{"as_of":"2026-08-14T20:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d13a54c98308d816bb9e393d6cb427748df1c83b0db92a4e32d2faa155c1b9fa","coverage":[{"denominator":50,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":50,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T06:04:43.802360Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T07:05:40.821282Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"cited_work":{"arxiv_id":"2506.06091","doi":"10.48550/arxiv.2506.06091","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.06091","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"doi:10.48550/arXiv.2506.06091","venue":"ArXiv.org","work_id":"e8ba2f6a-57ba-4759-a55f-e9599abf0021","year":null},"citing_paper":{"arxiv_id":"2605.29960","last_updated":"2026-05-28T14:02:00Z","snapshot_observed_at":"2026-08-04T10:03:16.376465Z","submitted_at":"2026-05-28T14:02:00Z","title":"Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-29T07:05:40.821282Z"},"links":{"cited_paper":"/paper/2506.06091","citing_paper":"/paper/2605.29960"},"observation_digest":"sha256:c4802cec27aa381100a09fae7ffc36555fc1a5a6dc8499ea6467c9aadaa4f98f","observation_id":"793e4c2b-727c-48d5-a345-2f21c6fb7ea6","resolution":{"observed_at":"2026-06-29T07:13:15.820189Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2506.06091/citation-record","integrity":"/paper/2506.06091/integrity","json":"/paper/2506.06091/citation-record.json","paper":"/paper/2506.06091"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.630471Z","title":"Gpt-4 technical report","venue":null,"work_id":"330b7790-1389-4762-9b72-562dda6887bc","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.578912Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:c4aa5d3eced31d3f9ed1344a3b183866f2ac21f22b24eb01766bc45748dd29d2","observation_id":"d7c777d9-73b5-4c83-adbc-16a1237d5675","resolution":{"observed_at":"2026-08-07T06:04:44.635323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"1611.09268","last_updated":"2018-10-31T14:46:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-11-28T18:14:11Z","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.09268","snapshot_observed_at":"2026-08-07T06:04:43.588790Z","title":"Ms marco: A human generated machine reading comprehension dataset","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.588790Z"},"links":{"cited_paper":"/paper/1611.09268","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:ef6638dd5ef58e2d57ba8355fd13b68181806337c4fc9aae53845d92b1bfe35f","observation_id":"d042c2e7-eb6f-4362-a605-39a92e3ef98e","resolution":{"observed_at":"2026-08-07T06:04:43.588790Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.616089Z","title":"Large language models in machine translation","venue":null,"work_id":"743b669a-0473-4d12-9595-f9485361ad1f","year":2007},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.594806Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:3845a2dc393cc8ddad040115feb9242610cc3dafa33abaf5e791d73c6394a1a4","observation_id":"5f3f381f-ca91-4a2c-b3ab-395369507e1f","resolution":{"observed_at":"2026-08-07T06:04:44.620655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.601517Z","title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020","venue":null,"work_id":"68a9919a-ab56-4de7-bb90-d2572d0c1be8","year":1901},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.599506Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:01a4fd23e52b23c46a13f193cccba4e224d78f22332c83215b2970ec04960e64","observation_id":"fd7fe0b5-09fb-494d-bd82-c4a464b5a4ea","resolution":{"observed_at":"2026-08-07T06:04:44.606241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:43.604392Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.604392Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:1c13d0a6467273f5352f6c0a8664321fd05e376bf386db2815f54fbfe9a56e2f","observation_id":"e49c8075-3e34-49bf-96fe-9a826b311564","resolution":{"observed_at":"2026-08-07T06:04:43.604392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-07T06:04:43.609072Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.609072Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:c05e06f32da307e64c4de76ba541b2697b1b1d285d83d3705b49855f050c592b","observation_id":"46d3fade-060b-441e-ab95-be3ef49430d2","resolution":{"observed_at":"2026-08-07T06:04:43.609072Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.577889Z","title":"Jina-colbert-v2: A general-purpose multilingual late interaction