{"as_of":"2026-08-14T18:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:880470802a32134a2b4b4e7d71c10e60f84eaf9e42b717c2740e9f2cf6f22ed4","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T15:42:29.744060Z","state":"measured"},{"denominator":65,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":65,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T10:40:04.488059Z","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":"2026-05-10T00:19:46.872557Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"cited_work":{"arxiv_id":"2512.16189","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2512.16189","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"15a7c68b-6d25-4943-9395-03a0d295fb29","year":2025},"citing_paper":{"arxiv_id":"2604.21076","last_updated":"2026-04-22T20:39:35Z","snapshot_observed_at":"2026-08-11T19:16:18.461473Z","submitted_at":"2026-04-22T20:39:35Z","title":"Serialisation Strategy Matters: How FHIR Data Format Affects LLM Medication Reconciliation","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-05-10T00:17:58.452177Z"},"links":{"cited_paper":"/paper/2512.16189","citing_paper":"/paper/2604.21076"},"observation_digest":"sha256:929324fb55ffbcb523df59f9d0987346cd522bb0ff21df9c995be50d9d7f8da0","observation_id":"40e95701-5e12-4901-bd4c-bb77c1d5bdfe","resolution":{"observed_at":"2026-05-26T02:03:06.972910Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.16189","snapshot_observed_at":"2026-08-02T10:40:04.488059Z","title":"Fact-checking module for llm-generated summaries in healthcare,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14126","last_updated":"2026-06-19T18:15:06Z","snapshot_observed_at":"2026-08-08T02:20:00.305918Z","submitted_at":"2026-06-19T18:15:06Z","title":"Interpretable Language Model for Closed-Loop Type 1 Diabetes Control","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T10:40:04.488059Z"},"links":{"cited_paper":"/paper/2512.16189","citing_paper":"/paper/2607.14126"},"observation_digest":"sha256:b8563889074118f311f2f5b34b96acbf27110d493d1656245667c6f46f8d8bfd","observation_id":"32ec17e5-e434-43a6-abbe-ae349aa6ac22","resolution":{"observed_at":"2026-08-02T10:40:04.488059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2512.16189/citation-record","integrity":"/paper/2512.16189/integrity","json":"/paper/2512.16189/citation-record.json","paper":"/paper/2512.16189"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:42:23.981412Z","title":"Roles and potential of large language models in healthcare: A comprehensive review,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:23.981412Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:ce60ede068eb4b3c5db2d702cf81793573c1aaad56500068328e86c2b9f0752f","observation_id":"137b9832-e447-426b-8290-3cd6d7da29f7","resolution":{"observed_at":"2026-08-03T15:42:23.981412Z","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":"2026-08-03T15:42:24.035871Z","title":"Bioknowprompt: Incorporating imprecise knowledge into prompt-tuning verbalizer with biomedical text for relation extraction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.035871Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:b1faadfad767cdbec956a68c1c08a5a8e5b819badb0e2c4d3518b422e5031847","observation_id":"052bd0b5-d94c-4e3f-8709-ec92cf2597ab","resolution":{"observed_at":"2026-08-03T15:42:24.035871Z","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":"2026-08-03T15:42:24.143430Z","title":"Medical hallucinations in foundation models and their impact on healthcare,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.143430Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:b451ea72095fbb511960352be5c53436694474c19667169beb36eeb02d6e3d1a","observation_id":"5f8304e6-db95-4125-8a0a-a8eeeca75a58","resolution":{"observed_at":"2026-08-03T15:42:24.143430Z","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":"2026-08-03T15:42:24.349021Z","title":"Uncertainty-aware multi- criteria decision analysis for evaluation of explainable ar- tificial intelligence methods: A use case from the health- care domain,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.349021Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:d518ada7def80d0e7d8440d838f749a2d0baa2dee1568b01bb24893a16c5fe99","observation_id":"3d92b693-de64-4f6b-8e2d-56052053ac58","resolution":{"observed_at":"2026-08-03T15:42:24.349021Z","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":"2026-08-03T15:42:24.466538Z","title":"Mcd-ears: A multi- modal cross-domain expertise-aware recommender sys- tem for healthcare applications,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.466538Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:0dfb1bbdb166c4d84e42c280c449cae99b46cba769179bc8b8ef1399de287f77","observation_id":"8a696284-8b2a-4c6d-9a47-bc42f263ade4","resolution":{"observed_at":"2026-08-03T15:42:24.466538Z","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":"2026-08-03T15:42:24.591378Z","title":"Scene