{"as_of":"2026-08-10T06:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1b2f0f33365d009d2bb8ed8ccacab3e0ec64d05636f871d3341b2c634c8caa71","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":"2026-08-09T06:31:02.800959+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":"2026-08-06T20:38:29.985659Z","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":"2026-05-11T09:00:59.407776Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.07306","last_updated":"2023-11-13T12:52:29Z","snapshot_observed_at":"2026-08-03T21:40:55.534458Z","submitted_at":"2023-11-13T12:52:29Z","title":"What Large Language Models Bring to Text-rich VQA?","version":1},"cited_work":{"arxiv_id":"2311.07306","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07306","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"InInternational conference on ma- chine learning, pages 19730–19742","venue":null,"work_id":"a827a89f-1277-4fce-9434-0a9b3fecb38c","year":2025},"citing_paper":{"arxiv_id":"2408.03326","last_updated":"2024-10-26T16:35:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:59:44Z","title":"LLaVA-OneVision: Easy Visual Task Transfer","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-05-10T14:23:49.412830Z"},"links":{"cited_paper":"/paper/2311.07306","citing_paper":"/paper/2408.03326"},"observation_digest":"sha256:f1af48c5ce534fa41d8cc3dd537a80dd4a9b08d89c8773ee8dd03843db49f322","observation_id":"d7382f9a-093c-4f1b-b359-133d9c7af79c","resolution":{"observed_at":"2026-05-10T14:23:49.604786Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07306","last_updated":"2023-11-13T12:52:29Z","snapshot_observed_at":"2026-08-03T21:40:55.534458Z","submitted_at":"2023-11-13T12:52:29Z","title":"What Large Language Models Bring to Text-rich VQA?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07306","snapshot_observed_at":"2026-08-06T20:38:29.985659Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.02279","last_updated":"2025-07-03T03:42:54Z","snapshot_observed_at":"2026-08-07T19:23:28.702632Z","submitted_at":"2025-07-03T03:42:54Z","title":"LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T20:38:29.985659Z"},"links":{"cited_paper":"/paper/2311.07306","citing_paper":"/paper/2507.02279"},"observation_digest":"sha256:3b37d95bedd6d18a8b821f742107ef8aa7a9c94e02ac98dbd5996c0f90f1d427","observation_id":"6e178c9b-eb14-4504-aba2-7da9adfe3b1b","resolution":{"observed_at":"2026-08-06T20:38:29.985659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07306","last_updated":"2023-11-13T12:52:29Z","snapshot_observed_at":"2026-08-03T21:40:55.534458Z","submitted_at":"2023-11-13T12:52:29Z","title":"What Large Language Models Bring to Text-rich VQA?","version":1},"cited_work":{"arxiv_id":"2311.07306","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.07306","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"InInternational conference on ma- chine learning, pages 19730–19742","venue":null,"work_id":"a827a89f-1277-4fce-9434-0a9b3fecb38c","year":2025},"citing_paper":{"arxiv_id":"2604.16502","last_updated":"2026-06-04T06:39:21Z","snapshot_observed_at":"2026-07-12T21:11:08.046069Z","submitted_at":"2026-04-14T14:36:53Z","title":"Topology-Aware Layer Pruning for Large Vision-Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T16:21:04.009413Z"},"links":{"cited_paper":"/paper/2311.07306","citing_paper":"/paper/2604.16502"},"observation_digest":"sha256:e54985437b09fb5911ae9b2cfa0f55f66584e8cd23b75c69dc842e5320fde9ec","observation_id":"2a77a71c-252e-49be-a044-b33fe765fa19","resolution":{"observed_at":"2026-05-11T09:00:59.413833Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2311.07306/citation-record","integrity":"/paper/2311.07306/integrity","json":"/paper/2311.07306/citation-record.json","paper":"/paper/2311.07306"},"outbound":[],"paper":{"arxiv_id":"2311.07306","last_updated":"2023-11-13T12:52:29Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T21:40:55.534458Z","submitted_at":"2023-11-13T12:52:29Z","title":"What Large Language Models Bring to Text-rich VQA?"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2311.07306."}