{"as_of":"2026-08-05T15:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2b1dfde8b1f0e99e1be88f1721521e4be2264140261848933c435ba263c18b61","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":"2026-08-05T06:32:48.257954+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":"2026-08-05T10:38:58.256253Z","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":"2026-07-02T11:56:54.989176Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.07906","last_updated":"2025-03-10T22:53:56Z","snapshot_observed_at":"2026-08-02T08:11:43.444133Z","submitted_at":"2025-03-10T22:53:56Z","title":"Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.07906","snapshot_observed_at":"2026-08-05T10:38:58.256253Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.03897","last_updated":"2025-09-12T05:44:35Z","snapshot_observed_at":"2026-08-05T10:38:53.771044Z","submitted_at":"2025-09-04T05:43:50Z","title":"SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluation","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-05T10:38:58.256253Z"},"links":{"cited_paper":"/paper/2503.07906","citing_paper":"/paper/2509.03897"},"observation_digest":"sha256:9ed7c1a7953d6da3acd846b120444133410898610f982f30fa2abfc8fb80b3a0","observation_id":"5deb4d36-5ac4-40d0-87cb-2096d54b96b6","resolution":{"observed_at":"2026-08-05T10:38:58.256253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.07906","last_updated":"2025-03-10T22:53:56Z","snapshot_observed_at":"2026-08-02T08:11:43.444133Z","submitted_at":"2025-03-10T22:53:56Z","title":"Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning","version":1},"cited_work":{"arxiv_id":"2503.07906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.07906","snapshot_observed_at":"2026-07-02T11:56:54.989176Z","title":"Painting with words: Elevating detailed image caption- ing with benchmark and alignment learning","venue":null,"work_id":"b17e5726-aa6c-4e37-85d7-5e42fef7fc22","year":2025},"citing_paper":{"arxiv_id":"2511.21025","last_updated":"2026-04-15T22:38:59Z","snapshot_observed_at":"2026-08-02T04:56:59.957039Z","submitted_at":"2025-11-26T03:43:32Z","title":"CaptionQA: Is Your Caption as Useful as the Image Itself?","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-17T05:42:57.288054Z"},"links":{"cited_paper":"/paper/2503.07906","citing_paper":"/paper/2511.21025"},"observation_digest":"sha256:174f650dd7e9a7bf90bf9ad6aa86290fae3ba845eb39bb412bd1a7f40d187b08","observation_id":"3fb35811-dcba-4017-8ac1-e248b70aa750","resolution":{"observed_at":"2026-05-17T05:44:07.279739Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.07906","last_updated":"2025-03-10T22:53:56Z","snapshot_observed_at":"2026-08-02T08:11:43.444133Z","submitted_at":"2025-03-10T22:53:56Z","title":"Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning","version":1},"cited_work":{"arxiv_id":"2503.07906","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.07906","snapshot_observed_at":"2026-07-02T11:56:54.989176Z","title":"Painting with words: Elevating detailed image caption- ing with benchmark and alignment learning","venue":null,"work_id":"b17e5726-aa6c-4e37-85d7-5e42fef7fc22","year":2025},"citing_paper":{"arxiv_id":"2607.00361","last_updated":"2026-07-01T02:59:59Z","snapshot_observed_at":"2026-08-01T11:21:56.371479Z","submitted_at":"2026-07-01T02:59:59Z","title":"ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-02T11:48:35.972372Z"},"links":{"cited_paper":"/paper/2503.07906","citing_paper":"/paper/2607.00361"},"observation_digest":"sha256:f61573098ea807f6b964ea4727e53fd45d26d7069ba43133371cb5fc78406cbe","observation_id":"14f60d05-5766-407e-98c3-79e44f32ebba","resolution":{"observed_at":"2026-07-02T11:56:54.990915Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.07906/citation-record","integrity":"/paper/2503.07906/integrity","json":"/paper/2503.07906/citation-record.json","paper":"/paper/2503.07906"},"outbound":[],"paper":{"arxiv_id":"2503.07906","last_updated":"2025-03-10T22:53:56Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T08:11:43.444133Z","submitted_at":"2025-03-10T22:53:56Z","title":"Painting with Words: Elevating Detailed Image Captioning with Benchmark and Alignment Learning"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.07906."}