{"as_of":"2026-08-17T22:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b88b7fe451d8c37b3b51a6e1e427f51642938d1447cf3d07bcfedd95d6d662de","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":"2026-08-17T06:30:58.91139+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":"2026-08-12T19:59:00.085021Z","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":"2026-05-12T06:36:29.124314Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.14073","last_updated":"2024-02-21T19:01:03Z","snapshot_observed_at":"2026-08-16T14:16:28.908976Z","submitted_at":"2024-02-21T19:01:03Z","title":"Improving Language Understanding from Screenshots","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14073","snapshot_observed_at":"2026-08-12T19:59:00.085021Z","title":"Improving language understanding from screenshots","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.10503","last_updated":"2025-07-28T11:18:49Z","snapshot_observed_at":"2026-08-16T21:52:02.547241Z","submitted_at":"2024-11-15T12:59:37Z","title":"Everything is a Video: Unifying Modalities through Next-Frame Prediction","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T19:59:00.085021Z"},"links":{"cited_paper":"/paper/2402.14073","citing_paper":"/paper/2411.10503"},"observation_digest":"sha256:ff77d9a8c139ed2c6e398b2bb93713d8f048878aa3f93b84dc6ddd167abf714f","observation_id":"4529372c-b4d8-4775-bb83-368e7da1498d","resolution":{"observed_at":"2026-08-12T19:59:00.085021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14073","last_updated":"2024-02-21T19:01:03Z","snapshot_observed_at":"2026-08-16T14:16:28.908976Z","submitted_at":"2024-02-21T19:01:03Z","title":"Improving Language Understanding from Screenshots","version":1},"cited_work":{"arxiv_id":"2402.14073","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.14073","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving language understanding from screenshots","venue":null,"work_id":"7fc7735f-811e-4298-8572-86d0d14d7e22","year":2024},"citing_paper":{"arxiv_id":"2605.09630","last_updated":"2026-05-10T16:18:22Z","snapshot_observed_at":"2026-08-14T10:03:16.402043Z","submitted_at":"2026-05-10T16:18:22Z","title":"Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-05-12T04:05:28.713898Z"},"links":{"cited_paper":"/paper/2402.14073","citing_paper":"/paper/2605.09630"},"observation_digest":"sha256:97d7ff90a781e7945619fe7337502cd7b86113eca040d3d810d77d7dd4ee0bb3","observation_id":"9138ff7f-3b7f-41bf-8e83-4b0a7ea88ed9","resolution":{"observed_at":"2026-05-12T06:36:29.128760Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.14073/citation-record","integrity":"/paper/2402.14073/integrity","json":"/paper/2402.14073/citation-record.json","paper":"/paper/2402.14073"},"outbound":[],"paper":{"arxiv_id":"2402.14073","last_updated":"2024-02-21T19:01:03Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T14:16:28.908976Z","submitted_at":"2024-02-21T19:01:03Z","title":"Improving Language Understanding from Screenshots"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.14073."}