{"as_of":"2026-08-05T22:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:306ee1b9b962e6432e4275627be57f195e107a45ceeccc1807d8cc5f6a668c25","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":"2026-08-05T06:32:48.257954+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":"2026-05-19T05:55:09.188048Z","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":"2026-05-19T05:57:08.139740Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.09406","last_updated":"2024-06-14T14:43:26Z","snapshot_observed_at":"2026-07-06T18:30:32.982860Z","submitted_at":"2024-06-13T17:59:42Z","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","version":2},"cited_work":{"arxiv_id":"2406.09406","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.09406","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"4m-21: An any-to-any vision model for tens of tasks and modalities","venue":null,"work_id":"fd743528-d309-4580-b78f-3266ded9b266","year":2024},"citing_paper":{"arxiv_id":"2507.01955","last_updated":"2026-05-01T00:57:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-07-02T17:59:07Z","title":"How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-19T05:55:09.188048Z"},"links":{"cited_paper":"/paper/2406.09406","citing_paper":"/paper/2507.01955"},"observation_digest":"sha256:987cc8ea2311f36207c8e51c2ab040ce799a168df2a97a8ef2f0e8b06cd549b5","observation_id":"f4f32294-4695-4628-aaf1-deb3244d8dec","resolution":{"observed_at":"2026-05-19T05:57:08.142513Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.09406/citation-record","integrity":"/paper/2406.09406/integrity","json":"/paper/2406.09406/citation-record.json","paper":"/paper/2406.09406"},"outbound":[],"paper":{"arxiv_id":"2406.09406","last_updated":"2024-06-14T14:43:26Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:30:32.982860Z","submitted_at":"2024-06-13T17:59:42Z","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2406.09406."}