{"as_of":"2026-08-14T12:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bdc722dd642f3d0c97f2881288ff05c77396f7e6af1e8bbf2fb308bf58185555","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":"2026-08-14T06:32:32.682623+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":"2026-08-05T11:27:47.082104Z","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":"2026-08-05T11:27:47.515908Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.05930","last_updated":"2024-09-17T02:10:16Z","snapshot_observed_at":"2026-08-13T12:04:11.297621Z","submitted_at":"2023-04-12T15:50:19Z","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer","version":3},"cited_work":{"arxiv_id":"2304.05930","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.05930","snapshot_observed_at":"2026-08-05T11:27:47.515908Z","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer","venue":"cs.CV","work_id":"18525668-89b5-4c48-9ed4-d1769a375b52","year":2023},"citing_paper":{"arxiv_id":"2509.02807","last_updated":"2025-09-02T20:21:11Z","snapshot_observed_at":"2026-08-09T21:27:46.268389Z","submitted_at":"2025-09-02T20:21:11Z","title":"PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T11:27:47.082104Z"},"links":{"cited_paper":"/paper/2304.05930","citing_paper":"/paper/2509.02807"},"observation_digest":"sha256:c38a7e9d47f6803dde303e6c110bb79f3e10f2b4965d55270df76fbeaf345307","observation_id":"2c9655e2-ebaa-4cb8-84bb-095876763e1c","resolution":{"observed_at":"2026-08-05T11:27:47.523163Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2304.05930/citation-record","integrity":"/paper/2304.05930/integrity","json":"/paper/2304.05930/citation-record.json","paper":"/paper/2304.05930"},"outbound":[],"paper":{"arxiv_id":"2304.05930","last_updated":"2024-09-17T02:10:16Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T12:04:11.297621Z","submitted_at":"2023-04-12T15:50:19Z","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2304.05930."}