generalization for biomedical fact verifi- cation via hierarchical mixture of experts,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.591378Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:6a48c95ea0b5950253682725f283bd7b41eecee171d9ceeaaf26efbb5f4dc408","observation_id":"2ac5969a-d385-4b85-9672-2c717f8da153","resolution":{"observed_at":"2026-08-03T15:42:24.591378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.05922","last_updated":"2023-09-12T02:34:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-12T02:34:06Z","title":"A Survey of Hallucination in Large Foundation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.05922","snapshot_observed_at":"2026-08-03T15:42:24.707994Z","title":"A survey of hal- lucination in large foundation models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.707994Z"},"links":{"cited_paper":"/paper/2309.05922","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:72d51abb106680bcfababb2c91e5fa7a064da768d2d214ac536a218fb328358d","observation_id":"1baf479b-02fa-4c8d-899a-31a1f43127ff","resolution":{"observed_at":"2026-08-03T15:42:24.707994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00661","last_updated":"2020-05-02T00:09:16Z","snapshot_observed_at":"2026-08-10T04:33:38.804864Z","submitted_at":"2020-05-02T00:09:16Z","title":"On Faithfulness and Factuality in Abstractive Summarization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00661","snapshot_observed_at":"2026-08-03T15:42:24.805420Z","title":"On faithfulness and factuality in abstractive summariza- tion,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.805420Z"},"links":{"cited_paper":"/paper/2005.00661","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:c259f00ce10d496b92c5b20ef53ad44eb543cc5fa8d1633a93cb2c46bad0ff8b","observation_id":"677347a8-c375-4836-8d5a-b5a7e72674d5","resolution":{"observed_at":"2026-08-03T15:42:24.805420Z","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":"2026-08-03T15:42:24.909884Z","title":"Prescrib- ing the right remedy: Mitigating hallucinations in large vision-language models via targeted instruction tuning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:24.909884Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:7befe87dab185b8ec0220980955165d6c1db4b691e6505ddd61bb95fd6e60d35","observation_id":"4b72e713-8aa1-4ebd-b012-00086e1d406c","resolution":{"observed_at":"2026-08-03T15:42:24.909884Z","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":"2026-08-03T15:42:25.031818Z","title":"Virtsi: A novel trust dynamics model enhancing artifi- cial intelligence collaboration with human users–insights from a chatgpt evaluation study,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:25.031818Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:1283040e3bf4fb2560bc98ec7513092f3a5a3e5324b8f3232420572f51dbf40f","observation_id":"57fc821c-e8a6-4c9e-944b-df5e7f32b103","resolution":{"observed_at":"2026-08-03T15:42:25.031818Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15343","last_updated":"2023-10-14T17:04:12Z","snapshot_observed_at":"2026-08-13T10:45:42.702671Z","submitted_at":"2023-07-28T06:43:04Z","title":"Med-HALT: Medical Domain Hallucination Test for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.15343","snapshot_observed_at":"2026-08-03T15:42:25.141856Z","title":"Med- halt: Medical domain hallucination test for large lan- guage models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:25.141856Z"},"links":{"cited_paper":"/paper/2307.15343","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:e8c484ccdb36f2a5068640aa87f8f983a22d794a51d5a851abf2fc0099a2e108","observation_id":"4c7ef403-d532-466b-b40a-93cbb6bffbd9","resolution":{"observed_at":"2026-08-03T15:42:25.141856Z","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":"2026-08-03T15:42:25.296281Z","title":"Generative ai hallucinations in health- care: A challenge for prompt engineering and creativity,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:25.296281Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:b07cc02557504c9cfa7c0e7807a7d6f5aad8d9aa1685232675b5d648059f44a3","observation_id":"7bc36fb3-e3c6-4fc4-ba1d-6d530a7e9bf7","resolution":{"observed_at":"2026-08-03T15:42:25.296281Z","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":"2026-08-03T15:42:25.547273Z","title":"Embracing large lan- guage models for medical applications: opportunities and challenges,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:25.547273Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:3aa0682501fb623b0077fcbb8a9bcda734ebafbc0dafa382b8908b2162bec9f6","observation_id":"c25de580-7472-4fbb-b8cc-e9038d1d2423","resolution":{"observed_at":"2026-08-03T15:42:25.547273Z","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":"2026-08-03T15:42:25.661814Z","title":"Large