{"as_of":"2026-08-10T06:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cea5bc38391799c64881af4c358c7ece14fe748bae08d0dd2280429a357a5cfe","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":"2026-08-08T16:52:00.857258Z","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":"2026-05-17T10:58:53.382007Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.15517","last_updated":"2023-02-07T16:11:42Z","snapshot_observed_at":"2026-07-06T13:58:18.393526Z","submitted_at":"2022-09-30T15:06:13Z","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","version":2},"cited_work":{"arxiv_id":"2209.15517","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2209.15517","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2209.15517 , year=","venue":null,"work_id":"81cec985-5f6a-49ba-9065-4c0c758e8359","year":null},"citing_paper":{"arxiv_id":"2402.11411","last_updated":"2024-02-18T00:56:16Z","snapshot_observed_at":"2026-07-06T17:31:41.687799Z","submitted_at":"2024-02-18T00:56:16Z","title":"Aligning Modalities in Vision Large Language Models via Preference Fine-tuning","version":1},"reference_index":102,"source":"arxiv_source","source_observed_at":"2026-05-17T10:58:53.215887Z"},"links":{"cited_paper":"/paper/2209.15517","citing_paper":"/paper/2402.11411"},"observation_digest":"sha256:86cb71dd7f60692f30004cedf85d351a9003f0f970f1b38c25f7910cc6569228","observation_id":"e2c0e346-1f0e-4f4f-ad9c-55340e05a152","resolution":{"observed_at":"2026-05-17T10:58:53.384587Z","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":"2209.15517","last_updated":"2023-02-07T16:11:42Z","snapshot_observed_at":"2026-07-06T13:58:18.393526Z","submitted_at":"2022-09-30T15:06:13Z","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15517","snapshot_observed_at":"2026-08-08T16:52:00.857258Z","title":"Medical image understanding with pretrained vision language models: A comprehensive study","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.06094","last_updated":"2025-02-10T01:45:26Z","snapshot_observed_at":"2026-08-10T01:55:11.255402Z","submitted_at":"2025-02-10T01:45:26Z","title":"Fair-MoE: Fairness-Oriented Mixture of Experts in Vision-Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T16:52:00.857258Z"},"links":{"cited_paper":"/paper/2209.15517","citing_paper":"/paper/2502.06094"},"observation_digest":"sha256:563304a39304b700d6e9afb84078b20b0077c1416248fcf99141caa213d185bb","observation_id":"3782bc0f-1769-485d-a385-51c956017367","resolution":{"observed_at":"2026-08-08T16:52:00.857258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.15517","last_updated":"2023-02-07T16:11:42Z","snapshot_observed_at":"2026-07-06T13:58:18.393526Z","submitted_at":"2022-09-30T15:06:13Z","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15517","snapshot_observed_at":"2026-08-07T12:35:10.621980Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24173","last_updated":"2025-05-30T03:33:25Z","snapshot_observed_at":"2026-08-07T20:54:16.475143Z","submitted_at":"2025-05-30T03:33:25Z","title":"DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T12:35:10.621980Z"},"links":{"cited_paper":"/paper/2209.15517","citing_paper":"/paper/2505.24173"},"observation_digest":"sha256:59cb50ffdc875a3bf6c8d3f728c3377f551f5fb59140cd41e496114d4c4b2b3d","observation_id":"a8ccac7d-a15e-4e24-a4de-012c6055534c","resolution":{"observed_at":"2026-08-07T12:35:10.621980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.15517","last_updated":"2023-02-07T16:11:42Z","snapshot_observed_at":"2026-07-06T13:58:18.393526Z","submitted_at":"2022-09-30T15:06:13Z","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15517","snapshot_observed_at":"2026-08-06T21:55:48.962631Z","title":"Medical image understanding with pretrained vision language mod- els: A comprehensive study","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.23102","last_updated":"2026-07-06T06:04:13Z","snapshot_observed_at":"2026-08-08T21:05:19.837782Z","submitted_at":"2025-06-29T06:08:55Z","title":"Region-Aware Multimodal Large Language Model via SlowFast Tokenization and Pseudo-Mask Guidance for 3D CT Report Generation","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:48.962631Z"},"links":{"cited_paper":"/paper/2209.15517","citing_paper":"/paper/2506.23102"},"observation_digest":"sha256:e7662c43a0c5207efe15ccf843863aa1c3d1c7dc35ce33fa1c1f9d21c0a6667a","observation_id":"8f300843-52fc-4b9e-904c-ab03b8a5d787","resolution":{"observed_at":"2026-08-06T21:55:48.962631Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2209.15517/citation-record","integrity":"/paper/2209.15517/integrity","json":"/paper/2209.15517/citation-record.json","paper":"/paper/2209.15517"},"outbound":[],"paper":{"arxiv_id":"2209.15517","last_updated":"2023-02-07T16:11:42Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T13:58:18.393526Z","submitted_at":"2022-09-30T15:06:13Z","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study"},"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 4 inbound Pith citation observations for arXiv:2209.15517."}