retriever","venue":null,"work_id":"8ed464a9-3b27-4e1d-9409-62873896f681","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.613846Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:2b2f951956aa52ab42e1dbd2b8f9f0dddd12e4dd4ce250f1056aaaf4b34e2976","observation_id":"2fe3c69e-2f16-4092-88f5-ee5ab956ebc2","resolution":{"observed_at":"2026-08-07T06:04:44.582512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:43.618690Z","title":"What disease does this patient have? a large-scale open domain question answering dataset from medical exams","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.618690Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:92a5ea4fb667d5413160df13aa33a0e7841201a235388d528aa7a310a2fefdeb","observation_id":"d65b1055-8eec-4abb-8986-3186d42610aa","resolution":{"observed_at":"2026-08-07T06:04:43.618690Z","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":"2026-08-07T06:04:43.622789Z","title":"Pubmedqa: A dataset for biomedical research question answering","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.622789Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:9246ff919d8f32bd24c3fe7d9342388f589d468231f616f7affbd8602a9187d2","observation_id":"6aa1fd24-6d1e-48be-b7eb-b0f80132cca0","resolution":{"observed_at":"2026-08-07T06:04:43.622789Z","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":"2026-08-07T06:04:43.627029Z","title":"Colbert: Efficient and effective passage search via contextualized late interaction over bert","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.627029Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:809e793d5783a7666ebe2ffbb373b5d3a4f4c34ce925b703bc835632bdd25993","observation_id":"e58d2672-cba0-492e-85c1-b811d7d3538b","resolution":{"observed_at":"2026-08-07T06:04:43.627029Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.532562Z","title":"Medexqa: Medical question answering benchmark with multiple explanations","venue":null,"work_id":"78fbfed0-563f-4e49-8a9b-a531f573fd51","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.631252Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:6cb1844d4a256f7b8c9f671ed06d052169b758a1d5999fc54f58a07a0f4e3f18","observation_id":"dab62534-cef1-42b6-853f-b58a85cd269e","resolution":{"observed_at":"2026-08-07T06:04:44.537868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.517859Z","title":"Bioasq-qa: A manually curated corpus for biomedical question answering.Scientific Data, 10(1):170, 2023","venue":null,"work_id":"a35957a7-f3c7-4215-8a62-d2eeceb12c86","year":2023},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.635794Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:ae00836bc96e15acbbc1f797870e148b123c6314bde8082b588616729b85a9fa","observation_id":"9471b9af-f52a-40b9-858b-093354c19ba1","resolution":{"observed_at":"2026-08-07T06:04:44.522634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:43.640074Z","title":"Halueval: A large-scale hallucination evaluation benchmark for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.640074Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:9700e1f5ea0d1c2edd9446776297ed07b371c37358b5b7896035bad036794664","observation_id":"dd50041e-379e-4068-992a-5d89c3361a72","resolution":{"observed_at":"2026-08-07T06:04:43.640074Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.492641Z","title":"Retrieval augmented generation or long-context llms? a comprehensive study and hybrid approach","venue":null,"work_id":"ea2cbcee-a65b-4abe-b040-29564b442bfc","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.644391Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:0b8691a7a3234c851361e12a34cef30639a4098f2d9209db23695ee4087ef104","observation_id":"f6fb5744-8768-47ee-9f1d-402603265bfc","resolution":{"observed_at":"2026-08-07T06:04:44.497449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.477730Z","title":"Can large language models reason about medical questions?Patterns, 5(3), 2024","venue":null,"work_id":"1d22331e-9949-4a17-98ac-8fb0bed1e833","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.648759Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:7f51cab3d17b95782861391acb9543da11616d7f4b32c3884687fbf71218f351","observation_id":"a84ac0b8-4ea2-49c6-b09a-f6f5f452204d","resolution":{"observed_at":"2026-08-07T06:04:44.482639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-08-11T01:48:59.557045Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-07T06:04:43.653070Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.653070Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:d3aa86eea5a3db7220663674e8bdc2434f6e6db24258a1d1e85ce81a1a6d7a62","observation_id":"c0d36719-932b-49ce-bca7-4bfedea32764","resolution":{"observed_at":"2026-08-07T06:04:43.653070Z","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":"2026-08-07T06:04:43.657625Z","title":"Query