language models encode clinical knowledge,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:25.661814Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:f0ba200718df4819cb588398f75f3887c8fb7eec7fe4c7eed8551a6c272865ca","observation_id":"cb3f40a9-fbdc-4599-a86f-9c30bcc44a33","resolution":{"observed_at":"2026-08-03T15:42:25.661814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09968","last_updated":"2023-06-16T16:56:32Z","snapshot_observed_at":"2026-08-13T11:15:08.522021Z","submitted_at":"2023-06-16T16:56:32Z","title":"ClinicalGPT: Large Language Models Finetuned with Diverse Medical Data and Comprehensive Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09968","snapshot_observed_at":"2026-08-03T15:42:25.848359Z","title":"Clin- icalgpt: Large language models finetuned with diverse medical data and comprehensive evaluation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:25.848359Z"},"links":{"cited_paper":"/paper/2306.09968","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:0101b616367b395a03213dac0ad5adc75b3583277811e120eef805ae59e7821c","observation_id":"0eeb3796-7b06-4d9d-ba52-b4cd1093069f","resolution":{"observed_at":"2026-08-03T15:42:25.848359Z","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":"2026-08-03T15:42:25.945249Z","title":"Evaluating large language models on medical evidence summarization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:25.945249Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:82c56ac5d1dd2445b95cad077ff7ddd51af3fad9a7d15bd7a2592f77d627f301","observation_id":"a5e97f7e-aa29-4c70-b999-414d944b72ed","resolution":{"observed_at":"2026-08-03T15:42:25.945249Z","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":"2026-08-03T15:42:26.051955Z","title":"Opportunities, chal- lenges, and future directions of large language models, including chatgpt in medical education: a systematic scoping review,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.051955Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:14cffd44d615a43c1c6797be69a1c3521c5db47db85e907d0ecd5211feb195f0","observation_id":"c125e36a-b320-4e0d-a5f3-52f028f14c83","resolution":{"observed_at":"2026-08-03T15:42:26.051955Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.11129","last_updated":"2025-06-10T17:12:28Z","snapshot_observed_at":"2026-08-12T03:42:52.845842Z","submitted_at":"2025-06-10T17:12:28Z","title":"Trustworthy AI for Medicine: Continuous Hallucination Detection and Elimination with CHECK","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.11129","snapshot_observed_at":"2026-08-03T15:42:26.131857Z","title":"Trustworthy ai for medicine: Continuous hallucination detection and elimination with check,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.131857Z"},"links":{"cited_paper":"/paper/2506.11129","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:2a24deec02cb6397e5151f2e86db452bd2a866dc076d093264f1228fb9fb6a4e","observation_id":"3f1cece9-d080-412f-86aa-618fe93c6843","resolution":{"observed_at":"2026-08-03T15:42:26.131857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.11401","last_updated":"2021-04-12T15:42:18Z","snapshot_observed_at":"2026-08-07T05:44:30.677502Z","submitted_at":"2020-05-22T21:34:34Z","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.11401","snapshot_observed_at":"2026-08-03T15:42:26.309903Z","title":"Retrieval- augmented generation for knowledge-intensive nlp tasks,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.309903Z"},"links":{"cited_paper":"/paper/2005.11401","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:f6e145f0636e15ab635c7a43ed1ab174e00f504036bde362b8ad98527002e07a","observation_id":"74a09b21-612c-4e1c-b741-14e83e89a0fd","resolution":{"observed_at":"2026-08-03T15:42:26.309903Z","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":"2026-08-03T15:42:26.380497Z","title":"Retrieval augmentation reduces hallucination in conversation,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.380497Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:3fc25a7ecfbb0652bd99ec3b7c4a6845e06e863bd11329f9e7e13f1263f2f226","observation_id":"3e6d87ee-8e83-40b7-97c0-47ab12921306","resolution":{"observed_at":"2026-08-03T15:42:26.380497Z","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":"2026-08-03T15:42:26.548314Z","title":"Survey of halluci- nation in natural language generation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.548314Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:81929b0b576e89070cced39e26c631e314c7020d673ce745eff796234a6505c9","observation_id":"c16fa803-3383-410f-b2ea-cfb34fa400f0","resolution":{"observed_at":"2026-08-03T15:42:26.548314Z","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":"2026-08-03T15:42:26.715363Z","title":"Mimic-iii, a freely accessi- ble critical care