{"as_of":"2026-08-10T19:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c979156793c8a02c98c19600dc2dd08e4ed084e5f975c580e9aed60ed79a05dc","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":"2026-08-10T06:31:04.303077+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":"2026-08-09T04:44:58.833389Z","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":"2026-08-06T23:20:49.500854Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2207.07646","last_updated":"2022-07-15T17:59:11Z","snapshot_observed_at":"2026-08-06T19:04:25.950223Z","submitted_at":"2022-07-15T17:59:11Z","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.07646","snapshot_observed_at":"2026-08-09T04:44:58.833389Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.03459","last_updated":"2025-02-05T18:57:04Z","snapshot_observed_at":"2026-08-09T18:52:00.002531Z","submitted_at":"2025-02-05T18:57:04Z","title":"SKI Models: Skeleton Induced Vision-Language Embeddings for Understanding Activities of Daily Living","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T04:44:58.833389Z"},"links":{"cited_paper":"/paper/2207.07646","citing_paper":"/paper/2502.03459"},"observation_digest":"sha256:a6ca046743bd6b469c65b6faffe843f78882f7b345c58aa558a4ce17c296986f","observation_id":"b78052dd-89a8-4c07-bc01-c7ccf6886ff5","resolution":{"observed_at":"2026-08-09T04:44:58.833389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.07646","last_updated":"2022-07-15T17:59:11Z","snapshot_observed_at":"2026-08-06T19:04:25.950223Z","submitted_at":"2022-07-15T17:59:11Z","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","version":1},"cited_work":{"arxiv_id":"2207.07646","doi":null,"metadata_source":"pith","pith_arxiv_id":"2207.07646","snapshot_observed_at":"2026-08-06T23:20:49.500854Z","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","venue":"cs.CV","work_id":"f07e851d-bbed-46b3-a06c-f3fa662b6363","year":2022},"citing_paper":{"arxiv_id":"2506.18557","last_updated":"2025-06-24T02:05:51Z","snapshot_observed_at":"2026-08-06T23:13:29.775397Z","submitted_at":"2025-06-23T12:08:07Z","title":"Object-aware Sound Source Localization via Audio-Visual Scene Understanding","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T23:20:47.607798Z"},"links":{"cited_paper":"/paper/2207.07646","citing_paper":"/paper/2506.18557"},"observation_digest":"sha256:a129a38717b23dd8646610e50197551986ddac284c69a4ad0f2d9df6bb19807f","observation_id":"a8698035-bfd8-4a4e-993b-51396e7e26a4","resolution":{"observed_at":"2026-08-06T23:20:49.591703Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.07646","last_updated":"2022-07-15T17:59:11Z","snapshot_observed_at":"2026-08-06T19:04:25.950223Z","submitted_at":"2022-07-15T17:59:11Z","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.07646","snapshot_observed_at":"2026-08-01T03:02:40.396304Z","title":"arXiv preprint arXiv:2207.07646 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.26097","last_updated":"2026-08-04T07:44:31Z","snapshot_observed_at":"2026-08-10T18:12:16.741162Z","submitted_at":"2026-07-28T03:54:27Z","title":"Knowledge-guided Disentanglement with Atomic Actions for Action Recognition","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-01T03:02:40.396304Z"},"links":{"cited_paper":"/paper/2207.07646","citing_paper":"/paper/2607.26097"},"observation_digest":"sha256:a76c34da44828998d0fa87ba3fa66dd48a68400fe9579becba878f519eee29f1","observation_id":"a49cd655-388a-47a3-ae8b-b360827aef80","resolution":{"observed_at":"2026-08-01T03:02:40.396304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2207.07646/citation-record","integrity":"/paper/2207.07646/integrity","json":"/paper/2207.07646/citation-record.json","paper":"/paper/2207.07646"},"outbound":[],"paper":{"arxiv_id":"2207.07646","last_updated":"2022-07-15T17:59:11Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T19:04:25.950223Z","submitted_at":"2022-07-15T17:59:11Z","title":"Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2207.07646."}