{"as_of":"2026-08-19T04:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:227a5fa58270af5495d65d69b2f25533fcaa83ce6d659aab6cd5d1c9229d8602","coverage":[{"denominator":68,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":68,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T00:54:37.900938Z","state":"measured"},{"denominator":68,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":68,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2608.00279/citation-record","integrity":"/paper/2608.00279/integrity","json":"/paper/2608.00279/citation-record.json","paper":"/paper/2608.00279"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.621562Z","title":"Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.621562Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:e2fe02253d7714d7a62fc134bd58ade5904cc7890f25c7079809a68995df1b78","observation_id":"162779e9-0618-462f-ad1d-8bd8e560e316","resolution":{"observed_at":"2026-08-04T00:54:34.621562Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.679868Z","title":"Improving patient safety: avoiding unread imaging exams in the national va en- terprise electronic health record.Journal of digital imaging, 30(3):309–313, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.679868Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:88330b089b57645ddf3cb08f78b50e0a173507b42a2b2d74e205d99bab141df7","observation_id":"6443e4e0-8ad3-4b95-b385-9979a4168179","resolution":{"observed_at":"2026-08-04T00:54:34.679868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.697294Z","title":"Making the most of text semantics to improve biomedical vision–language processing","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.697294Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:cc12b19c082193e4278110fd8fb2a0bd12c4b36dd659f44f6a6ca54ad4304d51","observation_id":"f972507a-ad32-4d66-a124-c65633ddfb6a","resolution":{"observed_at":"2026-08-04T00:54:34.697294Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.733110Z","title":"Generating radiology reports via memory-driven transformer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.733110Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:d311b2e5e3601145f07782c7ff02318966c15701256cf4dc6209803ca9c2acd5","observation_id":"043db249-8f6a-423b-a7a0-4de7426c0ad3","resolution":{"observed_at":"2026-08-04T00:54:34.733110Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.774220Z","title":"Generating radiology reports via memory-driven transformer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.774220Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:f7c1e1f7bebd49f49443557ed5084e65883e6030c20bad9bcca38de9c3c77c44","observation_id":"eb675e35-d9ae-4df6-b526-5cfe54250bfe","resolution":{"observed_at":"2026-08-04T00:54:34.774220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.834578Z","title":"Cross-modal memory networks for radiology report genera- tion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.834578Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:65b67787e4b9f38280d685cf9f346547add8cead51a39e434591a803979b645d","observation_id":"4a98aefb-75fd-4731-88dd-e787b4f6ff02","resolution":{"observed_at":"2026-08-04T00:54:34.834578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.896030Z","title":"Cross-modal memory networks for radiology report genera- tion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.896030Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:6e7f2322ea8ca1a267f5cc3c6955c572c90d5c11ad915431c12bbed96343e284","observation_id":"b61d2d59-e2ec-42ce-8381-ea9a4262dc2a","resolution":{"observed_at":"2026-08-04T00:54:34.896030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.909219Z","title":"Is the modality gap a bug or a feature? a robustness perspective","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.909219Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:c528422dcd7747ecaad09f1feb00697a1497b6a2f9e82aba0c4a65e8a0331a09","observation_id":"877d7088-35df-43fe-8b05-c34c2b798145","resolution":{"observed_at":"2026-08-04T00:54:34.909219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:34.995832Z","title":"Meshed-memory transformer for image caption- ing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:34.995832Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:358e6a90d060d553a0ce92c3da077adb0281dfa6966c81de7d8f91b781c81ca2","observation_id":"a01b08ab-e0c0-4ceb-9258-3337f3c2b168","resolution":{"observed_at":"2026-08-04T00:54:34.995832Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.017448Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport.Advances in neural information pro- cessing systems, 26, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.017448Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:66334823623bfb440263498453f5f10db565dbda8dbb203198fb9c183b53a985","observation_id":"024a0d4e-b347-4064-8db1-97f2d95b481c","resolution":{"observed_at":"2026-08-04T00:54:35.017448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.058424Z","title":"Preparing a collection of radiology examinations for distribution and retrieval.Journal of the American Medical Informatics As- sociation, 23(2):304–310, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.058424Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:0e7df6930d110a52b52696a5136eea1a57432ff7842ebaaa8deb6a5f4052bbb8","observation_id":"c35bc65b-61a3-457f-860e-ce55829eb2fc","resolution":{"observed_at":"2026-08-04T00:54:35.058424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.131011Z","title":"Huang, X","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.131011Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:4020036e65b04b3c7b140912fa95f7c49d95723fc514fff2678db25a80faf035","observation_id":"a8bd02ae-c747-4f2c-803e-0ba7d0d194e9","resolution":{"observed_at":"2026-08-04T00:54:35.131011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.191918Z","title":"Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.191918Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:929959feb788a169146abe80847aeff7499fc061cdc028b79aaebd1a99ddd2a3","observation_id":"d559602f-7c9d-43f2-834e-0c0d871a4087","resolution":{"observed_at":"2026-08-04T00:54:35.191918Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.14463","last_updated":"2021-08-29T23:19:33Z","snapshot_observed_at":"2026-08-16T18:14:04.811046Z","submitted_at":"2021-06-28T08:24:23Z","title":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.14463","snapshot_observed_at":"2026-08-04T00:54:35.233292Z","title":"Radgraph: Extracting clinical entities and relations from radiology re- ports.arXiv preprint arXiv:2106.14463, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.233292Z"},"links":{"cited_paper":"/paper/2106.14463","citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:fcc7a6706c1a8dcdbc86c49b920d83e25814cc0c99edb23b27dd705007d04dba","observation_id":"9b9f9c3a-0e7a-479f-8b6f-f5680deefa73","resolution":{"observed_at":"2026-08-04T00:54:35.233292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.293390Z","title":"On the automatic generation of medical imaging reports","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.293390Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:48d5377ee2c3fa3e8c22ea626ddaa5f87f6c0be649037947af8ee99b8894c35f","observation_id":"8074cc65-5078-4e1d-adcc-ff4ae96a6374","resolution":{"observed_at":"2026-08-04T00:54:35.293390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.320260Z","title":"Show, describe and conclude: On exploiting the structure information of chest x-ray reports","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.320260Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:f1c5c9274ee75d30bf7c110d8e962b63b22c68079bdf3940599106d4c5c4d5ee","observation_id":"0a16db64-16c5-4626-95ea-672f7b7eb160","resolution":{"observed_at":"2026-08-04T00:54:35.320260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.07042","last_updated":"2019-11-14T17:34:51Z","snapshot_observed_at":"2026-08-02T04:11:08.699777Z","submitted_at":"2019-01-21T19:01:00Z","title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.07042","snapshot_observed_at":"2026-08-04T00:54:35.358794Z","title":"Mimic-cxr-jpg, a large publicly available database of labeled chest radiographs.arXiv preprint arXiv:1901.07042, 2019","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.358794Z"},"links":{"cited_paper":"/paper/1901.07042","citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:6a91e09b4e9ab4d65525d1579ed3a3b87e6cb8f3daa79757315807ae22f6d77e","observation_id":"bf969351-2577-4a0c-80a5-13059b240bdd","resolution":{"observed_at":"2026-08-04T00:54:35.358794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.412129Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.412129Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:ab8acb2f8b57c481de38dd8f4c8dcb45c1c6d97192c12efe369234ab80a51e17","observation_id":"89c763c7-6126-45e1-bb7e-a22fc1421a93","resolution":{"observed_at":"2026-08-04T00:54:35.412129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.471027Z","title":"Llava-med: Training a large language- and-vision assistant for biomedicine in one day.Advances in Neural Information Processing Systems, 36:28541–28564,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.471027Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:27e576ca3cbdc4087543304252634e36d863711809158b1a7766889bab576f2d","observation_id":"d3f5ecb9-8d6e-490a-972b-93dde934bb8b","resolution":{"observed_at":"2026-08-04T00:54:35.471027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.525609Z","title":"Dynamic