{"as_of":"2026-08-10T14:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:57ac0dfd5dd44f4cb0adc8734018b43f4ea4b4169b9f222d80a38d0f4f38a5b9","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":"2026-08-10T06:31:04.303077+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":"2026-08-08T15:06:55.394071Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T23:25:53.750928Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.08385","last_updated":"2025-07-22T23:36:25Z","snapshot_observed_at":"2026-07-06T19:31:31.809692Z","submitted_at":"2024-10-10T21:44:56Z","title":"Language model developers should report train-test overlap","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.08385","snapshot_observed_at":"2026-08-08T15:06:55.394071Z","title":"Zhang, Kevin Klyman, Yifan Mai, Yoav Levine, Yian Zhang, Rishi Bommasani, and Percy Liang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06559","last_updated":"2025-05-25T23:36:47Z","snapshot_observed_at":"2026-08-08T23:28:10.897343Z","submitted_at":"2025-02-10T15:25:06Z","title":"Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation","version":2},"reference_index":138,"source":"arxiv_source","source_observed_at":"2026-08-08T15:06:55.394071Z"},"links":{"cited_paper":"/paper/2410.08385","citing_paper":"/paper/2502.06559"},"observation_digest":"sha256:09d612203f45a255612c7b8c60700fb9b0d7fb4a277be1e4408ea9a0285c5b82","observation_id":"acc757cd-6a7d-41f3-bbbb-fa8cc231c717","resolution":{"observed_at":"2026-08-08T15:06:55.394071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.08385","last_updated":"2025-07-22T23:36:25Z","snapshot_observed_at":"2026-07-06T19:31:31.809692Z","submitted_at":"2024-10-10T21:44:56Z","title":"Language model developers should report train-test overlap","version":2},"cited_work":{"arxiv_id":"2410.08385","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.08385","snapshot_observed_at":"2026-08-06T23:25:53.750928Z","title":"Language model developers should report train-test overlap","venue":"cs.LG","work_id":"00337004-df41-4c88-bf07-f0ee0f1feb64","year":2024},"citing_paper":{"arxiv_id":"2506.18213","last_updated":"2025-06-23T00:19:27Z","snapshot_observed_at":"2026-08-07T10:41:05.932475Z","submitted_at":"2025-06-23T00:19:27Z","title":"A Conceptual Framework for AI Capability Evaluations","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-06T23:25:52.690485Z"},"links":{"cited_paper":"/paper/2410.08385","citing_paper":"/paper/2506.18213"},"observation_digest":"sha256:0d1cff1cdf58ab903e015c6f8846cf19fc0969463b4f0b6d62090d17bf912df6","observation_id":"b7d1310d-4790-46ef-997a-f330a0adec6a","resolution":{"observed_at":"2026-08-06T23:25:53.854157Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.08385/citation-record","integrity":"/paper/2410.08385/integrity","json":"/paper/2410.08385/citation-record.json","paper":"/paper/2410.08385"},"outbound":[],"paper":{"arxiv_id":"2410.08385","last_updated":"2025-07-22T23:36:25Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:31:31.809692Z","submitted_at":"2024-10-10T21:44:56Z","title":"Language model developers should report train-test overlap"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.08385."}