{"as_of":"2026-08-09T02:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:276c1a70a54a853c337344cc5377500e9e81153b76bf3fd2458359065c99a628","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":"2026-08-08T06:32:00.761636+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":"2026-08-03T16:30:36.563313Z","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":"2026-07-04T08:19:43.747592Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.10804","last_updated":"2021-01-28T04:38:38Z","snapshot_observed_at":"2026-07-06T10:35:42.899065Z","submitted_at":"2021-01-26T14:29:52Z","title":"CPTR: Full Transformer Network for Image Captioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.10804","snapshot_observed_at":"2026-08-03T16:30:36.563313Z","title":"Cptr: Full transformer network for image captioning.arXiv preprint arXiv:2101.10804,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.13517","last_updated":"2026-05-28T15:09:34Z","snapshot_observed_at":"2026-08-06T09:36:40.415132Z","submitted_at":"2025-12-15T16:43:50Z","title":"A Deep Learning Model of Mental Rotation Informed by Interactive VR Experiments","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-03T16:30:36.563313Z"},"links":{"cited_paper":"/paper/2101.10804","citing_paper":"/paper/2512.13517"},"observation_digest":"sha256:f6b40abc64cb92fdd92a88e79af964f49a5f568622ef8a7ed4798dc4bca847d3","observation_id":"28f2fe28-7bcd-4702-89ad-5cde9496137c","resolution":{"observed_at":"2026-08-03T16:30:36.563313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.10804","last_updated":"2021-01-28T04:38:38Z","snapshot_observed_at":"2026-07-06T10:35:42.899065Z","submitted_at":"2021-01-26T14:29:52Z","title":"CPTR: Full Transformer Network for Image Captioning","version":3},"cited_work":{"arxiv_id":"2101.10804","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.10804","snapshot_observed_at":"2026-07-04T08:19:43.747592Z","title":"Cptr: Full transformer network for image captioning","venue":null,"work_id":"ad64c3a0-768f-4a10-af3e-0963c40f8c86","year":2021},"citing_paper":{"arxiv_id":"2606.22220","last_updated":"2026-06-23T14:03:33Z","snapshot_observed_at":"2026-08-03T12:18:51.021917Z","submitted_at":"2026-06-20T20:46:36Z","title":"MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-26T11:59:16.070464Z"},"links":{"cited_paper":"/paper/2101.10804","citing_paper":"/paper/2606.22220"},"observation_digest":"sha256:d0c074e2ade4558de2a386f3f9f88500acd2d43ff99093f7aa24bba8c6a0c0f0","observation_id":"2c6ade06-9ccd-4000-aaa6-b5c000e5c58b","resolution":{"observed_at":"2026-07-04T08:19:43.749040Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2101.10804/citation-record","integrity":"/paper/2101.10804/integrity","json":"/paper/2101.10804/citation-record.json","paper":"/paper/2101.10804"},"outbound":[],"paper":{"arxiv_id":"2101.10804","last_updated":"2021-01-28T04:38:38Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T10:35:42.899065Z","submitted_at":"2021-01-26T14:29:52Z","title":"CPTR: Full Transformer Network for Image Captioning"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2101.10804."}