{"as_of":"2026-08-22T06:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3dd4684cdaeab0993e5ac51af44cacbd2aec88b5681e8e42a9d0e47993f08f72","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":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":25,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:58:23.220001Z","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":"2026-06-30T06:44:18.784391Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2406.11354","last_updated":"2026-04-23T15:54:03Z","snapshot_observed_at":"2026-08-17T20:38:48.003295Z","submitted_at":"2024-06-17T09:17:40Z","title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","version":3},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-05-24T00:09:52.093810Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2406.11354"},"observation_digest":"sha256:0773dc430facb32c23c0e7941217532da5bb861115d0420b002fb156d83567d3","observation_id":"1efbd665-8e61-4f59-9a39-601f5debd3a3","resolution":{"observed_at":"2026-05-24T00:13:39.462264Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2411.04368","last_updated":"2024-11-07T01:58:42Z","snapshot_observed_at":"2026-08-17T10:08:57.374438Z","submitted_at":"2024-11-07T01:58:42Z","title":"Measuring short-form factuality in large language models","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-05-15T06:45:50.219157Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2411.04368"},"observation_digest":"sha256:0a7a61c7c9125c701266c924b06800509d6c854c8273dc25d75e2f877c6fe51b","observation_id":"06b1d0f2-7278-4747-b188-f7c739200a4b","resolution":{"observed_at":"2026-05-15T06:45:50.288896Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-12T14:18:31.629667Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.15477","last_updated":"2024-11-23T07:20:36Z","snapshot_observed_at":"2026-08-18T08:22:36.553000Z","submitted_at":"2024-11-23T07:20:36Z","title":"Towards Robust Evaluation of Unlearning in LLMs via Data Transformations","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T14:18:31.629667Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2411.15477"},"observation_digest":"sha256:cbb41dd592e155ff484b008162291d6916ea2403c8b7e733526e8d7db67d529b","observation_id":"c897e224-bf87-4b6e-ab14-3f6ae69407a8","resolution":{"observed_at":"2026-08-12T14:18:31.629667Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-11T23:08:16.330494Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02830","last_updated":"2025-06-02T17:40:21Z","snapshot_observed_at":"2026-08-15T19:21:48.309859Z","submitted_at":"2024-12-03T20:52:35Z","title":"RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models","version":4},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-11T23:08:16.330494Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2412.02830"},"observation_digest":"sha256:fe1c26631eaf5c6804a1b3372cce6cf380fc9d8934e5cf815239dfcef28f2b20","observation_id":"6002745f-df62-44e0-a74b-388e571d69eb","resolution":{"observed_at":"2026-08-11T23:08:16.330494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-10T23:53:12.361255Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19906","last_updated":"2024-12-27T19:42:25Z","snapshot_observed_at":"2026-08-15T18:48:00.753913Z","submitted_at":"2024-12-27T19:42:25Z","title":"Evaluate Summarization in Fine-Granularity: Auto Evaluation with LLM","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T23:53:12.361255Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2412.19906"},"observation_digest":"sha256:d35a6748b441c2de2183e091a71be8e39019a6d20ee30559f4df949fd890dad8","observation_id":"eb5678ae-067b-4754-9ba4-46a0538a337e","resolution":{"observed_at":"2026-08-10T23:53:12.361255Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-10T21:57:11.920951Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.03200","last_updated":"2025-01-06T18:28:04Z","snapshot_observed_at":"2026-08-18T21:49:44.851092Z","submitted_at":"2025-01-06T18:28:04Z","title":"The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T21:57:11.920951Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2501.03200"},"observation_digest":"sha256:3a88eb5a93b42882016de6d62ff5fcd9e976c41af6f00c9112e5ae7227e34b6a","observation_id":"435aeff9-4beb-40f2-abd4-64dea21e67fe","resolution":{"observed_at":"2026-08-10T21:57:11.920951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-15T20:58:23.220001Z","title":"Long-form