{"as_of":"2026-08-15T07:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:92ccdcb918187f16c3f7bf55c175ff43f01f327d884766a0c2e057fe052e9061","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":"2026-08-15T06:32:42.880941+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":"2026-08-07T11:37:27.764649Z","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":"2026-05-19T20:47:45.944229Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.20384","last_updated":"2025-04-29T03:09:46Z","snapshot_observed_at":"2026-08-07T15:58:23.453354Z","submitted_at":"2025-04-29T03:09:46Z","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.20384","snapshot_observed_at":"2026-08-07T11:37:27.764649Z","title":"Fila-video: Spatio-temporal compression for fine-grained long video understanding.arXiv preprint arXiv:2504.20384, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.01853","last_updated":"2025-06-02T16:40:50Z","snapshot_observed_at":"2026-08-15T01:34:26.509428Z","submitted_at":"2025-06-02T16:40:50Z","title":"ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:37:27.764649Z"},"links":{"cited_paper":"/paper/2504.20384","citing_paper":"/paper/2506.01853"},"observation_digest":"sha256:8477610009bbcd699dfe59c5948a1db8f35da30f17e64a726ed4404e19b21f66","observation_id":"e4f9af82-9a08-4a1f-9e1a-9e4809b1ea4a","resolution":{"observed_at":"2026-08-07T11:37:27.764649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.20384","last_updated":"2025-04-29T03:09:46Z","snapshot_observed_at":"2026-08-07T15:58:23.453354Z","submitted_at":"2025-04-29T03:09:46Z","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.20384","snapshot_observed_at":"2026-08-06T22:24:26.754753Z","title":"Fila-video: Spatio-temporal compression for fine-grained long video understanding.arXiv preprint arXiv:2504.20384, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.21862","last_updated":"2025-06-27T02:29:58Z","snapshot_observed_at":"2026-08-13T09:08:08.645501Z","submitted_at":"2025-06-27T02:29:58Z","title":"LLaVA-Scissor: Token Compression with Semantic Connected Components for Video LLMs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:24:26.754753Z"},"links":{"cited_paper":"/paper/2504.20384","citing_paper":"/paper/2506.21862"},"observation_digest":"sha256:a8ff7fddc97853788fd26570ee37c54cfb1935b773939357ea8dce1fff49698b","observation_id":"05f9062c-92a3-4ff4-b570-bd10ab8375c6","resolution":{"observed_at":"2026-08-06T22:24:26.754753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.20384","last_updated":"2025-04-29T03:09:46Z","snapshot_observed_at":"2026-08-07T15:58:23.453354Z","submitted_at":"2025-04-29T03:09:46Z","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding","version":1},"cited_work":{"arxiv_id":"2504.20384","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.20384","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fila-video: Spatio-temporal compression for fine- grained long video understanding","venue":null,"work_id":"9c9f1be5-2daf-4e4e-b0d6-172bcb5cf726","year":2025},"citing_paper":{"arxiv_id":"2605.16909","last_updated":"2026-05-16T09:49:25Z","snapshot_observed_at":"2026-08-15T02:58:40.135688Z","submitted_at":"2026-05-16T09:49:25Z","title":"TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-19T20:43:16.364125Z"},"links":{"cited_paper":"/paper/2504.20384","citing_paper":"/paper/2605.16909"},"observation_digest":"sha256:b5c90a3a4bc1c394adf612feacdc0b83fa8a7630a8290b1bc6349cde9297ac4f","observation_id":"ef82a27c-0001-42e7-bb4c-54dbc446d3f2","resolution":{"observed_at":"2026-05-19T20:47:45.945880Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.20384/citation-record","integrity":"/paper/2504.20384/integrity","json":"/paper/2504.20384/citation-record.json","paper":"/paper/2504.20384"},"outbound":[],"paper":{"arxiv_id":"2504.20384","last_updated":"2025-04-29T03:09:46Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T15:58:23.453354Z","submitted_at":"2025-04-29T03:09:46Z","title":"FiLA-Video: Spatio-Temporal Compression for Fine-Grained Long Video Understanding"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2504.20384."}