{"as_of":"2026-08-09T06:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:efd1f79f61f97042fd911d458148acc1aa3e2db896fe20766d1f1a0fad20cf7e","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":"2026-08-07T14:28:32.109779Z","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":"2026-07-04T15:09:55.198663Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.07304","last_updated":"2024-05-28T12:32:31Z","snapshot_observed_at":"2026-08-07T22:15:49.747620Z","submitted_at":"2024-03-12T04:13:45Z","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07304","snapshot_observed_at":"2026-08-07T14:28:32.109779Z","title":"Lumen: Unleashing versatile vision-centric capabilities of large multimodal models.arXiv preprint arXiv:2403.07304, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18775","last_updated":"2025-05-24T16:29:34Z","snapshot_observed_at":"2026-08-08T15:52:44.818177Z","submitted_at":"2025-05-24T16:29:34Z","title":"OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T14:28:32.109779Z"},"links":{"cited_paper":"/paper/2403.07304","citing_paper":"/paper/2505.18775"},"observation_digest":"sha256:08846d23ccc9f2f154138d61bf6ca6fb69fd07f0d7f6233d32973b7bf49c5260","observation_id":"80f0a40a-cea9-4987-898d-36caa0d6a161","resolution":{"observed_at":"2026-08-07T14:28:32.109779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07304","last_updated":"2024-05-28T12:32:31Z","snapshot_observed_at":"2026-08-07T22:15:49.747620Z","submitted_at":"2024-03-12T04:13:45Z","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models","version":2},"cited_work":{"arxiv_id":"2403.07304","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.07304","snapshot_observed_at":"2026-07-04T15:09:55.198663Z","title":"Lumen: Unleashing versatile vision-centric capabilities of large multimodal models","venue":null,"work_id":"2087294f-9f03-435b-b946-7036bd48e07a","year":2024},"citing_paper":{"arxiv_id":"2507.00748","last_updated":"2026-04-12T11:20:16Z","snapshot_observed_at":"2026-08-08T09:01:59.914584Z","submitted_at":"2025-07-01T13:48:57Z","title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-19T06:50:02.607136Z"},"links":{"cited_paper":"/paper/2403.07304","citing_paper":"/paper/2507.00748"},"observation_digest":"sha256:ff329d5441ba7d38c19f5d466bc21bafdc0dcf9ff196eba8f86e30b369faf558","observation_id":"0cd25c47-480e-42e9-9b53-bfe9f87287fe","resolution":{"observed_at":"2026-05-19T06:52:07.993595Z","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":"2403.07304","last_updated":"2024-05-28T12:32:31Z","snapshot_observed_at":"2026-08-07T22:15:49.747620Z","submitted_at":"2024-03-12T04:13:45Z","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models","version":2},"cited_work":{"arxiv_id":"2403.07304","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.07304","snapshot_observed_at":"2026-07-04T15:09:55.198663Z","title":"Lumen: Unleashing versatile vision-centric capabilities of large multimodal models","venue":null,"work_id":"2087294f-9f03-435b-b946-7036bd48e07a","year":2024},"citing_paper":{"arxiv_id":"2606.26196","last_updated":"2026-06-24T15:20:32Z","snapshot_observed_at":"2026-07-07T00:00:31.981360Z","submitted_at":"2026-06-24T15:20:32Z","title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-06-26T01:50:54.242508Z"},"links":{"cited_paper":"/paper/2403.07304","citing_paper":"/paper/2606.26196"},"observation_digest":"sha256:aa425a625fb2b6e9f2cb3eb4e083a33a2be635f6eb9d6ae2f637589992dc3f69","observation_id":"d46cb6f3-8119-4850-96a8-dfd6cbdc00ba","resolution":{"observed_at":"2026-07-04T15:09:55.200587Z","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/2403.07304/citation-record","integrity":"/paper/2403.07304/integrity","json":"/paper/2403.07304/citation-record.json","paper":"/paper/2403.07304"},"outbound":[],"paper":{"arxiv_id":"2403.07304","last_updated":"2024-05-28T12:32:31Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T22:15:49.747620Z","submitted_at":"2024-03-12T04:13:45Z","title":"Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2403.07304."}