{"as_of":"2026-08-21T15:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:31af97c802ce06c5affef2ad2ce2b8847b26f8f8515db9b9b5cc02f30b72febe","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T11:06:36.059077Z","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":"2026-05-19T00:36:56.324269Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.10504","last_updated":"2022-08-07T18:27:10Z","snapshot_observed_at":"2026-08-17T18:24:03.491526Z","submitted_at":"2021-09-22T03:38:05Z","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.10504","snapshot_observed_at":"2026-08-12T11:06:36.059077Z","title":"Kd-vlp: Improving end-to- end vision-and-language pretraining with object knowledge distillation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18674","last_updated":"2025-05-05T14:25:01Z","snapshot_observed_at":"2026-08-19T03:42:02.536774Z","submitted_at":"2024-11-27T18:50:15Z","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","version":2},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:36.059077Z"},"links":{"cited_paper":"/paper/2109.10504","citing_paper":"/paper/2411.18674"},"observation_digest":"sha256:4c1057b78271f79ce0889398fdbd75291b50098290092ec4768608d06ce848bf","observation_id":"45789d01-37e4-4696-ae7e-f64b9af9074c","resolution":{"observed_at":"2026-08-12T11:06:36.059077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.10504","last_updated":"2022-08-07T18:27:10Z","snapshot_observed_at":"2026-08-17T18:24:03.491526Z","submitted_at":"2021-09-22T03:38:05Z","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","version":3},"cited_work":{"arxiv_id":"2109.10504","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2109.10504","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"9cd1dc3b-f3ff-4c4f-8f8d-ae51de1e5004","year":2021},"citing_paper":{"arxiv_id":"2508.04427","last_updated":"2026-06-11T09:27:03Z","snapshot_observed_at":"2026-08-09T05:23:29.071990Z","submitted_at":"2025-08-06T13:14:20Z","title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","version":1},"reference_index":119,"source":"pdf_text","source_observed_at":"2026-05-19T00:34:38.247099Z"},"links":{"cited_paper":"/paper/2109.10504","citing_paper":"/paper/2508.04427"},"observation_digest":"sha256:191a58b3c232351d3a2d126ff54394059b74ea3db7e2e422723401ae2a3fcfb7","observation_id":"83cb7de2-bd82-4d65-b660-f4e7f2be974b","resolution":{"observed_at":"2026-05-19T00:36:56.326213Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.10504","last_updated":"2022-08-07T18:27:10Z","snapshot_observed_at":"2026-08-17T18:24:03.491526Z","submitted_at":"2021-09-22T03:38:05Z","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.10504","snapshot_observed_at":"2026-08-06T00:02:59.004908Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.04427","last_updated":"2026-06-11T09:27:03Z","snapshot_observed_at":"2026-08-09T05:23:29.071990Z","submitted_at":"2025-08-06T13:14:20Z","title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","version":2},"reference_index":119,"source":"pdf_text","source_observed_at":"2026-08-06T00:02:59.004908Z"},"links":{"cited_paper":"/paper/2109.10504","citing_paper":"/paper/2508.04427"},"observation_digest":"sha256:509d4826ca70c0ccd30f63f0c7b55a5da7db8de7d959544b1294280dd5aab3e0","observation_id":"4d2c5b22-3784-4561-9ec2-0c30a0606397","resolution":{"observed_at":"2026-08-06T00:02:59.004908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2109.10504/citation-record","integrity":"/paper/2109.10504/integrity","json":"/paper/2109.10504/citation-record.json","paper":"/paper/2109.10504"},"outbound":[],"paper":{"arxiv_id":"2109.10504","last_updated":"2022-08-07T18:27:10Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T18:24:03.491526Z","submitted_at":"2021-09-22T03:38:05Z","title":"KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge Distillation"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2109.10504."}