{"as_of":"2026-08-12T11:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:aecaae8b759a2eeec7eeb415a74cd9c4911a8dd4879d77e4c77e61abb49b8fd2","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":"2026-08-12T06:34:41.77262+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":"2026-08-06T05:56:41.159898Z","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":"2026-08-06T05:56:41.326008Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.14014","last_updated":"2024-12-24T04:27:37Z","snapshot_observed_at":"2026-07-06T15:31:23.076745Z","submitted_at":"2023-05-23T12:51:20Z","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","version":4},"cited_work":{"arxiv_id":"2305.14014","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.14014","snapshot_observed_at":"2026-08-06T05:56:41.326008Z","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","venue":"cs.CV","work_id":"bed28817-269f-4a10-a04e-61032793aa13","year":2023},"citing_paper":{"arxiv_id":"2508.01153","last_updated":"2025-08-02T02:28:09Z","snapshot_observed_at":"2026-08-08T09:50:24.385644Z","submitted_at":"2025-08-02T02:28:09Z","title":"TEACH: Text Encoding as Curriculum Hints for Scene Text Recognition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T05:56:41.159898Z"},"links":{"cited_paper":"/paper/2305.14014","citing_paper":"/paper/2508.01153"},"observation_digest":"sha256:b492f95faffa002cb14b6a317337e287d737a7f26c08167f74f8805c23c2715a","observation_id":"3cfee4c0-c6bb-4305-b7ef-1bc7fcb16e67","resolution":{"observed_at":"2026-08-06T05:56:41.329345Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14014","last_updated":"2024-12-24T04:27:37Z","snapshot_observed_at":"2026-07-06T15:31:23.076745Z","submitted_at":"2023-05-23T12:51:20Z","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14014","snapshot_observed_at":"2026-07-13T05:58:43.042797Z","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.08896","last_updated":"2026-07-09T19:36:57Z","snapshot_observed_at":"2026-08-06T04:49:11.626197Z","submitted_at":"2026-07-09T19:36:57Z","title":"HAT Super-Resolution and a PARSeq+CLIP4STR Voting Ensemble for Extreme In-the-Wild License Plate Recognition","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-13T05:58:43.042797Z"},"links":{"cited_paper":"/paper/2305.14014","citing_paper":"/paper/2607.08896"},"observation_digest":"sha256:391c83cf1251b9fa55b15bc315b18487655ac832fa47678b0710120c4e3d3827","observation_id":"512aa118-4c3b-4bb9-926b-fdb0ed05ef79","resolution":{"observed_at":"2026-07-13T05:58:43.042797Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2305.14014/citation-record","integrity":"/paper/2305.14014/integrity","json":"/paper/2305.14014/citation-record.json","paper":"/paper/2305.14014"},"outbound":[],"paper":{"arxiv_id":"2305.14014","last_updated":"2024-12-24T04:27:37Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:31:23.076745Z","submitted_at":"2023-05-23T12:51:20Z","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2305.14014."}