rewriting via large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.657625Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:dc552cf6c12487183e75476e50e8f20925113e517eb37cee13a4b9b59892f330","observation_id":"55d0ad95-15e8-4a60-89fa-de5e212c478a","resolution":{"observed_at":"2026-08-07T06:04:43.657625Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.462526Z","title":"S2orc: The semantic scholar open research corpus","venue":null,"work_id":"bb3bf4c5-fb1d-444c-a96a-85060339c53e","year":2020},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.661822Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:6da3c81615c1389200608e981ffb58c1ca673aafed64462b5a8326837ccc772a","observation_id":"1a8e12e3-28e2-49b9-867d-3265b02b0acb","resolution":{"observed_at":"2026-08-07T06:04:44.467600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2405.14431","last_updated":"2024-05-23T11:00:19Z","snapshot_observed_at":"2026-08-12T23:59:59.676859Z","submitted_at":"2024-05-23T11:00:19Z","title":"RaFe: Ranking Feedback Improves Query Rewriting for RAG","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14431","snapshot_observed_at":"2026-08-07T06:04:43.666531Z","title":"Rafe: ranking feedback improves query rewriting for rag","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.666531Z"},"links":{"cited_paper":"/paper/2405.14431","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:0b8b6e9bf8abf6ceb2e9e1c64a0109dbeb35ce0365f149c6da2dad63a25eeb92","observation_id":"57a56f97-0f57-4418-8a28-d22b32178b47","resolution":{"observed_at":"2026-08-07T06:04:43.666531Z","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":"2026-08-07T06:04:43.671207Z","title":"Med-flamingo: a multimodal medical few-shot learner","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.671207Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:f88c88173953de41ef6a5ecbb199d37a1729632fd276db68c991078bbcd61685","observation_id":"942caf96-6456-41c7-92d2-b9fa7658f263","resolution":{"observed_at":"2026-08-07T06:04:43.671207Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.437003Z","title":"Hybrid retrieval-augmented generation approach for llms query response enhancement","venue":null,"work_id":"1cf519fb-5c9b-4635-9d98-21fabb591f42","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.675676Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:9d987c46ba0bf8eff40be77764cdd63bd596617847f73fc49979b18d1e588412","observation_id":"a02713ed-9d11-4c6e-b88b-10f3ee21b653","resolution":{"observed_at":"2026-08-07T06:04:44.441857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.422076Z","title":"Openbiollms: Advancing open-source large lan- guage models for healthcare and life sciences","venue":null,"work_id":"dc352a52-2338-436b-b0eb-be6775185899","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.680178Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:5e57c19810101cd5ee1d8bfc3d1e29387a3b0da16abf68a16b33ec80aae435c0","observation_id":"7c2dc4a5-4506-44b8-8d34-0f82d5cd5526","resolution":{"observed_at":"2026-08-07T06:04:44.427191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.407584Z","title":"Medmcqa: A large-scale multi- subject multi-choice dataset for medical domain question answering","venue":null,"work_id":"82b05026-3cae-4b35-a140-a5307a7b63f4","year":2022},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.684368Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:1cafab34b1de77115ddc5f45d0239c629fb57d09fad2f2c52f0b3ef3f5892337","observation_id":"40b1d7c2-5cdb-4767-9ac9-b867d95a19a5","resolution":{"observed_at":"2026-08-07T06:04:44.412212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.393021Z","title":"Med-halt: Medical domain hallucination test for large language models","venue":null,"work_id":"567306d8-f5e8-4921-a714-bafc7e573b8f","year":2023},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.688871Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:951dfcbc0c5835382cd8ff02a53eea9ae530b5ef6583410ac66f7618a6b9d952","observation_id":"a813a628-08d9-4f50-a315-19107788858e","resolution":{"observed_at":"2026-08-07T06:04:44.397810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.378363Z","title":"Medhallu: A comprehensive benchmark for detecting medical hallucinations in large language models","venue":null,"work_id":"1d7782d0-0d96-4018-b127-098176e46228","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.693416Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:27c5b6b5ac730f0334425e1a97dd4c665557b1ad99e3814ffe419b799bf7aa95","observation_id":"1bf45452-7e9b-4caa-ae04-f2dc4c3af7cf","resolution":{"observed_at":"2026-08-07T06:04:44.383053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:43.703353Z","title":"The fineweb datasets: Decanting the web for the finest text data at scale","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.703353Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:9ef5f41f43ea05a5e87807d049d512239e9a0e44d218f3c6774a5e8c65bc4791","observation_id":"2a16df9e-1ab8-4ccf-890b-e08e40401804","resolution":{"observed_at":"2026-08-07T06:04:43.703353Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.355237Z","title":"Qdrant - vector database.https://qdrant.tech/","venue":null,"work_id":"05fd59f0-2c79-4064-ae06-e742ead973f5","year":2025},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.707580Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:796788f03b8061b1be993895d3b7d77137a1df382e95676681ae0d7bc95b1f3a","observation_id":"e1e7a82c-cff3-467f-91db-7fd56e400bda","resolution":{"observed_at":"2026-08-07T06:04:44.359844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.341988Z","title":"Language models are unsupervised multitask learners.OpenAI blog, 1(8):9, 2019","venue":null,"work_id":"08961adf-cb81-4bcd-8cb0-431bed5b3006","year":2019},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.711853Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:0d069124ab2c6daa7a9d8bdb67cbc995d01f3863dfe1b82f518115e0a182ae3b","observation_id":"88e99828-d665-41fa-bb64-d48be942fd26","resolution":{"observed_at":"2026-08-07T06:04:44.346226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.328020Z","title":"Colbertv2: Effective and efficient retrieval via lightweight late interaction","venue":null,"work_id":"93d353bc-83e6-473f-82b7-0c19e4603757","year":2022},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.716475Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:a49d5fe42f075c3395bd6dfd24e5a0d45dead93c876f73178ce62fe2fad24cb6","observation_id":"5263b2ea-586a-4513-a6d6-b0821d3192f9","resolution":{"observed_at":"2026-08-07T06:04:44.332606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-07T06:04:43.720972Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.720972Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:d8608396661dfe326b5c2c60c6e89c8b562a2aa80cc39341f959d8468722bc02","observation_id":"55d6d91f-8f72-4866-a6bd-b59bb7d1ec74","resolution":{"observed_at":"2026-08-07T06:04:43.720972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03533","last_updated":"2024-02-22T06:21:51Z","snapshot_observed_at":"2026-07-06T14:27:46.217000Z","submitted_at":"2022-12-07T09:25:54Z","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.03533","snapshot_observed_at":"2026-08-07T06:04:43.725330Z","title":"Text embeddings by weakly-supervised contrastive pre-training","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.725330Z"},"links":{"cited_paper":"/paper/2212.03533","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:87420d95e2a0243a1b86c79b07d7681ed969b9904cf466198fcb1bbcf9999c17","observation_id":"57a15689-e1d6-46ce-9211-6e145a12a4aa","resolution":{"observed_at":"2026-08-07T06:04:43.725330Z","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":"2026-08-07T06:04:43.729883Z","title":"Minilm: Deep self- attention distillation for task-agnostic compression of pre-trained transformers.Advances in neural information processing systems, 33:5776–5788, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.729883Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:479e92bb35965b577740e7184953e51276a5d9c7921b5e46a21227ead57d2fe3","observation_id":"b88a8d7f-3f54-4e15-b5d9-257bef1f5c68","resolution":{"observed_at":"2026-08-07T06:04:43.729883Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.304240Z","title":"Pmc-llama: to- ward building open-source language models for medicine.Journal of the American Medical Informatics Association, 31(9):1833–1843, 