{"as_of":"2026-08-07T08:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6e5bdfd1f48da3a8f072911123e89d465b74b254b00749cc5f920b74a3fa5b1d","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T02:10:04.003151Z","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":"2026-05-11T13:16:03.876935Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.07603","last_updated":"2025-03-10T17:58:19Z","snapshot_observed_at":"2026-08-04T07:24:00.037189Z","submitted_at":"2025-03-10T17:58:19Z","title":"Should VLMs be Pre-trained with Image Data?","version":1},"cited_work":{"arxiv_id":"2503.07603","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.07603","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Should VLMs be Pre-trained with Image Data?","venue":null,"work_id":"663c0644-79a4-4418-abd6-e818b263e493","year":2025},"citing_paper":{"arxiv_id":"2604.19728","last_updated":"2026-04-21T17:51:51Z","snapshot_observed_at":"2026-08-07T03:27:51.613115Z","submitted_at":"2026-04-21T17:51:51Z","title":"VLA Foundry: A Unified Framework for Training Vision-Language-Action Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T02:10:04.003151Z"},"links":{"cited_paper":"/paper/2503.07603","citing_paper":"/paper/2604.19728"},"observation_digest":"sha256:da0a3574bdea8152c7660687f41f68ab4a7da218a093adb50986e233a139cec0","observation_id":"ab335f5b-d315-4d77-bcdd-89df223d3f85","resolution":{"observed_at":"2026-05-11T13:16:03.883147Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.07603/citation-record","integrity":"/paper/2503.07603/integrity","json":"/paper/2503.07603/citation-record.json","paper":"/paper/2503.07603"},"outbound":[],"paper":{"arxiv_id":"2503.07603","last_updated":"2025-03-10T17:58:19Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T07:24:00.037189Z","submitted_at":"2025-03-10T17:58:19Z","title":"Should VLMs be Pre-trained with Image Data?"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2503.07603."}