{"as_of":"2026-08-08T17:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:54bc2e44d36d5dd93248ad767936b2750648c1ba8422c4b76a96fa02fe324af7","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":"2026-08-07T15:19:10.498757Z","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":"2026-08-05T23:32:19.158465Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.08585","last_updated":"2025-04-24T17:42:16Z","snapshot_observed_at":"2026-08-07T18:43:01.306583Z","submitted_at":"2025-03-11T16:21:23Z","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.08585","snapshot_observed_at":"2026-08-07T15:19:10.498757Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.17114","last_updated":"2025-09-05T17:40:14Z","snapshot_observed_at":"2026-08-07T15:12:15.780318Z","submitted_at":"2025-05-21T14:33:36Z","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","version":3},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T15:19:10.498757Z"},"links":{"cited_paper":"/paper/2503.08585","citing_paper":"/paper/2505.17114"},"observation_digest":"sha256:5817c05c932415e371a58807456f55ae7462c4e2119caea3a492836eae55b163","observation_id":"787cc205-5044-46c3-ba82-7d24d99337e9","resolution":{"observed_at":"2026-08-07T15:19:10.498757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08585","last_updated":"2025-04-24T17:42:16Z","snapshot_observed_at":"2026-08-07T18:43:01.306583Z","submitted_at":"2025-03-11T16:21:23Z","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.08585","snapshot_observed_at":"2026-08-06T23:42:20.273161Z","title":"Hierarq: Task-aware hierarchical q-former for enhanced video understanding.arXiv preprint arXiv:2503.08585, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.16701","last_updated":"2025-06-20T02:43:53Z","snapshot_observed_at":"2026-08-06T23:34:49.615098Z","submitted_at":"2025-06-20T02:43:53Z","title":"Language-driven Description Generation and Common Sense Reasoning for Video Action Recognition","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:42:20.273161Z"},"links":{"cited_paper":"/paper/2503.08585","citing_paper":"/paper/2506.16701"},"observation_digest":"sha256:e4e767990268bc1d8aa9c1c5e096afb1a904c2be5c8505d34f627c57fe79632f","observation_id":"0db42020-bc5d-4b84-bfe1-195443b6a256","resolution":{"observed_at":"2026-08-06T23:42:20.273161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.08585","last_updated":"2025-04-24T17:42:16Z","snapshot_observed_at":"2026-08-07T18:43:01.306583Z","submitted_at":"2025-03-11T16:21:23Z","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","version":2},"cited_work":{"arxiv_id":"2503.08585","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.08585","snapshot_observed_at":"2026-08-05T23:32:19.158465Z","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding","venue":"cs.CV","work_id":"16699353-29f7-4268-b473-f73433d6afb4","year":2025},"citing_paper":{"arxiv_id":"2508.10922","last_updated":"2025-08-07T08:52:11Z","snapshot_observed_at":"2026-08-06T10:35:41.875223Z","submitted_at":"2025-08-07T08:52:11Z","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-05T23:32:17.769503Z"},"links":{"cited_paper":"/paper/2503.08585","citing_paper":"/paper/2508.10922"},"observation_digest":"sha256:f0a9c4f224438b7d94c985e012dcd72cc7bc330cc409cf67dbd1b98d19de8f43","observation_id":"aecfe681-e828-44a6-94f9-67d088684a43","resolution":{"observed_at":"2026-08-05T23:32:19.163503Z","resolver_source":"local_arxiv","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/2503.08585/citation-record","integrity":"/paper/2503.08585/integrity","json":"/paper/2503.08585/citation-record.json","paper":"/paper/2503.08585"},"outbound":[],"paper":{"arxiv_id":"2503.08585","last_updated":"2025-04-24T17:42:16Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T18:43:01.306583Z","submitted_at":"2025-03-11T16:21:23Z","title":"HierarQ: Task-Aware Hierarchical Q-Former for Enhanced 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":"2026-08-08T06:32:00.761636+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:2503.08585."}