{"as_of":"2026-08-08T11:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c4ecf091064ba00918507586d0c7970658a2a10a90bf7bcbf206fea6ce562c72","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T15:38:43.162526Z","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":"2026-05-22T12:31:32.026683Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.13956","last_updated":"2025-06-18T08:04:33Z","snapshot_observed_at":"2026-08-07T16:55:46.935677Z","submitted_at":"2025-03-18T06:48:08Z","title":"Improving LLM Video Understanding with 16 Frames Per Second","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13956","snapshot_observed_at":"2026-08-06T15:38:43.162526Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.15428","last_updated":"2025-07-21T09:27:45Z","snapshot_observed_at":"2026-08-08T00:47:00.490358Z","submitted_at":"2025-07-21T09:27:45Z","title":"EgoPrune: Efficient Token Pruning for Egomotion Video Reasoning in Embodied Agent","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T15:38:43.162526Z"},"links":{"cited_paper":"/paper/2503.13956","citing_paper":"/paper/2507.15428"},"observation_digest":"sha256:384ac93ee960cf3e4320e608d225690f4f473770eca09bf29ac5bedb6df7c114","observation_id":"e4edf8d9-2055-4ef3-9d9c-be339becbab4","resolution":{"observed_at":"2026-08-06T15:38:43.162526Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13956","last_updated":"2025-06-18T08:04:33Z","snapshot_observed_at":"2026-08-07T16:55:46.935677Z","submitted_at":"2025-03-18T06:48:08Z","title":"Improving LLM Video Understanding with 16 Frames Per Second","version":2},"cited_work":{"arxiv_id":"2503.13956","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.13956","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Im- proving llm video understanding with 16 frames per second","venue":null,"work_id":"60d33124-daca-4fc4-b375-e64031e22902","year":2025},"citing_paper":{"arxiv_id":"2511.20785","last_updated":"2026-05-21T10:39:51Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-25T19:22:48Z","title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-22T12:26:35.347190Z"},"links":{"cited_paper":"/paper/2503.13956","citing_paper":"/paper/2511.20785"},"observation_digest":"sha256:9930dd527fb816935f4e4c68f01d5f6acc42006d94f4ecbcae6c30502b23dd73","observation_id":"e5e01f37-b4c6-474a-ad85-93bcaf1b25e0","resolution":{"observed_at":"2026-05-22T12:31:32.029653Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13956","last_updated":"2025-06-18T08:04:33Z","snapshot_observed_at":"2026-08-07T16:55:46.935677Z","submitted_at":"2025-03-18T06:48:08Z","title":"Improving LLM Video Understanding with 16 Frames Per Second","version":2},"cited_work":{"arxiv_id":"2503.13956","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.13956","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Im- proving llm video understanding with 16 frames per second","venue":null,"work_id":"60d33124-daca-4fc4-b375-e64031e22902","year":2025},"citing_paper":{"arxiv_id":"2604.08457","last_updated":"2026-04-10T14:52:27Z","snapshot_observed_at":"2026-07-06T22:57:31.046146Z","submitted_at":"2026-04-09T16:52:04Z","title":"CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T17:09:57.040135Z"},"links":{"cited_paper":"/paper/2503.13956","citing_paper":"/paper/2604.08457"},"observation_digest":"sha256:d8bf27c4b70e5d0bf838622db1cd5342e18b735d32bcf5ad45a0c722eb4676d8","observation_id":"d877a2ee-d6d5-4ee2-a6a3-a199ae0fd76d","resolution":{"observed_at":"2026-05-11T07:30:57.899474Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.13956/citation-record","integrity":"/paper/2503.13956/integrity","json":"/paper/2503.13956/citation-record.json","paper":"/paper/2503.13956"},"outbound":[],"paper":{"arxiv_id":"2503.13956","last_updated":"2025-06-18T08:04:33Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:55:46.935677Z","submitted_at":"2025-03-18T06:48:08Z","title":"Improving LLM Video Understanding with 16 Frames Per Second"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.13956."}