{"as_of":"2026-08-08T21:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:136dfbef3429b9f42d7bebc6549e13f93fb3ef62cfab49d6c40c58a8141583f1","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":"2026-08-08T06:32:00.761636+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":"2026-08-01T08:52:14.209492Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2012.04124","last_updated":"2021-09-22T16:19:39Z","snapshot_observed_at":"2026-08-05T17:42:51.919395Z","submitted_at":"2020-12-08T00:16:13Z","title":"Parameter Efficient Multimodal Transformers for Video Representation Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.04124","snapshot_observed_at":"2026-08-01T08:52:14.209492Z","title":"arXiv preprint arXiv:2012.04124 (2020)","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.20984","last_updated":"2026-07-23T07:07:28Z","snapshot_observed_at":"2026-08-06T22:09:00.863278Z","submitted_at":"2026-07-23T07:07:28Z","title":"Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T08:52:14.209492Z"},"links":{"cited_paper":"/paper/2012.04124","citing_paper":"/paper/2607.20984"},"observation_digest":"sha256:55056e51e097a1357f4c01b0e67e7e6b460acdb87222162b79c50beda825a26b","observation_id":"945dea58-fa68-4855-a91d-7f335998ca8f","resolution":{"observed_at":"2026-08-01T08:52:14.209492Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2012.04124/citation-record","integrity":"/paper/2012.04124/integrity","json":"/paper/2012.04124/citation-record.json","paper":"/paper/2012.04124"},"outbound":[],"paper":{"arxiv_id":"2012.04124","last_updated":"2021-09-22T16:19:39Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T17:42:51.919395Z","submitted_at":"2020-12-08T00:16:13Z","title":"Parameter Efficient Multimodal Transformers for Video Representation Learning"},"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 1 inbound Pith citation observation for arXiv:2012.04124."}