{"as_of":"2026-08-22T01:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:57fc1ec2ba77fdcf0e0fa9d47ac87c7c7c558eb59686cb731864cc8a26b53e8e","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":"2026-08-21T06:32:19.484+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":"2026-05-16T09:50:00.546571Z","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":"2026-05-16T09:50:00.747220Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2201.02639","last_updated":"2022-05-13T14:25:04Z","snapshot_observed_at":"2026-08-20T04:36:38.720185Z","submitted_at":"2022-01-07T19:00:21Z","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","version":4},"cited_work":{"arxiv_id":"2201.02639","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2201.02639","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zellers, J","venue":null,"work_id":"a5b519d4-e3c3-4f78-9efa-04de5b208a59","year":2022},"citing_paper":{"arxiv_id":"2204.00598","last_updated":"2022-05-27T17:52:50Z","snapshot_observed_at":"2026-08-13T04:37:51.649726Z","submitted_at":"2022-04-01T17:43:13Z","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-16T09:50:00.546571Z"},"links":{"cited_paper":"/paper/2201.02639","citing_paper":"/paper/2204.00598"},"observation_digest":"sha256:6f2a82291a7774e210639cc2eb9fec28c34c97c29afd009a9353210895a34a96","observation_id":"a27b90d9-17cc-423a-b683-a82404ff51d5","resolution":{"observed_at":"2026-05-16T09:50:00.748974Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2201.02639/citation-record","integrity":"/paper/2201.02639/integrity","json":"/paper/2201.02639/citation-record.json","paper":"/paper/2201.02639"},"outbound":[],"paper":{"arxiv_id":"2201.02639","last_updated":"2022-05-13T14:25:04Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T04:36:38.720185Z","submitted_at":"2022-01-07T19:00:21Z","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2201.02639."}