{"as_of":"2026-08-05T07:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:15d87140bd6e9b49b5e2ea2cd321096af5298a3fc319661f64b35ccf5a9a82ba","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-14T21:52:31.915302Z","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":"2026-05-14T21:53:02.063325Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2007.10558","last_updated":"2020-07-21T01:53:31Z","snapshot_observed_at":"2026-08-04T19:09:47.761678Z","submitted_at":"2020-07-21T01:53:31Z","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","version":1},"cited_work":{"arxiv_id":"2007.10558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.10558","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unified mul- tisensory perception: Weakly-supervised audio-visual video parsing.CoRR, abs/2007.10558","venue":null,"work_id":"fa352551-21d4-47a4-a1ef-c182b43a6844","year":2007},"citing_paper":{"arxiv_id":"2605.12145","last_updated":"2026-05-13T09:22:06Z","snapshot_observed_at":"2026-08-01T23:51:58.656704Z","submitted_at":"2026-05-12T14:03:30Z","title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-13T07:20:46.651636Z"},"links":{"cited_paper":"/paper/2007.10558","citing_paper":"/paper/2605.12145"},"observation_digest":"sha256:0e7fa725f7da1c923f3c6f60abd30f65da293c6fa80e9f4f38d7a128b7792bdb","observation_id":"cfc57e49-eb41-4989-a192-cf236656c13c","resolution":{"observed_at":"2026-05-13T07:22:28.865135Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.10558","last_updated":"2020-07-21T01:53:31Z","snapshot_observed_at":"2026-08-04T19:09:47.761678Z","submitted_at":"2020-07-21T01:53:31Z","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","version":1},"cited_work":{"arxiv_id":"2007.10558","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2007.10558","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unified mul- tisensory perception: Weakly-supervised audio-visual video parsing.CoRR, abs/2007.10558","venue":null,"work_id":"fa352551-21d4-47a4-a1ef-c182b43a6844","year":2007},"citing_paper":{"arxiv_id":"2605.12145","last_updated":"2026-05-13T09:22:06Z","snapshot_observed_at":"2026-08-01T23:51:58.656704Z","submitted_at":"2026-05-12T14:03:30Z","title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-14T21:52:31.915302Z"},"links":{"cited_paper":"/paper/2007.10558","citing_paper":"/paper/2605.12145"},"observation_digest":"sha256:9ad17136de1a219d56c83dd5633044f8a0d4f4c3981962690990fae8693e7929","observation_id":"3519fd8e-3c24-467f-9fb5-9d350305bda9","resolution":{"observed_at":"2026-05-14T21:53:02.066913Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2007.10558/citation-record","integrity":"/paper/2007.10558/integrity","json":"/paper/2007.10558/citation-record.json","paper":"/paper/2007.10558"},"outbound":[],"paper":{"arxiv_id":"2007.10558","last_updated":"2020-07-21T01:53:31Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T19:09:47.761678Z","submitted_at":"2020-07-21T01:53:31Z","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2007.10558."}