{"as_of":"2026-08-12T18:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:252afc93933d2e0bf94eb2bf5834029fb17b308b72c4fffadc44627b55de4a97","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T12:10:17.503202Z","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":"2026-06-28T23:32:47.450637Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2207.11100","last_updated":"2022-07-27T21:52:21Z","snapshot_observed_at":"2026-07-06T13:34:13.533549Z","submitted_at":"2022-07-22T14:19:31Z","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.11100","snapshot_observed_at":"2026-08-11T18:11:54.468557Z","title":"Zero- shot video captioning with evolving pseudo-tokens,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08158","last_updated":"2024-12-11T07:29:04Z","snapshot_observed_at":"2026-08-12T07:36:23.412895Z","submitted_at":"2024-12-11T07:29:04Z","title":"How Vision-Language Tasks Benefit from Large Pre-trained Models: A Survey","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T18:11:54.468557Z"},"links":{"cited_paper":"/paper/2207.11100","citing_paper":"/paper/2412.08158"},"observation_digest":"sha256:ebfcb56cb6b87ac7fb4f7fbd56bdeee5b5801fa0f98a54e5105a7821e7232d56","observation_id":"50cf5717-8a82-4a0f-a8c2-d066e766c04d","resolution":{"observed_at":"2026-08-11T18:11:54.468557Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.11100","last_updated":"2022-07-27T21:52:21Z","snapshot_observed_at":"2026-07-06T13:34:13.533549Z","submitted_at":"2022-07-22T14:19:31Z","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","version":2},"cited_work":{"arxiv_id":"2207.11100","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2207.11100","snapshot_observed_at":"2026-06-28T23:32:47.450637Z","title":"Zero-shot video captioning with evolving pseudo-tokens,","venue":null,"work_id":"6ba9f9da-8dba-4c0b-b1d5-a41cd38d6002","year":2022},"citing_paper":{"arxiv_id":"2605.30689","last_updated":"2026-05-29T00:34:17Z","snapshot_observed_at":"2026-08-11T17:55:34.097194Z","submitted_at":"2026-05-29T00:34:17Z","title":"ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T23:27:25.975576Z"},"links":{"cited_paper":"/paper/2207.11100","citing_paper":"/paper/2605.30689"},"observation_digest":"sha256:535d868b52012c0f40d09dc65fbcea1f1c67203e177e0b106bd11fa1717a141d","observation_id":"0ed6d25d-3e5e-431c-95c3-c1f38aa1e4c9","resolution":{"observed_at":"2026-06-28T23:32:47.452572Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.11100","last_updated":"2022-07-27T21:52:21Z","snapshot_observed_at":"2026-07-06T13:34:13.533549Z","submitted_at":"2022-07-22T14:19:31Z","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.11100","snapshot_observed_at":"2026-08-12T12:10:17.503202Z","title":"Zero- shot video captioning with evolving pseudo-tokens,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.11013","last_updated":"2026-08-11T14:57:44Z","snapshot_observed_at":"2026-08-12T18:21:48.282546Z","submitted_at":"2026-08-11T14:57:44Z","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T12:10:17.503202Z"},"links":{"cited_paper":"/paper/2207.11100","citing_paper":"/paper/2608.11013"},"observation_digest":"sha256:469953681d91d3baa70712b87edde430dd53e30a1b340dbca22ae6f1e077117e","observation_id":"d3429b60-cc3d-4cf0-a7cf-308a47018340","resolution":{"observed_at":"2026-08-12T12:10:17.503202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2207.11100/citation-record","integrity":"/paper/2207.11100/integrity","json":"/paper/2207.11100/citation-record.json","paper":"/paper/2207.11100"},"outbound":[],"paper":{"arxiv_id":"2207.11100","last_updated":"2022-07-27T21:52:21Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T13:34:13.533549Z","submitted_at":"2022-07-22T14:19:31Z","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2207.11100."}