graph enhanced contrastive learning for chest X-ray report generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.525609Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:fad95b559a0ef82869ac22ab9117839aea452fbe13eb9375eb7f6a651c1ce316","observation_id":"951829f1-b181-4743-9f94-2c86a4aa449e","resolution":{"observed_at":"2026-08-04T00:54:35.525609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.584101Z","title":"Con- trastive learning with counterfactual explanations for radiol- ogy report generation, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.584101Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:231977968c41fb81683bf0a3a7af3753d0fd90ffb9e16ff6189d939eb7d16cbb","observation_id":"e309f8a9-05ed-4c70-9673-98b346d506f2","resolution":{"observed_at":"2026-08-04T00:54:35.584101Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.627850Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.627850Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:598ed64351eedf895b5f7705c9a6dd0d8e21009ae9ceadc67adb89cda2580f62","observation_id":"95ef1671-b219-4d6b-a00e-eef424007ef9","resolution":{"observed_at":"2026-08-04T00:54:35.627850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.770909Z","title":"Bootstrapping large language models for radiology report generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.770909Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:c4cdeec8b9daedc742cdf4d504ffa6804cbfb7b37116635b20f4b186a568b66f","observation_id":"1d2938b9-93a6-48cf-9ca9-1280f9ddaf96","resolution":{"observed_at":"2026-08-04T00:54:35.770909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.825545Z","title":"Competence-based mul- timodal curriculum learning for medical report generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.825545Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:c931f8ac8231cdce8fe5b7040ed3703d5cbd8391c5adca3a99c64b16b4ea5a27","observation_id":"e01706d4-6e81-4aac-a34d-2df1081a330c","resolution":{"observed_at":"2026-08-04T00:54:35.825545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.853304Z","title":"Exploring and distilling posterior and prior knowledge for 9 radiology report generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.853304Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:b72ff43d292bbfaa03f7092184b4c9102fa2b7107fe776c7eec2611642566ccc","observation_id":"2f355c2e-178d-4cc6-b9a2-0e7766ac1511","resolution":{"observed_at":"2026-08-04T00:54:35.853304Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.894227Z","title":"Contrastive attention for automatic chest x-ray report generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.894227Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:4c2fa6307f9284f068d327341aa9fbd0d5ad21f599480e75ac6f0b27b1f775dd","observation_id":"faffe228-4ef2-42f0-915e-2288f8654241","resolution":{"observed_at":"2026-08-04T00:54:35.894227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.909088Z","title":"Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.909088Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:3ac402c4f6ec1f71a7ce45cb39a42fa07117084a01094b7b6da77c58ff0cdfcb","observation_id":"48c4954f-f93a-47d5-a4dd-4f2e20a89640","resolution":{"observed_at":"2026-08-04T00:54:35.909088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.945118Z","title":"Struc- tural entities extraction and patient indications incorporation for chest x-ray report generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.945118Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:3056b7287e20f431c472b6f93001193e2b8781e3e716d39981b3a5494e249230","observation_id":"32869119-05cf-4fc4-95f6-4af5d9236180","resolution":{"observed_at":"2026-08-04T00:54:35.945118Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.958721Z","title":"Enhanced contrastive learning with multi-view longitudinal data for chest x-ray report generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.958721Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:f2a08f8fefb994a330673e9db0eb5a59cdd3afb6336175d0e920f950fd344ec2","observation_id":"3ad61d5b-d2fc-45d7-9ce8-acd7b33e517d","resolution":{"observed_at":"2026-08-04T00:54:35.958721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:35.998355Z","title":"In-context learning for zero-shot medical re- port generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:35.998355Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:ad0eefb8029fa44da1849e4a062f42e924e58eca41e1f417826cfd88d2692135","observation_id":"4f8e9e8e-4aef-46e0-bf5f-c6c9779228e3","resolution":{"observed_at":"2026-08-04T00:54:35.998355Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.081553Z","title":"In-context