{"as_of":"2026-08-15T21:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:be655f223f9e5dde91350e367bfe7a209a43d154157c733202cd623e0af75a0a","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":"2026-08-15T06:32:42.880941+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":"2026-07-04T00:30:13.665405Z","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":"2026-07-04T00:39:16.488191Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.05590","last_updated":"2024-07-29T11:20:42Z","snapshot_observed_at":"2026-08-14T15:01:08.757572Z","submitted_at":"2024-04-08T15:03:57Z","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","version":2},"cited_work":{"arxiv_id":"2404.05590","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.05590","snapshot_observed_at":"2026-07-04T00:39:16.488191Z","title":"ArXivabs/2404.05590(2024)","venue":null,"work_id":"e65832d0-afe9-4fc2-b26d-37f6220368fa","year":2024},"citing_paper":{"arxiv_id":"2606.03305","last_updated":"2026-07-01T19:01:29Z","snapshot_observed_at":"2026-08-02T11:54:02.200908Z","submitted_at":"2026-06-02T08:21:22Z","title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T09:48:09.688745Z"},"links":{"cited_paper":"/paper/2404.05590","citing_paper":"/paper/2606.03305"},"observation_digest":"sha256:b792ab051ab9c584b96f2d7f426b7ed189246978b5e8541a3bda576cc873e9ae","observation_id":"6f1d19b3-64d2-43a1-b4b9-4717f1c4844d","resolution":{"observed_at":"2026-07-02T03:36:30.297341Z","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":"2404.05590","last_updated":"2024-07-29T11:20:42Z","snapshot_observed_at":"2026-08-14T15:01:08.757572Z","submitted_at":"2024-04-08T15:03:57Z","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering","version":2},"cited_work":{"arxiv_id":"2404.05590","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.05590","snapshot_observed_at":"2026-07-04T00:39:16.488191Z","title":"ArXivabs/2404.05590(2024)","venue":null,"work_id":"e65832d0-afe9-4fc2-b26d-37f6220368fa","year":2024},"citing_paper":{"arxiv_id":"2606.03305","last_updated":"2026-07-01T19:01:29Z","snapshot_observed_at":"2026-08-02T11:54:02.200908Z","submitted_at":"2026-06-02T08:21:22Z","title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-04T00:30:13.665405Z"},"links":{"cited_paper":"/paper/2404.05590","citing_paper":"/paper/2606.03305"},"observation_digest":"sha256:a168b81bdd399d513ab90b238832135173087ee8f449833c6e1b56f70f9fea75","observation_id":"208fe87f-df6a-4b35-8a00-363f8affc4f7","resolution":{"observed_at":"2026-07-04T00:39:16.489445Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2404.05590/citation-record","integrity":"/paper/2404.05590/integrity","json":"/paper/2404.05590/citation-record.json","paper":"/paper/2404.05590"},"outbound":[],"paper":{"arxiv_id":"2404.05590","last_updated":"2024-07-29T11:20:42Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-14T15:01:08.757572Z","submitted_at":"2024-04-08T15:03:57Z","title":"MedExpQA: Multilingual Benchmarking of Large Language Models for Medical Question Answering"},"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 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2404.05590."}