{"as_of":"2026-08-12T09:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cd0f979acee1bad2b81a93c5b3fc8e8da918e6c2d05ead84075ad465fabcc349","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":"2026-08-12T06:34:41.77262+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":"2026-08-10T22:44:42.374513Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":24,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2103.14899","last_updated":"2021-08-22T18:53:59Z","snapshot_observed_at":"2026-08-12T05:11:23.545190Z","submitted_at":"2021-03-27T13:03:17Z","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.14899","snapshot_observed_at":"2026-08-10T22:44:42.374513Z","title":"Crossvit: Cross attention multi- scale vision transformer for image classification,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.00935","last_updated":"2025-01-01T19:26:32Z","snapshot_observed_at":"2026-08-11T18:30:25.246196Z","submitted_at":"2025-01-01T19:26:32Z","title":"Multiscaled Multi-Head Attention-based Video Transformer Network for Hand Gesture Recognition","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T22:44:42.374513Z"},"links":{"cited_paper":"/paper/2103.14899","citing_paper":"/paper/2501.00935"},"observation_digest":"sha256:e8dab5a20099f44d421d2ece5d2b7004a2a19cb0b9e4bca8527d4c3192e7359b","observation_id":"cd7e5ee1-2f35-433d-ab50-f22063b446a8","resolution":{"observed_at":"2026-08-10T22:44:42.374513Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.14899","last_updated":"2021-08-22T18:53:59Z","snapshot_observed_at":"2026-08-12T05:11:23.545190Z","submitted_at":"2021-03-27T13:03:17Z","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","version":2},"cited_work":{"arxiv_id":"2103.14899","doi":"10.48550/arxiv.2103.14899","metadata_source":"arxiv_reference","pith_arxiv_id":"2103.14899","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ICCV 2021 , year =","venue":"arXiv (Cornell University)","work_id":"df1f2a77-86af-4491-9d73-1fde2e7d700d","year":2021},"citing_paper":{"arxiv_id":"2606.24790","last_updated":"2026-06-23T16:46:36Z","snapshot_observed_at":"2026-07-17T23:19:04.280621Z","submitted_at":"2026-06-23T16:46:36Z","title":"Grad Detect: Gradient-Based Hallucination Detection in LLMs","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-06-25T23:59:19.950066Z"},"links":{"cited_paper":"/paper/2103.14899","citing_paper":"/paper/2606.24790"},"observation_digest":"sha256:0010eae96b3e7c87866acd3cd3401b62ff99b5bc5af5cb8108f5b3ebd988a911","observation_id":"263eed06-21e5-4106-880b-70e2ce10e906","resolution":{"observed_at":"2026-06-26T00:08:43.186954Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2103.14899/citation-record","integrity":"/paper/2103.14899/integrity","json":"/paper/2103.14899/citation-record.json","paper":"/paper/2103.14899"},"outbound":[],"paper":{"arxiv_id":"2103.14899","last_updated":"2021-08-22T18:53:59Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T05:11:23.545190Z","submitted_at":"2021-03-27T13:03:17Z","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2103.14899."}