learning for zero-shot medical re- port generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.081553Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:ee772d57babcec6d2b3910989c7971110d38896349bf95d7b0746f14c9943b6d","observation_id":"d6e15659-99d4-4608-aef4-fef49980153c","resolution":{"observed_at":"2026-08-04T00:54:36.081553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.117374Z","title":"In-context learning for zero-shot medical re- port generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.117374Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:a074871a70d176a60c93a7760c7f055b9f657ffa96e185b7011d8f18698a4c58","observation_id":"7ceb6306-7c64-4326-a8b5-17d119b488a6","resolution":{"observed_at":"2026-08-04T00:54:36.117374Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.163659Z","title":"From observation to concept: A flexible multi-view paradigm for medical report generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.163659Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:9317b99fa20f2c3ce7f34a3a0a4e3fae8e28a9fa81891a11112f248ab1880b7c","observation_id":"b837aeb6-d204-4f19-a906-75020c4b8308","resolution":{"observed_at":"2026-08-04T00:54:36.163659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.173385Z","title":"Improving factual completeness and con- sistency of image-to-text radiology report generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.173385Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:5b787cd9875de23c74129e0763f74359955b654bf2c1b6884851634da9f929ee","observation_id":"9730f768-920e-4a10-94b3-9319f247cf9a","resolution":{"observed_at":"2026-08-04T00:54:36.173385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02467","last_updated":"2020-10-06T04:18:18Z","snapshot_observed_at":"2026-08-17T09:44:16.293709Z","submitted_at":"2020-10-06T04:18:18Z","title":"Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02467","snapshot_observed_at":"2026-08-04T00:54:36.179721Z","title":"Learning visual-semantic embeddings for re- porting abnormal findings on chest x-rays.arXiv preprint arXiv:2010.02467, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.179721Z"},"links":{"cited_paper":"/paper/2010.02467","citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:1e4a885606a15f2aac333f0808dce24a5babe5ca4c3ce7d08a9a5b95204522bd","observation_id":"cfa8a1e6-9c74-434d-9078-4e1b1c1cf340","resolution":{"observed_at":"2026-08-04T00:54:36.179721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.09405","last_updated":"2023-07-12T23:14:28Z","snapshot_observed_at":"2026-08-16T17:26:31.795765Z","submitted_at":"2022-01-24T00:46:37Z","title":"Improving Chest X-Ray Report Generation by Leveraging Warm Starting","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.09405","snapshot_observed_at":"2026-08-04T00:54:36.254292Z","title":"Im- proving chest x-ray report generation by leveraging warm- starting.arXiv preprint arXiv:2201.09405, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.254292Z"},"links":{"cited_paper":"/paper/2201.09405","citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:5604e357de262f56ac260c00d28b4e3871c19156941ee57761754f74e7a2a9c7","observation_id":"e0cb9fc9-6124-43a0-9321-8ba5ade587aa","resolution":{"observed_at":"2026-08-04T00:54:36.254292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.331836Z","title":"Lon- gitudinal data and a semantic similarity reward for chest x-ray report generation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.331836Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:4376d5ac229a423901d195267bb1d29dff70ceb3627524b3f50170b27ecbbe2b","observation_id":"e6c8ab74-abdf-440a-b931-80aa77f7d45f","resolution":{"observed_at":"2026-08-04T00:54:36.331836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.410876Z","title":"Dart: Disease-aware image-text alignment and self-correcting re-alignment for trustworthy radiology report generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.410876Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:13044157d234e56e2c9fabb86460790f3983889f4b9b50e1743fb3684e09947d","observation_id":"0d0ce69a-6720-4967-93bb-ccffa652ef7b","resolution":{"observed_at":"2026-08-04T00:54:36.410876Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.433547Z","title":"Rad-dino: Exploring scalable medical image encoders beyond text supervision; 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.433547Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:27d075816330acda81c67ae3797ee180050c9c34f3467d581254cd353b7b3623","observation_id":"19890c16-c2c0-41d5-b43f-a282de3d9533","resolution":{"observed_at":"2026-08-04T00:54:36.433547Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.469440Z","title":"Now