{"as_of":"2026-08-08T10:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0c6723035c3d9f3d39ed8d502fd1cc875b861309ff07f517be015cc632f99593","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:52:40.597487Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T14:33:47.014699Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1603.02814","last_updated":"2016-12-16T11:44:34Z","snapshot_observed_at":"2026-07-06T04:48:52.708353Z","submitted_at":"2016-03-09T08:56:45Z","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.02814","snapshot_observed_at":"2026-08-07T12:52:40.597487Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.23358","last_updated":"2025-05-29T11:33:36Z","snapshot_observed_at":"2026-08-08T02:12:28.249955Z","submitted_at":"2025-05-29T11:33:36Z","title":"Beam-Guided Knowledge Replay for Knowledge-Rich Image Captioning using Vision-Language Model","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:52:40.597487Z"},"links":{"cited_paper":"/paper/1603.02814","citing_paper":"/paper/2505.23358"},"observation_digest":"sha256:c0c91af30b192ba6f6ff0a8675df257c2444d1aba08097414b9052a9f944d0e3","observation_id":"62d4644b-8acb-453a-ba90-f045a5abbfc8","resolution":{"observed_at":"2026-08-07T12:52:40.597487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1603.02814","last_updated":"2016-12-16T11:44:34Z","snapshot_observed_at":"2026-07-06T04:48:52.708353Z","submitted_at":"2016-03-09T08:56:45Z","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","version":2},"cited_work":{"arxiv_id":"1603.02814","doi":null,"metadata_source":"pith","pith_arxiv_id":"1603.02814","snapshot_observed_at":"2026-08-06T14:33:47.014699Z","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge","venue":"cs.CV","work_id":"b1b91888-009b-48f7-8602-275374e2f04e","year":2016},"citing_paper":{"arxiv_id":"2507.22933","last_updated":"2025-07-24T16:27:38Z","snapshot_observed_at":"2026-08-07T10:18:49.594691Z","submitted_at":"2025-07-24T16:27:38Z","title":"Augmented Vision-Language Models: A Systematic Review","version":1},"reference_index":117,"source":"pdf_text","source_observed_at":"2026-08-06T14:33:43.052160Z"},"links":{"cited_paper":"/paper/1603.02814","citing_paper":"/paper/2507.22933"},"observation_digest":"sha256:dc84d652052e265c43241b77582cf9d061885d5f07286105d5ae1a5b734e352f","observation_id":"aa325fe5-85be-4e88-990f-e398715f0761","resolution":{"observed_at":"2026-08-06T14:33:47.085235Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1603.02814/citation-record","integrity":"/paper/1603.02814/integrity","json":"/paper/1603.02814/citation-record.json","paper":"/paper/1603.02814"},"outbound":[],"paper":{"arxiv_id":"1603.02814","last_updated":"2016-12-16T11:44:34Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T04:48:52.708353Z","submitted_at":"2016-03-09T08:56:45Z","title":"Image Captioning and Visual Question Answering Based on Attributes and External Knowledge"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:1603.02814."}