{"as_of":"2026-08-14T12:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5046f0106e48d93275c644723e1ba54d1fb1c568d16bba16fbf207e987a6a716","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T18:28:07.752724Z","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":"2026-08-06T17:38:21.212095Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.13911","last_updated":"2024-11-03T09:25:57Z","snapshot_observed_at":"2026-08-13T00:01:54.727751Z","submitted_at":"2024-05-22T18:35:10Z","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13911","snapshot_observed_at":"2026-08-12T18:28:07.752724Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.11531","last_updated":"2025-01-14T12:56:34Z","snapshot_observed_at":"2026-08-13T21:36:42.484194Z","submitted_at":"2024-11-18T12:40:51Z","title":"Addressing Hallucinations in Language Models with Knowledge Graph Embeddings as an Additional Modality","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T18:28:07.752724Z"},"links":{"cited_paper":"/paper/2405.13911","citing_paper":"/paper/2411.11531"},"observation_digest":"sha256:bb653b2f6312251b7f25430967accfe7478246bc966e7daddf97d8ca847d9d30","observation_id":"d62f5ef5-9c06-45a7-a678-14c4128cdadc","resolution":{"observed_at":"2026-08-12T18:28:07.752724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13911","last_updated":"2024-11-03T09:25:57Z","snapshot_observed_at":"2026-08-13T00:01:54.727751Z","submitted_at":"2024-05-22T18:35:10Z","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","version":2},"cited_work":{"arxiv_id":"2405.13911","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.13911","snapshot_observed_at":"2026-08-06T17:38:21.212095Z","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","venue":"cs.CV","work_id":"8afe9f53-b19d-4ff5-a826-56b7744db573","year":2024},"citing_paper":{"arxiv_id":"2507.10302","last_updated":"2025-07-14T14:05:19Z","snapshot_observed_at":"2026-08-13T10:47:40.351375Z","submitted_at":"2025-07-14T14:05:19Z","title":"DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T17:38:16.555603Z"},"links":{"cited_paper":"/paper/2405.13911","citing_paper":"/paper/2507.10302"},"observation_digest":"sha256:4b014113a190baf29422523c24e86993a9fdc2b0b3b9c763d657908b04387573","observation_id":"442b2771-6305-4adf-85c8-671c77800522","resolution":{"observed_at":"2026-08-06T17:38:21.336547Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.13911/citation-record","integrity":"/paper/2405.13911/integrity","json":"/paper/2405.13911/citation-record.json","paper":"/paper/2405.13911"},"outbound":[],"paper":{"arxiv_id":"2405.13911","last_updated":"2024-11-03T09:25:57Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T00:01:54.727751Z","submitted_at":"2024-05-22T18:35:10Z","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.13911."}