{"as_of":"2026-08-13T21:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:19f814f0a4105d61f1d02ac3bb81acf0b35e230062b4793593a326070dca46e9","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T18:56:47.992851Z","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":"2026-07-10T06:15:00.866473Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2004.06165","last_updated":"2020-07-26T00:46:46Z","snapshot_observed_at":"2026-08-09T03:42:28.505858Z","submitted_at":"2020-04-13T19:18:10Z","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.06165","snapshot_observed_at":"2026-08-12T18:56:47.992851Z","title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.11162","last_updated":"2024-11-17T19:45:26Z","snapshot_observed_at":"2026-08-12T18:48:55.100601Z","submitted_at":"2024-11-17T19:45:26Z","title":"RPN 2: On Interdependence Function Learning Towards Unifying and Advancing CNN, RNN, GNN, and Transformer","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T18:56:47.992851Z"},"links":{"cited_paper":"/paper/2004.06165","citing_paper":"/paper/2411.11162"},"observation_digest":"sha256:49a82cb5d2a59d168df143a0268b8544e18ac5228e18f5648683babfee0f4d76","observation_id":"5d658a5c-0910-4615-b36b-41f0d42c5839","resolution":{"observed_at":"2026-08-12T18:56:47.992851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.06165","last_updated":"2020-07-26T00:46:46Z","snapshot_observed_at":"2026-08-09T03:42:28.505858Z","submitted_at":"2020-04-13T19:18:10Z","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.06165","snapshot_observed_at":"2026-08-11T00:47:52.434115Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.19289","last_updated":"2025-01-24T16:16:52Z","snapshot_observed_at":"2026-08-13T07:02:32.543601Z","submitted_at":"2024-12-26T17:29:38Z","title":"ViPCap: Retrieval Text-Based Visual Prompts for Lightweight Image Captioning","version":3},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T00:47:52.434115Z"},"links":{"cited_paper":"/paper/2004.06165","citing_paper":"/paper/2412.19289"},"observation_digest":"sha256:2de82a6a5cb2ff82cdcbfc5aed54fd544f2ce4f54052ccc82337e78738f98a3f","observation_id":"fd13970e-17f6-4ac2-becd-daad3b68fff5","resolution":{"observed_at":"2026-08-11T00:47:52.434115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.06165","last_updated":"2020-07-26T00:46:46Z","snapshot_observed_at":"2026-08-09T03:42:28.505858Z","submitted_at":"2020-04-13T19:18:10Z","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","version":5},"cited_work":{"arxiv_id":"2004.06165","doi":"10.48550/arxiv.2004.06165","metadata_source":"arxiv_reference","pith_arxiv_id":"2004.06165","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":null,"venue":null,"work_id":"0e7beb92-91f2-4776-858d-82c7e0ca0743","year":2004},"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":56,"source":"pdf_text","source_observed_at":"2026-05-19T00:34:38.247099Z"},"links":{"cited_paper":"/paper/2004.06165","citing_paper":"/paper/2508.04427"},"observation_digest":"sha256:9074cb5559d1fc168aea424a1032874fcb57dbdbb57b205d42b5c8143909788c","observation_id":"0fa7c831-e022-4d76-9742-1d940667893e","resolution":{"observed_at":"2026-05-19T00:36:55.776764Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.06165","last_updated":"2020-07-26T00:46:46Z","snapshot_observed_at":"2026-08-09T03:42:28.505858Z","submitted_at":"2020-04-13T19:18:10Z","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.06165","snapshot_observed_at":"2026-08-06T00:02:58.745662Z","title":null,"venue":null,"work_id":null,"year":2004},"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":56,"source":"pdf_text","source_observed_at":"2026-08-06T00:02:58.745662Z"},"links":{"cited_paper":"/paper/2004.06165","citing_paper":"/paper/2508.04427"},"observation_digest":"sha256:84cacbabf9021da9169d3c7e89ea112202d2d9c1511b956a29626491fb23ede0","observation_id":"409c1e76-26e8-4e71-a914-790edc1896c8","resolution":{"observed_at":"2026-08-06T00:02:58.745662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2004.06165/citation-record","integrity":"/paper/2004.06165/integrity","json":"/paper/2004.06165/citation-record.json","paper":"/paper/2004.06165"},"outbound":[],"paper":{"arxiv_id":"2004.06165","last_updated":"2020-07-26T00:46:46Z","latest_version":5,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T03:42:28.505858Z","submitted_at":"2020-04-13T19:18:10Z","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2004.06165."}