{"as_of":"2026-08-17T13:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dc07252d84909aeb6fd36d510c4af61bbeeb9adc53e7574d53d041b81cb69100","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":"2026-08-17T06:30:58.91139+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":"2026-08-15T17:06:29.077558Z","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":"2026-05-25T12:16:56.513261Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1905.13648","last_updated":"2019-10-16T13:54:22Z","snapshot_observed_at":"2026-08-17T00:23:32.637504Z","submitted_at":"2019-05-31T14:47:55Z","title":"Scene Text Visual Question Answering","version":2},"cited_work":{"arxiv_id":"1905.13648","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1905.13648","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scene text visual question answering","venue":null,"work_id":"aad1a604-a6c8-4057-bd19-102e613fadb0","year":1905},"citing_paper":{"arxiv_id":"1907.00490","last_updated":"2019-06-30T22:46:11Z","snapshot_observed_at":"2026-08-03T04:51:19.980926Z","submitted_at":"2019-06-30T22:46:11Z","title":"ICDAR 2019 Competition on Scene Text Visual Question Answering","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-25T12:16:41.394335Z"},"links":{"cited_paper":"/paper/1905.13648","citing_paper":"/paper/1907.00490"},"observation_digest":"sha256:08cbdef7e955f3bd538697be7a4f81c80c3d7cf3af812a19e9416897cd5ddf6b","observation_id":"c8ed824c-c1b0-470b-a0a1-810d178d7dbe","resolution":{"observed_at":"2026-05-25T12:16:56.516651Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.13648","last_updated":"2019-10-16T13:54:22Z","snapshot_observed_at":"2026-08-17T00:23:32.637504Z","submitted_at":"2019-05-31T14:47:55Z","title":"Scene Text Visual Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.13648","snapshot_observed_at":"2026-08-12T18:54:49.933920Z","title":"Scene text visual question answering","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2411.11150","last_updated":"2024-11-17T18:52:06Z","snapshot_observed_at":"2026-08-16T11:06:30.381534Z","submitted_at":"2024-11-17T18:52:06Z","title":"A Comprehensive Survey on Visual Question Answering Datasets and Algorithms","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T18:54:49.933920Z"},"links":{"cited_paper":"/paper/1905.13648","citing_paper":"/paper/2411.11150"},"observation_digest":"sha256:1a88f1b395ed21be3dc44adc7ccc54b680c81b5a5604bd6570b6895d99b31caa","observation_id":"9142685d-a9df-49fc-b598-ae2295345612","resolution":{"observed_at":"2026-08-12T18:54:49.933920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.13648","last_updated":"2019-10-16T13:54:22Z","snapshot_observed_at":"2026-08-17T00:23:32.637504Z","submitted_at":"2019-05-31T14:47:55Z","title":"Scene Text Visual Question Answering","version":2},"cited_work":{"arxiv_id":"1905.13648","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1905.13648","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Scene text visual question answering","venue":null,"work_id":"aad1a604-a6c8-4057-bd19-102e613fadb0","year":1905},"citing_paper":{"arxiv_id":"2504.09925","last_updated":"2026-04-29T06:12:36Z","snapshot_observed_at":"2026-08-16T10:58:08.667292Z","submitted_at":"2025-04-14T06:33:29Z","title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-22T19:49:00.961388Z"},"links":{"cited_paper":"/paper/1905.13648","citing_paper":"/paper/2504.09925"},"observation_digest":"sha256:24c2f4c1338ec73b87c24a090a3bd720179017e5560818453137c088882c3bab","observation_id":"0f11cd6c-b670-47e5-ad24-9542d0d97fa0","resolution":{"observed_at":"2026-05-22T19:52:01.826761Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.13648","last_updated":"2019-10-16T13:54:22Z","snapshot_observed_at":"2026-08-17T00:23:32.637504Z","submitted_at":"2019-05-31T14:47:55Z","title":"Scene Text Visual Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.13648","snapshot_observed_at":"2026-08-15T17:06:29.077558Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.17398","last_updated":"2025-08-24T15:11:44Z","snapshot_observed_at":"2026-08-15T22:38:21.862876Z","submitted_at":"2025-08-24T15:11:44Z","title":"DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T17:06:29.077558Z"},"links":{"cited_paper":"/paper/1905.13648","citing_paper":"/paper/2508.17398"},"observation_digest":"sha256:bc0fa427e5da5abb3db86c9f86b20dba03636caab8ca1fcfd90ded6af048e45c","observation_id":"8fd2e405-9f03-490a-8ed5-6fecb2976baf","resolution":{"observed_at":"2026-08-15T17:06:29.077558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1905.13648/citation-record","integrity":"/paper/1905.13648/integrity","json":"/paper/1905.13648/citation-record.json","paper":"/paper/1905.13648"},"outbound":[],"paper":{"arxiv_id":"1905.13648","last_updated":"2019-10-16T13:54:22Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T00:23:32.637504Z","submitted_at":"2019-05-31T14:47:55Z","title":"Scene Text Visual Question Answering"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1905.13648."}