{"as_of":"2026-08-08T14:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d411f5ed6ba2bf525cf809d469f31f952619eae25b9ce7def2205dac02d37b51","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":"2026-08-06T21:52:06.981051Z","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":"2026-05-14T21:17:59.674795Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.02344","last_updated":"2023-03-04T07:21:37Z","snapshot_observed_at":"2026-08-02T08:51:23.860156Z","submitted_at":"2023-03-04T07:21:37Z","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.02344","snapshot_observed_at":"2026-08-06T21:52:06.981051Z","title":"Contrastive positive sample propagation along the audio-visual event line","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23271","last_updated":"2025-06-29T14:52:01Z","snapshot_observed_at":"2026-08-06T21:45:05.156058Z","submitted_at":"2025-06-29T14:52:01Z","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:52:06.981051Z"},"links":{"cited_paper":"/paper/2303.02344","citing_paper":"/paper/2506.23271"},"observation_digest":"sha256:af4517d3ab849a7ab64532e78e6c71fd50ebf32cc7fd7f966e8c695040d63821","observation_id":"1ad984aa-aba9-4c74-9a38-c644737b34d1","resolution":{"observed_at":"2026-08-06T21:52:06.981051Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02344","last_updated":"2023-03-04T07:21:37Z","snapshot_observed_at":"2026-08-02T08:51:23.860156Z","submitted_at":"2023-03-04T07:21:37Z","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels","version":1},"cited_work":{"arxiv_id":"2303.02344","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.02344","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving audio-visual video parsing with pseudo visual labels","venue":null,"work_id":"d5f93925-2a96-4a6a-b412-e54c6896d180","year":2023},"citing_paper":{"arxiv_id":"2605.11572","last_updated":"2026-05-13T06:26:49Z","snapshot_observed_at":"2026-07-06T23:23:26.077921Z","submitted_at":"2026-05-12T05:59:23Z","title":"TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-13T01:41:07.685217Z"},"links":{"cited_paper":"/paper/2303.02344","citing_paper":"/paper/2605.11572"},"observation_digest":"sha256:4be36a372339c949cfa373842c3dcdb24ca79c7196d904eb682a95e801d8e73b","observation_id":"46ff852f-c83c-4421-bbdc-7931b9c6ee02","resolution":{"observed_at":"2026-05-13T01:42:03.538240Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02344","last_updated":"2023-03-04T07:21:37Z","snapshot_observed_at":"2026-08-02T08:51:23.860156Z","submitted_at":"2023-03-04T07:21:37Z","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels","version":1},"cited_work":{"arxiv_id":"2303.02344","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2303.02344","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Improving audio-visual video parsing with pseudo visual labels","venue":null,"work_id":"d5f93925-2a96-4a6a-b412-e54c6896d180","year":2023},"citing_paper":{"arxiv_id":"2605.11572","last_updated":"2026-05-13T06:26:49Z","snapshot_observed_at":"2026-07-06T23:23:26.077921Z","submitted_at":"2026-05-12T05:59:23Z","title":"TB-AVA: Text as a Semantic Bridge for Audio-Visual Parameter Efficient Finetuning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-14T21:14:38.092918Z"},"links":{"cited_paper":"/paper/2303.02344","citing_paper":"/paper/2605.11572"},"observation_digest":"sha256:e8b609e929f95dfb36e79c0c51080911e51cffd547ef184c49932bfeebe86e2a","observation_id":"09634b60-a6c5-43b9-a616-b45d8a3245b5","resolution":{"observed_at":"2026-05-14T21:17:59.676964Z","resolver_source":"arxiv_id","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/2303.02344/citation-record","integrity":"/paper/2303.02344/integrity","json":"/paper/2303.02344/citation-record.json","paper":"/paper/2303.02344"},"outbound":[],"paper":{"arxiv_id":"2303.02344","last_updated":"2023-03-04T07:21:37Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T08:51:23.860156Z","submitted_at":"2023-03-04T07:21:37Z","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels"},"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:2303.02344."}