{"as_of":"2026-08-11T06:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:12fbf9fdf242535db69f7610f7ce3560b2c349d7dad8d751f0acc2f996cd2444","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":"2026-08-11T06:34:44.6726+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":"2026-08-05T05:12:54.505154Z","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":"2026-08-05T05:12:54.718605Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2001.07059","last_updated":"2020-01-20T11:27:21Z","snapshot_observed_at":"2026-08-06T00:10:50.635494Z","submitted_at":"2020-01-20T11:27:21Z","title":"Accuracy vs. Complexity: A Trade-off in Visual Question Answering Models","version":1},"cited_work":{"arxiv_id":"2001.07059","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.07059","snapshot_observed_at":"2026-08-05T05:12:54.718605Z","title":"Accuracy vs. Complexity: A Trade-off in Visual Question Answering Models","venue":"cs.CV","work_id":"fb28c155-3611-4e58-b4aa-c2b47be1ed76","year":2020},"citing_paper":{"arxiv_id":"2509.05695","last_updated":"2025-09-06T12:11:43Z","snapshot_observed_at":"2026-08-10T08:18:23.630848Z","submitted_at":"2025-09-06T12:11:43Z","title":"Leveraging Vision-Language Large Models for Interpretable Video Action Recognition with Semantic Tokenization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T05:12:54.505154Z"},"links":{"cited_paper":"/paper/2001.07059","citing_paper":"/paper/2509.05695"},"observation_digest":"sha256:405e87130d51df1894a1b6d1f623165c4bfee00851e2a144d56726ee608aa60c","observation_id":"12d6837f-c665-4907-b5b0-6392d1f23f88","resolution":{"observed_at":"2026-08-05T05:12:54.723613Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2001.07059/citation-record","integrity":"/paper/2001.07059/integrity","json":"/paper/2001.07059/citation-record.json","paper":"/paper/2001.07059"},"outbound":[],"paper":{"arxiv_id":"2001.07059","last_updated":"2020-01-20T11:27:21Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T00:10:50.635494Z","submitted_at":"2020-01-20T11:27:21Z","title":"Accuracy vs. Complexity: A Trade-off in Visual Question Answering Models"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2001.07059."}