{"as_of":"2026-08-09T20:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:40be74e59f9e11fd68205e29414a1fbce9ceab4ab3c47fad6203e49c8e5be28d","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:38:43.276662Z","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":"2026-08-06T21:38:45.877367Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2207.01814","last_updated":"2023-01-20T00:18:49Z","snapshot_observed_at":"2026-07-06T13:27:49.894090Z","submitted_at":"2022-07-05T05:14:15Z","title":"Multimodal Frame-Scoring Transformer for Video Summarization","version":3},"cited_work":{"arxiv_id":"2207.01814","doi":null,"metadata_source":"pith","pith_arxiv_id":"2207.01814","snapshot_observed_at":"2026-08-06T21:38:45.877367Z","title":"Multimodal Frame-Scoring Transformer for Video Summarization","venue":"cs.LG","work_id":"89846e4e-851c-4086-83bb-6b239cd03eba","year":2022},"citing_paper":{"arxiv_id":"2506.23714","last_updated":"2025-06-30T10:41:33Z","snapshot_observed_at":"2026-08-08T16:30:17.795530Z","submitted_at":"2025-06-30T10:41:33Z","title":"Towards an Automated Multimodal Approach for Video Summarization: Building a Bridge Between Text, Audio and Facial Cue-Based Summarization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:38:43.276662Z"},"links":{"cited_paper":"/paper/2207.01814","citing_paper":"/paper/2506.23714"},"observation_digest":"sha256:a48d1e996df1d62e026bffcc801a0d77c3c8dafb25fee055f76c0393b76e2658","observation_id":"fb2656d3-fa37-472f-b2af-f9f51d9aa4df","resolution":{"observed_at":"2026-08-06T21:38:45.965102Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2207.01814/citation-record","integrity":"/paper/2207.01814/integrity","json":"/paper/2207.01814/citation-record.json","paper":"/paper/2207.01814"},"outbound":[],"paper":{"arxiv_id":"2207.01814","last_updated":"2023-01-20T00:18:49Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T13:27:49.894090Z","submitted_at":"2022-07-05T05:14:15Z","title":"Multimodal Frame-Scoring Transformer for Video Summarization"},"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 1 inbound Pith citation observation for arXiv:2207.01814."}