{"as_of":"2026-08-15T19:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:be933384fd99a3ddcf7f6147d9f0fa281a4a7ee2096edce7e28488c127306d80","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T20:41:42.404387Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2412.05533/citation-record","integrity":"/paper/2412.05533/integrity","json":"/paper/2412.05533/citation-record.json","paper":"/paper/2412.05533"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T20:41:42.251709Z","title":"Deep learning with differential privacy","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.251709Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:8c9a670c4ce68713d40f2fb80743b6995ad4cdc55bc83abe3657089ba1494044","observation_id":"d0660e66-29d0-48fa-b5e5-df673b759bce","resolution":{"observed_at":"2026-08-11T20:41:42.251709Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.19215","last_updated":"2023-10-30T01:01:15Z","snapshot_observed_at":"2026-08-13T05:37:57.573661Z","submitted_at":"2023-10-30T01:01:15Z","title":"On the accuracy and efficiency of group-wise clipping in differentially private optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.19215","snapshot_observed_at":"2026-08-11T20:41:42.257683Z","title":"On the accuracy and efficiency of group-wise clipping in differentially private optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.257683Z"},"links":{"cited_paper":"/paper/2310.19215","citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:ea79a65ad266aaf47370f0faf14bbcaf7ebbe7567697887784559e1e9c0de5ae","observation_id":"c73d6ebe-7e85-4e1c-87ed-0221e5ff6234","resolution":{"observed_at":"2026-08-11T20:41:42.257683Z","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":"2026-08-11T20:41:43.152092Z","title":"Differentially private optimization on large model at small cost","venue":null,"work_id":"2da7d6d9-3f61-4193-a63a-d600e1d7e266","year":2023},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.262969Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:d10514aa6819d773b48812a08b987bf8ec53ffa6e285516faefa0622c3f4add5","observation_id":"69782e2a-6f2e-42b5-ba50-8061c058f85c","resolution":{"observed_at":"2026-08-11T20:41:43.158694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T20:41:42.268257Z","title":"Extracting training data from large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.268257Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:00c969593bd715823a6283d6515ceaea8fc0a8b2c080bc077904e7aaaa4a9040","observation_id":"44b441a5-855f-46d2-8e9b-224805eb551f","resolution":{"observed_at":"2026-08-11T20:41:42.268257Z","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":"2026-08-11T20:41:43.119661Z","title":"Membership inference attacks from first principles","venue":null,"work_id":"e48e682f-4bee-42c3-bdca-43b5af944c26","year":2022},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.274582Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:337375a41796e4395955c715a11c56da962423d74c2a07369604471c11eca78f","observation_id":"b4c97a3a-4766-4526-b45b-d243b1b8556d","resolution":{"observed_at":"2026-08-11T20:41:43.125398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T20:41:42.280092Z","title":"Meditron-70b: Scaling medical pretraining for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.280092Z"},"links":{"cited_paper":"/paper/2311.16079","citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:db88f5c9f2bee7ac7ac16a4c058d7081ef40b1a430d1d774cf8032b03fe650fb","observation_id":"521a9073-140f-46e4-ad8a-ede222aee540","resolution":{"observed_at":"2026-08-11T20:41:42.280092Z","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":"2026-08-11T20:41:42.286012Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.286012Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:07226fd33e925d8ea1359f6df97d75bcac7559407f35e6821f13575c8cfaa0b3","observation_id":"9fc383bd-6689-4568-a4b2-caee13937f32","resolution":{"observed_at":"2026-08-11T20:41:42.286012Z","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":"2026-08-11T20:41:42.297141Z","title":"Havtorn, Lasse Borgholt, Maria Maistro, Tuukka Ruotsalo, and Lars Maaløe","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.297141Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:33342bd328070a233166225985b97c6c95aa79670287c17929daa4e1d0c9b554","observation_id":"f195632d-4c62-4c50-85ec-804aaa5dbca4","resolution":{"observed_at":"2026-08-11T20:41:42.297141Z","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":"2026-08-11T20:41:42.302723Z","title":"Numerical composition of differential privacy","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.302723Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:aadbab3d4f2293934399721b291202c1279e43e22686334953be09119f0f5a79","observation_id":"ee96eb53-f002-479c-96d6-fff3e3833733","resolution":{"observed_at":"2026-08-11T20:41:42.302723Z","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":"2026-08-11T20:41:42.308209Z","title":"PLM - ICD : Automatic ICD coding with pretrained