{"as_of":"2026-08-09T20:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:803f5470c28894e32c628a7e1eb68bbc27790e5e6678a333c7386b6f01718ff5","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T13:18:19.411600Z","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":"2026-05-23T08:12:43.902365Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.13915","last_updated":"2021-05-27T13:17:38Z","snapshot_observed_at":"2026-07-06T10:53:21.486703Z","submitted_at":"2021-03-25T15:25:17Z","title":"An Image is Worth 16x16 Words, What is a Video Worth?","version":2},"cited_work":{"arxiv_id":"2103.13915","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.13915","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An image is worth 16x16 words, what is a video worth?","venue":null,"work_id":"324de36a-078f-4d80-a469-9a9935c0f0bf","year":2021},"citing_paper":{"arxiv_id":"2412.02930","last_updated":"2026-04-19T04:24:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-04T00:50:33Z","title":"TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos","version":6},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-23T08:08:01.889675Z"},"links":{"cited_paper":"/paper/2103.13915","citing_paper":"/paper/2412.02930"},"observation_digest":"sha256:e7136e8667b350bed1b902add6aca19ad8d4de2985bb25ef16b027b3e9997f21","observation_id":"2665189e-f7c6-4415-956b-945c7aacb13f","resolution":{"observed_at":"2026-05-23T08:12:43.906439Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.13915","last_updated":"2021-05-27T13:17:38Z","snapshot_observed_at":"2026-07-06T10:53:21.486703Z","submitted_at":"2021-03-25T15:25:17Z","title":"An Image is Worth 16x16 Words, What is a Video Worth?","version":2},"cited_work":{"arxiv_id":"2103.13915","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2103.13915","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An image is worth 16x16 words, what is a video worth?","venue":null,"work_id":"324de36a-078f-4d80-a469-9a9935c0f0bf","year":2021},"citing_paper":{"arxiv_id":"2501.12632","last_updated":"2026-04-29T19:18:41Z","snapshot_observed_at":"2026-07-06T20:24:12.803909Z","submitted_at":"2025-01-22T04:36:17Z","title":"TeD-Loc: Text Distillation for Weakly Supervised Object Localization","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-23T05:11:17.213575Z"},"links":{"cited_paper":"/paper/2103.13915","citing_paper":"/paper/2501.12632"},"observation_digest":"sha256:07d1e953483aabc765e61f66518f2a49a42809b5930829d3e6669878292842c8","observation_id":"c3d05f09-e4c3-4425-813d-fcff56b9cb91","resolution":{"observed_at":"2026-05-23T05:12:34.876761Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.13915","last_updated":"2021-05-27T13:17:38Z","snapshot_observed_at":"2026-07-06T10:53:21.486703Z","submitted_at":"2021-03-25T15:25:17Z","title":"An Image is Worth 16x16 Words, What is a Video Worth?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.13915","snapshot_observed_at":"2026-08-08T13:18:19.411600Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.07277","last_updated":"2025-02-11T05:44:50Z","snapshot_observed_at":"2026-08-08T13:13:50.722462Z","submitted_at":"2025-02-11T05:44:50Z","title":"Enhancing Video Understanding: Deep Neural Networks for Spatiotemporal Analysis","version":1},"reference_index":119,"source":"pdf_text","source_observed_at":"2026-08-08T13:18:19.411600Z"},"links":{"cited_paper":"/paper/2103.13915","citing_paper":"/paper/2502.07277"},"observation_digest":"sha256:f01b304122d200a2e420de88fed8f87b1266c2216c538862b4f1befd32533627","observation_id":"8de95228-e4ab-4f9a-824e-62b48a43f162","resolution":{"observed_at":"2026-08-08T13:18:19.411600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.13915","last_updated":"2021-05-27T13:17:38Z","snapshot_observed_at":"2026-07-06T10:53:21.486703Z","submitted_at":"2021-03-25T15:25:17Z","title":"An Image is Worth 16x16 Words, What is a Video Worth?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.13915","snapshot_observed_at":"2026-08-07T14:09:33.385463Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.19928","last_updated":"2025-05-26T12:55:27Z","snapshot_observed_at":"2026-08-08T11:16:13.922243Z","submitted_at":"2025-05-26T12:55:27Z","title":"CA3D: Convolutional-Attentional 3D Nets for Efficient Video Activity Recognition on the Edge","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T14:09:33.385463Z"},"links":{"cited_paper":"/paper/2103.13915","citing_paper":"/paper/2505.19928"},"observation_digest":"sha256:4db5037acb769919f31fcfc43e2dbae7a19b7609649a850229be3324e26be123","observation_id":"3a9d2793-0b66-4b17-8c98-6e4c3a5ce66a","resolution":{"observed_at":"2026-08-07T14:09:33.385463Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2103.13915/citation-record","integrity":"/paper/2103.13915/integrity","json":"/paper/2103.13915/citation-record.json","paper":"/paper/2103.13915"},"outbound":[],"paper":{"arxiv_id":"2103.13915","last_updated":"2021-05-27T13:17:38Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T10:53:21.486703Z","submitted_at":"2021-03-25T15:25:17Z","title":"An Image is Worth 16x16 Words, What is a Video Worth?"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2103.13915."}