{"as_of":"2026-08-09T13:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:09da053138c38fdddc7837ecce88f856d522c560f1748db1eee536fc660bd094","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T13:35:05.078035Z","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":"2026-05-13T22:10:10.292933Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.14233","last_updated":"2023-12-21T18:49:47Z","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:49:47Z","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":"2312.14233","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.14233","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vcoder: Versatile vision encoders for multimodal large language models","venue":null,"work_id":"89399f8e-349f-467b-a1e2-563cf70f5694","year":2023},"citing_paper":{"arxiv_id":"2402.00253","last_updated":"2024-05-06T01:10:01Z","snapshot_observed_at":"2026-07-06T17:23:26.913214Z","submitted_at":"2024-02-01T00:33:21Z","title":"A Survey on Hallucination in Large Vision-Language Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-13T22:10:10.186950Z"},"links":{"cited_paper":"/paper/2312.14233","citing_paper":"/paper/2402.00253"},"observation_digest":"sha256:0f3eff4079915890a67e3c367d320cadde8552855fba54a447f6612aad9dab2c","observation_id":"1b228bad-1e14-4810-9911-4e5f8997abda","resolution":{"observed_at":"2026-05-13T22:10:10.294607Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14233","last_updated":"2023-12-21T18:49:47Z","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:49:47Z","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":"2312.14233","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.14233","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vcoder: Versatile vision encoders for multimodal large language models","venue":null,"work_id":"89399f8e-349f-467b-a1e2-563cf70f5694","year":2023},"citing_paper":{"arxiv_id":"2404.18930","last_updated":"2025-04-01T18:36:08Z","snapshot_observed_at":"2026-08-06T19:08:14.800394Z","submitted_at":"2024-04-29T17:59:41Z","title":"Hallucination of Multimodal Large Language Models: A Survey","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-05-11T12:33:32.631346Z"},"links":{"cited_paper":"/paper/2312.14233","citing_paper":"/paper/2404.18930"},"observation_digest":"sha256:1fd96db3b8688a7e34733e2f6186117bb95528ccbe9debdfa4df8d79c0f78e63","observation_id":"9fb6423b-d55c-4622-ab6a-f5ee9241372b","resolution":{"observed_at":"2026-05-11T12:33:33.837887Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14233","last_updated":"2023-12-21T18:49:47Z","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:49:47Z","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.14233","snapshot_observed_at":"2026-08-08T13:35:05.078035Z","title":"Vcoder: Versatile vision encoders for multimodal large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07838","last_updated":"2025-02-13T11:13:14Z","snapshot_observed_at":"2026-08-09T08:00:43.529354Z","submitted_at":"2025-02-11T02:31:45Z","title":"NanoVLMs: How small can we go and still make coherent Vision Language Models?","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-08T13:35:05.078035Z"},"links":{"cited_paper":"/paper/2312.14233","citing_paper":"/paper/2502.07838"},"observation_digest":"sha256:ee4d8bdc960e9c01aee2b4a37834f18bf8482dc35290faa877af36fa26086d1c","observation_id":"7d471db5-6a7a-4d2f-9df2-6cb1182a2437","resolution":{"observed_at":"2026-08-08T13:35:05.078035Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14233","last_updated":"2023-12-21T18:49:47Z","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:49:47Z","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.14233","snapshot_observed_at":"2026-08-07T05:43:31.570069Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07184","last_updated":"2025-06-08T15:08:52Z","snapshot_observed_at":"2026-08-08T16:44:02.022482Z","submitted_at":"2025-06-08T15:08:52Z","title":"Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T05:43:31.570069Z"},"links":{"cited_paper":"/paper/2312.14233","citing_paper":"/paper/2506.07184"},"observation_digest":"sha256:07ce189df6915df4226d461c6ea170ff9a194a9aaba30c100953363c7cc84684","observation_id":"1cd5d190-9626-4add-b0dd-78d1d0d58adf","resolution":{"observed_at":"2026-08-07T05:43:31.570069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2312.14233/citation-record","integrity":"/paper/2312.14233/integrity","json":"/paper/2312.14233/citation-record.json","paper":"/paper/2312.14233"},"outbound":[],"paper":{"arxiv_id":"2312.14233","last_updated":"2023-12-21T18:49:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:06:50.350562Z","submitted_at":"2023-12-21T18:49:47Z","title":"VCoder: Versatile Vision Encoders for Multimodal Large Language 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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2312.14233."}