Founda- tions and Trends, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.469440Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:70b1b4c719d0baf47455fc21ce74cfa2f9b6a368f5eba4e6cf0778982ebdb0c0","observation_id":"f1b198d8-53e1-423f-92c5-1f509db2b301","resolution":{"observed_at":"2026-08-04T00:54:36.469440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.537948Z","title":"Im- proving radiology report generation systems by removing hallucinated references to non-existent priors","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.537948Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:7dbb33764f0d8d5c737bebd04d25f0a851fee16305b83a6ad24b9873e8fa2857","observation_id":"574eca6d-c492-4d50-8dec-a2ba2f46c111","resolution":{"observed_at":"2026-08-04T00:54:36.537948Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.577251Z","title":"Rosenow III","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.577251Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:341c4cf4e5d75703db50e805d341d851ffcb57ae4286bf77e0e514c807c71fe6","observation_id":"a0c26914-7417-4e14-adfe-0cdc7dfe7122","resolution":{"observed_at":"2026-08-04T00:54:36.577251Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.648963Z","title":"Radiologist shortage leaves patient care at risk, warns royal college.BMJ, 359, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.648963Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:41b66b59df2154ff959ea4e70f52e5a4caa1a1292734d85684ea56b7b8ed16dd","observation_id":"109a0646-d5d9-411b-ac97-c0debca8af47","resolution":{"observed_at":"2026-08-04T00:54:36.648963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.688488Z","title":"Rosenkrantz, Danny R","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.688488Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:694b8636f505ccdb0cc5188da419d2f8291fa188e38334e478b2309ab296a835","observation_id":"834ee2e4-63c1-459a-94eb-4a64a80dbc00","resolution":{"observed_at":"2026-08-04T00:54:36.688488Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-04T00:54:36.719693Z","title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter.arXiv preprint arXiv:1910.01108, 2019","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.719693Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:99a153b29205db60325514ee1a1357d89fc30ec435e075961b55c36f40fb4197","observation_id":"af2d8893-d9aa-469b-8ece-e2817a835f41","resolution":{"observed_at":"2026-08-04T00:54:36.719693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.760467Z","title":"Automatic radiology reports generation via memory align- ment network","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.760467Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:9d65b5a0ad530953301a5d500a19b0c422dfddf981696b2da3e8d78113e70b8d","observation_id":"f81a8589-10be-4268-a7b0-708c73475414","resolution":{"observed_at":"2026-08-04T00:54:36.760467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.788947Z","title":"Automatic radiology reports generation via memory align- ment network","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.788947Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:6140def3153d98da574f5c148d9da305d88dc2618efe1e7de866cca0b491f47c","observation_id":"47a7fe5b-6af9-4451-884b-6bb46be7db3b","resolution":{"observed_at":"2026-08-04T00:54:36.788947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.822734Z","title":"Cwcd: Category-wise contrastive decoding for structured medical report generation","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.822734Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:4cc1f009c0125fa48be154a6ba2d73560afeab67176a4f6545fe259930fdd04c","observation_id":"731dd3a6-fead-4daa-ad9c-f3e192027a29","resolution":{"observed_at":"2026-08-04T00:54:36.822734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.834852Z","title":"Interactive and explainable region-guided radi- ology report generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.834852Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:271f818c815881e6484a1bbc9389f22b157d19d98e6d3821d2dbe473b2379001","observation_id":"0740ad62-56d8-47c6-ab75-c8646717ccb2","resolution":{"observed_at":"2026-08-04T00:54:36.834852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.867510Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.867510Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:90995bc8d196cb0a7d1fd1f61f5390c9bdd627d67af438c75eab4382d1e19ec1","observation_id":"9c94296d-4241-47c5-bb86-28d4fb54dd6d","resolution":{"observed_at":"2026-08-04T00:54:36.867510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.895665Z","title":"Show