{"as_of":"2026-08-17T22:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b4ac44deeaf0517f8517491d840fcf7a044004c7921fe1a284892a225a07937","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T16:22:25.180917Z","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":"2026-08-07T00:26:05.896375Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.16669","last_updated":"2023-09-28T17:59:50Z","snapshot_observed_at":"2026-08-17T21:50:31.665565Z","submitted_at":"2023-09-28T17:59:50Z","title":"Training a Large Video Model on a Single Machine in a Day","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16669","snapshot_observed_at":"2026-08-12T16:22:25.180917Z","title":"Training a large video model on a single machine in a day","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13683","last_updated":"2024-11-20T20:00:38Z","snapshot_observed_at":"2026-08-16T13:56:11.227401Z","submitted_at":"2024-11-20T20:00:38Z","title":"Extending Video Masked Autoencoders to 128 frames","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T16:22:25.180917Z"},"links":{"cited_paper":"/paper/2309.16669","citing_paper":"/paper/2411.13683"},"observation_digest":"sha256:21b7eea9749a26c1468f4f8749dc96cd50b6e9d499611bd9e4909b8c0d3072fe","observation_id":"2f028e33-ae02-4d0b-8d47-ea889ce8eda2","resolution":{"observed_at":"2026-08-12T16:22:25.180917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16669","last_updated":"2023-09-28T17:59:50Z","snapshot_observed_at":"2026-08-17T21:50:31.665565Z","submitted_at":"2023-09-28T17:59:50Z","title":"Training a Large Video Model on a Single Machine in a Day","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16669","snapshot_observed_at":"2026-08-10T23:07:14.736293Z","title":"Training a large video model on a single machine in a day","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.21080","last_updated":"2024-12-30T16:57:05Z","snapshot_observed_at":"2026-08-16T22:23:33.828463Z","submitted_at":"2024-12-30T16:57:05Z","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-10T23:07:14.736293Z"},"links":{"cited_paper":"/paper/2309.16669","citing_paper":"/paper/2412.21080"},"observation_digest":"sha256:306ede612b9c29ac1eb310ba0164dc0277ddc11f958b8c55f07879bd449ca683","observation_id":"a7309c89-6de1-4361-8b8b-09e82da33cdd","resolution":{"observed_at":"2026-08-10T23:07:14.736293Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16669","last_updated":"2023-09-28T17:59:50Z","snapshot_observed_at":"2026-08-17T21:50:31.665565Z","submitted_at":"2023-09-28T17:59:50Z","title":"Training a Large Video Model on a Single Machine in a Day","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16669","snapshot_observed_at":"2026-08-07T11:42:35.247796Z","title":"Training a large video model on a single machine in a day","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.01608","last_updated":"2025-08-25T13:46:38Z","snapshot_observed_at":"2026-08-17T13:06:51.323994Z","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":101,"source":"pdf_text","source_observed_at":"2026-08-07T11:42:35.247796Z"},"links":{"cited_paper":"/paper/2309.16669","citing_paper":"/paper/2506.01608"},"observation_digest":"sha256:a4e82142a1aeb41350146cc01ea20c9b1dd094cad6d09bdedbcf996353180cd0","observation_id":"a7b81eb3-a405-45a5-afa6-8dfe0d3a0b67","resolution":{"observed_at":"2026-08-07T11:42:35.247796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16669","last_updated":"2023-09-28T17:59:50Z","snapshot_observed_at":"2026-08-17T21:50:31.665565Z","submitted_at":"2023-09-28T17:59:50Z","title":"Training a Large Video Model on a Single Machine in a Day","version":1},"cited_work":{"arxiv_id":"2309.16669","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.16669","snapshot_observed_at":"2026-08-07T00:26:05.896375Z","title":"Training a Large Video Model on a Single Machine in a Day","venue":"cs.CV","work_id":"8c42d068-7973-4b68-a59f-bce8ede97627","year":2023},"citing_paper":{"arxiv_id":"2506.14356","last_updated":"2025-06-17T09:51:51Z","snapshot_observed_at":"2026-08-17T04:56:22.532342Z","submitted_at":"2025-06-17T09:51:51Z","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T00:25:59.818943Z"},"links":{"cited_paper":"/paper/2309.16669","citing_paper":"/paper/2506.14356"},"observation_digest":"sha256:8b10226ec830ee371386acb4a87a03ae7252f555f2bcb5373cd3944cf4748092","observation_id":"416ae5dc-9eea-4ae5-8c37-38a17c72361d","resolution":{"observed_at":"2026-08-07T00:26:05.951232Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.16669/citation-record","integrity":"/paper/2309.16669/integrity","json":"/paper/2309.16669/citation-record.json","paper":"/paper/2309.16669"},"outbound":[],"paper":{"arxiv_id":"2309.16669","last_updated":"2023-09-28T17:59:50Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T21:50:31.665565Z","submitted_at":"2023-09-28T17:59:50Z","title":"Training a Large Video Model on a Single Machine in a Day"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2309.16669."}