language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.308209Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:d115dfda229c99c4eca161ddd0d415ca96527561da074f983a0517319e04aa9f","observation_id":"17428716-5a4a-4ea3-9844-38f3a0c5b1e3","resolution":{"observed_at":"2026-08-11T20:41:42.308209Z","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":"2026-08-11T20:41:42.314483Z","title":"Mimic-iii, a freely accessible critical care database","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.314483Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:e4628e66e72847d72fc6ee05c51ee3d5772063bfce1329fb3ad64ad3cfeb45c0","observation_id":"73203d1e-3c51-4a8c-af46-4935d06fcafe","resolution":{"observed_at":"2026-08-11T20:41:42.314483Z","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":"2026-08-11T20:41:42.321089Z","title":"Computing tight differential privacy guarantees using fft","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.321089Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:3fadf79e12ae5474453a226e8b27bbcf0270b88688057e7681fb4fae98e8d5af","observation_id":"48f3ce42-346e-476b-aff2-fe561f8669a7","resolution":{"observed_at":"2026-08-11T20:41:42.321089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.00862","last_updated":"2019-11-25T11:23:04Z","snapshot_observed_at":"2026-07-06T08:41:25.156353Z","submitted_at":"2019-11-25T11:23:04Z","title":"ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network","version":1},"cited_work":{"arxiv_id":"1912.00862","doi":null,"metadata_source":"pith","pith_arxiv_id":"1912.00862","snapshot_observed_at":"2026-08-11T20:41:42.837979Z","title":"ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network","venue":"cs.CL","work_id":"ccdba962-6d4f-4d73-a355-8f19071cefac","year":2019},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.326160Z"},"links":{"cited_paper":"/paper/1912.00862","citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:f2202ea980766b5bec4a6bcc3d11c35ba6d53eb293a2c6e4fa37d5085c0da643","observation_id":"2a97b95f-ef2a-49d8-bd36-c02bd10fa015","resolution":{"observed_at":"2026-08-11T20:41:42.844809Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T20:41:43.046369Z","title":"Large language models can be strong differentially private learners","venue":null,"work_id":"7c816378-becd-4768-adf5-5ce12c58644b","year":2022},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.331862Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:b5a93588ccaa8c1a990be7bbf3246e1a399127095c777dc2f18ba7686312d2bf","observation_id":"50dd206a-d8b9-442c-be59-32b091084c68","resolution":{"observed_at":"2026-08-11T20:41:43.050858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06963","last_updated":"2018-02-24T00:40:30Z","snapshot_observed_at":"2026-08-14T20:22:22.512463Z","submitted_at":"2017-10-18T23:46:57Z","title":"Learning Differentially Private Recurrent Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06963","snapshot_observed_at":"2026-08-11T20:41:42.337136Z","title":"Learning differentially private recurrent language models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.337136Z"},"links":{"cited_paper":"/paper/1710.06963","citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:f947982f6d5670ae34df842eeba0a4c98a251af8f125bb6703573146b81152c7","observation_id":"beda9542-5eb7-4b5b-b8f7-c05b30c2985b","resolution":{"observed_at":"2026-08-11T20:41:42.337136Z","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":"2026-08-11T20:41:42.342852Z","title":"Quantifying privacy risks of masked language models using membership inference attacks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.342852Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:cd2a922b389ce5546612da56ccdffdc4d8fad3ad57c467ec885f57570afaa1ac","observation_id":"4df76e27-8025-4289-9f4b-b229ff70098e","resolution":{"observed_at":"2026-08-11T20:41:42.342852Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10530","last_updated":"2019-08-28T03:03:25Z","snapshot_observed_at":"2026-08-14T10:38:47.550021Z","submitted_at":"2019-08-28T03:03:25Z","title":"R\\'enyi Differential Privacy of the Sampled Gaussian Mechanism","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10530","snapshot_observed_at":"2026-08-11T20:41:42.348084Z","title":"R \\'e nyi differential privacy of the sampled gaussian mechanism","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.348084Z"},"links":{"cited_paper":"/paper/1908.10530","citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:8750b9975959049afb02d574f232d6b90397bf2bbef58f0cc16a0eb37c9cf6ee","observation_id":"b2691107-d5c5-4130-84cf-8eec231f2378","resolution":{"observed_at":"2026-08-11T20:41:42.348084Z","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":"2026-08-11T20:41:42.353453Z","title":"Explainable prediction of medical codes from clinical