database,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.715363Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:6fb8a1f3d83ce36849ae1e60729286fc44bf77c80e9572d31b85e4cc7feb312f","observation_id":"76cb4819-1092-4ea2-bcb0-eade69b17021","resolution":{"observed_at":"2026-08-03T15:42:26.715363Z","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":"2026-08-03T15:42:26.784996Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.784996Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:87a5e3795c2ffb3f0fd0f3a0f24a8d482c5c95dde1a9aa259736c491c5e41085","observation_id":"ca5d83b0-ee18-40d4-8c49-8052969d1c96","resolution":{"observed_at":"2026-08-03T15:42:26.784996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11456","last_updated":"2024-06-05T01:27:00Z","snapshot_observed_at":"2026-08-13T04:16:51.405467Z","submitted_at":"2024-02-18T04:45:01Z","title":"FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11456","snapshot_observed_at":"2026-08-03T15:42:26.848012Z","title":"Factpico: Factuality evaluation for plain language summarization of medical 17 evidence,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.848012Z"},"links":{"cited_paper":"/paper/2402.11456","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:722347a34625b8bcb9ee70e4ee9e6b8acf6acd3b1bc14a38c0921c8d7c7a0834","observation_id":"a2f001fe-cc40-4c45-a31c-abdfdc673794","resolution":{"observed_at":"2026-08-03T15:42:26.848012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08503","last_updated":"2024-03-25T08:33:37Z","snapshot_observed_at":"2026-08-14T05:11:54.659962Z","submitted_at":"2023-09-15T16:05:48Z","title":"HealthFC: Verifying Health Claims with Evidence-Based Medical Fact-Checking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.08503","snapshot_observed_at":"2026-08-03T15:42:26.908385Z","title":"Healthfc: Verifying health claims with evidence-based medical fact- checking,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.908385Z"},"links":{"cited_paper":"/paper/2309.08503","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:88d7e63cd1b2f8f70a745c0168e608f72d135f34de11c1603e885f44a877b49b","observation_id":"d5abf19a-ecf1-4ba9-8f69-d7309701251f","resolution":{"observed_at":"2026-08-03T15:42:26.908385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.10774","last_updated":"2024-10-01T15:39:48Z","snapshot_observed_at":"2026-08-13T00:28:52.552089Z","submitted_at":"2024-04-16T17:59:10Z","title":"MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.10774","snapshot_observed_at":"2026-08-03T15:42:27.011663Z","title":"Minicheck: Efficient fact-checking of llms on grounding documents,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.011663Z"},"links":{"cited_paper":"/paper/2404.10774","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:29e2a8e5fee99c773850991167a7b472ad72f786cdd06f798204f99f872bf105","observation_id":"e7b751b0-2b0c-4fc3-8216-3f9125a70099","resolution":{"observed_at":"2026-08-03T15:42:27.011663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.16514","last_updated":"2025-05-28T07:57:49Z","snapshot_observed_at":"2026-08-07T17:55:26.202432Z","submitted_at":"2025-02-23T09:25:00Z","title":"GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-Checking","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.16514","snapshot_observed_at":"2026-08-03T15:42:27.080073Z","title":"Graphcheck: Breaking long-term text barriers with ex- tracted knowledge graph-powered fact-checking,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.080073Z"},"links":{"cited_paper":"/paper/2502.16514","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:e037a8ea6b44ebdf9ed1b39e9a020b18d0f64b183a9f25a8c6a00912dff1cd85","observation_id":"07a6996e-5842-410d-acc9-8a4f35aa81ca","resolution":{"observed_at":"2026-08-03T15:42:27.080073Z","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":"2026-08-03T15:42:27.174803Z","title":"DOSSIER: Fact checking in electronic health records while preserving patient privacy,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.174803Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:c59de1ce663d9ff9ce50e72c4392b326ac69d5bdb79caf6dded7d4b89135736c","observation_id":"2ac1fe34-91f6-4f0e-8e12-eed8a79cba36","resolution":{"observed_at":"2026-08-03T15:42:27.174803Z","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":"2026-08-03T15:42:27.322047Z","title":"Brainllama at semeval-2024 task 6: Prompt- ing llama to detect hallucinations and related observ- able overgeneration mistakes,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.322047Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:58b2b7a2ad3c5773a8f6a302f874e4632c697620f053c3dfd19ebd584a65cd4e","observation_id":"4bcd3bbf-61a9-4006-bec4-987f5b6d38ae","resolution":{"observed_at":"2026-08-03T15:42:27.322047Z","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":"2026-08-03T15:42:27.484824Z","title":"Gpt