factuality in large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11365","last_updated":"2025-05-26T12:21:14Z","snapshot_observed_at":"2026-08-18T18:59:35.551356Z","submitted_at":"2025-05-16T15:31:08Z","title":"Phare: A Safety Probe for Large Language Models","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:58:23.220001Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2505.11365"},"observation_digest":"sha256:90cce22368916e0817a0943871d29ba3e7727ea90992a52dfa337952261606e1","observation_id":"68e4e313-b78e-46bd-afcc-62d90a6680bd","resolution":{"observed_at":"2026-08-15T20:58:23.220001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-15T20:41:35.414809Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.12265","last_updated":"2025-05-18T07:10:03Z","snapshot_observed_at":"2026-08-16T20:26:55.026371Z","submitted_at":"2025-05-18T07:10:03Z","title":"Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T20:41:35.414809Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2505.12265"},"observation_digest":"sha256:138e42763c13c21bac0286574b37ac51d93ab4871fe86b2918f0f0baa2622f88","observation_id":"0c1cca02-e050-42b6-81ca-fa039b8bc8a7","resolution":{"observed_at":"2026-08-15T20:41:35.414809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-07T12:34:07.814259Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.00088","last_updated":"2025-05-30T06:19:49Z","snapshot_observed_at":"2026-08-13T08:56:09.524139Z","submitted_at":"2025-05-30T06:19:49Z","title":"HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T12:34:07.814259Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2506.00088"},"observation_digest":"sha256:a1225c3c3bc904ca306e1b40ab8befac1f3953e31f4cb880dccb619c9f988120","observation_id":"93e1b83e-2620-44ce-86b5-de939e95e8df","resolution":{"observed_at":"2026-08-07T12:34:07.814259Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-07T00:51:47.184863Z","title":"arXiv:2403.18802 [cs.CL] https://arxiv.org/abs/2403.18802","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.12538","last_updated":"2025-06-14T15:27:44Z","snapshot_observed_at":"2026-08-18T16:54:28.804697Z","submitted_at":"2025-06-14T15:27:44Z","title":"RealFactBench: A Benchmark for Evaluating Large Language Models in Real-World Fact-Checking","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T00:51:47.184863Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2506.12538"},"observation_digest":"sha256:76ad889d5b61140a35498f8d4f3293fa9e0fce40f64d6c5e8f0c76ed8146d2c3","observation_id":"c2dcf01b-4e35-4276-95f5-0e034b3270a4","resolution":{"observed_at":"2026-08-07T00:51:47.184863Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-06T23:53:39.856611Z","title":"Long-form factuality in large language models.arXiv preprint arXiv:2403.18802,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.15794","last_updated":"2025-06-18T18:24:59Z","snapshot_observed_at":"2026-08-20T05:57:33.951137Z","submitted_at":"2025-06-18T18:24:59Z","title":"Veracity: An Open-Source AI Fact-Checking System","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:53:39.856611Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2506.15794"},"observation_digest":"sha256:f64654dc74192ab213f23c31074ec9efdc24bf6f0b29ce1dd0e582cc3bbc8294","observation_id":"0f995fdc-e477-4550-9282-17b2f2db3e86","resolution":{"observed_at":"2026-08-06T23:53:39.856611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-06T15:02:21.746960Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17015","last_updated":"2025-07-22T20:57:09Z","snapshot_observed_at":"2026-08-17T23:12:52.821740Z","submitted_at":"2025-07-22T20:57:09Z","title":"Can External Validation Tools Improve Annotation Quality for LLM-as-a-Judge?","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T15:02:21.746960Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2507.17015"},"observation_digest":"sha256:fd0f3d4dcb27775e1801fa76e5ecf613b717968e45e91ec8a9594d2efda1234e","observation_id":"2fce3b73-9d30-4887-902c-f4726afa870e","resolution":{"observed_at":"2026-08-06T15:02:21.746960Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-05T14:51:03.793719Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.20848","last_updated":"2025-08-28T14:40:27Z","snapshot_observed_at":"2026-08-20T22:43:25.873807Z","submitted_at":"2025-08-28T14:40:27Z","title":"JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T14:51:03.793719Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2508.20848"},"observation_digest":"sha256:0d4b5f43204c7ad82a34e280f30b60a2bea5948dc107998cb5fa9ba9bf33c1c0","observation_id":"9e1a384a-f6b2-4472-b578-acd638b17247","resolution":{"observed_at":"2026-08-05T14:51:03.793719Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-05T13:18:40.851754Z","title":"arXiv