{"as_of":"2026-08-07T01:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f70f1042ec40c5155d3f609d32913a1473b5c8330737ec06b4e9cda779ec499d","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T18:24:52.156204Z","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":"2026-05-17T10:16:43.917557Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2308.10253","last_updated":"2023-12-28T03:44:28Z","snapshot_observed_at":"2026-07-06T16:08:13.029564Z","submitted_at":"2023-08-20T12:43:52Z","title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data","version":2},"cited_work":{"arxiv_id":"2308.10253","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.10253","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Stablellava: Enhanced visual instruction tuning with synthe- sized image-dialogue data","venue":null,"work_id":"4f342781-2ee1-47e9-9b43-b755ce52d8dd","year":2023},"citing_paper":{"arxiv_id":"2310.14566","last_updated":"2024-03-25T06:05:24Z","snapshot_observed_at":"2026-08-02T21:20:28.501823Z","submitted_at":"2023-10-23T04:49:09Z","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","version":5},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-17T01:22:04.035994Z"},"links":{"cited_paper":"/paper/2308.10253","citing_paper":"/paper/2310.14566"},"observation_digest":"sha256:8a834665ce9c72f9afdbaa72c63a2d0469f24021493959eed59d27b08c1b046e","observation_id":"fc66c79f-d895-4146-9bb9-ab2d894100b1","resolution":{"observed_at":"2026-05-17T01:22:04.276991Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.10253","last_updated":"2023-12-28T03:44:28Z","snapshot_observed_at":"2026-07-06T16:08:13.029564Z","submitted_at":"2023-08-20T12:43:52Z","title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data","version":2},"cited_work":{"arxiv_id":"2308.10253","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2308.10253","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Stablellava: Enhanced visual instruction tuning with synthe- sized image-dialogue data","venue":null,"work_id":"4f342781-2ee1-47e9-9b43-b755ce52d8dd","year":2023},"citing_paper":{"arxiv_id":"2312.13771","last_updated":"2026-07-05T07:51:04Z","snapshot_observed_at":"2026-08-04T19:11:48.797552Z","submitted_at":"2023-12-21T11:52:45Z","title":"AppAgent: Multimodal Agents as Smartphone Users","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-05-17T10:16:43.364787Z"},"links":{"cited_paper":"/paper/2308.10253","citing_paper":"/paper/2312.13771"},"observation_digest":"sha256:a33ed60902aee477533c596be3c6da0c17f04fe6336d38efb6164fb7785b37dc","observation_id":"86880e42-d145-4175-86a2-1cfbdf6bacdb","resolution":{"observed_at":"2026-05-17T10:16:43.920193Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.10253","last_updated":"2023-12-28T03:44:28Z","snapshot_observed_at":"2026-07-06T16:08:13.029564Z","submitted_at":"2023-08-20T12:43:52Z","title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.10253","snapshot_observed_at":"2026-08-06T18:24:52.156204Z","title":"Stablellava: Enhanced visual instruction tun- ing with synthesized image-dialogue data","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08513","last_updated":"2025-07-23T22:34:55Z","snapshot_observed_at":"2026-08-06T18:14:17.022825Z","submitted_at":"2025-07-11T12:00:10Z","title":"Advancing Multimodal LLMs by Large-Scale 3D Visual Instruction Dataset Generation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:24:52.156204Z"},"links":{"cited_paper":"/paper/2308.10253","citing_paper":"/paper/2507.08513"},"observation_digest":"sha256:526bb2c89012b47053ae1be523f0b81eff773ab92c56232b2cb2c43df4822acc","observation_id":"e92f5ebe-1327-4337-bc68-0d2a152b7e54","resolution":{"observed_at":"2026-08-06T18:24:52.156204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2308.10253/citation-record","integrity":"/paper/2308.10253/integrity","json":"/paper/2308.10253/citation-record.json","paper":"/paper/2308.10253"},"outbound":[],"paper":{"arxiv_id":"2308.10253","last_updated":"2023-12-28T03:44:28Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:08:13.029564Z","submitted_at":"2023-08-20T12:43:52Z","title":"StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2308.10253."}