{"as_of":"2026-08-08T14:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:714dcd2360f0745238124142365446173160affb668a8ed4eaa031129128d782","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T12:41:51.586700Z","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":"2026-05-21T04:53:57.813016Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1804.02516","last_updated":"2020-01-16T13:18:58Z","snapshot_observed_at":"2026-07-06T06:32:12.791177Z","submitted_at":"2018-04-07T06:59:45Z","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","version":2},"cited_work":{"arxiv_id":"1804.02516","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1804.02516","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning a text-video embedding from incomplete and heterogeneous data","venue":null,"work_id":"b83676cf-7897-4079-a7a5-5db3e3b52fc0","year":2018},"citing_paper":{"arxiv_id":"2409.07825","last_updated":"2026-02-04T04:12:12Z","snapshot_observed_at":"2026-08-02T14:14:17.863359Z","submitted_at":"2024-09-12T08:15:39Z","title":"Deep Multimodal Learning with Missing Modality: A Survey","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-17T22:26:03.706725Z"},"links":{"cited_paper":"/paper/1804.02516","citing_paper":"/paper/2409.07825"},"observation_digest":"sha256:b00b274ee6944c6c61aa701168370970360225c4bcfd770bc233930b8b604282","observation_id":"d4183e7c-97a9-428d-a6f9-00fbd91a4b2a","resolution":{"observed_at":"2026-05-17T22:26:03.869102Z","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":"1804.02516","last_updated":"2020-01-16T13:18:58Z","snapshot_observed_at":"2026-07-06T06:32:12.791177Z","submitted_at":"2018-04-07T06:59:45Z","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.02516","snapshot_observed_at":"2026-08-07T12:41:51.586700Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.23952","last_updated":"2025-05-29T19:02:48Z","snapshot_observed_at":"2026-08-07T12:35:45.450197Z","submitted_at":"2025-05-29T19:02:48Z","title":"Leveraging Auxiliary Information in Text-to-Video Retrieval: A Review","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T12:41:51.586700Z"},"links":{"cited_paper":"/paper/1804.02516","citing_paper":"/paper/2505.23952"},"observation_digest":"sha256:a9da6b9e5401fcf85ae3009cec4c3e6c15a2b47da5aa7475812aec3d4282ddd0","observation_id":"2b6eac4a-d29e-4b4d-85cc-ea42bfca7299","resolution":{"observed_at":"2026-08-07T12:41:51.586700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.02516","last_updated":"2020-01-16T13:18:58Z","snapshot_observed_at":"2026-07-06T06:32:12.791177Z","submitted_at":"2018-04-07T06:59:45Z","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.02516","snapshot_observed_at":"2026-08-06T21:06:56.162437Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.00950","last_updated":"2025-07-01T16:52:20Z","snapshot_observed_at":"2026-08-07T08:54:27.720341Z","submitted_at":"2025-07-01T16:52:20Z","title":"MVP: Winning Solution to SMP Challenge 2025 Video Track","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:06:56.162437Z"},"links":{"cited_paper":"/paper/1804.02516","citing_paper":"/paper/2507.00950"},"observation_digest":"sha256:6eef943fbf386c23e581d39602b5a19a0284ff1a0baa2eaffe9639a0b90fabf3","observation_id":"45ad7e20-8d8b-4053-ba0d-1e69ddd4d1e1","resolution":{"observed_at":"2026-08-06T21:06:56.162437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.02516","last_updated":"2020-01-16T13:18:58Z","snapshot_observed_at":"2026-07-06T06:32:12.791177Z","submitted_at":"2018-04-07T06:59:45Z","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","version":2},"cited_work":{"arxiv_id":"1804.02516","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1804.02516","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning a text-video embedding from incomplete and heterogeneous data","venue":null,"work_id":"b83676cf-7897-4079-a7a5-5db3e3b52fc0","year":2018},"citing_paper":{"arxiv_id":"2605.20838","last_updated":"2026-05-20T07:27:36Z","snapshot_observed_at":"2026-08-03T00:00:48.827421Z","submitted_at":"2026-05-20T07:27:36Z","title":"USV: Towards Understanding the User-generated Short-form Videos","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-21T04:52:12.045880Z"},"links":{"cited_paper":"/paper/1804.02516","citing_paper":"/paper/2605.20838"},"observation_digest":"sha256:4f0e39017bb5fca019a898be4bbc1367b79eac05b442c9cde18675e1c16a4302","observation_id":"04316950-5876-422d-acfb-ed2ea017f449","resolution":{"observed_at":"2026-05-21T04:53:57.814545Z","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/1804.02516/citation-record","integrity":"/paper/1804.02516/integrity","json":"/paper/1804.02516/citation-record.json","paper":"/paper/1804.02516"},"outbound":[],"paper":{"arxiv_id":"1804.02516","last_updated":"2020-01-16T13:18:58Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T06:32:12.791177Z","submitted_at":"2018-04-07T06:59:45Z","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data"},"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 4 inbound Pith citation observations for arXiv:1804.02516."}