{"as_of":"2026-08-09T14:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c54eb3c10a2898800dd5a36fd5146f3961d632897c68fb64983dccaa6edba9f9","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":"2026-08-09T06:31:02.800959+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":"2026-08-06T23:29:21.886373Z","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":"2026-08-05T23:32:19.419023Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.04388","last_updated":"2025-05-16T08:24:31Z","snapshot_observed_at":"2026-07-06T19:11:36.358087Z","submitted_at":"2024-09-06T16:27:52Z","title":"Question-Answering Dense Video Events","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.04388","snapshot_observed_at":"2026-08-06T23:29:21.886373Z","title":"Question-Answering Dense Video Events,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.18071","last_updated":"2025-06-27T06:32:43Z","snapshot_observed_at":"2026-08-08T12:15:56.187844Z","submitted_at":"2025-06-22T15:39:02Z","title":"MUPA: Towards Multi-Path Agentic Reasoning for Grounded Video Question Answering","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:21.886373Z"},"links":{"cited_paper":"/paper/2409.04388","citing_paper":"/paper/2506.18071"},"observation_digest":"sha256:86750686109a9fc7f41abbbe256ab77ec372dc16153f21eac6b459c3ee4c9d23","observation_id":"34393161-975c-44b4-a476-336271239f40","resolution":{"observed_at":"2026-08-06T23:29:21.886373Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.04388","last_updated":"2025-05-16T08:24:31Z","snapshot_observed_at":"2026-07-06T19:11:36.358087Z","submitted_at":"2024-09-06T16:27:52Z","title":"Question-Answering Dense Video Events","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.04388","snapshot_observed_at":"2026-08-06T22:41:10.769779Z","title":"Question-answering dense video events","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20960","last_updated":"2025-06-29T15:16:22Z","snapshot_observed_at":"2026-08-07T12:35:43.320358Z","submitted_at":"2025-06-26T02:54:24Z","title":"OmniEval: A Benchmark for Evaluating Omni-modal Models with Visual, Auditory, and Textual Inputs","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T22:41:10.769779Z"},"links":{"cited_paper":"/paper/2409.04388","citing_paper":"/paper/2506.20960"},"observation_digest":"sha256:a2327bb7219c71ec864ce8cab2af5a49967ba4280f7afa895d3ab190399649c1","observation_id":"572dbd7c-2733-4873-b333-0f651e326e04","resolution":{"observed_at":"2026-08-06T22:41:10.769779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.04388","last_updated":"2025-05-16T08:24:31Z","snapshot_observed_at":"2026-07-06T19:11:36.358087Z","submitted_at":"2024-09-06T16:27:52Z","title":"Question-Answering Dense Video Events","version":5},"cited_work":{"arxiv_id":"2409.04388","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.04388","snapshot_observed_at":"2026-08-05T23:32:19.419023Z","title":"Question-Answering Dense Video Events","venue":"cs.CV","work_id":"b474f3a4-b69e-466c-b3a5-00156359a356","year":2024},"citing_paper":{"arxiv_id":"2508.10922","last_updated":"2025-08-07T08:52:11Z","snapshot_observed_at":"2026-08-09T09:33:06.733360Z","submitted_at":"2025-08-07T08:52:11Z","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-05T23:32:17.590085Z"},"links":{"cited_paper":"/paper/2409.04388","citing_paper":"/paper/2508.10922"},"observation_digest":"sha256:e954be599c30264f36c248f9f8dec038a760faedf8bd68794e6eefa052f4040f","observation_id":"8094023f-5c7d-4f0c-95cf-a041a5174776","resolution":{"observed_at":"2026-08-05T23:32:19.423928Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.04388/citation-record","integrity":"/paper/2409.04388/integrity","json":"/paper/2409.04388/citation-record.json","paper":"/paper/2409.04388"},"outbound":[],"paper":{"arxiv_id":"2409.04388","last_updated":"2025-05-16T08:24:31Z","latest_version":5,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:11:36.358087Z","submitted_at":"2024-09-06T16:27:52Z","title":"Question-Answering Dense Video Events"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2409.04388."}