{"as_of":"2026-08-10T08:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b1718b0a7db8eafab1a9ca0fd2b016730187e8b5b218f8ac7789cb6c3aed3f85","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T12:40:45.454890Z","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":"2026-05-14T22:08:04.336820Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.15415","last_updated":"2025-04-21T19:53:44Z","snapshot_observed_at":"2026-08-09T06:57:55.123045Z","submitted_at":"2025-04-21T19:53:44Z","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.15415","snapshot_observed_at":"2026-08-07T12:40:45.454890Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.23922","last_updated":"2025-05-29T18:15:07Z","snapshot_observed_at":"2026-08-09T06:58:13.030008Z","submitted_at":"2025-05-29T18:15:07Z","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T12:40:45.454890Z"},"links":{"cited_paper":"/paper/2504.15415","citing_paper":"/paper/2505.23922"},"observation_digest":"sha256:dd55a5d3877c6c6fe7522103e08f3a7b7f6d7836fa87903c9eb94a67403fa06a","observation_id":"c26723eb-e2b1-4f10-8436-71652711cd66","resolution":{"observed_at":"2026-08-07T12:40:45.454890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.15415","last_updated":"2025-04-21T19:53:44Z","snapshot_observed_at":"2026-08-09T06:57:55.123045Z","submitted_at":"2025-04-21T19:53:44Z","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs","version":1},"cited_work":{"arxiv_id":"2504.15415","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.15415","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Iv-bench: A benchmark for image-grounded video perception and reasoning in multi- modal llms","venue":null,"work_id":"d652a670-0e34-4622-b82d-b6203a58e458","year":2025},"citing_paper":{"arxiv_id":"2603.27259","last_updated":"2026-06-18T21:01:40Z","snapshot_observed_at":"2026-08-02T11:52:58.572026Z","submitted_at":"2026-03-28T12:44:19Z","title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-14T22:05:07.326202Z"},"links":{"cited_paper":"/paper/2504.15415","citing_paper":"/paper/2603.27259"},"observation_digest":"sha256:40812f676d182fc60ba0967413c3e4c80d972b01a1e471b7bc47fe0394d680b6","observation_id":"9c374a8b-c52c-4030-a89b-8b90e1d33953","resolution":{"observed_at":"2026-05-14T22:08:04.340470Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.15415","last_updated":"2025-04-21T19:53:44Z","snapshot_observed_at":"2026-08-09T06:57:55.123045Z","submitted_at":"2025-04-21T19:53:44Z","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.15415","snapshot_observed_at":"2026-08-02T14:24:57.558996Z","title":"Preprint, arXiv:2504.15415","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2605.10579","last_updated":"2026-07-30T05:06:10Z","snapshot_observed_at":"2026-08-02T23:16:55.313881Z","submitted_at":"2026-05-11T13:50:47Z","title":"VISTA: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T14:24:57.558996Z"},"links":{"cited_paper":"/paper/2504.15415","citing_paper":"/paper/2605.10579"},"observation_digest":"sha256:25cc376d6c5a757bd1f5bee270b66ae717733ac0ec7873bf135fb51a5f830f76","observation_id":"9eae78df-52db-4e45-8a2d-286cbb6c826a","resolution":{"observed_at":"2026-08-02T14:24:57.558996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2504.15415/citation-record","integrity":"/paper/2504.15415/integrity","json":"/paper/2504.15415/citation-record.json","paper":"/paper/2504.15415"},"outbound":[],"paper":{"arxiv_id":"2504.15415","last_updated":"2025-04-21T19:53:44Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T06:57:55.123045Z","submitted_at":"2025-04-21T19:53:44Z","title":"IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2504.15415."}