{"as_of":"2026-08-09T14:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2ac433fa5729d829027a947eb223ac09388b966749f3491218147f19fee5bdae","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":"2026-08-07T14:01:23.643676Z","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":"2026-05-14T00:51:48.385456Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.17647","last_updated":"2024-06-10T23:39:24Z","snapshot_observed_at":"2026-07-06T16:54:22.039181Z","submitted_at":"2023-11-29T14:08:53Z","title":"Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?","version":2},"cited_work":{"arxiv_id":"2311.17647","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.17647","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"a8c6e353-2845-40b0-8b78-340eb41f2cf4","year":2023},"citing_paper":{"arxiv_id":"2409.02813","last_updated":"2025-05-22T08:22:02Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-04T15:31:26Z","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","version":3},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-05-14T00:51:48.163349Z"},"links":{"cited_paper":"/paper/2311.17647","citing_paper":"/paper/2409.02813"},"observation_digest":"sha256:2ec6fd0821bc650166da0e6d4951771c394fe10cf434f3de3eafe976e6d32cb7","observation_id":"4f54a0a3-89cf-49cb-b35a-da29ab164ff8","resolution":{"observed_at":"2026-05-14T00:51:48.388348Z","resolver_source":"arxiv_id","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":"2311.17647","last_updated":"2024-06-10T23:39:24Z","snapshot_observed_at":"2026-07-06T16:54:22.039181Z","submitted_at":"2023-11-29T14:08:53Z","title":"Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17647","snapshot_observed_at":"2026-08-07T14:01:23.643676Z","title":null,"venue":null,"work_id":null,"year":2024},"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":18,"source":"arxiv_source","source_observed_at":"2026-08-07T14:01:23.643676Z"},"links":{"cited_paper":"/paper/2311.17647","citing_paper":"/paper/2505.20236"},"observation_digest":"sha256:5c6a2954c8831a3c6f6c4e28bd99dc2b0ce64a9a30a0e306c917b09dfc6088cf","observation_id":"12de5b99-01a3-4278-83ce-e0e4dd4be166","resolution":{"observed_at":"2026-08-07T14:01:23.643676Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.17647/citation-record","integrity":"/paper/2311.17647/integrity","json":"/paper/2311.17647/citation-record.json","paper":"/paper/2311.17647"},"outbound":[],"paper":{"arxiv_id":"2311.17647","last_updated":"2024-06-10T23:39:24Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:54:22.039181Z","submitted_at":"2023-11-29T14:08:53Z","title":"Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?"},"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:2311.17647."}