{"as_of":"2026-08-08T11:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7a1129a5901ec19baef804f89c1d8a5233f7e2129a47c3dc141a67060e1fe9c4","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:26:13.739653Z","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":"2026-06-29T13:23:28.470664Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.08614","last_updated":"2025-03-26T06:10:20Z","snapshot_observed_at":"2026-08-02T11:55:01.072868Z","submitted_at":"2024-12-11T18:37:42Z","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.08614","snapshot_observed_at":"2026-08-07T15:26:13.739653Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15172","last_updated":"2025-05-21T06:42:17Z","snapshot_observed_at":"2026-08-07T15:20:37.318165Z","submitted_at":"2025-05-21T06:42:17Z","title":"Harnessing Caption Detailness for Data-Efficient Text-to-Image Generation","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T15:26:13.739653Z"},"links":{"cited_paper":"/paper/2412.08614","citing_paper":"/paper/2505.15172"},"observation_digest":"sha256:764f68e9a0529ac3e71f1836b1bc2c451f8f4fdb5ce5753870530c5c61b9c326","observation_id":"d044ec13-7184-4972-a7ea-39a5ebb7ebea","resolution":{"observed_at":"2026-08-07T15:26:13.739653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08614","last_updated":"2025-03-26T06:10:20Z","snapshot_observed_at":"2026-08-02T11:55:01.072868Z","submitted_at":"2024-12-11T18:37:42Z","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.08614","snapshot_observed_at":"2026-08-07T13:08:05.395780Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22613","last_updated":"2025-05-28T17:29:34Z","snapshot_observed_at":"2026-08-07T13:00:45.454980Z","submitted_at":"2025-05-28T17:29:34Z","title":"RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T13:08:05.395780Z"},"links":{"cited_paper":"/paper/2412.08614","citing_paper":"/paper/2505.22613"},"observation_digest":"sha256:12872458e13b5f8424d36777bd4b0bc34662faf60a36ff67ab78f09d0d143fbd","observation_id":"050d1fec-5a17-4cbb-a3dd-6661b90d05d4","resolution":{"observed_at":"2026-08-07T13:08:05.395780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08614","last_updated":"2025-03-26T06:10:20Z","snapshot_observed_at":"2026-08-02T11:55:01.072868Z","submitted_at":"2024-12-11T18:37:42Z","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning","version":3},"cited_work":{"arxiv_id":"2412.08614","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.08614","snapshot_observed_at":"2026-06-29T13:23:28.470664Z","title":"Benchmarking large vision-language models via directed scene graph for comprehensive image captioning.ArXiv preprint, abs/2412.08614, 2024","venue":null,"work_id":"7c2e5c8c-4076-4373-9055-82dd06aa7af8","year":2024},"citing_paper":{"arxiv_id":"2605.28023","last_updated":"2026-05-27T06:27:04Z","snapshot_observed_at":"2026-08-02T21:20:31.316522Z","submitted_at":"2026-05-27T06:27:04Z","title":"VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-29T13:13:57.599970Z"},"links":{"cited_paper":"/paper/2412.08614","citing_paper":"/paper/2605.28023"},"observation_digest":"sha256:f9c6faba3c8d6e2d54a341c5fc0d6a46f5c53f2b433e49cd3d87ac113f7b0ce9","observation_id":"97d20f53-4d32-4f37-b8a1-ff70a14b00e7","resolution":{"observed_at":"2026-06-29T13:23:28.472112Z","resolver_source":"arxiv_id","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/2412.08614/citation-record","integrity":"/paper/2412.08614/integrity","json":"/paper/2412.08614/citation-record.json","paper":"/paper/2412.08614"},"outbound":[],"paper":{"arxiv_id":"2412.08614","last_updated":"2025-03-26T06:10:20Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T11:55:01.072868Z","submitted_at":"2024-12-11T18:37:42Z","title":"Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning"},"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 3 inbound Pith citation observations for arXiv:2412.08614."}