{"as_of":"2026-08-09T12:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9a4ddabfa6ed92b24cef0e4a2ac64bab691b0e0f57bf4bacac5aea1ffcdbd7e2","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T15:02:28.118849Z","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":"2026-05-15T06:30:22.640312Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.13167","last_updated":"2023-05-22T15:54:22Z","snapshot_observed_at":"2026-08-05T23:33:04.454032Z","submitted_at":"2023-05-22T15:54:22Z","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","version":1},"cited_work":{"arxiv_id":"2305.13167","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.13167","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vlab: Enhancing video language pre-training by feature adapting and blending","venue":null,"work_id":"832a7370-ef4d-4585-bce9-77ea1600fecd","year":2023},"citing_paper":{"arxiv_id":"2307.06942","last_updated":"2024-01-04T05:00:34Z","snapshot_observed_at":"2026-07-06T15:53:46.393481Z","submitted_at":"2023-07-13T17:58:32Z","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-15T06:30:22.431538Z"},"links":{"cited_paper":"/paper/2305.13167","citing_paper":"/paper/2307.06942"},"observation_digest":"sha256:fea1d30d22b9bc50054000f605f3c495c537485cc021ee7fa70e0c5fb09f9d70","observation_id":"7e688be5-ca48-41f7-aeaf-ac5f652c5230","resolution":{"observed_at":"2026-05-15T06:30:22.643920Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13167","last_updated":"2023-05-22T15:54:22Z","snapshot_observed_at":"2026-08-05T23:33:04.454032Z","submitted_at":"2023-05-22T15:54:22Z","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13167","snapshot_observed_at":"2026-08-07T15:02:28.118849Z","title":"Vlab: Enhancing video language pre- training by feature adapting and blending,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16594","last_updated":"2025-05-22T12:28:50Z","snapshot_observed_at":"2026-08-07T14:55:54.546955Z","submitted_at":"2025-05-22T12:28:50Z","title":"Temporal Object Captioning for Street Scene Videos from LiDAR Tracks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:02:28.118849Z"},"links":{"cited_paper":"/paper/2305.13167","citing_paper":"/paper/2505.16594"},"observation_digest":"sha256:7df9d7571410a5cdd60c739a8709ba2e09fa08ab13f8b5f6bba0d19fbfc460fa","observation_id":"b6247258-8cda-4e7a-a7c6-2fc1cfed444c","resolution":{"observed_at":"2026-08-07T15:02:28.118849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2305.13167/citation-record","integrity":"/paper/2305.13167/integrity","json":"/paper/2305.13167/citation-record.json","paper":"/paper/2305.13167"},"outbound":[],"paper":{"arxiv_id":"2305.13167","last_updated":"2023-05-22T15:54:22Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T23:33:04.454032Z","submitted_at":"2023-05-22T15:54:22Z","title":"VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2305.13167."}