and tell: A neural image caption generator","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.895665Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:6b91d678e9abd3317b57e852aa25c87349c6963166dbffaf89b0a67719f1d33b","observation_id":"ca3b164f-dadb-46ce-bc65-5c3a8fcc1c9f","resolution":{"observed_at":"2026-08-04T00:54:36.895665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.927231Z","title":"Multi-granularity cross-modal align- ment for generalized medical visual representation learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.927231Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:158b00c62368538b7678cad305de69c986e028db0149061df8e3f282ca7a97c7","observation_id":"958fc994-1fe1-4b0e-b030-f7301567cc93","resolution":{"observed_at":"2026-08-04T00:54:36.927231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.946555Z","title":"Hergen: Ele- vating radiology report generation with longitudinal data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.946555Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:e5596162307fb1c6915f422a3ca08a444f96dc2fbd2a4c0d12028e83148571e0","observation_id":"5dfc52bb-52a0-44c6-ad07-b5b1b96791a3","resolution":{"observed_at":"2026-08-04T00:54:36.946555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:36.965194Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:36.965194Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:618b39833d193b0ad4b2da523bfd6f847f4f55e0dcb9af1c85f0022e8d84e8c1","observation_id":"f26ee8a1-d81b-427b-9210-7384f9a73774","resolution":{"observed_at":"2026-08-04T00:54:36.965194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.020614Z","title":"A medical semantic-assisted transformer for ra- diographic report generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.020614Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:bcc2244fd94b7d678cf0f933617f3a4344cbf458365209eea717b044d2fd05b1","observation_id":"e37644a1-8964-481e-8ef9-e353946fffe7","resolution":{"observed_at":"2026-08-04T00:54:37.020614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.064519Z","title":"Metransformer: Radiology report generation by transformer with multiple learnable expert tokens","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.064519Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:4cea8df6d8f1d15db964b6ef8edfdccc245e607b8524d9c9b5558f006e8f6483","observation_id":"74761da5-0538-4641-9183-ab2c598e0194","resolution":{"observed_at":"2026-08-04T00:54:37.064519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.124493Z","title":"Medklip: Medical knowledge enhanced language- image pre-training for x-ray diagnosis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.124493Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:8a8bc4cb5952c8226c09d0c24b9468e8196962b62dcff8ae4f525266286d7d42","observation_id":"4435eeae-33f2-43de-a9f8-7edd7d06ffbc","resolution":{"observed_at":"2026-08-04T00:54:37.124493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.00316","last_updated":"2021-07-31T20:10:30Z","snapshot_observed_at":"2026-08-18T10:20:10.768334Z","submitted_at":"2021-07-31T20:10:30Z","title":"Chest ImaGenome Dataset for Clinical Reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.00316","snapshot_observed_at":"2026-08-04T00:54:37.167649Z","title":"Chest imagenome dataset for clinical reasoning.arXiv preprint arXiv:2108.00316, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.167649Z"},"links":{"cited_paper":"/paper/2108.00316","citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:822667d846c66c7c2c805c708264cc2c6e1d4411a13e6ed4a3e493cb074ac8b3","observation_id":"65bd577b-b453-4438-90ef-72adbf5ba585","resolution":{"observed_at":"2026-08-04T00:54:37.167649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.275244Z","title":"Show, attend and tell: Neural image caption genera- tion with visual attention","venue":null,"work_id":null,"year":2048},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.275244Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:28760d9e1808bea91ab68f95896d960e2f7ea3ce412a9c012d5ffa02647dad08","observation_id":"59050111-4ca8-4738-9025-68d8cdfdba26","resolution":{"observed_at":"2026-08-04T00:54:37.275244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.326552Z","title":"Multimodal recurrent model with attention for automated radiology report generation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.326552Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:5295d661fbc5b84a583c6947051b36aa8698a3a95067f63e210d87f15199fbb3","observation_id":"a76eac96-b732-464a-a3a5-fd04f9935895","resolution":{"observed_at":"2026-08-04T00:54:37.326552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.386714Z","title":"Kuo, Subathra