{"as_of":"2026-08-16T11:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:692050ea3df30febaea92d2e932c8176a6c4a65de07041fa35894b9bb7b415a7","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":"2026-08-16T06:30:59.297886+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":"2026-08-16T00:09:18.957380Z","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":"2026-07-04T06:29:37.645431Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.13898","last_updated":"2025-06-25T23:11:51Z","snapshot_observed_at":"2026-08-12T20:29:42.338670Z","submitted_at":"2025-02-19T17:31:59Z","title":"GroundCap: A Visually Grounded Image Captioning Dataset","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13898","snapshot_observed_at":"2026-08-15T21:15:57.744826Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.10292","last_updated":"2025-08-30T14:31:15Z","snapshot_observed_at":"2026-08-15T21:09:56.037181Z","submitted_at":"2025-05-15T13:42:14Z","title":"StoryReasoning Dataset: Using Chain-of-Thought for Scene Understanding and Grounded Story Generation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T21:15:57.744826Z"},"links":{"cited_paper":"/paper/2502.13898","citing_paper":"/paper/2505.10292"},"observation_digest":"sha256:1606d1061dd7554d2793ff6f3e1d60eb3d1b0f9dca91ba6c9268553ec76bdbbf","observation_id":"2da9c6f4-782b-4e4f-850a-0261185c6c9b","resolution":{"observed_at":"2026-08-15T21:15:57.744826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13898","last_updated":"2025-06-25T23:11:51Z","snapshot_observed_at":"2026-08-12T20:29:42.338670Z","submitted_at":"2025-02-19T17:31:59Z","title":"GroundCap: A Visually Grounded Image Captioning Dataset","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13898","snapshot_observed_at":"2026-08-06T18:49:49.705978Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07340","last_updated":"2025-07-11T00:58:38Z","snapshot_observed_at":"2026-08-12T20:30:13.499042Z","submitted_at":"2025-07-09T23:52:10Z","title":"Entity Re-identification in Visual Storytelling via Contrastive Reinforcement Learning","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T18:49:49.705978Z"},"links":{"cited_paper":"/paper/2502.13898","citing_paper":"/paper/2507.07340"},"observation_digest":"sha256:bc0607895fb7e52809c97b528e727c771ce30b00295422a846d643b21674997c","observation_id":"36bf99ab-258d-438d-848f-0776559749d0","resolution":{"observed_at":"2026-08-06T18:49:49.705978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13898","last_updated":"2025-06-25T23:11:51Z","snapshot_observed_at":"2026-08-12T20:29:42.338670Z","submitted_at":"2025-02-19T17:31:59Z","title":"GroundCap: A Visually Grounded Image Captioning Dataset","version":3},"cited_work":{"arxiv_id":"2502.13898","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.13898","snapshot_observed_at":"2026-07-04T06:29:37.645431Z","title":null,"venue":null,"work_id":"3f0c3722-e800-4c65-b89e-2c441e33d9b3","year":2025},"citing_paper":{"arxiv_id":"2606.21419","last_updated":"2026-06-19T13:39:09Z","snapshot_observed_at":"2026-08-14T21:17:30.836151Z","submitted_at":"2026-06-19T13:39:09Z","title":"MIRCaps: A Large-Scale Mixed-Domain Dataset with Image-Level and Region-Level Captions for Fine-Grained Vision-Language Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-26T14:26:21.304670Z"},"links":{"cited_paper":"/paper/2502.13898","citing_paper":"/paper/2606.21419"},"observation_digest":"sha256:e4a421c0bea6e3d73968a44bc74a9bed63418a11cf4264ec3c7cbe5a9b19349a","observation_id":"7bce3e2f-2452-4a1e-a436-cd2504839dc0","resolution":{"observed_at":"2026-07-04T06:29:37.646931Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13898","last_updated":"2025-06-25T23:11:51Z","snapshot_observed_at":"2026-08-12T20:29:42.338670Z","submitted_at":"2025-02-19T17:31:59Z","title":"GroundCap: A Visually Grounded Image Captioning Dataset","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13898","snapshot_observed_at":"2026-08-16T00:09:18.957380Z","title":"arXiv preprint arXiv:2502.13898 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.12748","last_updated":"2026-08-13T02:57:21Z","snapshot_observed_at":"2026-08-16T11:10:45.197621Z","submitted_at":"2026-08-13T02:57:21Z","title":"Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding","version":1},"reference_index":237,"source":"arxiv_source","source_observed_at":"2026-08-16T00:09:18.957380Z"},"links":{"cited_paper":"/paper/2502.13898","citing_paper":"/paper/2608.12748"},"observation_digest":"sha256:39b6ecfcc208f26eeecc4e322cd62719c9bcfe9bce684117ca8ac5cab25c7693","observation_id":"5b6fd212-55fe-4588-9332-2344f95dbfbd","resolution":{"observed_at":"2026-08-16T00:09:18.957380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.13898/citation-record","integrity":"/paper/2502.13898/integrity","json":"/paper/2502.13898/citation-record.json","paper":"/paper/2502.13898"},"outbound":[],"paper":{"arxiv_id":"2502.13898","last_updated":"2025-06-25T23:11:51Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T20:29:42.338670Z","submitted_at":"2025-02-19T17:31:59Z","title":"GroundCap: A Visually Grounded Image Captioning Dataset"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2502.13898."}