{"as_of":"2026-08-08T20:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a39d8cd15c259e01810ec7a1e674df7516ca05e3b43241d3b4ad9cff8ea193f7","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":"2026-08-08T06:32:00.761636+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":"2026-08-08T00:49:55.158116Z","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":"2026-05-18T15:36:34.016359Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.05348","last_updated":"2024-08-28T14:26:07Z","snapshot_observed_at":"2026-07-06T16:45:11.604296Z","submitted_at":"2023-11-09T13:18:27Z","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05348","snapshot_observed_at":"2026-08-06T23:27:46.102560Z","title":"u-llava: Unifying multi-modal tasks via large language model,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.18048","last_updated":"2025-08-11T14:18:57Z","snapshot_observed_at":"2026-08-07T22:53:48.054431Z","submitted_at":"2025-06-22T14:32:15Z","title":"CLGRPO: Reasoning Ability Enhancement for Small VLMs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:27:46.102560Z"},"links":{"cited_paper":"/paper/2311.05348","citing_paper":"/paper/2506.18048"},"observation_digest":"sha256:3c0e1139a17dcaaf5f845a7893bdc644c76263d9ac83cc71ea020d4a68fdb568","observation_id":"3e0302b2-4c90-4d32-b153-02826c9f8c20","resolution":{"observed_at":"2026-08-06T23:27:46.102560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05348","last_updated":"2024-08-28T14:26:07Z","snapshot_observed_at":"2026-07-06T16:45:11.604296Z","submitted_at":"2023-11-09T13:18:27Z","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","version":4},"cited_work":{"arxiv_id":"2311.05348","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.05348","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"u-llava: Unifying multi-modal tasks via large language model","venue":null,"work_id":"5ae24aee-6f03-40d6-b757-c5907e2261f9","year":2024},"citing_paper":{"arxiv_id":"2509.13484","last_updated":"2026-01-15T21:33:56Z","snapshot_observed_at":"2026-07-06T22:30:07.020487Z","submitted_at":"2025-09-16T19:31:40Z","title":"MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-18T15:35:30.549656Z"},"links":{"cited_paper":"/paper/2311.05348","citing_paper":"/paper/2509.13484"},"observation_digest":"sha256:54b82bd4df782a6be3572c0506eb1b3ee8c13a5e869f9e5a744d26b5817de8b3","observation_id":"67f82c73-78c0-4c7c-a433-0ab6aff10414","resolution":{"observed_at":"2026-05-18T15:36:34.019765Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05348","last_updated":"2024-08-28T14:26:07Z","snapshot_observed_at":"2026-07-06T16:45:11.604296Z","submitted_at":"2023-11-09T13:18:27Z","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05348","snapshot_observed_at":"2026-08-06T00:48:45.470485Z","title":"arXiv preprint arXiv:2311.05348 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03147","last_updated":"2026-08-05T06:08:54Z","snapshot_observed_at":"2026-08-08T19:10:59.549223Z","submitted_at":"2026-08-04T05:24:05Z","title":"CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T00:48:45.470485Z"},"links":{"cited_paper":"/paper/2311.05348","citing_paper":"/paper/2608.03147"},"observation_digest":"sha256:0c280ae4c32ce81507e42099720ab972b9328832fd9707ecc115f294eba52a84","observation_id":"4eeb3ec6-d20a-4bff-a11d-4d7377ab8468","resolution":{"observed_at":"2026-08-06T00:48:45.470485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.05348","last_updated":"2024-08-28T14:26:07Z","snapshot_observed_at":"2026-07-06T16:45:11.604296Z","submitted_at":"2023-11-09T13:18:27Z","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.05348","snapshot_observed_at":"2026-08-08T00:49:55.158116Z","title":"arXiv preprint arXiv:2311.05348 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03147","last_updated":"2026-08-05T06:08:54Z","snapshot_observed_at":"2026-08-08T19:10:59.549223Z","submitted_at":"2026-08-04T05:24:05Z","title":"CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-08T00:49:55.158116Z"},"links":{"cited_paper":"/paper/2311.05348","citing_paper":"/paper/2608.03147"},"observation_digest":"sha256:0cba2bc5291d54ad1a6fd7d11a23e9403ddbd8f4f975a1b39a89c5a4bff75cb3","observation_id":"f43e1b53-f549-4a85-b80b-000d89afe81f","resolution":{"observed_at":"2026-08-08T00:49:55.158116Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.05348/citation-record","integrity":"/paper/2311.05348/integrity","json":"/paper/2311.05348/citation-record.json","paper":"/paper/2311.05348"},"outbound":[],"paper":{"arxiv_id":"2311.05348","last_updated":"2024-08-28T14:26:07Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:45:11.604296Z","submitted_at":"2023-11-09T13:18:27Z","title":"u-LLaVA: Unifying Multi-Modal Tasks via Large 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":"2026-08-08T06:32:00.761636+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 4 inbound Pith citation observations for arXiv:2311.05348."}