{"as_of":"2026-08-04T15:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:729349e833a1bbd951425a991a9e3c85754c8ee9f8ac862bcc8b2256fe0b295d","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T17:32:32.229775Z","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":"2026-07-04T09:09:42.707307Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.16128","last_updated":"2024-03-24T12:55:50Z","snapshot_observed_at":"2026-07-06T17:49:40.841846Z","submitted_at":"2024-03-24T12:55:50Z","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","version":1},"cited_work":{"arxiv_id":"2403.16128","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.16128","snapshot_observed_at":"2026-07-04T09:09:42.707307Z","title":"Enhancing video transformers for action understanding with vlm-aided training,","venue":null,"work_id":"50752981-b97d-4513-86c7-3f52238f3da1","year":2024},"citing_paper":{"arxiv_id":"2606.22409","last_updated":"2026-06-21T09:54:39Z","snapshot_observed_at":"2026-07-06T23:57:18.596834Z","submitted_at":"2026-06-21T09:54:39Z","title":"Gold Points Sniper: Self-guided Visual Reasoning in VLM for Fine-grained Action Understanding","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-26T10:32:33.117191Z"},"links":{"cited_paper":"/paper/2403.16128","citing_paper":"/paper/2606.22409"},"observation_digest":"sha256:bbfaf7d5ab2f3b4f3f0607c9852c79c586597d2d2d273af1441902d32f442272","observation_id":"171b18df-0519-4532-85cc-404a3a7ba722","resolution":{"observed_at":"2026-07-04T09:09:42.708761Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.16128","last_updated":"2024-03-24T12:55:50Z","snapshot_observed_at":"2026-07-06T17:49:40.841846Z","submitted_at":"2024-03-24T12:55:50Z","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.16128","snapshot_observed_at":"2026-08-01T17:32:32.229775Z","title":"arXiv preprint arXiv:2403.16128","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17625","last_updated":"2026-07-20T07:30:16Z","snapshot_observed_at":"2026-08-01T17:32:30.525904Z","submitted_at":"2026-07-20T07:30:16Z","title":"Brain-Aligned Multi-Stream Video Transformers with Sparse Self-Selection","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-01T17:32:32.229775Z"},"links":{"cited_paper":"/paper/2403.16128","citing_paper":"/paper/2607.17625"},"observation_digest":"sha256:ca75ee7d2862b15f5b5a46632ea90d793dd5c324ea905f430850474d06088737","observation_id":"76cbf30b-ec71-491e-884d-c9542975eeca","resolution":{"observed_at":"2026-08-01T17:32:32.229775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2403.16128/citation-record","integrity":"/paper/2403.16128/integrity","json":"/paper/2403.16128/citation-record.json","paper":"/paper/2403.16128"},"outbound":[],"paper":{"arxiv_id":"2403.16128","last_updated":"2024-03-24T12:55:50Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:49:40.841846Z","submitted_at":"2024-03-24T12:55:50Z","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training"},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.16128."}