2024","venue":null,"work_id":"076ae258-58d8-4245-832e-353ad56d315a","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.734208Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:acf8f361301e107651c4bf245aa7ffdd4cb10870eb11cabd9d9aa5761f566984","observation_id":"22fa3658-dee2-44ee-b988-f82d27b96b17","resolution":{"observed_at":"2026-08-07T06:04:44.309317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:43.738956Z","title":"C-pack: Packed resources for general chinese embeddings","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.738956Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:447c817a5082284fdecb61aeedb195f1786149f41a6991f417412a873eb87dfd","observation_id":"30ebd207-4525-4d5e-8387-5adc4116e80d","resolution":{"observed_at":"2026-08-07T06:04:43.738956Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.280226Z","title":"Benchmarking retrieval-augmented generation for medicine","venue":null,"work_id":"54262958-e4cf-4e3f-8f21-caeb2b58d91a","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.743164Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:6b9ee7c98de43acc34402ce3e04523fbf25930ae6561efe5065b968d2275166b","observation_id":"9ab9a0ca-e001-418d-bc58-a8e3137cf534","resolution":{"observed_at":"2026-08-07T06:04:44.284780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.266367Z","title":"Medicine","venue":null,"work_id":"c7ac5d7b-09cb-4318-b923-3d7cea23d977","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.747464Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:45cf2d29fdc74b30ace4c269a4b3e4227984662ec11aad746c4537faf04aeb5a","observation_id":"3a1182cd-44b8-473c-b37a-dad959a2ca0e","resolution":{"observed_at":"2026-08-07T06:04:44.270992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.252126Z","title":null,"venue":null,"work_id":"9927dfa4-86c1-42a4-8965-c63cf78f09b9","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.752128Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:35fbda590cc2ced221bebf4547a0f2e7b28f56614f72ea2f713a77d2125cff7a","observation_id":"06b52c33-2af3-46fe-b4f7-237f02335f14","resolution":{"observed_at":"2026-08-07T06:04:44.256483Z","resolver_source":"raw_fallback","status":"unresolved"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.238675Z","title":"Streamlit","venue":null,"work_id":"9fcb5ed7-4e51-4449-9d65-08e93bd8ebef","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.756727Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:9504a7e9c9e82c04ec6c718452aa89c6fe4b0999e3ace775fbc39113c66933b9","observation_id":"1f4ee02d-0e8f-4118-ae02-101bd28b6ddd","resolution":{"observed_at":"2026-08-07T06:04:44.242966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.224727Z","title":"bge-base-en-v1.5","venue":null,"work_id":"828b918c-42fc-4301-ae54-966b6d126334","year":2024},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.761981Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:46e1f634e07acf63bddb57b0fc9b688b73f8995ea2e3f477f42c201b948255d2","observation_id":"6258872c-d816-4858-a76b-d569a1aecfa1","resolution":{"observed_at":"2026-08-07T06:04:44.229154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.210168Z","title":"28 Prompt for Quality Control - Relevance Check (Cont’d)","venue":null,"work_id":"b2f2537d-4f3a-40ef-9fb4-bb6ae22c84a3","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.767050Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:b2bbf19e7c07d9857928c6c91cb4148894bcc4e9fc8fb755f0f5e20cb9b33e4a","observation_id":"f3bbd178-59b0-4433-8585-1e7d896551b7","resolution":{"observed_at":"2026-08-07T06:04:44.215190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.195784Z","title":null,"venue":null,"work_id":"e9a480d1-a404-4441-ab28-9d1a1e27f495","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.771216Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:c47e0478b4ebd9cc70312e325341793f6f890ff056203bfac5313b388ed8d835","observation_id":"50b15b54-a60b-4ab3-881a-d951745d0b75","resolution":{"observed_at":"2026-08-07T06:04:44.200269Z","resolver_source":"raw_fallback","status":"unresolved"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.181527Z","title":"good\" or","venue":null,"work_id":"8fa28f43-97e1-4c73-9cc4-ebc040c8b5d4","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.775813Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:8f735b1462b79dbc2636dfbcb102e98b49b3ed913ee08cda7a27364c0d72acc6","observation_id":"a7e793b0-509c-49fd-91f0-8d5986289e99","resolution":{"observed_at":"2026-08-07T06:04:44.186128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.165202Z","title":"Provide