text","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.353453Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:9d4d503577529e4f857ce12062d0bd076c1a1a421e366092a7fc287dd90ee205","observation_id":"4be9a49b-25b0-40d1-93a2-62b195233612","resolution":{"observed_at":"2026-08-11T20:41:42.353453Z","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":"2026-08-11T20:41:43.030128Z","title":"Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters","venue":null,"work_id":"ee1643e4-c06c-4da1-9ee9-258e953b158b","year":2020},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.358391Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:acf6b13e1b7c4413a9fd75fe5805ffcf062640ec78553ee65368be249d05e304","observation_id":"35bebb67-d8a3-4d04-a74f-850308ef70a0","resolution":{"observed_at":"2026-08-11T20:41:43.035634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T20:41:42.363558Z","title":"Suriyakumar, Nicolas Papernot, Anna Goldenberg, and Marzyeh Ghassemi","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.363558Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:a3f364eca4b552afca80fab06104f520ffa344b781d2617edf452fb66fc5913a","observation_id":"2c59c74c-93e9-40ad-bbac-2350fe58f18d","resolution":{"observed_at":"2026-08-11T20:41:42.363558Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.06351","last_updated":"2020-07-13T12:42:43Z","snapshot_observed_at":"2026-08-04T08:18:05.169169Z","submitted_at":"2020-07-13T12:42:43Z","title":"A Label Attention Model for ICD Coding from Clinical Text","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.06351","snapshot_observed_at":"2026-08-11T20:41:42.369928Z","title":"A label attention model for ICD coding from clinical text","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.369928Z"},"links":{"cited_paper":"/paper/2007.06351","citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:f997521b70f3165f02cb0a6b6f5c473a67ea7ee7630d90e4af7109acfef7bf86","observation_id":"12f4c479-58df-4a1e-92c8-35c8f8bf3fdb","resolution":{"observed_at":"2026-08-11T20:41:42.369928Z","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":"2026-08-11T20:41:43.011554Z","title":"Multi-stage retrieve and re-rank model for automatic medical coding recommendation","venue":null,"work_id":"8eead3c6-1d5a-4ec1-a229-42689f5e2ccd","year":2024},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.375611Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:04fb1fcdc59fd27c3b02c1db00a89d787db0371de39f42b636de78d1eefa1df2","observation_id":"a3ea175e-5718-41e4-957a-9390b81699d5","resolution":{"observed_at":"2026-08-11T20:41:43.017546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T20:41:42.990988Z","title":"Subsampled r \\'e nyi differential privacy and analytical moments accountant","venue":null,"work_id":"06ad92ae-2dbf-4dc2-8487-b8acd478104c","year":2019},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.381453Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:f1bce037ed1bede1a58df663ddbd2f871a93d4d7b21871431322ed8e9982d64f","observation_id":"7f96a810-56a7-404b-a878-55bf1072aee7","resolution":{"observed_at":"2026-08-11T20:41:42.996485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03771","last_updated":"2020-07-14T03:42:34Z","snapshot_observed_at":"2026-07-06T08:27:58.343233Z","submitted_at":"2019-10-09T03:23:22Z","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03771","snapshot_observed_at":"2026-08-11T20:41:42.386378Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.386378Z"},"links":{"cited_paper":"/paper/1910.03771","citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:6097d5fcd1cb2564e289f4f475d601f3fa9cb5c479f18cbfe7fc2b73c498c63c","observation_id":"c99b2d7b-84bd-489b-8b3a-8931c24aa3c1","resolution":{"observed_at":"2026-08-11T20:41:42.386378Z","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":"2026-08-11T20:41:42.391517Z","title":"Yu, and Yangyong Zhu","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.391517Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:0944c6f185d16471abd504d24c29ce429712b35e6362e5f73d74bfeed0c5de65","observation_id":"05fcce30-2660-4920-863b-ea103ce9a283","resolution":{"observed_at":"2026-08-11T20:41:42.391517Z","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":"2026-08-11T20:41:42.970046Z","title":"A large language model for electronic health records","venue":null,"work_id":"7d65f3f4-a61a-4bb8-9d47-5a8d486342a4","year":2022},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.398411Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:0ea6dac6adc96710b71dffa746f61986b2066581189c2f0e13b9219c7b0adc8a","observation_id":"7680a347-75dd-42a3-89a3-af163aa199ea","resolution":{"observed_at":"2026-08-11T20:41:42.977149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-11T20:41:42.404387Z","title":"Knowledge injected prompt based fine-tuning for multi-label few-shot ICD coding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T20:41:42.404387Z"},"links":{"citing_paper":"/paper/2412.05533"},"observation_digest":"sha256:5b8325e710aeb32de7da41838036b69493cc7cda32bcf1aefc6ac0a14f72804b","observation_id":"f9154b35-accc-429c-825c-3f958e1d906f","resolution":{"observed_at":"2026-08-11T20:41:42.404387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.05533","last_updated":"2024-12-07T04:27:05Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T17:16:05.009231Z","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":7},"total_outbound_references":27},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2412.05533."}