{"as_of":"2026-08-11T06:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f228266bdf631a0590aa4ee3fb4ed9d96c284954a309d091c81140a6fb906394","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T06:02:27.919399Z","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":"2026-05-22T23:10:41.019958Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.13125","last_updated":"2024-12-13T10:48:13Z","snapshot_observed_at":"2026-08-05T01:40:57.962531Z","submitted_at":"2024-02-20T16:38:33Z","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","version":2},"cited_work":{"arxiv_id":"2402.13125","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.13125","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"c4d6711a-8855-445b-b26a-4d16000cd8de","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":92,"source":"pdf_text","source_observed_at":"2026-05-22T23:10:40.420241Z"},"links":{"cited_paper":"/paper/2402.13125","citing_paper":"/paper/2406.04244"},"observation_digest":"sha256:78a7628f82bcba4f5ea018cea02e35b54252cadaab5687d8a670afaec76d4a75","observation_id":"e4e8f9c5-4969-4ea9-886f-66ee45bb76ff","resolution":{"observed_at":"2026-05-22T23:10:41.022739Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13125","last_updated":"2024-12-13T10:48:13Z","snapshot_observed_at":"2026-08-05T01:40:57.962531Z","submitted_at":"2024-02-20T16:38:33Z","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13125","snapshot_observed_at":"2026-08-10T06:02:27.919399Z","title":"arXiv preprint arXiv:2402.13125 , eprint =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.07341","last_updated":"2026-08-07T15:37:03Z","snapshot_observed_at":"2026-08-11T06:14:00.092410Z","submitted_at":"2026-08-07T15:37:03Z","title":"Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark Contamination","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T06:02:27.919399Z"},"links":{"cited_paper":"/paper/2402.13125","citing_paper":"/paper/2608.07341"},"observation_digest":"sha256:5aba03a512d6df1cb221575c2a4640963939a25b4a1631fc536ca3485f2ebc8e","observation_id":"ed307eb7-0c73-44fa-a888-517c3b418fd1","resolution":{"observed_at":"2026-08-10T06:02:27.919399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2402.13125/citation-record","integrity":"/paper/2402.13125/integrity","json":"/paper/2402.13125/citation-record.json","paper":"/paper/2402.13125"},"outbound":[],"paper":{"arxiv_id":"2402.13125","last_updated":"2024-12-13T10:48:13Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T01:40:57.962531Z","submitted_at":"2024-02-20T16:38:33Z","title":"TreeEval: Benchmark-Free Evaluation of Large Language Models through Tree Planning"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.13125."}