{"as_of":"2026-08-17T06:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fb6dde84eaa0d3132b907c2a2bb74e7cbd4ba285a9b5cf26aeb1275d759bf669","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":"2026-08-16T06:30:59.297886+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":"2026-08-15T18:47:36.945204Z","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":"2026-05-16T09:20:20.381982Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2006.09199","last_updated":"2021-06-29T18:44:50Z","snapshot_observed_at":"2026-08-13T22:24:31.904822Z","submitted_at":"2020-06-16T14:38:03Z","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","version":2},"cited_work":{"arxiv_id":"2006.09199","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2006.09199","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2006.09199 , year=","venue":null,"work_id":"2ab8fe58-144a-4614-90f9-317308be95cc","year":2006},"citing_paper":{"arxiv_id":"2309.16671","last_updated":"2025-11-23T00:34:43Z","snapshot_observed_at":"2026-08-02T18:24:11.208164Z","submitted_at":"2023-09-28T17:59:56Z","title":"Demystifying CLIP Data","version":6},"reference_index":118,"source":"arxiv_source","source_observed_at":"2026-05-16T09:20:20.143143Z"},"links":{"cited_paper":"/paper/2006.09199","citing_paper":"/paper/2309.16671"},"observation_digest":"sha256:b80ac65fd4949ff0a4f6a7fc030aebcb1c7a2aa089a1149d646bc95e8e2f6ca3","observation_id":"11680cb7-39f8-473f-b195-f4f99c2a785e","resolution":{"observed_at":"2026-05-16T09:20:20.383374Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.09199","last_updated":"2021-06-29T18:44:50Z","snapshot_observed_at":"2026-08-13T22:24:31.904822Z","submitted_at":"2020-06-16T14:38:03Z","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.09199","snapshot_observed_at":"2026-08-12T14:04:00.668160Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.00049","last_updated":"2024-11-24T03:26:34Z","snapshot_observed_at":"2026-08-13T20:27:52.554751Z","submitted_at":"2024-11-24T03:26:34Z","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","version":1},"reference_index":116,"source":"pdf_text","source_observed_at":"2026-08-12T14:04:00.668160Z"},"links":{"cited_paper":"/paper/2006.09199","citing_paper":"/paper/2412.00049"},"observation_digest":"sha256:732d8dc8e47c76654e0ae0fb8521ae5324f01741b6ac4f7fb0bae1300c3ee92b","observation_id":"459571b3-142a-4071-b225-8db17a4b4b01","resolution":{"observed_at":"2026-08-12T14:04:00.668160Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.09199","last_updated":"2021-06-29T18:44:50Z","snapshot_observed_at":"2026-08-13T22:24:31.904822Z","submitted_at":"2020-06-16T14:38:03Z","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.09199","snapshot_observed_at":"2026-08-15T18:47:36.945204Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.18881","last_updated":"2025-06-23T17:52:16Z","snapshot_observed_at":"2026-08-15T23:43:09.962411Z","submitted_at":"2025-06-23T17:52:16Z","title":"Let Your Video Listen to Your Music!","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:47:36.945204Z"},"links":{"cited_paper":"/paper/2006.09199","citing_paper":"/paper/2506.18881"},"observation_digest":"sha256:2d2f358ea33ed870bc35b913549cfdc2e4bd62ff6f5d481a67e239b9d67b8350","observation_id":"9911d891-0b72-49d8-bc37-43364ff35891","resolution":{"observed_at":"2026-08-15T18:47:36.945204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2006.09199/citation-record","integrity":"/paper/2006.09199/integrity","json":"/paper/2006.09199/citation-record.json","paper":"/paper/2006.09199"},"outbound":[],"paper":{"arxiv_id":"2006.09199","last_updated":"2021-06-29T18:44:50Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T22:24:31.904822Z","submitted_at":"2020-06-16T14:38:03Z","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2006.09199."}