preprint","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.04483","last_updated":"2025-08-31T10:22:54Z","snapshot_observed_at":"2026-08-13T11:15:25.516450Z","submitted_at":"2025-08-31T10:22:54Z","title":"DecMetrics: Structured Claim Decomposition Scoring for Factually Consistent LLM Outputs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T13:18:40.851754Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2509.04483"},"observation_digest":"sha256:fe3c16adc7c860bfcd86c743b91e7ba3e9f13f02d76519c61efa1c1e7931d9c8","observation_id":"cf27c228-ad09-4a55-bc2a-242a563f198e","resolution":{"observed_at":"2026-08-05T13:18:40.851754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-04T07:21:22.548978Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.26518","last_updated":"2026-06-25T13:34:02Z","snapshot_observed_at":"2026-08-10T01:21:56.171636Z","submitted_at":"2025-10-30T14:11:52Z","title":"Human-AI Complementarity: A Goal for Amplified Oversight","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T07:21:22.548978Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2510.26518"},"observation_digest":"sha256:c081384904124ba83d3be55edddc9a4f8ce1eed3768524b831a8c9884f87dd61","observation_id":"0da5c309-6527-475d-86f9-86c56defb8bc","resolution":{"observed_at":"2026-08-04T07:21:22.548978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-02T22:21:36.837859Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2602.17234","last_updated":"2026-05-25T04:53:29Z","snapshot_observed_at":"2026-08-19T15:15:17.350031Z","submitted_at":"2026-02-19T10:28:00Z","title":"All Leaks Count, Some Count More: Interpretable Temporal Contamination Detection and Mitigation in LLM Backtesting","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T22:21:36.837859Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2602.17234"},"observation_digest":"sha256:4c116038985b37eaa229116c906bf9e171bedb3e4d1c17893d3a2ec68efe8dc7","observation_id":"2829bc8c-14c0-46d3-8f85-8ca0e8a248ff","resolution":{"observed_at":"2026-08-02T22:21:36.837859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2604.03141","last_updated":"2026-04-03T16:03:56Z","snapshot_observed_at":"2026-08-14T20:19:40.213123Z","submitted_at":"2026-04-03T16:03:56Z","title":"Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-13T20:20:16.299929Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2604.03141"},"observation_digest":"sha256:c74a9fd74148dd562ab1fef25ac8ca59a3565e337f9c299306c4deab45a22a24","observation_id":"b23702a5-67fc-4a5b-992c-45f6d364fca5","resolution":{"observed_at":"2026-05-13T20:23:13.860761Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2604.08549","last_updated":"2026-01-16T09:08:17Z","snapshot_observed_at":"2026-08-12T23:02:08.229000Z","submitted_at":"2026-01-16T09:08:17Z","title":"VerifAI: A Verifiable Open-Source Search Engine for Biomedical Question Answering","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-16T14:03:58.706599Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2604.08549"},"observation_digest":"sha256:bf047e536bf33c83573672b76f6652d59ea9a62cdc43b8cb5c0f22e23e73d3e8","observation_id":"69ce7a89-cf1a-4c6a-9687-9ed399fd4f38","resolution":{"observed_at":"2026-05-16T14:07:58.734248Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2604.17487","last_updated":"2026-05-17T16:25:26Z","snapshot_observed_at":"2026-08-11T03:09:00.626807Z","submitted_at":"2026-04-19T15:20:02Z","title":"Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T05:31:11.718051Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2604.17487"},"observation_digest":"sha256:4637fad7c13fec6a5f25364ddea979a485e1ee2a873e3be151bb4788915362d3","observation_id":"e771731a-56e5-4628-ae6f-3b69b81154bb","resolution":{"observed_at":"2026-05-10T05:36:02.238245Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2604.17487","last_updated":"2026-05-17T16:25:26Z","snapshot_observed_at":"2026-08-11T03:09:00.626807Z","submitted_at":"2026-04-19T15:20:02Z","title":"Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-20T23:56:44.979471Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2604.17487"},"observation_digest":"sha256:c8eee83d27368bb432032a3cc257c7828954cee0b9e913ed384bf7ded51787d3","observation_id":"1257812d-bb5c-4dab-a9a8-fe38ec1b1653","resolution":{"observed_at":"2026-05-20T23:59:15.228903Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2604.23588","last_updated":"2026-04-26T07:52:59Z","snapshot_observed_at":"2026-08-17T04:19:31.740620Z","submitted_at":"2026-04-26T07:52:59Z","title":"FinGround: