{"as_of":"2026-08-13T13:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:806b47a7b27b349a0cd0cc912e9dbf1e9fa2efe0c0230faa34d950ca3f4cd3c6","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T14:04:00.452825Z","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":"2026-08-07T15:32:28.498361Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1909.08782","last_updated":"2019-09-19T02:50:23Z","snapshot_observed_at":"2026-07-06T08:22:58.185275Z","submitted_at":"2019-09-19T02:50:23Z","title":"Large-scale representation learning from visually grounded untranscribed speech","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.08782","snapshot_observed_at":"2026-08-12T14:04:00.452825Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.00049","last_updated":"2024-11-24T03:26:34Z","snapshot_observed_at":"2026-08-13T08:29:44.393581Z","submitted_at":"2024-11-24T03:26:34Z","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T14:04:00.452825Z"},"links":{"cited_paper":"/paper/1909.08782","citing_paper":"/paper/2412.00049"},"observation_digest":"sha256:8cb238dc6ed86b9138903dce1803386dbe36b99f0e2d035a0349a070654dc298","observation_id":"9db3643a-b657-4fe0-8353-787a4ec163e8","resolution":{"observed_at":"2026-08-12T14:04:00.452825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08782","last_updated":"2019-09-19T02:50:23Z","snapshot_observed_at":"2026-07-06T08:22:58.185275Z","submitted_at":"2019-09-19T02:50:23Z","title":"Large-scale representation learning from visually grounded untranscribed speech","version":1},"cited_work":{"arxiv_id":"1909.08782","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.08782","snapshot_observed_at":"2026-08-07T15:32:28.498361Z","title":"Large-scale representation learning from visually grounded untranscribed speech","venue":"cs.CV","work_id":"c056850d-b843-4fc5-9712-fb5e415abc9a","year":2019},"citing_paper":{"arxiv_id":"2505.14802","last_updated":"2025-05-20T18:12:19Z","snapshot_observed_at":"2026-08-13T09:57:29.338426Z","submitted_at":"2025-05-20T18:12:19Z","title":"Text embedding models can be great data engineers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:32:25.641047Z"},"links":{"cited_paper":"/paper/1909.08782","citing_paper":"/paper/2505.14802"},"observation_digest":"sha256:11725f14910055e7a9f8e490f12e8bad04be2ec0551f724e6bebc76057c04dcd","observation_id":"74a333e3-b53f-4b99-bce4-83831901fd62","resolution":{"observed_at":"2026-08-07T15:32:28.628245Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1909.08782/citation-record","integrity":"/paper/1909.08782/integrity","json":"/paper/1909.08782/citation-record.json","paper":"/paper/1909.08782"},"outbound":[],"paper":{"arxiv_id":"1909.08782","last_updated":"2019-09-19T02:50:23Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T08:22:58.185275Z","submitted_at":"2019-09-19T02:50:23Z","title":"Large-scale representation learning from visually grounded untranscribed speech"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1909.08782."}