{"as_of":"2026-08-20T07:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:760c0c4c098fd21733bd04c27e9db1e43e3f9d19f12fd687f7759f3a9ff5834c","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:09:42.422554Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.10717/citation-record","integrity":"/paper/2505.10717/integrity","json":"/paper/2505.10717/citation-record.json","paper":"/paper/2505.10717"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:09:42.805748Z","title":null,"venue":null,"work_id":"dbd72674-1706-449d-a25d-0698397cbd67","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.335708Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:01e0da43d4e5095c3877cc11b850114f67d17e1e3e59c8355aafae1caa26a238","observation_id":"78a7323e-a078-4ecd-a082-42ab69f97f4f","resolution":{"observed_at":"2026-08-15T21:09:42.808820Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.796915Z","title":null,"venue":null,"work_id":"155ae41d-b0b8-4e45-bd9c-1cb192e08999","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.338462Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:b27acdb0287c8c5a759d5dabd451e05cd2cb0bf94b467c9ae223841a4d47b0db","observation_id":"cfb1d8bd-87d0-493b-93d9-4f98bef05ecc","resolution":{"observed_at":"2026-08-15T21:09:42.800247Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16079","last_updated":"2023-11-27T18:49:43Z","snapshot_observed_at":"2026-07-06T16:53:18.275859Z","submitted_at":"2023-11-27T18:49:43Z","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16079","snapshot_observed_at":"2026-08-15T21:09:42.300294Z","title":"Zeming Chen, Alejandro Hernández Cano, Angelika Romanou, Antoine Bonnet, Kyle Matoba, Francesco Salvi, Matteo Pagliardini, Simin Fan, Andreas Köpf, Amirkeivan Mohtashami, et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.300294Z"},"links":{"cited_paper":"/paper/2311.16079","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:8d3d2a5a319b0c4527cc794d7f91948be051f005562b2bb1cee2688c73099506","observation_id":"b967b63f-e9fe-4cda-b0f5-f182fe0868b8","resolution":{"observed_at":"2026-08-15T21:09:42.300294Z","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":"2026-08-15T21:09:42.303649Z","title":"In Forty-first International Conference on Machine Learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.303649Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:854c8e505678e8ae554b1ed8b06675b09a6834e5e31d567374a6b71d3f9ab700","observation_id":"3fedeadf-2ee8-4fa0-aa8d-22b34bfd3dbe","resolution":{"observed_at":"2026-08-15T21:09:42.303649Z","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":"2026-08-15T21:09:42.591692Z","title":"entity\": The specific category of the extracted information, chosen from the predefined taxonomy below. -","venue":null,"work_id":"26283477-7b9e-46dc-b18d-ab0abec0a938","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.405738Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:c6285eda7c0d8103ed539935cefc067ae04563801ad922606bdfcc24019d967c","observation_id":"6bf7b96d-c0c6-474a-aac7-00ed1ad4901a","resolution":{"observed_at":"2026-08-15T21:09:42.594602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.787116Z","title":null,"venue":null,"work_id":"2373f16f-9b94-4c1c-be91-d3290cf90403","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.341156Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:c1cbd121f5f6ade1b24228198c7dd1daccf1548da51b70b45e32831573ee37cc","observation_id":"c8db84e3-d202-4f43-8dbb-0780cb62a191","resolution":{"observed_at":"2026-08-15T21:09:42.790944Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.02707","last_updated":"2023-06-05T08:58:39Z","snapshot_observed_at":"2026-08-09T03:29:22.849759Z","submitted_at":"2023-06-05T08:58:39Z","title":"Orca: Progressive Learning from Complex Explanation Traces of GPT-4","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.02707","snapshot_observed_at":"2026-08-15T21:09:42.315956Z","title":"Advances in Neural Information Processing Systems, 36:50358–50376","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.315956Z"},"links":{"cited_paper":"/paper/2306.02707","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:c81c93acc894453f6675817b7117cb05eaaf31ae9c1c9b29ad578d9da3edd827","observation_id":"af572968-f9db-4b7b-9a7d-5be627aab60c","resolution":{"observed_at":"2026-08-15T21:09:42.315956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.03590","last_updated":"2024-11-06T01:09:17Z","snapshot_observed_at":"2026-08-17T18:13:42.083292Z","submitted_at":"2024-11-06T01:09:17Z","title":"From Medprompt to o1: Exploration of Run-Time Strategies for Medical Challenge Problems and Beyond","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.03590","snapshot_observed_at":"2026-08-15T21:09:42.319096Z","title":"Medicine, 