{"as_of":"2026-08-11T15:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:577477beb0631af8a7718f4cc735dd7b7cd0ff081b467efc24b0fca4b9bcd627","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":"2026-08-11T06:34:44.6726+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":"2026-05-17T00:36:53.235740Z","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":"2026-05-17T00:36:53.350076Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.07160","last_updated":"2022-06-14T20:43:25Z","snapshot_observed_at":"2026-07-06T13:20:51.362304Z","submitted_at":"2022-06-14T20:43:25Z","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","version":1},"cited_work":{"arxiv_id":"2206.07160","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.07160","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lavender: Unifying video-language understanding as masked language modeling","venue":null,"work_id":"a66881b8-36b2-40f7-94ff-15730443b004","year":2022},"citing_paper":{"arxiv_id":"2212.03191","last_updated":"2022-12-07T12:20:55Z","snapshot_observed_at":"2026-07-06T14:27:34.639236Z","submitted_at":"2022-12-06T18:09:49Z","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-17T00:36:53.235740Z"},"links":{"cited_paper":"/paper/2206.07160","citing_paper":"/paper/2212.03191"},"observation_digest":"sha256:52f4f4a6566a22b34fa2f43ff1020652748a1ab1c945b95eb897fd8383ee1a85","observation_id":"43d26c3f-fb83-487a-9878-515c56343167","resolution":{"observed_at":"2026-05-17T00:36:53.351832Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07160","last_updated":"2022-06-14T20:43:25Z","snapshot_observed_at":"2026-07-06T13:20:51.362304Z","submitted_at":"2022-06-14T20:43:25Z","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","version":1},"cited_work":{"arxiv_id":"2206.07160","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.07160","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lavender: Unifying video-language understanding as masked language modeling","venue":null,"work_id":"a66881b8-36b2-40f7-94ff-15730443b004","year":2022},"citing_paper":{"arxiv_id":"2305.06355","last_updated":"2024-01-04T02:06:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-10T17:59:04Z","title":"VideoChat: Chat-Centric Video Understanding","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-13T23:30:00.457974Z"},"links":{"cited_paper":"/paper/2206.07160","citing_paper":"/paper/2305.06355"},"observation_digest":"sha256:b167fe0b3e007fe478f2e1b415d32bd0b0a1eb99996de9ccdfbc3d221d33a44e","observation_id":"95867805-c515-4620-b73c-0fb3e2bf0c0a","resolution":{"observed_at":"2026-05-13T23:30:00.578691Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07160","last_updated":"2022-06-14T20:43:25Z","snapshot_observed_at":"2026-07-06T13:20:51.362304Z","submitted_at":"2022-06-14T20:43:25Z","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","version":1},"cited_work":{"arxiv_id":"2206.07160","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.07160","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Lavender: Unifying video-language understanding as masked language modeling","venue":null,"work_id":"a66881b8-36b2-40f7-94ff-15730443b004","year":2022},"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":39,"source":"pdf_text","source_observed_at":"2026-05-15T06:30:22.431538Z"},"links":{"cited_paper":"/paper/2206.07160","citing_paper":"/paper/2307.06942"},"observation_digest":"sha256:b021ff51c491959523997632ceaec531ef1af14d48b3e6c16606816dd86058f6","observation_id":"10fb84ee-7504-4aef-be19-cc3458e42a42","resolution":{"observed_at":"2026-05-15T06:30:22.608373Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2206.07160/citation-record","integrity":"/paper/2206.07160/integrity","json":"/paper/2206.07160/citation-record.json","paper":"/paper/2206.07160"},"outbound":[],"paper":{"arxiv_id":"2206.07160","last_updated":"2022-06-14T20:43:25Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T13:20:51.362304Z","submitted_at":"2022-06-14T20:43:25Z","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2206.07160."}