{"as_of":"2026-08-09T09:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:17fd4d7e24d32c48c3d7a3f7ad0d050cc04474a21c86fe36c41a4de27d1a5761","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T05:26:16.561169Z","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":"2026-07-04T04:29:35.618998Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.09167","last_updated":"2025-01-15T21:36:19Z","snapshot_observed_at":"2026-08-01T14:14:10.437004Z","submitted_at":"2025-01-15T21:36:19Z","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09167","snapshot_observed_at":"2026-08-07T05:26:16.561169Z","title":"Embodied scene understanding for vision language models via metavqa.arXiv preprint arXiv:2501.09167, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.08006","last_updated":"2025-06-09T17:59:52Z","snapshot_observed_at":"2026-08-07T20:46:06.872501Z","submitted_at":"2025-06-09T17:59:52Z","title":"Dreamland: Controllable World Creation with Simulator and Generative Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T05:26:16.561169Z"},"links":{"cited_paper":"/paper/2501.09167","citing_paper":"/paper/2506.08006"},"observation_digest":"sha256:cade638fe01e1fc46fe4d9477497827628f592c4967c78603507404e50e8ff0d","observation_id":"6540e05e-b877-4a08-8c87-cb52f2737317","resolution":{"observed_at":"2026-08-07T05:26:16.561169Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09167","last_updated":"2025-01-15T21:36:19Z","snapshot_observed_at":"2026-08-01T14:14:10.437004Z","submitted_at":"2025-01-15T21:36:19Z","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA","version":1},"cited_work":{"arxiv_id":"2501.09167","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.09167","snapshot_observed_at":"2026-07-04T04:29:35.618998Z","title":"Embodied scene understand- ing for vision language models via metavqa.arXiv preprint arXiv:2501.09167, 2025","venue":null,"work_id":"6552623f-09a7-4971-b6ad-07d9f14da03e","year":2025},"citing_paper":{"arxiv_id":"2606.20905","last_updated":"2026-06-18T20:01:32Z","snapshot_observed_at":"2026-08-03T03:13:19.923134Z","submitted_at":"2026-06-18T20:01:32Z","title":"Vesta: A Generalist Embodied Reasoning Model","version":1},"reference_index":125,"source":"pdf_text","source_observed_at":"2026-06-26T16:55:12.518255Z"},"links":{"cited_paper":"/paper/2501.09167","citing_paper":"/paper/2606.20905"},"observation_digest":"sha256:f8f8e5488e4b69e7451acaa7cb0ba51454f67a64ec4ee2b586ba0a62683973d9","observation_id":"5d27a2dc-8b8b-44a5-a981-d70e7e2e29f2","resolution":{"observed_at":"2026-07-04T04:29:35.620749Z","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":"2501.09167","last_updated":"2025-01-15T21:36:19Z","snapshot_observed_at":"2026-08-01T14:14:10.437004Z","submitted_at":"2025-01-15T21:36:19Z","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09167","snapshot_observed_at":"2026-08-01T07:02:52.563375Z","title":"arXiv preprint arXiv:2501.09167 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21594","last_updated":"2026-07-23T17:59:58Z","snapshot_observed_at":"2026-08-07T01:32:12.278950Z","submitted_at":"2026-07-23T17:59:58Z","title":"Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers","version":1},"reference_index":143,"source":"arxiv_source","source_observed_at":"2026-08-01T07:02:52.563375Z"},"links":{"cited_paper":"/paper/2501.09167","citing_paper":"/paper/2607.21594"},"observation_digest":"sha256:c4afa81acbb94549416822dceddfa39d9f9acf795e9eef5538edfa27fde4ceb3","observation_id":"fd61dd70-9e2c-45f7-ae68-c961c5ad0e27","resolution":{"observed_at":"2026-08-01T07:02:52.563375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.09167/citation-record","integrity":"/paper/2501.09167/integrity","json":"/paper/2501.09167/citation-record.json","paper":"/paper/2501.09167"},"outbound":[],"paper":{"arxiv_id":"2501.09167","last_updated":"2025-01-15T21:36:19Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-01T14:14:10.437004Z","submitted_at":"2025-01-15T21:36:19Z","title":"Embodied Scene Understanding for Vision Language Models via MetaVQA"},"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 3 inbound Pith citation observations for arXiv:2501.09167."}