{"as_of":"2026-08-11T16:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e48b0c5862056aec28d1644b37e8dae1fd88d338dcad7d580e1be332c33e6ced","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":"2026-08-11T06:34:44.6726+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":"2026-08-10T22:33:45.160967Z","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":"2026-07-03T21:28:58.461251Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.02330","last_updated":"2024-03-04T18:58:08Z","snapshot_observed_at":"2026-08-04T19:14:19.335752Z","submitted_at":"2024-03-04T18:58:08Z","title":"RegionGPT: Towards Region Understanding Vision Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02330","snapshot_observed_at":"2026-08-10T22:33:45.160967Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.01377","last_updated":"2025-06-02T09:56:36Z","snapshot_observed_at":"2026-08-11T01:20:05.033313Z","submitted_at":"2025-01-02T17:37:20Z","title":"Improving Medical Large Vision-Language Models with Abnormal-Aware Feedback","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T22:33:45.160967Z"},"links":{"cited_paper":"/paper/2403.02330","citing_paper":"/paper/2501.01377"},"observation_digest":"sha256:4ff76f49aedf4e8f95e7790d3d1a24694f5fa1e9105eef781210c890708474cc","observation_id":"17d7fcd7-9fbf-4d05-b6a2-d0a645a6210f","resolution":{"observed_at":"2026-08-10T22:33:45.160967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02330","last_updated":"2024-03-04T18:58:08Z","snapshot_observed_at":"2026-08-04T19:14:19.335752Z","submitted_at":"2024-03-04T18:58:08Z","title":"RegionGPT: Towards Region Understanding Vision Language Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.02330","snapshot_observed_at":"2026-08-09T11:52:14.708786Z","title":"Regiongpt: Towards region understanding vision lan- guage model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.02548","last_updated":"2025-04-14T18:27:02Z","snapshot_observed_at":"2026-08-10T15:28:53.008606Z","submitted_at":"2025-02-04T18:18:50Z","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T11:52:14.708786Z"},"links":{"cited_paper":"/paper/2403.02330","citing_paper":"/paper/2502.02548"},"observation_digest":"sha256:8ebde9f97ba4fbfe8ac06213abab66dbfcd06d164376c30640bcff5aaa514656","observation_id":"29f12a23-69f1-4df5-9e6f-7afb377fbebb","resolution":{"observed_at":"2026-08-09T11:52:14.708786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02330","last_updated":"2024-03-04T18:58:08Z","snapshot_observed_at":"2026-08-04T19:14:19.335752Z","submitted_at":"2024-03-04T18:58:08Z","title":"RegionGPT: Towards Region Understanding Vision Language Model","version":1},"cited_work":{"arxiv_id":"2403.02330","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02330","snapshot_observed_at":"2026-07-03T21:28:58.461251Z","title":"arXiv preprint arXiv:2403.02330 , year =","venue":null,"work_id":"bd99fbc5-3616-4660-9bef-ac43e411f9a1","year":2024},"citing_paper":{"arxiv_id":"2606.17539","last_updated":"2026-06-16T05:32:39Z","snapshot_observed_at":"2026-07-06T23:53:07.149182Z","submitted_at":"2026-06-16T05:32:39Z","title":"Reinforcing Dual-Path Reasoning in Spatial Vision Language Models","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-06-27T01:42:30.005911Z"},"links":{"cited_paper":"/paper/2403.02330","citing_paper":"/paper/2606.17539"},"observation_digest":"sha256:8773caf969a89d4c12c60400afded6cf75d4f2647c9078bb3557fffe607cb70c","observation_id":"48aa3e7f-4c64-4e41-8bb0-587ad7eae9e3","resolution":{"observed_at":"2026-07-03T20:08:55.672844Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.02330","last_updated":"2024-03-04T18:58:08Z","snapshot_observed_at":"2026-08-04T19:14:19.335752Z","submitted_at":"2024-03-04T18:58:08Z","title":"RegionGPT: Towards Region Understanding Vision Language Model","version":1},"cited_work":{"arxiv_id":"2403.02330","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.02330","snapshot_observed_at":"2026-07-03T21:28:58.461251Z","title":"arXiv preprint arXiv:2403.02330 , year =","venue":null,"work_id":"bd99fbc5-3616-4660-9bef-ac43e411f9a1","year":2024},"citing_paper":{"arxiv_id":"2607.02089","last_updated":"2026-07-01T14:25:43Z","snapshot_observed_at":"2026-08-02T16:57:02.105465Z","submitted_at":"2026-07-01T14:25:43Z","title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-03T21:20:00.041277Z"},"links":{"cited_paper":"/paper/2403.02330","citing_paper":"/paper/2607.02089"},"observation_digest":"sha256:5a0785d857006da8257b8a3ed63c3f94422781cd1b0d3df4cd2b4e7b4100d24c","observation_id":"85ec625b-b834-48e1-af8e-1f660fa7b610","resolution":{"observed_at":"2026-07-03T21:28:58.463068Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.02330/citation-record","integrity":"/paper/2403.02330/integrity","json":"/paper/2403.02330/citation-record.json","paper":"/paper/2403.02330"},"outbound":[],"paper":{"arxiv_id":"2403.02330","last_updated":"2024-03-04T18:58:08Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-04T19:14:19.335752Z","submitted_at":"2024-03-04T18:58:08Z","title":"RegionGPT: Towards Region Understanding 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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2403.02330."}