{"as_of":"2026-08-24T00:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f9080ca0472085322abb1ea3c2a1b0f9aaa3974781903462490d1a7792977f9d","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:17:23.071573Z","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":"2026-05-14T18:02:32.593241Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.02208","last_updated":"2024-06-04T11:06:13Z","snapshot_observed_at":"2026-08-19T04:37:43.692520Z","submitted_at":"2024-06-04T11:06:13Z","title":"Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02208","snapshot_observed_at":"2026-08-10T22:17:23.071573Z","title":"Why only text: Empowering vision-and-language navigation with multi-modal prompts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.02189","last_updated":"2025-04-06T03:12:51Z","snapshot_observed_at":"2026-08-20T17:46:54.459933Z","submitted_at":"2025-01-04T04:59:33Z","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","version":6},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-10T22:17:23.071573Z"},"links":{"cited_paper":"/paper/2406.02208","citing_paper":"/paper/2501.02189"},"observation_digest":"sha256:5f84ee51fce552bdd20d88982ad4ca1e3433188237623e5d74606938f5fa4d78","observation_id":"fffde891-225b-4daf-be82-45acb1cba0b0","resolution":{"observed_at":"2026-08-10T22:17:23.071573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02208","last_updated":"2024-06-04T11:06:13Z","snapshot_observed_at":"2026-08-19T04:37:43.692520Z","submitted_at":"2024-06-04T11:06:13Z","title":"Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts","version":1},"cited_work":{"arxiv_id":"2406.02208","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.02208","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Why only text: Empowering vision-and-language navigation with multi-modal prompts","venue":null,"work_id":"99ba4039-0b95-4982-b07f-c0582c64d4e8","year":2024},"citing_paper":{"arxiv_id":"2605.13328","last_updated":"2026-05-13T10:41:24Z","snapshot_observed_at":"2026-08-11T08:12:01.149533Z","submitted_at":"2026-05-13T10:41:24Z","title":"What Limits Vision-and-Language Navigation ?","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-14T17:59:58.891151Z"},"links":{"cited_paper":"/paper/2406.02208","citing_paper":"/paper/2605.13328"},"observation_digest":"sha256:97039a89718989968a06e402dc63d59de8e56bbbb717aa36d270ecae7a600035","observation_id":"9ba2f86a-19c3-4c8b-8a57-bf26eb9c8132","resolution":{"observed_at":"2026-05-14T18:02:32.597075Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.02208/citation-record","integrity":"/paper/2406.02208/integrity","json":"/paper/2406.02208/citation-record.json","paper":"/paper/2406.02208"},"outbound":[],"paper":{"arxiv_id":"2406.02208","last_updated":"2024-06-04T11:06:13Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T04:37:43.692520Z","submitted_at":"2024-06-04T11:06:13Z","title":"Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.02208."}