{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SWDPQX2JTE67BADN34OFJQKLC6","short_pith_number":"pith:SWDPQX2J","canonical_record":{"source":{"id":"2402.15422","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T16:32:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1afdbed5f21b5aba7a0ceb9d95c402c597917b279209c079ddad08247095fee5","abstract_canon_sha256":"44f97d95041d1ca05b5f014faca3eba420a220d58f7c8eb200a01c54ad2a4785"},"schema_version":"1.0"},"canonical_sha256":"9586f85f49993df0806ddf1c54c14b179c1e09724295a5504152e1db102dc30d","source":{"kind":"arxiv","id":"2402.15422","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15422","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15422v2","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15422","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"SWDPQX2JTE67","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"SWDPQX2JTE67BADN","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"SWDPQX2J","created_at":"2026-07-05T08:36:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SWDPQX2JTE67BADN34OFJQKLC6","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15422","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T16:32:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1afdbed5f21b5aba7a0ceb9d95c402c597917b279209c079ddad08247095fee5","abstract_canon_sha256":"44f97d95041d1ca05b5f014faca3eba420a220d58f7c8eb200a01c54ad2a4785"},"schema_version":"1.0"},"canonical_sha256":"9586f85f49993df0806ddf1c54c14b179c1e09724295a5504152e1db102dc30d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:22.965293Z","signature_b64":"Jlubj1LvpDPNiRdSRt1UXS2sJNPgNUB5iS5PNXzI5S6JWrVrcNICjdUjppvUbaWivJIRJrts2W06MYI+vPjgAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9586f85f49993df0806ddf1c54c14b179c1e09724295a5504152e1db102dc30d","last_reissued_at":"2026-07-05T08:36:22.964813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:22.964813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15422","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BqZAot5QDEPKyk14dQabyPJ/6//3qQy/2K9umKYN3LqApUqlLy4UC5fyxtgUpuEFmnY06dLOkvwafGS1NqC7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:00:04.436807Z"},"content_sha256":"f67245e7d5466fbdac4228da7f989c2d5e3b213b84fc961a2f3791cba26a95c8","schema_version":"1.0","event_id":"sha256:f67245e7d5466fbdac4228da7f989c2d5e3b213b84fc961a2f3791cba26a95c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SWDPQX2JTE67BADN34OFJQKLC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"David Sontag, Florian Gierse, Monica Agrawal, Shannon Zejiang Shen, Stefan Hegselmann, Xiaoyi Jiang","submitted_at":"2024-02-23T16:32:28Z","abstract_excerpt":"Patients often face difficulties in understanding their hospitalizations, while healthcare workers have limited resources to provide explanations. In this work, we investigate the potential of large language models to generate patient summaries based on doctors' notes and study the effect of training data on the faithfulness and quality of the generated summaries. To this end, we release (i) a rigorous labeling protocol for errors in medical texts and (ii) a publicly available dataset of annotated hallucinations in 100 doctor-written and 100 generated summaries. We show that fine-tuning on hal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15422","kind":"arxiv","version":2},"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/2402.15422/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":"2026-07-05T08:36:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yCeRJmivVEwQKv3HDSKqPXcsoUDa77WK0BVUc3evjAm+lojHd3j+PpinOkBTwHSFuGcZXKe0qwXcaMJW9DRSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T10:00:04.437318Z"},"content_sha256":"4ea93201ea78b1206782b956afda406fa16e246b8dcbf8e9119ed120911ccc95","schema_version":"1.0","event_id":"sha256:4ea93201ea78b1206782b956afda406fa16e246b8dcbf8e9119ed120911ccc95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SWDPQX2JTE67BADN34OFJQKLC6/bundle.json","state_url":"https://pith.science/pith/SWDPQX2JTE67BADN34OFJQKLC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SWDPQX2JTE67BADN34OFJQKLC6/