{"as_of":"2026-08-19T20:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7c155ff7fde36d05121622df5c1246838d04461e877fd4aecde91be4bfad93c8","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":"2026-08-19T06:32:44.657259+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":"2026-08-16T11:06:08.303001Z","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":"2026-08-16T11:06:09.811873Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.03454","last_updated":"2021-03-05T03:41:00Z","snapshot_observed_at":"2026-08-17T11:36:47.102276Z","submitted_at":"2021-03-05T03:41:00Z","title":"Structured Scene Memory for Vision-Language Navigation","version":1},"cited_work":{"arxiv_id":"2103.03454","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.03454","snapshot_observed_at":"2026-08-16T11:06:09.811873Z","title":"Structured Scene Memory for Vision-Language Navigation","venue":"cs.CV","work_id":"b133870d-5af5-4dac-be71-9f6dadef75ea","year":2021},"citing_paper":{"arxiv_id":"2504.16516","last_updated":"2025-04-24T19:36:09Z","snapshot_observed_at":"2026-08-18T14:44:46.063293Z","submitted_at":"2025-04-23T08:41:27Z","title":"Think Hierarchically, Act Dynamically: Hierarchical Multi-modal Fusion and Reasoning for Vision-and-Language Navigation","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T11:06:08.303001Z"},"links":{"cited_paper":"/paper/2103.03454","citing_paper":"/paper/2504.16516"},"observation_digest":"sha256:ea6ee13ed3da8a8459701b13fad8cdde1e055f7321f401040a7af4b7907601bc","observation_id":"11977878-68ad-45d8-b322-28adfcc7d736","resolution":{"observed_at":"2026-08-16T11:06:09.830680Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2103.03454/citation-record","integrity":"/paper/2103.03454/integrity","json":"/paper/2103.03454/citation-record.json","paper":"/paper/2103.03454"},"outbound":[],"paper":{"arxiv_id":"2103.03454","last_updated":"2021-03-05T03:41:00Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T11:36:47.102276Z","submitted_at":"2021-03-05T03:41:00Z","title":"Structured Scene Memory for Vision-Language Navigation"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2103.03454."}