84(88.3):77–3","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.319096Z"},"links":{"cited_paper":"/paper/2411.03590","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:901d209bf95a3986649cf30e0ca8cbdb8c0514ef32e0ff71cf43eb83b59be2b7","observation_id":"7b650fda-bb19-4620-ab97-679619e38ea1","resolution":{"observed_at":"2026-08-15T21:09:42.319096Z","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":"2026-08-15T21:09:42.778451Z","title":null,"venue":null,"work_id":"7b34ab0b-9c99-4d48-812a-25ec9c2ef40f","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.343771Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:1bd6b1da2b07abdf01dd6ee90ac97d78a1c423bddd9ff438a96a634d563e534a","observation_id":"f4487611-6526-469d-9a16-6496ee489a03","resolution":{"observed_at":"2026-08-15T21:09:42.781487Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.814607Z","title":"Junda Wang, Zonghai Yao, Zhichao Yang, Huixue Zhou, Rumeng Li, Xun Wang, Yucheng Xu, and Hong Yu","venue":null,"work_id":"0c762daa-9f6f-4650-aebf-9e708d5b87a6","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.325481Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:3afa51c799a475e63f8ef36a896f639debe9a9bfed7095d12c8f2d067016d5c9","observation_id":"f7418646-b194-4afd-94d8-6bfaca79d52f","resolution":{"observed_at":"2026-08-15T21:09:42.817394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15959","last_updated":"2024-06-28T13:28:08Z","snapshot_observed_at":"2026-08-16T14:49:16.872679Z","submitted_at":"2023-10-24T15:59:43Z","title":"NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15959","snapshot_observed_at":"2026-08-15T21:09:42.328886Z","title":"arXiv preprint arXiv:2310.15959","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.328886Z"},"links":{"cited_paper":"/paper/2310.15959","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:4c347c694d5abaf50801cafa66f9b7f57788a256d85cfebec1a34a0b08b2179b","observation_id":"2664d398-09e2-48ee-8708-96857ee15b55","resolution":{"observed_at":"2026-08-15T21:09:42.328886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03617","last_updated":"2024-10-04T17:17:19Z","snapshot_observed_at":"2026-08-19T15:55:04.477849Z","submitted_at":"2024-10-04T17:17:19Z","title":"What Matters for Model Merging at Scale?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03617","snapshot_observed_at":"2026-08-15T21:09:42.332558Z","title":"Journal of the Ameri- can Medical Informatics Association: JAMIA, pages ocae045–ocae045","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.332558Z"},"links":{"cited_paper":"/paper/2410.03617","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:e69152ff40c3e835834021feeab238b050c55b987b5139d6972b44014fc5484d","observation_id":"47c6660c-931e-4b2e-bc01-8e705d04aba0","resolution":{"observed_at":"2026-08-15T21:09:42.332558Z","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":"2026-08-15T21:09:42.754378Z","title":null,"venue":null,"work_id":"eea3b56c-cdab-4b18-a55a-3152bab710a4","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.352883Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:206b49b721d89c6cd6a5850146f81d0bb41d43aa8293ca1e022f82bc3f35f5ab","observation_id":"1afac5eb-f81f-47f3-96aa-8cd573547c98","resolution":{"observed_at":"2026-08-15T21:09:42.757039Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.745585Z","title":null,"venue":null,"work_id":"aecc570b-0273-4a6c-bdd2-10c1e20303b0","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.355738Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:55565bf4171e9b2e3dbe09103208d9de30ba23aa528bd7d809a202133e2d027f","observation_id":"2afb3162-8b74-4c71-b9d5-05b910ef23fd","resolution":{"observed_at":"2026-08-15T21:09:42.748248Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.737425Z","title":null,"venue":null,"work_id":"eec9ef78-d64e-4731-99ce-d3f17eb19c12","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.358334Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:f115f983fc5d452f06fb931809b3466aaeb1b189ae7dde408feb2e56c530cdc8","observation_id":"af7fa51e-fbf4-45aa-82db-278740980bc6","resolution":{"observed_at":"2026-08-15T21:09:42.740061Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.770780Z","title":null,"venue":null,"work_id":"e514d250-c27c-443f-a7bf-e1b6a4b39e3c","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.347083Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:41d506c0fe646b37a209d15f1da0c1fea07580e9c03abb838d719fe6313c2bb6","observation_id":"322d1a9c-e9e6-4f05-9f17-3a1fc5bca5ac","resolution":{"observed_at":"2026-08-15T21:09:42.773514Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.762453Z","title":null,"venue":null,"work_id":"2fa0b562-f1b1-425a-ab71-0e103a10450e","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.350139Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:39b5657510030ec28d3a1e505dec09b08cb8106e0b8b3de3318ad84c18747bf4","observation_id":"ac5d4587-4469-4142-9ec0-61ca4a064086