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":"2026-08-04T10:00:04Z","links":{"resolver":"https://pith.science/pith/SWDPQX2JTE67BADN34OFJQKLC6","bundle":"https://pith.science/pith/SWDPQX2JTE67BADN34OFJQKLC6/bundle.json","state":"https://pith.science/pith/SWDPQX2JTE67BADN34OFJQKLC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SWDPQX2JTE67BADN34OFJQKLC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SWDPQX2JTE67BADN34OFJQKLC6","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":"44f97d95041d1ca05b5f014faca3eba420a220d58f7c8eb200a01c54ad2a4785","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T16:32:28Z","title_canon_sha256":"1afdbed5f21b5aba7a0ceb9d95c402c597917b279209c079ddad08247095fee5"},"schema_version":"1.0","source":{"id":"2402.15422","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15422","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15422v2","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15422","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_12","alias_value":"SWDPQX2JTE67","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_16","alias_value":"SWDPQX2JTE67BADN","created_at":"2026-07-05T08:36:22Z"},{"alias_kind":"pith_short_8","alias_value":"SWDPQX2J","created_at":"2026-07-05T08:36:22Z"}],"graph_snapshots":[{"event_id":"sha256:4ea93201ea78b1206782b956afda406fa16e246b8dcbf8e9119ed120911ccc95","target":"graph","created_at":"2026-07-05T08:36:22Z","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/2402.15422/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Patients often face difficulties in understanding their hospitalizations, while healthcare workers have limited resources to provide explanations. In this work, we investigate the potential of large language models to generate patient summaries based on doctors' notes and study the effect of training data on the faithfulness and quality of the generated summaries. To this end, we release (i) a rigorous labeling protocol for errors in medical texts and (ii) a publicly available dataset of annotated hallucinations in 100 doctor-written and 100 generated summaries. We show that fine-tuning on hal","authors_text":"David Sontag, Florian Gierse, Monica Agrawal, Shannon Zejiang Shen, Stefan Hegselmann, Xiaoyi Jiang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T16:32:28Z","title":"A Data-Centric Approach To Generate Faithful and High Quality Patient Summaries with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15422","kind":"arxiv","version":2},"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:f67245e7d5466fbdac4228da7f989c2d5e3b213b84fc961a2f3791cba26a95c8","target":"record","created_at":"2026-07-05T08:36:22Z","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":"44f97d95041d1ca05b5f014faca3eba420a220d58f7c8eb200a01c54ad2a4785","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-23T16:32:28Z","title_canon_sha256":"1afdbed5f21b5aba7a0ceb9d95c402c597917b279209c079ddad08247095fee5"},"schema_version":"1.0","source":{"id":"2402.15422","kind":"arxiv","version":2}},"canonical_sha256":"9586f85f49993df0806ddf1c54c14b179c1e09724295a5504152e1db102dc30d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9586f85f49993df0806ddf1c54c14b179c1e09724295a5504152e1db102dc30d","first_computed_at":"2026-07-05T08:36:22.964813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:22.964813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jlubj1LvpDPNiRdSRt1UXS2sJNPgNUB5iS5PNXzI5S6JWrVrcNICjdUjppvUbaWivJIRJrts2W06MYI+vPjgAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:22.965293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15422","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f67245e7d5466fbdac4228da7f989c2d5e3b213b84fc961a2f3791cba26a95c8","sha256:4ea93201ea78b1206782b956afda406fa16e246b8dcbf8e9119ed120911ccc95"],"state_sha256":"26b1aec807d0446928248cfee5575183a1d44d28bf25e9a91f61a49b8ab4b3cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tNkGOOEhPtxYqSrzJ9I1o84D5G/U9WeZ6KL8xhxEJnPggxl1fUcEpQENJUV2HU0225v04RtioE8Lu8RvAMBSAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T10:00:04.441111Z","bundle_sha256":"77f6ead475dc9afce3d4e44a38969e952ea65c6606aaf33424b69837cf8b0406"}}