{"as_of":"2026-08-09T02:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:11adb3f6dee28cf3bab71cdfbba8ca41d0f255c4946ada16e76e6948c99c91f2","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T13:20:15.714734Z","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":"2026-08-07T13:20:18.135780Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2107.09817","last_updated":"2021-07-21T00:31:50Z","snapshot_observed_at":"2026-08-05T22:00:33.145653Z","submitted_at":"2021-07-21T00:31:50Z","title":"Audio Captioning Transformer","version":1},"cited_work":{"arxiv_id":"2107.09817","doi":null,"metadata_source":"pith","pith_arxiv_id":"2107.09817","snapshot_observed_at":"2026-08-07T13:20:18.135780Z","title":"Audio Captioning Transformer","venue":"eess.AS","work_id":"c397f728-4970-4f02-a404-a534d0a580bb","year":2021},"citing_paper":{"arxiv_id":"2505.22045","last_updated":"2025-05-28T07:08:17Z","snapshot_observed_at":"2026-08-07T13:14:09.265446Z","submitted_at":"2025-05-28T07:08:17Z","title":"Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:20:15.714734Z"},"links":{"cited_paper":"/paper/2107.09817","citing_paper":"/paper/2505.22045"},"observation_digest":"sha256:1959514f957e9dbe9331da7b80b8fd97b1411301185d7645ca9e0dec97837168","observation_id":"b8e6e2e4-5745-481d-abaa-bceab90c8304","resolution":{"observed_at":"2026-08-07T13:20:18.267155Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2107.09817","last_updated":"2021-07-21T00:31:50Z","snapshot_observed_at":"2026-08-05T22:00:33.145653Z","submitted_at":"2021-07-21T00:31:50Z","title":"Audio Captioning Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.09817","snapshot_observed_at":"2026-08-01T03:12:06.514554Z","title":"Audio captioning transformer,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.25197","last_updated":"2026-07-28T02:04:00Z","snapshot_observed_at":"2026-08-08T11:34:00.014616Z","submitted_at":"2026-07-28T02:04:00Z","title":"LGFNet: A CTC-Guided Local-Global Fusion Framework for Single-Channel Sleep Staging","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T03:12:06.514554Z"},"links":{"cited_paper":"/paper/2107.09817","citing_paper":"/paper/2607.25197"},"observation_digest":"sha256:189142e8d364c113c0087a1c34957977aa3073fb77299cab7db094091ca8537d","observation_id":"69b1d4a8-4ef6-45f9-9aa4-545aa54c80d8","resolution":{"observed_at":"2026-08-01T03:12:06.514554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2107.09817/citation-record","integrity":"/paper/2107.09817/integrity","json":"/paper/2107.09817/citation-record.json","paper":"/paper/2107.09817"},"outbound":[],"paper":{"arxiv_id":"2107.09817","last_updated":"2021-07-21T00:31:50Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-05T22:00:33.145653Z","submitted_at":"2021-07-21T00:31:50Z","title":"Audio Captioning Transformer"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2107.09817."}