","resolution":{"observed_at":"2026-08-15T21:09:42.765235Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.710053Z","title":null,"venue":null,"work_id":"d467e9cd-5c42-465d-807b-cf099e4c30b6","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.366047Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:0bdd010419f39b1de2990fe800b78a8963b632eff07b689555aa1ec8fb58df38","observation_id":"11663846-ada4-4c5c-a7d1-862382b847ab","resolution":{"observed_at":"2026-08-15T21:09:42.712789Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.702660Z","title":null,"venue":null,"work_id":"48fe7b3f-9ea7-40a7-926d-96ead83856b4","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.368586Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:eff9951ab9d2c0c9d6fe86152a31b02168fe084c584fd4824851e042b6fe721a","observation_id":"e52c4a2e-0d58-46e2-aa32-89bbb9159771","resolution":{"observed_at":"2026-08-15T21:09:42.705242Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.695390Z","title":null,"venue":null,"work_id":"e33ed1f0-9834-4c64-813e-d324157706e3","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.370983Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:ade5b4883123c6e887568714cc6ac2a40cb10af939b1b6d20b7cf11a57ce0b27","observation_id":"3cc04fe3-6fc6-4a3d-bd1e-e19e964e758d","resolution":{"observed_at":"2026-08-15T21:09:42.697945Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.728992Z","title":null,"venue":null,"work_id":"a75ac323-0258-4406-8d34-9bb90ffce8be","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.360933Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:ff4601078648999e79b9c8dcd03a67fc431b0122d40e19152a1ef7acadbf408b","observation_id":"b86fbd8c-fa43-41e2-a3ef-015c46bdf9b3","resolution":{"observed_at":"2026-08-15T21:09:42.732188Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.718865Z","title":null,"venue":null,"work_id":"670ad132-65ad-4ac4-8321-0797fb1ecd14","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.363649Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:46097e1cab4ab6974c50339ca821f4623ca55fd2a01959a51847074841c84777","observation_id":"ee493164-69f0-41e9-9424-1ea5acb58a56","resolution":{"observed_at":"2026-08-15T21:09:42.722399Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.680380Z","title":null,"venue":null,"work_id":"3c4c4dc0-082e-4d09-837d-b1c1204c8ef1","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.376846Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:b08e224f130afc95e8942d47660943f1ff586efb24f2b17b77abd6d520aff46e","observation_id":"ef7d3fab-3472-42c7-a881-b6560526bade","resolution":{"observed_at":"2026-08-15T21:09:42.682948Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.688175Z","title":null,"venue":null,"work_id":"fc086e91-693e-4e99-a08c-06cd913f7ec0","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.373883Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:539ca0df442fca47c9453fb9f0ee82cb93966aa522629ccd897f27046c7a44a3","observation_id":"1b714a90-89bd-4acb-b42a-3f03bbc47884","resolution":{"observed_at":"2026-08-15T21:09:42.690640Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.672354Z","title":null,"venue":null,"work_id":"58db6d4d-f824-4bc1-8ade-d1d448aaaee3","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.379473Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:a9e1cb9718578098786f861d83a63bae96954c0fc257261a086cf1e3218f7f8d","observation_id":"987ddea9-0810-40a4-855c-af9abc5b6c62","resolution":{"observed_at":"2026-08-15T21:09:42.675124Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.664439Z","title":null,"venue":null,"work_id":"92280fd0-53e2-499d-9324-ee92efb5f30d","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.381999Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:69b9bc2a1bcaf1b2b5a394f079d13736c71e6e406c84f879eab5a70859c1eebc","observation_id":"f7814471-7a3c-4ed8-9a3e-bf6935236b67","resolution":{"observed_at":"2026-08-15T21:09:42.667130Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.655568Z","title":null,"venue":null,"work_id":"6f9a0fc2-9fae-407d-8beb-4d8b25ae80eb","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.384576Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:77aee3a638175f7e4a76dbaaa064708b67116f9978c6fb36ae17a5d95f3dc505","observation_id":"cf800401-066e-4067-9975-8d2c57342137","resolution":{"observed_at":"2026-08-15T21:09:42.658427Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.647029Z","title":null,"venue":null,"work_id":"aa04f83b-1e8d-4a1d-959b-6945a70d9276","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.387223Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:77860a8a1e57863f643514b0ec511a063af4c9fb5fb85f6d468e60342f69349b","observation_id":"d9e214f4-2917-45e7-8de0-a7a37cae8a95","resolution":{"observed_at":"2026-08-15T21:09:42.650477Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.638216Z","title":null,"venue":null,"work_id":"70461e60-5632-4c65-b551-d60c56271767","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.389771Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:063033e8ceb59bc407dd3b2ae32a57234e8a9a8f0d979dd273a82277864fd078","observation_id":"65c0a87e-0571-4aeb-89c1-24fe57cb15f4","resolution":{"observed_at":"2026-08-15T21:09:42.641939Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.623050Z","title":"Chest