hallucination detection through prompt engineering,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.484824Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:c95e367b299678647361d093777866734477152329b0c2890df81c94fcf2d8bf","observation_id":"8c59a1af-f1a8-4830-ac19-53fcae6d1129","resolution":{"observed_at":"2026-08-03T15:42:27.484824Z","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":"2026-08-03T15:42:27.561646Z","title":"Factselfcheck: Fact-level black- box hallucination detection for llms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.561646Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:715ee19fa364c7885e37e1c1514b69f7ffdbe65b24566a05194a8455578e02a5","observation_id":"3f961a94-3131-4fc0-b049-da6b280c5f5a","resolution":{"observed_at":"2026-08-03T15:42:27.561646Z","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":"2026-08-03T15:42:27.665107Z","title":"Zero-knowledge llm hallucination detection and mitigation through fine-grained cross-model consistency,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.665107Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:aa281d630b9e1dea0d55374c0612edbdcf4299ed669c1ac0ffc4057e15cf1f84","observation_id":"427d36e9-b8ec-43bb-9b31-939748098fee","resolution":{"observed_at":"2026-08-03T15:42:27.665107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.01862","last_updated":"2025-08-03T17:29:48Z","snapshot_observed_at":"2026-08-06T05:23:58.304118Z","submitted_at":"2025-08-03T17:29:48Z","title":"Counterfactual Probing for Hallucination Detection and Mitigation in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.01862","snapshot_observed_at":"2026-08-03T15:42:27.753911Z","title":"Counterfactual probing for hallucination de- tection and mitigation in large language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.753911Z"},"links":{"cited_paper":"/paper/2508.01862","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:de8b8188255714b7ce344d3fc3d70f89787e105318c35bb8ef25cadc8476f43c","observation_id":"d55f69c9-5251-47f3-bd5c-058b17863403","resolution":{"observed_at":"2026-08-03T15:42:27.753911Z","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":"2026-08-03T15:42:27.840885Z","title":"Large language models in health care: Development, applications, and challenges,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.840885Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:163280b4d06df423be87c86ef8199f99bc7c83294a01d579e0705e0d03c08d89","observation_id":"574c96ef-0584-44df-bf61-859c4bbce22c","resolution":{"observed_at":"2026-08-03T15:42:27.840885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.17124","last_updated":"2024-09-08T19:17:32Z","snapshot_observed_at":"2026-08-13T23:23:30.267794Z","submitted_at":"2024-02-27T01:37:23Z","title":"Fact-and-Reflection (FaR) Improves Confidence Calibration of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.17124","snapshot_observed_at":"2026-08-03T15:42:27.932287Z","title":"Fact-and-reflection (far) improves confidence calibration of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.932287Z"},"links":{"cited_paper":"/paper/2402.17124","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:3da948133e3a334ebc593089e79f481d11696d86e1aa47037b6a2d6926c80ac4","observation_id":"6396faf8-9ad8-4286-94ec-d08842517c3f","resolution":{"observed_at":"2026-08-03T15:42:27.932287Z","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":"2026-08-03T15:42:28.001656Z","title":"Ethical and regulatory challenges of large language models in medicine,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.001656Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:21f4904e6b7b2104d38d099c2e38b173727dc219052ae702ba1ef1fd42b10693","observation_id":"2f88940b-3f50-4a3f-9113-1fa6fdbd70af","resolution":{"observed_at":"2026-08-03T15:42:28.001656Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15422","last_updated":"2024-06-25T17:02:10Z","snapshot_observed_at":"2026-08-13T04:12:00.176978Z","submitted_at":"2024-02-23T16:32:28Z","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15422","snapshot_observed_at":"2026-08-03T15:42:28.051483Z","title":"A data-centric approach to generate faithful and high quality patient sum- maries with large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.051483Z"},"links":{"cited_paper":"/paper/2402.15422","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:7f87956e472dd2c8b42832e62dd2de19944f4c6b0c0fc168a33c17e9f3e6349f","observation_id":"429a0a88-1db1-4bc6-bca1-b46bdc301ba7","resolution":{"observed_at":"2026-08-03T15:42:28.051483Z","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":"2026-08-03T15:42:28.112373Z","title":"Deploy llama 3 8b with