{"as_of":"2026-08-09T23:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b95578c312e2df906f954fd12810cdea20c6718bee32e46a85ab2a5f9e39cd8f","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:56:46.295352Z","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":"2026-07-02T01:06:24.813495Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1910.09387","last_updated":"2019-10-21T14:06:01Z","snapshot_observed_at":"2026-08-09T22:30:28.514802Z","submitted_at":"2019-10-21T14:06:01Z","title":"Clotho: An Audio Captioning Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.09387","snapshot_observed_at":"2026-08-06T22:56:46.295352Z","title":"Clotho: An Audio Captioning Dataset","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2507.02915","last_updated":"2025-06-25T08:38:27Z","snapshot_observed_at":"2026-08-08T07:26:02.720545Z","submitted_at":"2025-06-25T08:38:27Z","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:56:46.295352Z"},"links":{"cited_paper":"/paper/1910.09387","citing_paper":"/paper/2507.02915"},"observation_digest":"sha256:43799f29b1ad5176486ec1406ce718884de20dd10c9922b5ff0cff1935d92e86","observation_id":"84372658-ed8d-4e29-b5b9-d66d883a3b6b","resolution":{"observed_at":"2026-08-06T22:56:46.295352Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.09387","last_updated":"2019-10-21T14:06:01Z","snapshot_observed_at":"2026-08-09T22:30:28.514802Z","submitted_at":"2019-10-21T14:06:01Z","title":"Clotho: An Audio Captioning Dataset","version":1},"cited_work":{"arxiv_id":"1910.09387","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1910.09387","snapshot_observed_at":"2026-07-02T01:06:24.813495Z","title":"Tianyu Gao, Xingcheng Yao, and Danqi Chen","venue":null,"work_id":"9d48980b-8a82-4c75-b4f7-824226b23d7e","year":2019},"citing_paper":{"arxiv_id":"2604.16678","last_updated":"2026-04-17T20:21:34Z","snapshot_observed_at":"2026-07-06T23:03:57.199731Z","submitted_at":"2026-04-17T20:21:34Z","title":"UniCon: Unified Framework for Efficient Contrastive Alignment via Kernels","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T08:32:36.729122Z"},"links":{"cited_paper":"/paper/1910.09387","citing_paper":"/paper/2604.16678"},"observation_digest":"sha256:a00a797b4147be0a6740fe83ccecfed19163533a18ebe1f7a73efddcc03d0955","observation_id":"6c0d06ff-d5fb-48d2-9611-b5173754536c","resolution":{"observed_at":"2026-05-10T08:32:52.008833Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.09387","last_updated":"2019-10-21T14:06:01Z","snapshot_observed_at":"2026-08-09T22:30:28.514802Z","submitted_at":"2019-10-21T14:06:01Z","title":"Clotho: An Audio Captioning Dataset","version":1},"cited_work":{"arxiv_id":"1910.09387","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1910.09387","snapshot_observed_at":"2026-07-02T01:06:24.813495Z","title":"Tianyu Gao, Xingcheng Yao, and Danqi Chen","venue":null,"work_id":"9d48980b-8a82-4c75-b4f7-824226b23d7e","year":2019},"citing_paper":{"arxiv_id":"2606.02739","last_updated":"2026-06-01T18:05:18Z","snapshot_observed_at":"2026-07-06T23:43:07.940839Z","submitted_at":"2026-06-01T18:05:18Z","title":"EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-06-28T12:34:06.024192Z"},"links":{"cited_paper":"/paper/1910.09387","citing_paper":"/paper/2606.02739"},"observation_digest":"sha256:b28a506e007e04be4b154746d4f5e2d3df899fc7731c7c93f4470b54b9e01db9","observation_id":"61937904-c645-4c0d-bce4-7d3ef32ab832","resolution":{"observed_at":"2026-07-02T01:06:24.815094Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.09387","last_updated":"2019-10-21T14:06:01Z","snapshot_observed_at":"2026-08-09T22:30:28.514802Z","submitted_at":"2019-10-21T14:06:01Z","title":"Clotho: An Audio Captioning Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.09387","snapshot_observed_at":"2026-08-01T14:46:35.273134Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18666","last_updated":"2026-07-21T03:25:34Z","snapshot_observed_at":"2026-08-06T07:56:47.796949Z","submitted_at":"2026-07-21T03:25:34Z","title":"Fusion Embedding: A Unified Embedding Space for Text, Image, Video, and Audio","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-01T14:46:35.273134Z"},"links":{"cited_paper":"/paper/1910.09387","citing_paper":"/paper/2607.18666"},"observation_digest":"sha256:e7e5023cabd81268ab2c549194c9c05048b4dc7995f1020c42a65ca737f8d07e","observation_id":"1bb70593-9ea8-46d8-870c-9f531e446cea","resolution":{"observed_at":"2026-08-01T14:46:35.273134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1910.09387/citation-record","integrity":"/paper/1910.09387/integrity","json":"/paper/1910.09387/citation-record.json","paper":"/paper/1910.09387"},"outbound":[],"paper":{"arxiv_id":"1910.09387","last_updated":"2019-10-21T14:06:01Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-09T22:30:28.514802Z","submitted_at":"2019-10-21T14:06:01Z","title":"Clotho: An Audio Captioning Dataset"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1910.09387."}