{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:O5KK7X543GNUSTH3MBEDK7DEFP","short_pith_number":"pith:O5KK7X54","canonical_record":{"source":{"id":"2412.05533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T04:27:05Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"f1057847ba381d79aba73d81719fd1b477b73924092cfefd7261ec245b515018","abstract_canon_sha256":"62c26206075dc79a95f865ce13c90172b5e6eae4c5cd25722510786d640fb5a3"},"schema_version":"1.0"},"canonical_sha256":"7754afdfbcd99b494cfb6048357c642bdae07ac80051d4014105df5e57ae44ed","source":{"kind":"arxiv","id":"2412.05533","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05533","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05533v1","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05533","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"pith_short_12","alias_value":"O5KK7X543GNU","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"pith_short_16","alias_value":"O5KK7X543GNUSTH3","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"pith_short_8","alias_value":"O5KK7X54","created_at":"2026-07-05T09:46:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:O5KK7X543GNUSTH3MBEDK7DEFP","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T04:27:05Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"f1057847ba381d79aba73d81719fd1b477b73924092cfefd7261ec245b515018","abstract_canon_sha256":"62c26206075dc79a95f865ce13c90172b5e6eae4c5cd25722510786d640fb5a3"},"schema_version":"1.0"},"canonical_sha256":"7754afdfbcd99b494cfb6048357c642bdae07ac80051d4014105df5e57ae44ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:04.838848Z","signature_b64":"Uyyh5O1BV3YPbRCx6ttKpSX3eEO2S+fo+CA9XU4gKWlNAKHOgek8DyMGMka4dIR/7wYAa1QlGgnsX+K9NfRmBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7754afdfbcd99b494cfb6048357c642bdae07ac80051d4014105df5e57ae44ed","last_reissued_at":"2026-07-05T09:46:04.838446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:04.838446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05533","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cz8hUGvs+lXe6L8qkjs9lgIMe3wJVdGeuyaXXFBgw+8FDDkFIZLWgqaie9ap8S69xwhVFHF92tb2JjJGw5MdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:56:50.817604Z"},"content_sha256":"41c5e7adde8eddefe0f2999cfc4b86e4c4ae5f0218a2e6c61d99e25f1bf97002","schema_version":"1.0","event_id":"sha256:41c5e7adde8eddefe0f2999cfc4b86e4c4ae5f0218a2e6c61d99e25f1bf97002"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:O5KK7X543GNUSTH3MBEDK7DEFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can large language models be privacy preserving and fair medical coders?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Ali Dadsetan, Dorsa Soleymani, Frank Rudzicz, Xijie Zeng","submitted_at":"2024-12-07T04:27:05Z","abstract_excerpt":"Protecting patient data privacy is a critical concern when deploying machine learning algorithms in healthcare. Differential privacy (DP) is a common method for preserving privacy in such settings and, in this work, we examine two key trade-offs in applying DP to the NLP task of medical coding (ICD classification). Regarding the privacy-utility trade-off, we observe a significant performance drop in the privacy preserving models, with more than a 40% reduction in micro F1 scores on the top 50 labels in the MIMIC-III dataset. From the perspective of the privacy-fairness trade-off, we also obser"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05533","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.05533/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9PKe+oIMtb5SmYC+4gp1hpOL/RtO4Al5byqU6Z84ouI6XHk7I85eeMJoIb/6LgiMQlHv24ekYE2221ukUgmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:56:50.818112Z"},"content_sha256":"7e488b1e513741b51f770e0de9919962fc1af0ec96e906f514ee36d0d3972f9b","schema_version":"1.0","event_id":"sha256:7e488b1e513741b51f770e0de9919962fc1af0ec96e906f514ee36d0d3972f9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5KK7X543GNUSTH3MBEDK7DEFP/bundle.json","state_url":"https://pith.science/pith/O5KK7X543GNUSTH3MBEDK7DEFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