pain for two days","venue":null,"work_id":"372d1048-aa87-44de-86c6-885e3bab10d6","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.395598Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:2e18e8b24347a2acfa380a06d41d6544dc7e904a56c5efa6115b23b8d944dcc2","observation_id":"5504351f-1cfc-4a97-ad88-9e635cac8c85","resolution":{"observed_at":"2026-08-15T21:09:42.625666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.630431Z","title":"rationale","venue":null,"work_id":"166b0e8d-eb8e-4eb6-8050-ff616547c0c0","year":2019},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.392278Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:64d2c9fc1ef46591abc4fd773090b07469aee24c67c1f27e44816f5b8fcebecd","observation_id":"5b6da3e4-6f08-40bf-90e6-e0079f1d0cd7","resolution":{"observed_at":"2026-08-15T21:09:42.633212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.615416Z","title":"- Duration: Progression over time","venue":null,"work_id":"0d55d85e-b29c-442a-a53b-7fda904ab041","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.398190Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:b79038785da00287cb870ced18f922cddcdf067ae1de548bd5baf548230fafcc","observation_id":"693f9b3b-e812-47dd-bb1f-d22962f4d002","resolution":{"observed_at":"2026-08-15T21:09:42.618104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.607725Z","title":"Describe specific observations for each system: - Vital Signs: BP, HR, Temp, O2 Sat, RR","venue":null,"work_id":"3593efd6-7896-4a3a-ba2c-cbf3ee087857","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.400794Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:5dbdc360cc9bc5263537014db813f2599074298fcf89e6e8e05c149a563c599a","observation_id":"4a6d8ee7-7ec9-4f57-8d39-01e750eafc8c","resolution":{"observed_at":"2026-08-15T21:09:42.610497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.600305Z","title":"List both abnormal and pertinent normal find- ings","venue":null,"work_id":"a3bf87a7-1fd0-430e-a079-6edd51937079","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.403307Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:659fdbe47ad753df93d697765b9a7340e15a811d087c6f380513f043351f9802","observation_id":"0249f717-ffad-4a32-a36d-0935095551a1","resolution":{"observed_at":"2026-08-15T21:09:42.602948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.584310Z","title":"entity\":","venue":null,"work_id":"56e77e96-c697-4261-adfc-57040cfa7f5c","year":2010},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.408272Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:dcca862ed6f9185f13430dd379d31090366ae519de4301c9e0d285db250505ca","observation_id":"584fc31a-41f4-4613-896e-5d1aa36c9190","resolution":{"observed_at":"2026-08-15T21:09:42.586810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.575174Z","title":"entity\":","venue":null,"work_id":"8815715a-3201-497a-9a15-d460eb328527","year":2015},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.410527Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:1a85822ceb6fbc14fdd815fbc36085ae60cf739bfbc0104a210ac5555b3347ad","observation_id":"c1b0bb8e-29af-46bf-a9b0-78eda34099ec","resolution":{"observed_at":"2026-08-15T21:09:42.578416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.566612Z","title":"entity\":","venue":null,"work_id":"ceadc8f6-380b-4790-b53a-4f906b8e4830","year":2005},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.412807Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:9760f0cee45e753f53677669dfb2ad1a52dfd90618bcf540f8d57cfa2a77020a","observation_id":"4763169b-f64d-4f04-b9f7-95ede196e757","resolution":{"observed_at":"2026-08-15T21:09:42.569312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.557601Z","title":null,"venue":null,"work_id":"a5266245-600f-41b3-827e-6e7f56696cb3","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.414980Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:b3e0ff4ba28b2ffeba661cccc2b314f370148173b79b457dc228f74e4479bc77","observation_id":"cff609e8-db15-4f3e-bf97-20758652c242","resolution":{"observed_at":"2026-08-15T21:09:42.560912Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.548608Z","title":null,"venue":null,"work_id":"4215743c-12a1-47f2-9666-cca1b59d3345","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.417394Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:cccfad1dc64ce5a4900fc758da1ea05be2837deb2639efed696959a19793a568","observation_id":"bd93a308-73b6-45a2-81bb-da7efd9da76b","resolution":{"observed_at":"2026-08-15T21:09:42.551737Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.539556Z","title":"entity\" and","venue":null,"work_id":"05bc1f98-da58-443b-b6ab-ee59aa52b08c","year":null},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.420156Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:f7ff37328defcc9e9c86cf38d04e2e6ea5bb00e27782a3f258b59cd6de7135de","observation_id":"d64aabd6-909a-4afd-bf32-e7745cd257d1","resolution":{"observed_at":"2026-08-15T21:09:42.542521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:09:42.528332Z","title":"Your