{"as_of":"2026-08-04T20:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2853dd2ffc55746122a10cfbb7ec33197bc7db0d10a93d5ae3f3a41b162299e5","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T23:45:15.752844Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.05526","last_updated":"2021-11-10T04:40:12Z","snapshot_observed_at":"2026-08-03T02:42:16.998766Z","submitted_at":"2021-11-10T04:40:12Z","title":"Space-Time Memory Network for Sounding Object Localization in Videos","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.05526","snapshot_observed_at":"2026-08-01T23:45:15.752844Z","title":"Space-time memory network for sounding object localization in videos.arXiv preprint arXiv:2111.05526, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15265","last_updated":"2026-07-16T17:55:15Z","snapshot_observed_at":"2026-08-04T19:45:23.483841Z","submitted_at":"2026-07-16T17:55:15Z","title":"SceneBind: Binding What and Where Across Vision, Audio and Language","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T23:45:15.752844Z"},"links":{"cited_paper":"/paper/2111.05526","citing_paper":"/paper/2607.15265"},"observation_digest":"sha256:0af21298685e705f648639bebb3c9b50a46cfc84fbb106d6fc1d22faebd64238","observation_id":"3d48dc4b-3740-4396-a076-f6b30842fbb9","resolution":{"observed_at":"2026-08-01T23:45:15.752844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2111.05526/citation-record","integrity":"/paper/2111.05526/integrity","json":"/paper/2111.05526/citation-record.json","paper":"/paper/2111.05526"},"outbound":[],"paper":{"arxiv_id":"2111.05526","last_updated":"2021-11-10T04:40:12Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T02:42:16.998766Z","submitted_at":"2021-11-10T04:40:12Z","title":"Space-Time Memory Network for Sounding Object Localization in Videos"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2111.05526."}