{"as_of":"2026-08-09T23:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c61a5002797afc88df642e4ee7d14753fec1a1d38661aad378d9caea12014aa1","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T10:33:57.108940Z","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":"2026-05-10T06:46:37.494820Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.14232","last_updated":"2024-02-01T13:06:51Z","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:46:46Z","title":"Parrot Captions Teach CLIP to Spot Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.14232","snapshot_observed_at":"2026-08-07T10:33:57.108940Z","title":"J., Wang, B., Li, W., and Shou, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04999","last_updated":"2025-06-05T13:10:17Z","snapshot_observed_at":"2026-08-07T10:26:27.509847Z","submitted_at":"2025-06-05T13:10:17Z","title":"Beyond Cropped Regions: New Benchmark and Corresponding Baseline for Chinese Scene Text Retrieval in Diverse Layouts","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T10:33:57.108940Z"},"links":{"cited_paper":"/paper/2312.14232","citing_paper":"/paper/2506.04999"},"observation_digest":"sha256:6abb90308cc41ab32d6629a3b2bd1cfb0e01924e5d3e7bbb6609105bef8f912d","observation_id":"9bd96913-088a-4be8-9437-307444e8fa51","resolution":{"observed_at":"2026-08-07T10:33:57.108940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14232","last_updated":"2024-02-01T13:06:51Z","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:46:46Z","title":"Parrot Captions Teach CLIP to Spot Text","version":3},"cited_work":{"arxiv_id":"2312.14232","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.14232","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5f4a49cc-c09a-41ea-9e38-1fc22012f638","year":2024},"citing_paper":{"arxiv_id":"2604.17375","last_updated":"2026-04-19T10:58:40Z","snapshot_observed_at":"2026-08-02T21:21:44.410489Z","submitted_at":"2026-04-19T10:58:40Z","title":"When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-10T06:41:59.641410Z"},"links":{"cited_paper":"/paper/2312.14232","citing_paper":"/paper/2604.17375"},"observation_digest":"sha256:0c29713ccf1f78aa39919f64582e239d162b98b00297e311142f49f2d7e80569","observation_id":"1251cb99-aa1f-4266-ac86-01c70b75a703","resolution":{"observed_at":"2026-05-10T06:46:37.496024Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2312.14232/citation-record","integrity":"/paper/2312.14232/integrity","json":"/paper/2312.14232/citation-record.json","paper":"/paper/2312.14232"},"outbound":[],"paper":{"arxiv_id":"2312.14232","last_updated":"2024-02-01T13:06:51Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:46:46Z","title":"Parrot Captions Teach CLIP to Spot Text"},"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 2 inbound Pith citation observations for arXiv:2312.14232."}