{"as_of":"2026-08-19T00:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aee92c105d7fa72a4b2731f631c0096b424d7547dfdefce2f207ce4635df67cd","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":"2026-08-18T06:34:40.430872+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":"2026-08-07T11:42:33.221391Z","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":"2026-05-10T11:35:18.630764Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.05653","last_updated":"2024-02-06T11:12:02Z","snapshot_observed_at":"2026-08-18T13:33:30.159485Z","submitted_at":"2022-09-13T00:01:23Z","title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.05653","snapshot_observed_at":"2026-08-07T11:42:33.221391Z","title":"Semantic2graph: Graph-based multi- modal feature fusion for action segmentation in videos","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.01608","last_updated":"2025-08-25T13:46:38Z","snapshot_observed_at":"2026-08-18T09:25:07.501467Z","submitted_at":"2025-06-02T12:46:44Z","title":"EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:42:33.221391Z"},"links":{"cited_paper":"/paper/2209.05653","citing_paper":"/paper/2506.01608"},"observation_digest":"sha256:6a1d04a413f9c46f8babfc8ed9c1866389a4f9b1f3e7f5c6bbad5c53c8216dbd","observation_id":"ef1abd6d-5f2d-4370-862b-ae274a9b831d","resolution":{"observed_at":"2026-08-07T11:42:33.221391Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.05653","last_updated":"2024-02-06T11:12:02Z","snapshot_observed_at":"2026-08-18T13:33:30.159485Z","submitted_at":"2022-09-13T00:01:23Z","title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","version":5},"cited_work":{"arxiv_id":"2209.05653","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2209.05653","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Semantic2graph: graph-based multi-modal feature fusion for action segmentation in videos","venue":null,"work_id":"870812c6-f1b0-4e84-8ec7-bdba03e285b5","year":2022},"citing_paper":{"arxiv_id":"2604.15173","last_updated":"2026-04-16T15:50:21Z","snapshot_observed_at":"2026-08-11T03:45:09.007199Z","submitted_at":"2026-04-16T15:50:21Z","title":"Boundary-Centric Active Learning for Temporal Action Segmentation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-10T11:35:01.198645Z"},"links":{"cited_paper":"/paper/2209.05653","citing_paper":"/paper/2604.15173"},"observation_digest":"sha256:2ed6d08d31e4b3faa68c0a8367cb2ba693ad59316c3c797ef5e646843f076eac","observation_id":"c4a576c2-c519-4130-bfb4-d8915a8c5514","resolution":{"observed_at":"2026-05-10T11:35:18.632192Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2209.05653/citation-record","integrity":"/paper/2209.05653/integrity","json":"/paper/2209.05653/citation-record.json","paper":"/paper/2209.05653"},"outbound":[],"paper":{"arxiv_id":"2209.05653","last_updated":"2024-02-06T11:12:02Z","latest_version":5,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T13:33:30.159485Z","submitted_at":"2022-09-13T00:01:23Z","title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2209.05653."}