{"as_of":"2026-08-16T01:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c55db4fea56440b47b9dc593b130e5322a81aa28c44e000e7df200fc9cb51f59","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":"2026-08-15T06:32:42.880941+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":"2026-08-11T13:04:20.245797Z","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":"2026-05-22T23:10:41.136065Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.11894","last_updated":"2024-06-06T12:49:44Z","snapshot_observed_at":"2026-08-15T18:20:56.348724Z","submitted_at":"2024-02-19T07:15:59Z","title":"Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models","version":3},"cited_work":{"arxiv_id":"2402.11894","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.11894","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"1a46d445-b51c-421c-9888-a02ad410ad83","year":2024},"citing_paper":{"arxiv_id":"2406.04244","last_updated":"2024-06-06T16:41:39Z","snapshot_observed_at":"2026-07-30T15:43:06.151242Z","submitted_at":"2024-06-06T16:41:39Z","title":"Benchmark Data Contamination of Large Language Models: A Survey","version":1},"reference_index":173,"source":"pdf_text","source_observed_at":"2026-05-22T23:10:40.420241Z"},"links":{"cited_paper":"/paper/2402.11894","citing_paper":"/paper/2406.04244"},"observation_digest":"sha256:a06f0b987a80dafab9394ee377919df1dac09cb162223220a25d91c75626579d","observation_id":"541754cc-16a8-4055-8f4a-2da374e7f92a","resolution":{"observed_at":"2026-05-22T23:10:41.138063Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2402.11894","last_updated":"2024-06-06T12:49:44Z","snapshot_observed_at":"2026-08-15T18:20:56.348724Z","submitted_at":"2024-02-19T07:15:59Z","title":"Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11894","snapshot_observed_at":"2026-08-11T13:04:20.245797Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13582","last_updated":"2024-12-18T08:04:57Z","snapshot_observed_at":"2026-08-12T16:05:46.582881Z","submitted_at":"2024-12-18T08:04:57Z","title":"EvoWiki: Evaluating LLMs on Evolving Knowledge","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-11T13:04:20.245797Z"},"links":{"cited_paper":"/paper/2402.11894","citing_paper":"/paper/2412.13582"},"observation_digest":"sha256:e5d7209f868ab38f341d793d88382cdbb624e3a6e8df17e10ab5da917b83a31f","observation_id":"2adef595-f78f-4422-9908-be10ecc07f7b","resolution":{"observed_at":"2026-08-11T13:04:20.245797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11894","last_updated":"2024-06-06T12:49:44Z","snapshot_observed_at":"2026-08-15T18:20:56.348724Z","submitted_at":"2024-02-19T07:15:59Z","title":"Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11894","snapshot_observed_at":"2026-08-11T12:58:02.299587Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.13670","last_updated":"2025-05-29T03:19:42Z","snapshot_observed_at":"2026-08-15T06:36:37.650310Z","submitted_at":"2024-12-18T09:53:12Z","title":"AntiLeakBench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-11T12:58:02.299587Z"},"links":{"cited_paper":"/paper/2402.11894","citing_paper":"/paper/2412.13670"},"observation_digest":"sha256:c6ce57fa3b1b0894d53e30bb7567c8ff193cee7470dc3c8f1c2402fa844541a3","observation_id":"5e17b376-f3b9-425f-a496-d0551c2da108","resolution":{"observed_at":"2026-08-11T12:58:02.299587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11894","last_updated":"2024-06-06T12:49:44Z","snapshot_observed_at":"2026-08-15T18:20:56.348724Z","submitted_at":"2024-02-19T07:15:59Z","title":"Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11894","snapshot_observed_at":"2026-08-07T11:04:07.119152Z","title":"Automating dataset updates towards reliable and timely evaluation of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03637","last_updated":"2025-07-07T09:53:22Z","snapshot_observed_at":"2026-08-08T03:23:19.289933Z","submitted_at":"2025-06-04T07:30:16Z","title":"RewardAnything: Generalizable Principle-Following Reward Models","version":2},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T11:04:07.119152Z"},"links":{"cited_paper":"/paper/2402.11894","citing_paper":"/paper/2506.03637"},"observation_digest":"sha256:186fcc8b405d4293cd787fd6f4166d01f131c9ba4d46a3c828ad99e6fb04f565","observation_id":"77f5f3d2-ef74-4f68-a451-c39f90ca04b3","resolution":{"observed_at":"2026-08-07T11:04:07.119152Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.11894/citation-record","integrity":"/paper/2402.11894/integrity","json":"/paper/2402.11894/citation-record.json","paper":"/paper/2402.11894"},"outbound":[],"paper":{"arxiv_id":"2402.11894","last_updated":"2024-06-06T12:49:44Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T18:20:56.348724Z","submitted_at":"2024-02-19T07:15:59Z","title":"Automating Dataset Updates Towards Reliable and Timely Evaluation of 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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2402.11894."}