{"as_of":"2026-08-07T15:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f6c68351de4072add911435d4d77d0e36e27266fcba46f6bb663b8eb4290dfa7","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T02:14:08.103425Z","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":"2026-05-16T10:47:31.141279Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.01781","last_updated":"2024-07-03T11:20:43Z","snapshot_observed_at":"2026-07-31T17:52:54.507082Z","submitted_at":"2024-02-01T19:12:25Z","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","version":2},"cited_work":{"arxiv_id":"2402.01781","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.01781","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"When benchmarks are targets: Revealing the sensitivity of large language model leaderboards","venue":null,"work_id":"e17be6ab-246f-48c4-b76e-49c58b63b133","year":2024},"citing_paper":{"arxiv_id":"2403.12031","last_updated":"2024-03-28T17:56:28Z","snapshot_observed_at":"2026-07-06T17:46:29.153377Z","submitted_at":"2024-03-18T17:59:04Z","title":"RouterBench: A Benchmark for Multi-LLM Routing System","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-05-16T10:47:31.006944Z"},"links":{"cited_paper":"/paper/2402.01781","citing_paper":"/paper/2403.12031"},"observation_digest":"sha256:47f478bc5f2e95077647b7a111946f2e2ec58d9ed7d0164e912a7bbf02246ce1","observation_id":"fba070fe-dd71-477f-9785-f490b8588e91","resolution":{"observed_at":"2026-05-16T10:47:31.143539Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01781","last_updated":"2024-07-03T11:20:43Z","snapshot_observed_at":"2026-07-31T17:52:54.507082Z","submitted_at":"2024-02-01T19:12:25Z","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","version":2},"cited_work":{"arxiv_id":"2402.01781","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.01781","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"When benchmarks are targets: Revealing the sensitivity of large language model leaderboards","venue":null,"work_id":"e17be6ab-246f-48c4-b76e-49c58b63b133","year":2024},"citing_paper":{"arxiv_id":"2406.01574","last_updated":"2024-11-06T02:54:00Z","snapshot_observed_at":"2026-08-06T00:29:17.674418Z","submitted_at":"2024-06-03T17:53:00Z","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","version":6},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-11T15:51:04.674346Z"},"links":{"cited_paper":"/paper/2402.01781","citing_paper":"/paper/2406.01574"},"observation_digest":"sha256:c506536797da40fb0edb505a0c484cde545af8f780c394c2b09c8626fab1505a","observation_id":"a93ec630-105a-4a4c-a428-285fb95e7f65","resolution":{"observed_at":"2026-05-11T15:51:06.285386Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01781","last_updated":"2024-07-03T11:20:43Z","snapshot_observed_at":"2026-07-31T17:52:54.507082Z","submitted_at":"2024-02-01T19:12:25Z","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01781","snapshot_observed_at":"2026-08-02T02:14:08.103425Z","title":"A Helpful Assistant","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14399","last_updated":"2026-07-15T22:33:53Z","snapshot_observed_at":"2026-08-06T15:16:58.279444Z","submitted_at":"2026-07-15T22:33:53Z","title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T02:14:08.103425Z"},"links":{"cited_paper":"/paper/2402.01781","citing_paper":"/paper/2607.14399"},"observation_digest":"sha256:9e78655e04f9b09fcba04675e44449ba6460dd4cd5cfa33241d5d374588f63be","observation_id":"67b6341e-63f4-46a0-8f7d-e48e562108f8","resolution":{"observed_at":"2026-08-02T02:14:08.103425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.01781/citation-record","integrity":"/paper/2402.01781/integrity","json":"/paper/2402.01781/citation-record.json","paper":"/paper/2402.01781"},"outbound":[],"paper":{"arxiv_id":"2402.01781","last_updated":"2024-07-03T11:20:43Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-31T17:52:54.507082Z","submitted_at":"2024-02-01T19:12:25Z","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2402.01781."}