Encoder to Mitigate NSFW Content Generation","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T19:03:13.982844Z"},"links":{"cited_paper":"/paper/2403.13031","citing_paper":"/paper/2412.07249"},"observation_digest":"sha256:4db788b046f30e9fefcd4d4224ea788de39a44024fb699c445f81e7202b6f8a8","observation_id":"3e2707fe-ef53-4fff-8cfc-78d1871b5d94","resolution":{"observed_at":"2026-08-11T19:03:13.982844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13031","snapshot_observed_at":"2026-08-10T12:52:40.950778Z","title":"Rigor- LLM: Resilient guardrails for large language models against undesired content","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.16497","last_updated":"2025-01-27T20:57:26Z","snapshot_observed_at":"2026-08-17T20:21:25.789773Z","submitted_at":"2025-01-27T20:57:26Z","title":"Smoothed Embeddings for Robust Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T12:52:40.950778Z"},"links":{"cited_paper":"/paper/2403.13031","citing_paper":"/paper/2501.16497"},"observation_digest":"sha256:76336b13db4d6d0d2d7aee4eddc5e567050b5ec345972e6df24cb61fdb7f11c6","observation_id":"acfdb9bd-c0c1-4c3d-917e-4abc7ae5493f","resolution":{"observed_at":"2026-08-10T12:52:40.950778Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13031","snapshot_observed_at":"2026-08-16T05:57:58.384912Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.19440","last_updated":"2025-04-28T03:01:51Z","snapshot_observed_at":"2026-08-20T07:16:03.686107Z","submitted_at":"2025-04-28T03:01:51Z","title":"JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T05:57:58.384912Z"},"links":{"cited_paper":"/paper/2403.13031","citing_paper":"/paper/2504.19440"},"observation_digest":"sha256:55a2c420bd1edf48898f7bebd3a31741e49435cb43f75c639a988f305160428f","observation_id":"ef7ecd9e-9642-4a97-b3c0-7bba149a644c","resolution":{"observed_at":"2026-08-16T05:57:58.384912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13031","snapshot_observed_at":"2026-08-05T10:44:10.624358Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03787","last_updated":"2025-09-04T00:45:58Z","snapshot_observed_at":"2026-08-18T00:30:11.532287Z","submitted_at":"2025-09-04T00:45:58Z","title":"Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T10:44:10.624358Z"},"links":{"cited_paper":"/paper/2403.13031","citing_paper":"/paper/2509.03787"},"observation_digest":"sha256:93ce8b10e348df13fd4ca0ff60655589065c326af82874b77fa5d9d79e76995e","observation_id":"89484cf8-d788-442d-9c63-6211efac8682","resolution":{"observed_at":"2026-08-05T10:44:10.624358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","version":2},"cited_work":{"arxiv_id":"2403.13031","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.13031","snapshot_observed_at":"2026-07-02T00:56:24.433405Z","title":"Rigorllm: Resilient guardrails for large language models against undesired content","venue":null,"work_id":"2ab7468d-cec9-479f-a851-2cdbd9e5ef77","year":2024},"citing_paper":{"arxiv_id":"2605.01899","last_updated":"2026-05-03T14:28:08Z","snapshot_observed_at":"2026-08-17T00:31:30.183586Z","submitted_at":"2026-05-03T14:28:08Z","title":"Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-09T17:24:54.796037Z"},"links":{"cited_paper":"/paper/2403.13031","citing_paper":"/paper/2605.01899"},"observation_digest":"sha256:436a2f326b008af5b87ec3214e318aa37e2dbc38d98ab40e7a96b26168de90d1","observation_id":"c19da607-435b-4a4f-8f24-46cb95381005","resolution":{"observed_at":"2026-05-11T16:21:07.466667Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content","version":2},"cited_work":{"arxiv_id":"2403.13031","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.13031","snapshot_observed_at":"2026-07-02T00:56:24.433405Z","title":"Rigorllm: Resilient guardrails for large language models against undesired content","venue":null,"work_id":"2ab7468d-cec9-479f-a851-2cdbd9e5ef77","year":2024},"citing_paper":{"arxiv_id":"2606.01513","last_updated":"2026-06-01T00:24:30Z","snapshot_observed_at":"2026-08-07T00:02:03.501606Z","submitted_at":"2026-06-01T00:24:30Z","title":"Compliance-Scored Best-of-N Guardrail Orchestration for Multimodal Document Generation in Payments Dispute Defense","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T13:13:05.210457Z"},"links":{"cited_paper":"/paper/2403.13031","citing_paper":"/paper/2606.01513"},"observation_digest":"sha256:034ec7f0233c7502eb89dca375a7170d785178642cda2e9b74339a31543d560a","observation_id":"42b76940-f5db-41c5-aef4-1a63bdb05f07","resolution":{"observed_at":"2026-07-02T00:56:24.435393Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.13031/citation-record","integrity":"/paper/2403.13031/integrity","json":"/paper/2403.13031/citation-record.json","paper":"/paper/2403.13031"},"outbound":[],"paper":{"arxiv_id":"2403.13031","last_updated":"2024-07-23T22:56:13Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-20T02:52:47.433585Z","submitted_at":"2024-03-19T07:25:02Z","title":"RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 7 inbound Pith citation observations for arXiv:2403.13031."}