{"as_of":"2026-08-16T01:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dd17607b22802d2ed9fe9191dc1b1a6187ed40ab3722a045e979f716d1176ddc","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":"2026-08-15T06:32:42.880941+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":"2026-08-07T15:38:44.914015Z","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":"2026-08-06T17:37:52.994728Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2402.09816","last_updated":"2025-07-18T11:42:52Z","snapshot_observed_at":"2026-08-13T11:04:16.310449Z","submitted_at":"2024-02-15T09:31:07Z","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09816","snapshot_observed_at":"2026-08-07T15:38:44.914015Z","title":"Mind the modality gap: Towards a remote sensing vision-language model via cross-modal alignment,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.14361","last_updated":"2025-05-20T13:47:40Z","snapshot_observed_at":"2026-08-10T20:27:13.425753Z","submitted_at":"2025-05-20T13:47:40Z","title":"Vision-Language Modeling Meets Remote Sensing: Models, Datasets and Perspectives","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:38:44.914015Z"},"links":{"cited_paper":"/paper/2402.09816","citing_paper":"/paper/2505.14361"},"observation_digest":"sha256:6e3de6023c27c2c8c12bbe64ab238f044ca882d62b5d3fb54a76d4b5e837c764","observation_id":"cb51dcff-43d7-4a42-8371-a7f4ee1c1383","resolution":{"observed_at":"2026-08-07T15:38:44.914015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09816","last_updated":"2025-07-18T11:42:52Z","snapshot_observed_at":"2026-08-13T11:04:16.310449Z","submitted_at":"2024-02-15T09:31:07Z","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","version":2},"cited_work":{"arxiv_id":"2402.09816","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.09816","snapshot_observed_at":"2026-08-06T17:37:52.994728Z","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment","venue":"cs.CV","work_id":"63fb9276-361e-41d7-a37a-c7ac6de3a209","year":2024},"citing_paper":{"arxiv_id":"2507.10473","last_updated":"2025-07-25T21:08:55Z","snapshot_observed_at":"2026-08-14T03:14:20.244546Z","submitted_at":"2025-07-14T16:54:57Z","title":"GT-Loc: Unifying When and Where in Images Through a Joint Embedding Space","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:37:50.920528Z"},"links":{"cited_paper":"/paper/2402.09816","citing_paper":"/paper/2507.10473"},"observation_digest":"sha256:3dbe638c2cadc3a243568e6c2ec32a2378fc92fe4197e4ea8ba12f79dfcf06f7","observation_id":"6db9bcab-05ec-4544-acbb-7961952b08d0","resolution":{"observed_at":"2026-08-06T17:37:53.067152Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2402.09816/citation-record","integrity":"/paper/2402.09816/integrity","json":"/paper/2402.09816/citation-record.json","paper":"/paper/2402.09816"},"outbound":[],"paper":{"arxiv_id":"2402.09816","last_updated":"2025-07-18T11:42:52Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T11:04:16.310449Z","submitted_at":"2024-02-15T09:31:07Z","title":"Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2402.09816."}