Adithan, Eduardo Pontes Reis, Stephen Kwak, Vasantha Ku- mar Venugopal, Chloe O’Connell, Agustina Saenz, Pranav Rajpurkar, and Michael Moor","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.386714Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:4f2bcc4061b6e8f97f484013d2d072dd8e0fa0f9276ff5321630aed5abe6a715","observation_id":"473a421c-51c0-4694-bed0-e06e1e048249","resolution":{"observed_at":"2026-08-04T00:54:37.386714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.426700Z","title":"Automatic gener- ation of medical imaging diagnostic report with hierarchical recurrent neural network","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.426700Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:da314c87d74cfe173b388b8bf0e1c6c24d59a99905288322f5c54e7d00f26301","observation_id":"3031411c-3844-46b5-b3ea-8a3f34bebbba","resolution":{"observed_at":"2026-08-04T00:54:37.426700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.496521Z","title":"Aligntransformer: Hierarchical alignment of visual regions and disease tags for medical report generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.496521Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:4f454db192b33e88138ae335e6ac0dd2a50e7d4a7f28d2492c66c011d88d8224","observation_id":"6bcb8dc1-f01c-416d-9c57-8b7b79934011","resolution":{"observed_at":"2026-08-04T00:54:37.496521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.564134Z","title":"Image captioning with semantic attention","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.564134Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:ae26c2b7bfff07442e3e077adf5c42d9cfcda1ced44cbe851d2b2fd87dbeca84","observation_id":"5a9cf5ba-2d2e-4d6c-a77f-4d16d0caf39b","resolution":{"observed_at":"2026-08-04T00:54:37.564134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.604641Z","title":"A clinically accessible small multimodal radiology model and evaluation metric for chest x-ray findings.Nature Communications, 16 (1):3108, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.604641Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:0e0b2e8fab4c4a136fa5825a1078f6acdfd0f6e4cfa8bff1f21b2884fb374801","observation_id":"6a1f106f-df44-4f92-8ed3-a3e0c67a01fd","resolution":{"observed_at":"2026-08-04T00:54:37.604641Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00299","last_updated":"2024-11-16T04:37:48Z","snapshot_observed_at":"2026-08-16T13:03:55.956558Z","submitted_at":"2024-11-01T01:38:42Z","title":"RadFlag: A Black-Box Hallucination Detection Method for Medical Vision Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00299","snapshot_observed_at":"2026-08-04T00:54:37.672577Z","title":"Radflag: A black-box hallucination detec- tion method for medical vision language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.672577Z"},"links":{"cited_paper":"/paper/2411.00299","citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:764f50af391011b21c1fa8feb6a7bf5705e9214882a50a7b09e56a52d25c4765","observation_id":"c8348acf-1580-49a8-8946-17dca487d8e2","resolution":{"observed_at":"2026-08-04T00:54:37.672577Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.742982Z","title":"Knowledge-enhanced visual-language pre- training on chest radiology images.Nature Communications, 14(1):4542, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.742982Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:070c1acf23c2b4eff0620353ccf8f25e6c9562cd4d4d37dba21bc9e1fbf54b18","observation_id":"792391cd-7d53-431c-96d2-48ab87e679e9","resolution":{"observed_at":"2026-08-04T00:54:37.742982Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T00:54:37.900938Z","title":"When radiology report generation meets knowledge graph","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-04T00:54:37.900938Z"},"links":{"citing_paper":"/paper/2608.00279"},"observation_digest":"sha256:64fa9f27c413fa984747902d83b7b8c812fd39b1ac3a5ba8a5fdae90e7631ba6","observation_id":"797865b6-c265-41e4-8227-f607025f167e","resolution":{"observed_at":"2026-08-04T00:54:37.900938Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.00279","last_updated":"2026-07-31T20:31:19Z","latest_version":1,"primary_category":"eess.IV","snapshot_observed_at":"2026-08-15T15:44:26.022852Z","submitted_at":"2026-07-31T20:31:19Z","title":"Learning to See Locally and Align Clinically with Pathology Semantics for Radiology Report Generation"},"reference_resolution":{"displayed":68,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":68,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":68},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 68 of 68 outbound references and 0 inbound Pith citation observations for arXiv:2608.00279."}