vllm,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.112373Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:ceda6d90c0140271cbb8f46b3a3e883d7a6c4793331444d398b94565125058e9","observation_id":"defce365-edc6-4c52-82a7-44868a7e2a3f","resolution":{"observed_at":"2026-08-03T15:42:28.112373Z","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":"2026-08-03T15:42:28.168193Z","title":"Benchmarking llm inference back- ends,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.168193Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:5069530ded943888943c3d168d264d70f9bc9e3461361e7b86500902f208f534","observation_id":"0fd0f6af-7838-47d2-9a8e-94cfd77aa80e","resolution":{"observed_at":"2026-08-03T15:42:28.168193Z","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":"2026-08-03T15:42:28.225645Z","title":"Evidencemap: a three-level knowledge representation for medical evidence computation and comprehension,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.225645Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:7a66ece620ac723fef0e07afcb49104e11282bb18e47dd524afed49772c23d45","observation_id":"90d2dc27-9a20-4d31-8360-85c83bb6d57a","resolution":{"observed_at":"2026-08-03T15:42:28.225645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.07687","last_updated":"2018-09-05T12:47:39Z","snapshot_observed_at":"2026-08-09T08:19:50.449392Z","submitted_at":"2018-06-20T12:13:53Z","title":"Automated Fact Checking: Task formulations, methods and future directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.07687","snapshot_observed_at":"2026-08-03T15:42:28.283948Z","title":"Automated fact check- ing: Task formulations, methods and future directions,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.283948Z"},"links":{"cited_paper":"/paper/1806.07687","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:8338e8725ed0309358b89895c43b86fdc2d839ff66c7fb187eedac3634edc22f","observation_id":"fbc9f12b-2906-4c92-af77-a67e2b7e60d2","resolution":{"observed_at":"2026-08-03T15:42:28.283948Z","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":"2026-08-03T15:42:28.346785Z","title":"The perils and promises of fact-checking with large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.346785Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:11849b9815c5d746dcebb18dc9dccc261d2013a0f36450d45ee3c6cfc6661a63","observation_id":"76926eb4-0369-48c3-a8ee-e26a0fa12865","resolution":{"observed_at":"2026-08-03T15:42:28.346785Z","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":"2026-08-03T15:42:28.401684Z","title":"Scientific claim verification with fine- tuned nli models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.401684Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:9f84e70f3448c99edcdc0ce659adb3626b56c7f6c9a3d9202599154298a0fc9a","observation_id":"3a4a05f8-924c-4733-bd14-6e395e3d39f6","resolution":{"observed_at":"2026-08-03T15:42:28.401684Z","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":"2026-08-03T15:42:28.494186Z","title":"Large language models in medicine,","venue":null,"work_id":null,"year":1930},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.494186Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:e69872ff5f5de73070dcfb72803db8fa67a05fbff9b1fd79ac8e9e9c97e69b60","observation_id":"737c77a1-6c7f-4bc5-864c-4296dba060d6","resolution":{"observed_at":"2026-08-03T15:42:28.494186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01313","last_updated":"2024-01-08T16:19:17Z","snapshot_observed_at":"2026-07-06T17:10:56.398607Z","submitted_at":"2024-01-02T17:56:30Z","title":"A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.01313","snapshot_observed_at":"2026-08-03T15:42:28.561218Z","title":"A comprehensive survey of hal- lucination mitigation techniques in large language mod- els,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.561218Z"},"links":{"cited_paper":"/paper/2401.01313","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:90f102bcd02c3a5c9fd9f73dd5e348659f00181a999e72878a1935d20d628903","observation_id":"e2e385bd-61f4-4e9b-b649-1e76b4d586bc","resolution":{"observed_at":"2026-08-03T15:42:28.561218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.02351","last_updated":"2026-06-29T08:12:53Z","snapshot_observed_at":"2026-08-12T23:30:19.527362Z","submitted_at":"2024-07-02T15:16:46Z","title":"Generative Large Language Models in Automated Fact-Checking: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.02351","snapshot_observed_at":"2026-08-03T15:42:28.620494Z","title":"Generative large language models in automated fact- checking: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.620494Z"},"links":{"cited_paper":"/paper/2407.02351","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:97592c1a57950350685f1c04ce9182f0eb919ca45e4f9a19207c282cf5e1930d","observation_id":"8b90ae38-44c2-464c-a738-d84a0b4044eb","resolution":{"observed_at":"2026-08-03T15:42:28.620494Z","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":"2026-08-03T15:42:28.708277Z","title":"A survey on