{"as_of":"2026-08-16T15:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2d1ffd99ea2b805dc282b35bd815d0e29ab233a4dbbe4afea33c4f0b475eab30","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":"2026-08-16T06:30:59.297886+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":"2026-08-14T14:07:22.214925Z","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":"2026-05-16T09:20:20.430370Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1610.02947","last_updated":"2017-07-25T10:12:31Z","snapshot_observed_at":"2026-08-14T21:35:55.476144Z","submitted_at":"2016-10-10T15:03:15Z","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.02947","snapshot_observed_at":"2026-08-14T14:07:22.214925Z","title":"Video captioning and retrieval models with semantic attention","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03744","last_updated":"2019-08-10T12:29:05Z","snapshot_observed_at":"2026-08-16T10:57:02.472516Z","submitted_at":"2019-08-10T12:29:05Z","title":"Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:07:22.214925Z"},"links":{"cited_paper":"/paper/1610.02947","citing_paper":"/paper/1908.03744"},"observation_digest":"sha256:9760d6c3df0535522fcb307c42ac31b72b5838277f7e3f88ecc7e05b2297ca39","observation_id":"f1aaf072-eba7-4ebe-a8fa-857543c9aab4","resolution":{"observed_at":"2026-08-14T14:07:22.214925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.02947","last_updated":"2017-07-25T10:12:31Z","snapshot_observed_at":"2026-08-14T21:35:55.476144Z","submitted_at":"2016-10-10T15:03:15Z","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","version":3},"cited_work":{"arxiv_id":"1610.02947","doi":null,"metadata_source":"pith","pith_arxiv_id":"1610.02947","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering","venue":"cs.CV","work_id":"8072cc20-c058-4c9a-931a-92abc27fc0bc","year":2016},"citing_paper":{"arxiv_id":"2309.16671","last_updated":"2025-11-23T00:34:43Z","snapshot_observed_at":"2026-08-02T18:24:11.208164Z","submitted_at":"2023-09-28T17:59:56Z","title":"Demystifying CLIP Data","version":6},"reference_index":179,"source":"arxiv_source","source_observed_at":"2026-05-16T09:20:20.143143Z"},"links":{"cited_paper":"/paper/1610.02947","citing_paper":"/paper/2309.16671"},"observation_digest":"sha256:a15e4d40ae1659deb594a155dfbabe728d7256462fc096e6d779cc7bc03f4b35","observation_id":"eacf7e76-a076-4c40-a161-de511c272aa2","resolution":{"observed_at":"2026-05-16T09:20:20.431855Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1610.02947/citation-record","integrity":"/paper/1610.02947/integrity","json":"/paper/1610.02947/citation-record.json","paper":"/paper/1610.02947"},"outbound":[],"paper":{"arxiv_id":"1610.02947","last_updated":"2017-07-25T10:12:31Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T21:35:55.476144Z","submitted_at":"2016-10-10T15:03:15Z","title":"End-to-end Concept Word Detection for Video Captioning, Retrieval, and Question Answering"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1610.02947."}