final output should be a list of JSON objects containing only the entities present in the document","venue":null,"work_id":"0ba9ef02-be01-4a7b-a4fe-94fd7bcd6d6e","year":2004},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.422554Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:fe0181ebda0fa83b0f00683cbcbb39a38e4b78de9de908d1bd6b10b5dd5a664f","observation_id":"7cff25be-57d8-46f1-806c-df7bf485d8e6","resolution":{"observed_at":"2026-08-15T21:09:42.533576Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-08-17T03:25:04.404839Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14219","snapshot_observed_at":"2026-08-15T21:09:42.292786Z","title":"https://mtsamples.com/","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.292786Z"},"links":{"cited_paper":"/paper/2404.14219","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:e8272c0453236a93fb89282fb75a3cab781ce2ab50ef03d5c42c0e9cfac177ac","observation_id":"a7a4d332-4efb-49ec-9077-ca3c55b4e063","resolution":{"observed_at":"2026-08-15T21:09:42.292786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.08870","last_updated":"2025-06-28T21:17:10Z","snapshot_observed_at":"2026-08-15T05:40:09.612647Z","submitted_at":"2024-11-13T18:50:13Z","title":"The Limited Impact of Medical Adaptation of Large Language and Vision-Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.08870","snapshot_observed_at":"2026-08-15T21:09:42.307920Z","title":"In International Conference on Learning Representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.307920Z"},"links":{"cited_paper":"/paper/2411.08870","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:449863d008fee2af857876a094751a9c5fb42ebcdf2bc1abc12c0732a84aec4e","observation_id":"a179d080-15d0-4237-9184-fc09349732c9","resolution":{"observed_at":"2026-08-15T21:09:42.307920Z","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":"2026-08-15T21:09:42.823186Z","title":"zero-shot","venue":null,"work_id":"5ddb5e62-1d62-4854-b5f7-904ef23e890c","year":2022},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.322050Z"},"links":{"citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:f379bb328dc1edfe2b72fd05c431db2a32c6098fa369702fa5173dd6f60e0282","observation_id":"a4f4d5fb-53c3-434b-a921-005e5da9fc08","resolution":{"observed_at":"2026-08-15T21:09:42.826053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.03502","last_updated":"2024-07-03T21:01:12Z","snapshot_observed_at":"2026-08-18T11:12:13.041122Z","submitted_at":"2024-07-03T21:01:12Z","title":"AgentInstruct: Toward Generative Teaching with Agentic Flows","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.03502","snapshot_observed_at":"2026-08-15T21:09:42.311893Z","title":"Journal of the Amer- ican Medical Informatics Association, 30(8):1367– 1378","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.311893Z"},"links":{"cited_paper":"/paper/2407.03502","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:8d55ca8c84e8aa4b1094f6335010bec7516433ada7de627c72dd8d018da8b306","observation_id":"970fcf8a-2d94-4044-827f-a062ffa69a16","resolution":{"observed_at":"2026-08-15T21:09:42.311893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19260","last_updated":"2025-01-02T18:46:05Z","snapshot_observed_at":"2026-08-16T13:53:04.662481Z","submitted_at":"2024-12-26T15:54:10Z","title":"MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19260","snapshot_observed_at":"2026-08-15T21:09:42.296863Z","title":"arXiv preprint arXiv:2412.19260","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T21:09:42.296863Z"},"links":{"cited_paper":"/paper/2412.19260","citing_paper":"/paper/2505.10717"},"observation_digest":"sha256:a63daeda5d6956e363114f9f6168eada3cc3437362c1e80f5da66449e71c506c","observation_id":"da24b324-c869-42fb-bdfb-96b9203cccd9","resolution":{"observed_at":"2026-08-15T21:09:42.296863Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.10717","last_updated":"2025-05-21T17:36:21Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T11:15:07.089978Z","submitted_at":"2025-05-15T21:40:21Z","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":13,"unresolved":20,"verified_exact":0,"verified_fuzzy":12},"total_outbound_references":46},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2505.10717."}