hallucination in large language models: Prin- ciples, taxonomy, challenges, and open questions,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.708277Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:af3db5bd41dfe928eaa676dbd1a4a1dc4b1135ddb1a2dcaeca29afa8904d30f9","observation_id":"1a7c5e8d-d8a8-47d8-a663-5b52f70e6b70","resolution":{"observed_at":"2026-08-03T15:42:28.708277Z","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":"2026-08-03T15:42:28.768065Z","title":"Overview of the mediqa-corr 2024 shared task on medical error detection and correction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.768065Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:a3cf4a6333dccbec3152bac8fa3de311223833c6f7dc0159ff6a3dc0be083f54","observation_id":"f0d62acb-347a-4b7f-b3a0-6f5597f5b99e","resolution":{"observed_at":"2026-08-03T15:42:28.768065Z","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":"2026-08-03T15:42:28.836910Z","title":"Bridg- ing pre-trained models to continual learning: A hyper- network based framework with parameter-efficient fine- tuning techniques,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.836910Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:0e33cd5efa7f77224293a8562b86318a231e079d4e63e511204a7392f59c62fb","observation_id":"13f748c7-7801-46ae-aa52-ca63803affc2","resolution":{"observed_at":"2026-08-03T15:42:28.836910Z","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":"2026-08-03T15:42:28.935462Z","title":"Bioportal: ontologies and in- tegrated data resources at the click of a mouse,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:28.935462Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:a6832310944e9a53694083733e819433389bc703926553ef6237ad350bd29ea2","observation_id":"0796d13f-7466-4c18-9401-43776494a0fe","resolution":{"observed_at":"2026-08-03T15:42:28.935462Z","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":"2026-08-03T15:42:29.009409Z","title":"Improving natural language arguments’ identification by leveraging semantic similarity,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.009409Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:744e4403920d0694282e52af7b2d8afeaa884e385ac6d9db9fd29e95980b0fc1","observation_id":"241cb15a-6e5c-4ae2-b57a-bfc38133b430","resolution":{"observed_at":"2026-08-03T15:42:29.009409Z","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":"2026-08-03T15:42:29.071666Z","title":"Negation scope detection for sentiment analysis: A re- inforcement learning framework for replicating human interpretations,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.071666Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:3bce9a2a0fad75c7b0b2eeadc3d20fde27a7c3667726182b81a63b2f6d5bebaf","observation_id":"758af956-6368-4ad9-a05f-ea1985fccf37","resolution":{"observed_at":"2026-08-03T15:42:29.071666Z","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":"2026-08-03T15:42:29.153925Z","title":"Mimic-iii, a freely accessible critical care database,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.153925Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:c8db069647a820978303f57c484673a7745f6e37e1cf74905a1f849c86dad0bd","observation_id":"e03a2a77-db0f-4695-85f8-f86ccdef6aed","resolution":{"observed_at":"2026-08-03T15:42:29.153925Z","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":"2026-08-03T15:42:29.221460Z","title":"Releasing claude instant 1.2,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.221460Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:ee98d7259c46ce8316792ba5fda473a149223efc51c40ef455d19cec63dc4dd7","observation_id":"05709708-9426-48cc-b167-d85cfae52973","resolution":{"observed_at":"2026-08-03T15:42:29.221460Z","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":"2026-08-03T15:42:29.275078Z","title":"Claude 2,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.275078Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:0381c0aaeec72c90be61806905821c59d0026c060e9fb2e47b8aa1a1402bd90a","observation_id":"ffd1c010-540b-4a31-b566-7a482a1b4923","resolution":{"observed_at":"2026-08-03T15:42:29.275078Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12950","last_updated":"2024-01-31T19:47:26Z","snapshot_observed_at":"2026-08-13T04:25:38.282910Z","submitted_at":"2023-08-24T17:39:13Z","title":"Code Llama: Open Foundation Models for Code","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12950","snapshot_observed_at":"2026-08-03T15:42:29.345281Z","title":"Code llama: Open foundation models for code,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.345281Z"},"links":{"cited_paper":"/paper/2308.12950","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:bb8b49774c6c05d54d559144824465b1677583e8bab1344cf2eb4482ab4bcf2c","observation_id":"34798110-d13b-4ca9-a55c-f30275ed9d0b","resolution":{"observed_at":"2026-08-03T15:42:29.345281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08247","last_updated":"2025-03-18T21:31:51Z","snapshot_observed_at":"2026-08-13T12:02:57.819222Z","submitted_at":"2023-04-14T11:28:08Z","title":"MedAlpaca -- An Open-Source Collection of Medical Conversational AI Models and Training Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08247","snapshot_observed_at":"2026-08-03T15:42:29.445366Z","title":"Medalpaca – an open-source collection of medical conversational ai models and training data,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.445366Z"},"links":{"cited_paper":"/paper/2304.08247","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:fab9a95204069911762287453c1245d9b74832269980dc83816fb12a82f11dd6","observation_id":"790d07be-fbbe-468b-b54e-40f156fc9a91","resolution":{"observed_at":"2026-08-03T15:42:29.445366Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.12031","last_updated":"2023-08-17T17:19:02Z","snapshot_observed_at":"2026-08-13T11:38:24.544752Z","submitted_at":"2023-05-19T23:07:09Z","title":"Clinical Camel: An Open Expert-Level Medical Language Model with Dialogue-Based Knowledge Encoding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.12031","snapshot_observed_at":"2026-08-03T15:42:29.515722Z","title":"Clinical camel: An open expert-level medical language model with dialogue- based knowledge encoding,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.515722Z"},"links":{"cited_paper":"/paper/2305.12031","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:7406d1318314eac843af69b897418030070b510967a840043785927ee0de2378","observation_id":"39a0885d-ba6c-4071-87ca-d8fe9da87780","resolution":{"observed_at":"2026-08-03T15:42:29.515722Z","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":"2026-08-03T15:42:29.574157Z","title":"Ehrsql: A practical text-to-sql benchmark for electronic health records,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.574157Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:97670e05b9378f6b764cde97b572139f16da800ec6cb1dcd2ae250d9177e2df6","observation_id":"c48740c4-73a2-48ab-803f-3c1e403cc12e","resolution":{"observed_at":"2026-08-03T15:42:29.574157Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.00237","last_updated":"2024-07-29T15:52:22Z","snapshot_observed_at":"2026-08-13T10:22:53.159212Z","submitted_at":"2023-09-01T04:01:20Z","title":"Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00237","snapshot_observed_at":"2026-08-03T15:42:29.656537Z","title":"Publicly shareable clinical large language model built on synthetic clinical notes,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.656537Z"},"links":{"cited_paper":"/paper/2309.00237","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:17a4c4c4212cf7ee23731315b2b4066a941a8f0d62a7865e37c93ab48936bfcb","observation_id":"429a4952-31b6-4e5f-92f5-0b47ce9c74e4","resolution":{"observed_at":"2026-08-03T15:42:29.656537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-03T15:42:29.744060Z","title":"Llama 2: Open foundation and fine- tuned chat models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:29.744060Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:5c7f06d6e18f69a553c76ea799994aa1db51eaadbab587389f4e7c3e78eb9947","observation_id":"7e64c5c5-b3a5-4973-b5e5-c0746c0eff90","resolution":{"observed_at":"2026-08-03T15:42:29.744060Z","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":"2026-08-03T15:42:27.266237Z","title":"[Online]","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":252,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:27.266237Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:5d45566f823fde63a1d6f630e22f04ccc608ac5d5bfc5a44de1d8871c1539151","observation_id":"4598ac43-b4e8-44fa-b21b-4aa0e35e306b","resolution":{"observed_at":"2026-08-03T15:42:27.266237Z","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":"2026-08-03T15:42:26.474477Z","title":"3784–3803","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation","version":4},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-03T15:42:26.474477Z"},"links":{"citing_paper":"/paper/2512.16189"},"observation_digest":"sha256:b9c403f4868894142fa8b342f09d6e8c7aa1496a360b7c4738b14831b40c42dd","observation_id":"b06710ac-4c25-4cba-9ce2-ddba53f37bd9","resolution":{"observed_at":"2026-08-03T15:42:26.474477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.16189","last_updated":"2026-06-09T06:01:03Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T07:13:30.291001Z","submitted_at":"2025-12-18T05:23:47Z","title":"Mitigating hallucinations in healthcare LLMs with granular fact-checking and domain-specific adaptation"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":63,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":63},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 2 inbound Pith citation observations for arXiv:2512.16189."}