{"as_of":"2026-08-14T23:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:da46c420b3e6aa2e3407301dd70880049a7ac40c5334cf9dc17ceac9e66514e3","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T20:53:20.489681Z","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":"2026-05-11T08:30:57.001382Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.05541","last_updated":"2025-04-09T02:30:44Z","snapshot_observed_at":"2026-08-07T16:07:46.494762Z","submitted_at":"2025-04-07T22:35:36Z","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.05541","snapshot_observed_at":"2026-08-06T20:53:20.489681Z","title":"Caption anything in video: Fine- grained object-centric captioning via spatiotemporal multi- modal prompting","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.01492","last_updated":"2025-07-02T08:51:45Z","snapshot_observed_at":"2026-08-14T00:45:58.834747Z","submitted_at":"2025-07-02T08:51:45Z","title":"AVC-DPO: Aligned Video Captioning via Direct Preference Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T20:53:20.489681Z"},"links":{"cited_paper":"/paper/2504.05541","citing_paper":"/paper/2507.01492"},"observation_digest":"sha256:2ac047ecc9c2871d4c8a3b6414ac44a339f83167105b2ba1ca06982cef9901a7","observation_id":"e7e616bd-45a4-4437-83a7-612507711469","resolution":{"observed_at":"2026-08-06T20:53:20.489681Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.05541","last_updated":"2025-04-09T02:30:44Z","snapshot_observed_at":"2026-08-07T16:07:46.494762Z","submitted_at":"2025-04-07T22:35:36Z","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.05541","snapshot_observed_at":"2026-08-06T14:36:29.394779Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.18531","last_updated":"2025-07-24T15:58:36Z","snapshot_observed_at":"2026-08-07T22:13:34.998544Z","submitted_at":"2025-07-24T15:58:36Z","title":"IntentVCNet: Bridging Spatio-Temporal Gaps for Intention-Oriented Controllable Video Captioning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T14:36:29.394779Z"},"links":{"cited_paper":"/paper/2504.05541","citing_paper":"/paper/2507.18531"},"observation_digest":"sha256:1622238aa724befcefd8af782a45c7433352c12929e2d15a4f60e837df33850c","observation_id":"ad3ad4e7-b1ae-4c7d-b6bc-9f6e5a73b46a","resolution":{"observed_at":"2026-08-06T14:36:29.394779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.05541","last_updated":"2025-04-09T02:30:44Z","snapshot_observed_at":"2026-08-07T16:07:46.494762Z","submitted_at":"2025-04-07T22:35:36Z","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","version":2},"cited_work":{"arxiv_id":"2504.05541","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.05541","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Caption anything in video: Fine-grained object-centric captioning via spatiotemporal multimodal prompting","venue":null,"work_id":"17802ec5-fd79-4701-9371-3d0bbbfeb412","year":2025},"citing_paper":{"arxiv_id":"2604.11283","last_updated":"2026-06-01T08:50:38Z","snapshot_observed_at":"2026-08-02T05:26:21.584719Z","submitted_at":"2026-04-13T10:42:31Z","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","version":1},"reference_index":222,"source":"pdf_text","source_observed_at":"2026-05-10T16:36:33.264166Z"},"links":{"cited_paper":"/paper/2504.05541","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:e7f9280eac85d17ed70e024c8efd53fc8be440fdf1796aea2981d3b4ad7d6591","observation_id":"7ce0e4dc-a08a-40a8-bc3f-3ab48f0fb4c1","resolution":{"observed_at":"2026-05-11T08:30:57.002947Z","resolver_source":"arxiv_id","status":"verified_exact"},"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"}},{"citation":{"cited_paper":{"arxiv_id":"2504.05541","last_updated":"2025-04-09T02:30:44Z","snapshot_observed_at":"2026-08-07T16:07:46.494762Z","submitted_at":"2025-04-07T22:35:36Z","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.05541","snapshot_observed_at":"2026-07-12T22:04:31.302192Z","title":"Caption anything in video: Fine-grained object-centric captioning via spatiotemporal multimodal prompting,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.11283","last_updated":"2026-06-01T08:50:38Z","snapshot_observed_at":"2026-08-02T05:26:21.584719Z","submitted_at":"2026-04-13T10:42:31Z","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","version":2},"reference_index":167,"source":"pdf_text","source_observed_at":"2026-07-12T22:04:31.302192Z"},"links":{"cited_paper":"/paper/2504.05541","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:ae9036ab2e61232367ecf8c26825c21528ec138d3a421eceb2c92692d0b28890","observation_id":"d1823757-acc2-4d25-a9d5-5743d4bb96a5","resolution":{"observed_at":"2026-07-12T22:04:31.302192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2504.05541/citation-record","integrity":"/paper/2504.05541/integrity","json":"/paper/2504.05541/citation-record.json","paper":"/paper/2504.05541"},"outbound":[],"paper":{"arxiv_id":"2504.05541","last_updated":"2025-04-09T02:30:44Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T16:07:46.494762Z","submitted_at":"2025-04-07T22:35:36Z","title":"Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting"},"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 4 inbound Pith citation observations for arXiv:2504.05541."}