Detecting and Grounding Financial Hallucinations via Atomic Claim Verification","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-08T06:24:43.021602Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2604.23588"},"observation_digest":"sha256:34361a01de71f84adcf4f9a0ba4abba89e94bed18b2b0a8cc9f50cc3b0b05b70","observation_id":"3133827c-6439-48ad-bf6a-4851398e89b2","resolution":{"observed_at":"2026-05-11T21:11:20.023407Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2605.10442","last_updated":"2026-05-12T10:07:26Z","snapshot_observed_at":"2026-08-20T12:25:19.347451Z","submitted_at":"2026-05-11T12:12:28Z","title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","version":1},"reference_index":115,"source":"pdf_text","source_observed_at":"2026-05-12T04:50:17.399580Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2605.10442"},"observation_digest":"sha256:e81db8552ea62f4c95886b0a0cd789efa486541a757675982cb0ef744d037441","observation_id":"7ed87e6d-64d2-4283-816f-b245dccae29e","resolution":{"observed_at":"2026-05-12T05:51:27.235175Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2605.10442","last_updated":"2026-05-12T10:07:26Z","snapshot_observed_at":"2026-08-20T12:25:19.347451Z","submitted_at":"2026-05-11T12:12:28Z","title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","version":2},"reference_index":115,"source":"pdf_text","source_observed_at":"2026-05-13T07:20:32.494840Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2605.10442"},"observation_digest":"sha256:e536479003f83958216b3e75eae3f9c66a8ebc522b0bbec6d9e8a7bd44bf0ba9","observation_id":"b24693e0-49c3-4527-9bf8-95a34920c2dd","resolution":{"observed_at":"2026-05-13T07:22:28.962869Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":"2403.18802","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-06-30T06:44:18.784391Z","title":"Yang, Z., Qi, P., Zhang, S., Bengio, Y ., Cohen, W","venue":null,"work_id":"7729c367-1948-46b8-998b-0d5dc60bdbfc","year":2026},"citing_paper":{"arxiv_id":"2606.29920","last_updated":"2026-06-29T07:57:23Z","snapshot_observed_at":"2026-08-17T04:20:54.401844Z","submitted_at":"2026-06-29T07:57:23Z","title":"Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-30T06:42:30.226214Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2606.29920"},"observation_digest":"sha256:c6f8a732af055b6599a3512b6873cdaf284fd88913e95f0cb54f21c256e6abcc","observation_id":"cb1d8c87-bea7-45d8-8671-28a21c766c1a","resolution":{"observed_at":"2026-06-30T06:44:18.785878Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.18802","snapshot_observed_at":"2026-08-01T14:03:17.719461Z","title":", title =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18904","last_updated":"2026-07-21T09:46:30Z","snapshot_observed_at":"2026-08-15T09:02:48.519665Z","submitted_at":"2026-07-21T09:46:30Z","title":"Answer-Reconstruction Search Density: Measuring the Query and Source Work Compressed by Conversational Answers","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-01T14:03:17.719461Z"},"links":{"cited_paper":"/paper/2403.18802","citing_paper":"/paper/2607.18904"},"observation_digest":"sha256:09248dc60cca6a69c6ae96f41a745a6e2ba71806c8e04da5191fa348779a1cd0","observation_id":"dc54ef0c-6cf5-47bc-b6ae-eea8cc20e1f2","resolution":{"observed_at":"2026-08-01T14:03:17.719461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.18802/citation-record","integrity":"/paper/2403.18802/integrity","json":"/paper/2403.18802/citation-record.json","paper":"/paper/2403.18802"},"outbound":[],"paper":{"arxiv_id":"2403.18802","last_updated":"2024-11-07T03:14:38Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T15:09:21.692133Z","submitted_at":"2024-03-27T17:48:55Z","title":"Long-form factuality in large language models"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 25 inbound Pith citation observations for arXiv:2403.18802."}