{"as_of":"2026-08-09T20:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2a5cc1562180e6f5b7dc3a0dfd0a73f29f297e019e3292c2ff44dbcb04ca6967","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T14:01:25.047482Z","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":"2026-08-07T14:01:26.424935Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.06492","last_updated":"2025-03-09T07:25:32Z","snapshot_observed_at":"2026-08-07T17:19:21.009730Z","submitted_at":"2025-03-09T07:25:32Z","title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering","version":1},"cited_work":{"arxiv_id":"2503.06492","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.06492","snapshot_observed_at":"2026-08-07T14:01:26.424935Z","title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering","venue":"cs.CL","work_id":"4d21c30a-e59f-4626-96b3-7cff3c93037e","year":2025},"citing_paper":{"arxiv_id":"2505.20236","last_updated":"2025-05-26T17:16:36Z","snapshot_observed_at":"2026-08-09T09:47:04.301294Z","submitted_at":"2025-05-26T17:16:36Z","title":"Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Models","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T14:01:25.047482Z"},"links":{"cited_paper":"/paper/2503.06492","citing_paper":"/paper/2505.20236"},"observation_digest":"sha256:e421550af709263a0b4ed1d4116182ab42e257ccc3998ecdab2e3e49a28aea26","observation_id":"65e97d08-87bc-493e-a73f-9e4b9d3f9984","resolution":{"observed_at":"2026-08-07T14:01:26.473041Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06492","last_updated":"2025-03-09T07:25:32Z","snapshot_observed_at":"2026-08-07T17:19:21.009730Z","submitted_at":"2025-03-09T07:25:32Z","title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06492","snapshot_observed_at":"2026-08-01T08:23:21.295736Z","title":"arXiv preprint (2025),https: //arxiv.org/abs/2503.064924, 22, 27, 29","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.21155","last_updated":"2026-07-23T10:37:01Z","snapshot_observed_at":"2026-08-01T08:23:18.056458Z","submitted_at":"2026-07-23T10:37:01Z","title":"CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T08:23:21.295736Z"},"links":{"cited_paper":"/paper/2503.06492","citing_paper":"/paper/2607.21155"},"observation_digest":"sha256:036fc2f6311a370845c5f0454577f83daab70075e03318ce1301f9a116c9302c","observation_id":"0d9147b3-b056-4166-bbb6-58779054246b","resolution":{"observed_at":"2026-08-01T08:23:21.295736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2503.06492/citation-record","integrity":"/paper/2503.06492/integrity","json":"/paper/2503.06492/citation-record.json","paper":"/paper/2503.06492"},"outbound":[],"paper":{"arxiv_id":"2503.06492","last_updated":"2025-03-09T07:25:32Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T17:19:21.009730Z","submitted_at":"2025-03-09T07:25:32Z","title":"VisualSimpleQA: A Benchmark for Decoupled Evaluation of Large Vision-Language Models in Fact-Seeking 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2503.06492."}