{"as_of":"2026-08-19T13:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:52b328ea32679d351f3ca68683b2631662a5224a9c46ed0b42ebcaefd41a5051","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T22:37:33.931226Z","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":"2026-05-11T08:40:59.514398Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2208.01897","last_updated":"2022-08-03T08:01:55Z","snapshot_observed_at":"2026-08-18T20:13:21.116897Z","submitted_at":"2022-08-03T08:01:55Z","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01897","snapshot_observed_at":"2026-08-10T22:37:33.931226Z","title":"arXiv preprint arXiv:2208.01897","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01245","last_updated":"2025-01-02T13:12:12Z","snapshot_observed_at":"2026-08-16T06:54:33.623506Z","submitted_at":"2025-01-02T13:12:12Z","title":"SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T22:37:33.931226Z"},"links":{"cited_paper":"/paper/2208.01897","citing_paper":"/paper/2501.01245"},"observation_digest":"sha256:cd03d0c17deb91044e4bc53ed06e536302ecb7b71597c1187d24c93fed313f87","observation_id":"915ee6af-cd7b-4b20-b759-8362c0016d8b","resolution":{"observed_at":"2026-08-10T22:37:33.931226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01897","last_updated":"2022-08-03T08:01:55Z","snapshot_observed_at":"2026-08-18T20:13:21.116897Z","submitted_at":"2022-08-03T08:01:55Z","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition","version":1},"cited_work":{"arxiv_id":"2208.01897","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.01897","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2208.01897 (2022)","venue":null,"work_id":"2a930237-1c90-4c2d-9e5c-aff7e67eab7a","year":2022},"citing_paper":{"arxiv_id":"2604.11498","last_updated":"2026-04-13T14:03:58Z","snapshot_observed_at":"2026-08-03T00:38:30.162712Z","submitted_at":"2026-04-13T14:03:58Z","title":"TAG-Head: Time-Aligned Graph Head for Plug-and-Play Fine-grained Action Recognition","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T16:33:28.632640Z"},"links":{"cited_paper":"/paper/2208.01897","citing_paper":"/paper/2604.11498"},"observation_digest":"sha256:c997b8f8e524db1cec09d8a27e26d2d8d72ac51721ad81bc26201893fae34f60","observation_id":"f0dad7bd-7f64-4690-8b05-46f1e1bb702b","resolution":{"observed_at":"2026-05-11T08:40:59.516839Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01897","last_updated":"2022-08-03T08:01:55Z","snapshot_observed_at":"2026-08-18T20:13:21.116897Z","submitted_at":"2022-08-03T08:01:55Z","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition","version":1},"cited_work":{"arxiv_id":"2208.01897","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.01897","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv:2208.01897 (2022)","venue":null,"work_id":"2a930237-1c90-4c2d-9e5c-aff7e67eab7a","year":2022},"citing_paper":{"arxiv_id":"2604.20760","last_updated":"2026-04-22T16:48:43Z","snapshot_observed_at":"2026-08-11T00:18:47.816514Z","submitted_at":"2026-04-22T16:48:43Z","title":"Exploring High-Order Self-Similarity for Video Understanding","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-10T00:59:03.890135Z"},"links":{"cited_paper":"/paper/2208.01897","citing_paper":"/paper/2604.20760"},"observation_digest":"sha256:4f5e9988ad3c7840a9e7b83cb7e6a1d568593f60488699e25b20c472a5b6bff7","observation_id":"387627db-c62c-4c74-86ff-921e5f8d9328","resolution":{"observed_at":"2026-05-10T00:59:49.441895Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2208.01897/citation-record","integrity":"/paper/2208.01897/integrity","json":"/paper/2208.01897/citation-record.json","paper":"/paper/2208.01897"},"outbound":[],"paper":{"arxiv_id":"2208.01897","last_updated":"2022-08-03T08:01:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T20:13:21.116897Z","submitted_at":"2022-08-03T08:01:55Z","title":"Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2208.01897."}