{"as_of":"2026-08-18T21:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3680c159793bcd0129347eda77d852160e2865c651f2f213f357f85aae05c28b","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":"2026-08-18T06:34:40.430872+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":"2026-08-11T12:55:31.887791Z","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":"2026-08-11T12:55:32.075857Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.08815","last_updated":"2024-05-14T17:59:40Z","snapshot_observed_at":"2026-08-18T00:58:41.469627Z","submitted_at":"2024-05-14T17:59:40Z","title":"Efficient Vision-Language Pre-training by Cluster Masking","version":1},"cited_work":{"arxiv_id":"2405.08815","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.08815","snapshot_observed_at":"2026-08-11T12:55:32.075857Z","title":"Efficient Vision-Language Pre-training by Cluster Masking","venue":"cs.CV","work_id":"5194ad4f-e308-461d-89a0-466d808ff64c","year":2024},"citing_paper":{"arxiv_id":"2412.13732","last_updated":"2025-02-24T14:34:07Z","snapshot_observed_at":"2026-08-18T06:19:19.593728Z","submitted_at":"2024-12-18T11:10:18Z","title":"Modeling Multi-modal Cross-interaction for Multi-label Few-shot Image Classification Based on Local Feature Selection","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T12:55:31.887791Z"},"links":{"cited_paper":"/paper/2405.08815","citing_paper":"/paper/2412.13732"},"observation_digest":"sha256:5bf5f6703fa497535a2bc0d9d4fb3ab7f232c489a5bf41bf0561f07b3b335924","observation_id":"32b588dd-4269-48bc-937e-63bb9ea8c0ec","resolution":{"observed_at":"2026-08-11T12:55:32.085237Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.08815/citation-record","integrity":"/paper/2405.08815/integrity","json":"/paper/2405.08815/citation-record.json","paper":"/paper/2405.08815"},"outbound":[],"paper":{"arxiv_id":"2405.08815","last_updated":"2024-05-14T17:59:40Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T00:58:41.469627Z","submitted_at":"2024-05-14T17:59:40Z","title":"Efficient Vision-Language Pre-training by Cluster Masking"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2405.08815."}