{"as_of":"2026-08-15T15:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bfe4d23b0d831349bfc5bae3e8a014672c752eb13116d2cf484fe689e74afc9f","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":"2026-08-15T06:32:42.880941+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":"2026-08-11T20:23:34.396167Z","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":"2026-07-04T00:49:19.179579Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2205.01883","last_updated":"2022-05-04T04:09:23Z","snapshot_observed_at":"2026-08-13T15:50:26.868977Z","submitted_at":"2022-05-04T04:09:23Z","title":"All You May Need for VQA are Image Captions","version":1},"cited_work":{"arxiv_id":"2205.01883","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.01883","snapshot_observed_at":"2026-07-04T00:49:19.179579Z","title":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H","venue":null,"work_id":"9d6e4be6-a94f-464a-9061-a8e316ae711b","year":null},"citing_paper":{"arxiv_id":"2303.03378","last_updated":"2023-03-06T18:58:06Z","snapshot_observed_at":"2026-08-14T18:47:26.721223Z","submitted_at":"2023-03-06T18:58:06Z","title":"PaLM-E: An Embodied Multimodal Language Model","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T22:29:29.631351Z"},"links":{"cited_paper":"/paper/2205.01883","citing_paper":"/paper/2303.03378"},"observation_digest":"sha256:2b8413b84b7d8ad7dab39abc65ed68101f6365b55989255e2b6d0d82d195f605","observation_id":"811630a8-0bf9-44f0-8603-2461f295d179","resolution":{"observed_at":"2026-05-10T22:29:29.812541Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01883","last_updated":"2022-05-04T04:09:23Z","snapshot_observed_at":"2026-08-13T15:50:26.868977Z","submitted_at":"2022-05-04T04:09:23Z","title":"All You May Need for VQA are Image Captions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01883","snapshot_observed_at":"2026-08-11T20:23:34.396167Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05821","last_updated":"2024-12-10T17:42:49Z","snapshot_observed_at":"2026-08-14T19:35:59.801396Z","submitted_at":"2024-12-08T05:47:55Z","title":"An Entailment Tree Generation Approach for Multimodal Multi-Hop Question Answering with Mixture-of-Experts and Iterative Feedback Mechanism","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T20:23:34.396167Z"},"links":{"cited_paper":"/paper/2205.01883","citing_paper":"/paper/2412.05821"},"observation_digest":"sha256:64359d231f39115520689e253466bb611550879edc34bb69f3fe27aedc0e05a1","observation_id":"56c87514-cf0e-41a9-aeda-92431e604e32","resolution":{"observed_at":"2026-08-11T20:23:34.396167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.01883","last_updated":"2022-05-04T04:09:23Z","snapshot_observed_at":"2026-08-13T15:50:26.868977Z","submitted_at":"2022-05-04T04:09:23Z","title":"All You May Need for VQA are Image Captions","version":1},"cited_work":{"arxiv_id":"2205.01883","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2205.01883","snapshot_observed_at":"2026-07-04T00:49:19.179579Z","title":"Chen, M., Tworek, J., Jun, H., Yuan, Q., Pinto, H","venue":null,"work_id":"9d6e4be6-a94f-464a-9061-a8e316ae711b","year":null},"citing_paper":{"arxiv_id":"2606.19584","last_updated":"2026-06-17T20:39:04Z","snapshot_observed_at":"2026-08-09T11:39:14.249967Z","submitted_at":"2026-06-17T20:39:04Z","title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-26T20:54:48.203293Z"},"links":{"cited_paper":"/paper/2205.01883","citing_paper":"/paper/2606.19584"},"observation_digest":"sha256:a5c575d56db119c0cf9b00f025ae530c5a6a7ad9a25028db65f22f4798c3939c","observation_id":"f65f8726-a036-4254-9f67-75bccbe48d5f","resolution":{"observed_at":"2026-07-04T00:49:19.182325Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2205.01883/citation-record","integrity":"/paper/2205.01883/integrity","json":"/paper/2205.01883/citation-record.json","paper":"/paper/2205.01883"},"outbound":[],"paper":{"arxiv_id":"2205.01883","last_updated":"2022-05-04T04:09:23Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T15:50:26.868977Z","submitted_at":"2022-05-04T04:09:23Z","title":"All You May Need for VQA are Image Captions"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2205.01883."}