a short explanation for your classification","venue":null,"work_id":"72cc091b-5368-4f67-ad2a-d2b77f58d71c","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.780302Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:4aea697ad48b30635a05577c066923f40b1f99214a7d09f1601545efe0f60797","observation_id":"b1b40de9-2ace-4354-8299-a50261c6d70e","resolution":{"observed_at":"2026-08-07T06:04:44.171034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.150257Z","title":null,"venue":null,"work_id":"d3cb0447-e0e2-43a3-8ca2-081d7ed8f1e6","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.784635Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:847e91a6c356f2c1d51bde9248551e0fd0fce04c2d04ce2b2a4bacd538e7dfb7","observation_id":"f1aa1a7f-dfce-4145-8fce-95fea7d670a7","resolution":{"observed_at":"2026-08-07T06:04:44.154565Z","resolver_source":"raw_fallback","status":"unresolved"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.135972Z","title":null,"venue":null,"work_id":"caf1d990-7209-4776-a918-768237ed4c19","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.789108Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:7838f166f925aed66c93b7297e5a79e7b3b5d45e3c7b3ac325c44f5ce017def3","observation_id":"5658cc73-be62-4ed8-875f-7649922d9df4","resolution":{"observed_at":"2026-08-07T06:04:44.140574Z","resolver_source":"raw_fallback","status":"unresolved"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.120826Z","title":null,"venue":null,"work_id":"d6f7a4ed-e884-4978-bbf8-785a3a35a7ab","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.793611Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:b0416c167249fc4b4ce7bfd8e8f27fa535ee9094739c2c0c4b3f8893cc1b351c","observation_id":"51a523d2-5497-4c68-9c56-34cb609c6f1d","resolution":{"observed_at":"2026-08-07T06:04:44.125428Z","resolver_source":"raw_fallback","status":"unresolved"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.106439Z","title":null,"venue":null,"work_id":"f1dee795-c622-43b9-b6f6-fad7c1ff2757","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.798188Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:6116116ff7b5a33ddc47542f3a63a609fc16bdb5de766ce5bec70cc8d6ae55d1","observation_id":"d6d2733a-2043-4430-82b3-141e2940bbb1","resolution":{"observed_at":"2026-08-07T06:04:44.110892Z","resolver_source":"raw_fallback","status":"unresolved"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T06:04:44.090482Z","title":"The” or “In","venue":null,"work_id":"e0758322-24fb-4c4f-b3f9-141ec727bce3","year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.802360Z"},"links":{"citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:d470f026814b6ca67534dde162f42718698959dfd5158b501b825248d7dee5a4","observation_id":"33aba751-5964-436a-bcc8-d9efadda2407","resolution":{"observed_at":"2026-08-07T06:04:44.096323Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-07T06:04:43.584030Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.584030Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:20afef4dcb9232b2ac5631a3f12dc118b4d294e1cd059347ec84c41e1e9ca5f3","observation_id":"41ab1746-4269-47ee-927c-04dfd90b0ebc","resolution":{"observed_at":"2026-08-07T06:04:43.584030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.14302","last_updated":"2025-02-20T06:33:23Z","snapshot_observed_at":"2026-08-10T14:08:13.669449Z","submitted_at":"2025-02-20T06:33:23Z","title":"MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.14302","snapshot_observed_at":"2026-08-07T06:04:43.698234Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T06:04:43.698234Z"},"links":{"cited_paper":"/paper/2502.14302","citing_paper":"/paper/2506.06091"},"observation_digest":"sha256:a27a9ecdb0dbd205bfc946b73cf7515c6e19cde6ec84c871d543c1e959aa471d","observation_id":"dee28d99-0f05-47a3-ab70-c6ddcfb66ee1","resolution":{"observed_at":"2026-08-07T06:04:43.698234Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.06091","last_updated":"2025-06-09T14:21:53Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-12T19:24:53.752004Z","submitted_at":"2025-06-06T13:52:32Z","title":"MIRIAD: Augmenting LLMs with millions of medical query-response pairs"},"reference_resolution":{"displayed":50,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":25},"total_outbound_references":50},"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 50 of 50 outbound references and 1 inbound Pith citation observation for arXiv:2506.06091."}