{"as_of":"2026-08-14T01:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f6e8b9a791bb40504a63754eb0d8a69ef84f5f5867d182b40f0dbedd901c688a","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T16:39:40.528370Z","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":"2026-08-12T16:39:41.015681Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.22330","last_updated":"2025-05-07T17:59:59Z","snapshot_observed_at":"2026-08-12T22:12:29.955096Z","submitted_at":"2024-10-29T17:59:45Z","title":"Vision-Language Models Create Cross-Modal Task Representations","version":2},"cited_work":{"arxiv_id":"2410.22330","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.22330","snapshot_observed_at":"2026-08-12T16:39:41.015681Z","title":"Vision-Language Models Create Cross-Modal Task Representations","venue":"cs.CV","work_id":"f88a82d6-c0b8-4523-8ad7-6a81e7db8b79","year":2024},"citing_paper":{"arxiv_id":"2411.13317","last_updated":"2025-03-12T19:43:14Z","snapshot_observed_at":"2026-08-12T16:31:13.006323Z","submitted_at":"2024-11-20T13:34:22Z","title":"Teaching VLMs to Localize Specific Objects from In-context Examples","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T16:39:40.528370Z"},"links":{"cited_paper":"/paper/2410.22330","citing_paper":"/paper/2411.13317"},"observation_digest":"sha256:3d7dbb4fd7a993ed91fdb1b76f07a0fb05323c53804b549f418385db2a0ead9f","observation_id":"d571833c-e27a-4c74-b083-dcc1f19b7e47","resolution":{"observed_at":"2026-08-12T16:39:41.022727Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.22330/citation-record","integrity":"/paper/2410.22330/integrity","json":"/paper/2410.22330/citation-record.json","paper":"/paper/2410.22330"},"outbound":[],"paper":{"arxiv_id":"2410.22330","last_updated":"2025-05-07T17:59:59Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T22:12:29.955096Z","submitted_at":"2024-10-29T17:59:45Z","title":"Vision-Language Models Create Cross-Modal Task Representations"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2410.22330."}