{"as_of":"2026-08-09T10:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:53227ca3c95f80b4862ae509024d19efd3392099c273158873b1977da824af6d","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":"2026-08-09T06:31:02.800959+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":"2026-08-04T09:27:29.897347Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2304.00719","last_updated":"2023-04-03T05:07:49Z","snapshot_observed_at":"2026-07-06T15:11:11.523214Z","submitted_at":"2023-04-03T05:07:49Z","title":"Multi-Modal Representation Learning with Text-Driven Soft Masks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.00719","snapshot_observed_at":"2026-08-04T09:27:29.897347Z","title":"Multi-modal representation learning with text- driven soft masks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.15470","last_updated":"2025-10-17T09:26:28Z","snapshot_observed_at":"2026-08-07T16:33:53.114091Z","submitted_at":"2025-10-17T09:26:28Z","title":"MSAM: Multi-Semantic Adaptive Mining for Cross-Modal Drone Video-Text Retrieval","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T09:27:29.897347Z"},"links":{"cited_paper":"/paper/2304.00719","citing_paper":"/paper/2510.15470"},"observation_digest":"sha256:d5bc5b7961d175245e9ae06e472d8b60f26dd8c1fee898ba35ac07b2bd499e9f","observation_id":"55782fe3-41b3-400b-84f8-223174cbb07d","resolution":{"observed_at":"2026-08-04T09:27:29.897347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2304.00719/citation-record","integrity":"/paper/2304.00719/integrity","json":"/paper/2304.00719/citation-record.json","paper":"/paper/2304.00719"},"outbound":[],"paper":{"arxiv_id":"2304.00719","last_updated":"2023-04-03T05:07:49Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:11:11.523214Z","submitted_at":"2023-04-03T05:07:49Z","title":"Multi-Modal Representation Learning with Text-Driven Soft Masks"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2304.00719."}