{"as_of":"2026-08-22T15:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c990d68023df02316e6162703634b544239d154c1ba14b81c53545c8c075f6e8","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T19:54:58.135809Z","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":"2026-07-02T21:07:24.219142Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.08669","last_updated":"2023-11-06T18:44:33Z","snapshot_observed_at":"2026-08-16T14:52:33.451259Z","submitted_at":"2023-10-12T19:01:06Z","title":"Multimodal Large Language Model for Visual Navigation","version":2},"cited_work":{"arxiv_id":"2310.08669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.08669","snapshot_observed_at":"2026-07-02T21:07:24.219142Z","title":"Multimodal large lan- guage model for visual navigation","venue":null,"work_id":"42e9e228-026e-48df-b36c-2a837e87457e","year":2023},"citing_paper":{"arxiv_id":"2402.15852","last_updated":"2024-06-30T11:14:13Z","snapshot_observed_at":"2026-08-18T12:12:42.503422Z","submitted_at":"2024-02-24T16:39:16Z","title":"NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation","version":7},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-05-18T04:55:20.362512Z"},"links":{"cited_paper":"/paper/2310.08669","citing_paper":"/paper/2402.15852"},"observation_digest":"sha256:d8a4cdcbe134540add70491b5899958d7a96bd24a3a6129704acd5d54d219ac1","observation_id":"d6f13854-21a2-45cb-b542-629a815e207b","resolution":{"observed_at":"2026-05-18T04:55:20.525137Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08669","last_updated":"2023-11-06T18:44:33Z","snapshot_observed_at":"2026-08-16T14:52:33.451259Z","submitted_at":"2023-10-12T19:01:06Z","title":"Multimodal Large Language Model for Visual Navigation","version":2},"cited_work":{"arxiv_id":"2310.08669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.08669","snapshot_observed_at":"2026-07-02T21:07:24.219142Z","title":"Multimodal large lan- guage model for visual navigation","venue":null,"work_id":"42e9e228-026e-48df-b36c-2a837e87457e","year":2023},"citing_paper":{"arxiv_id":"2512.17435","last_updated":"2026-04-30T09:47:33Z","snapshot_observed_at":"2026-08-15T17:02:07.568102Z","submitted_at":"2025-12-19T10:40:16Z","title":"ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-16T21:07:54.497999Z"},"links":{"cited_paper":"/paper/2310.08669","citing_paper":"/paper/2512.17435"},"observation_digest":"sha256:5af99d4e5669a21e845feb3736d0fabd14a446e4e441876e1b376240d9764862","observation_id":"8f472edf-0c23-4c66-b7e7-44edb5936767","resolution":{"observed_at":"2026-05-16T21:08:32.505862Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08669","last_updated":"2023-11-06T18:44:33Z","snapshot_observed_at":"2026-08-16T14:52:33.451259Z","submitted_at":"2023-10-12T19:01:06Z","title":"Multimodal Large Language Model for Visual Navigation","version":2},"cited_work":{"arxiv_id":"2310.08669","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.08669","snapshot_observed_at":"2026-07-02T21:07:24.219142Z","title":"Multimodal large lan- guage model for visual navigation","venue":null,"work_id":"42e9e228-026e-48df-b36c-2a837e87457e","year":2023},"citing_paper":{"arxiv_id":"2606.08029","last_updated":"2026-06-06T07:45:19Z","snapshot_observed_at":"2026-08-12T17:40:58.190866Z","submitted_at":"2026-06-06T07:45:19Z","title":"IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-27T19:54:58.135809Z"},"links":{"cited_paper":"/paper/2310.08669","citing_paper":"/paper/2606.08029"},"observation_digest":"sha256:26c9053902ccde99d65b7c2a96b7f0dfe32f07aefc6c34820bd6e65f6d732615","observation_id":"9cba033b-5cdb-45ae-9d23-71a860a3d69e","resolution":{"observed_at":"2026-07-02T21:07:24.220811Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.08669/citation-record","integrity":"/paper/2310.08669/integrity","json":"/paper/2310.08669/citation-record.json","paper":"/paper/2310.08669"},"outbound":[],"paper":{"arxiv_id":"2310.08669","last_updated":"2023-11-06T18:44:33Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T14:52:33.451259Z","submitted_at":"2023-10-12T19:01:06Z","title":"Multimodal Large Language Model for Visual 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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2310.08669."}