{"as_of":"2026-08-11T18:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dfc99e3a16bb2fec0faa06ad6a4e5e4c4cd95f00be133111e22479aed809d00a","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":"2026-08-11T06:34:44.6726+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":"2026-05-21T22:00:45.377456Z","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":"2026-05-21T22:04:24.220026Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.02547","last_updated":"2024-06-04T17:59:25Z","snapshot_observed_at":"2026-08-11T14:28:53.408835Z","submitted_at":"2024-06-04T17:59:25Z","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning","version":1},"cited_work":{"arxiv_id":"2406.02547","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.02547","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Leveraging visual tokens for ex- tended text contexts in multi-modal learning","venue":null,"work_id":"b753f08e-27dd-44ed-a1ad-d0b968d97149","year":2024},"citing_paper":{"arxiv_id":"2509.18150","last_updated":"2026-05-18T07:54:25Z","snapshot_observed_at":"2026-08-03T19:54:51.242122Z","submitted_at":"2025-09-16T11:33:20Z","title":"Improving MLLM Training Efficiency via Stage-Aware Sparsity","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-21T22:00:45.377456Z"},"links":{"cited_paper":"/paper/2406.02547","citing_paper":"/paper/2509.18150"},"observation_digest":"sha256:a85e80f4b3760fc13469c0113e634748cbf6f37046704a0cf93ba2923dce2ac1","observation_id":"6623c92a-1315-499e-bacb-3f490b497a14","resolution":{"observed_at":"2026-05-21T22:04:24.222596Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.02547/citation-record","integrity":"/paper/2406.02547/integrity","json":"/paper/2406.02547/citation-record.json","paper":"/paper/2406.02547"},"outbound":[],"paper":{"arxiv_id":"2406.02547","last_updated":"2024-06-04T17:59:25Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T14:28:53.408835Z","submitted_at":"2024-06-04T17:59:25Z","title":"Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2406.02547."}