5KK7X543GNUSTH3MBEDK7DEFP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T17:56:50Z","links":{"resolver":"https://pith.science/pith/O5KK7X543GNUSTH3MBEDK7DEFP","bundle":"https://pith.science/pith/O5KK7X543GNUSTH3MBEDK7DEFP/bundle.json","state":"https://pith.science/pith/O5KK7X543GNUSTH3MBEDK7DEFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5KK7X543GNUSTH3MBEDK7DEFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O5KK7X543GNUSTH3MBEDK7DEFP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"62c26206075dc79a95f865ce13c90172b5e6eae4c5cd25722510786d640fb5a3","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T04:27:05Z","title_canon_sha256":"f1057847ba381d79aba73d81719fd1b477b73924092cfefd7261ec245b515018"},"schema_version":"1.0","source":{"id":"2412.05533","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05533","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05533v1","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05533","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"pith_short_12","alias_value":"O5KK7X543GNU","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"pith_short_16","alias_value":"O5KK7X543GNUSTH3","created_at":"2026-07-05T09:46:04Z"},{"alias_kind":"pith_short_8","alias_value":"O5KK7X54","created_at":"2026-07-05T09:46:04Z"}],"graph_snapshots":[{"event_id":"sha256:7e488b1e513741b51f770e0de9919962fc1af0ec96e906f514ee36d0d3972f9b","target":"graph","created_at":"2026-07-05T09:46:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.05533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protecting patient data privacy is a critical concern when deploying machine learning algorithms in healthcare. Differential privacy (DP) is a common method for preserving privacy in such settings and, in this work, we examine two key trade-offs in applying DP to the NLP task of medical coding (ICD classification). Regarding the privacy-utility trade-off, we observe a significant performance drop in the privacy preserving models, with more than a 40% reduction in micro F1 scores on the top 50 labels in the MIMIC-III dataset. From the perspective of the privacy-fairness trade-off, we also obser","authors_text":"Ali Dadsetan, Dorsa Soleymani, Frank Rudzicz, Xijie Zeng","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T04:27:05Z","title":"Can large language models be privacy preserving and fair medical coders?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05533","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:41c5e7adde8eddefe0f2999cfc4b86e4c4ae5f0218a2e6c61d99e25f1bf97002","target":"record","created_at":"2026-07-05T09:46:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"62c26206075dc79a95f865ce13c90172b5e6eae4c5cd25722510786d640fb5a3","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-07T04:27:05Z","title_canon_sha256":"f1057847ba381d79aba73d81719fd1b477b73924092cfefd7261ec245b515018"},"schema_version":"1.0","source":{"id":"2412.05533","kind":"arxiv","version":1}},"canonical_sha256":"7754afdfbcd99b494cfb6048357c642bdae07ac80051d4014105df5e57ae44ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7754afdfbcd99b494cfb6048357c642bdae07ac80051d4014105df5e57ae44ed","first_computed_at":"2026-07-05T09:46:04.838446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:04.838446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uyyh5O1BV3YPbRCx6ttKpSX3eEO2S+fo+CA9XU4gKWlNAKHOgek8DyMGMka4dIR/7wYAa1QlGgnsX+K9NfRmBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:04.838848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05533","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41c5e7adde8eddefe0f2999cfc4b86e4c4ae5f0218a2e6c61d99e25f1bf97002","sha256:7e488b1e513741b51f770e0de9919962fc1af0ec96e906f514ee36d0d3972f9b"],"state_sha256":"561efb39ed68c6affe3ccbc0b1bfcc34de263551d93c6c6be36c3c5a52da1a96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vy419BX1rLy8IIORWzI1/gjq/qq08mWva1HDf1lhCv4fmUMj+0+fPZ7Cerio/sC/m7EmzDUGw7Bzy/xGj1UCBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:56:50.821808Z","bundle_sha256":"1b76d1af34a35847d09a4cb1efb1425f6308588c1be5e6946ff6310cbaec57ce"}}