{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WOMO6KIUD7VOIWDPEYMLDF5VU7","short_pith_number":"pith:WOMO6KIU","canonical_record":{"source":{"id":"2605.09505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-10T12:27:32Z","cross_cats_sorted":[],"title_canon_sha256":"40cc4f0d515f2499fd64cd9e6002303e52a5717c016898cd75dce709756f7b64","abstract_canon_sha256":"e861df0feb384199b01d1eb821cbea234da36d18e91b7a6d650e58a6bf6b1fa8"},"schema_version":"1.0"},"canonical_sha256":"b398ef29141feae4586f2618b197b5a7c09832eabceae13db8cc8779e72f5718","source":{"kind":"arxiv","id":"2605.09505","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09505","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09505v2","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09505","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"WOMO6KIUD7VO","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"WOMO6KIUD7VOIWDP","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"WOMO6KIU","created_at":"2026-05-18T15:04:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WOMO6KIUD7VOIWDPEYMLDF5VU7","target":"record","payload":{"canonical_record":{"source":{"id":"2605.09505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-10T12:27:32Z","cross_cats_sorted":[],"title_canon_sha256":"40cc4f0d515f2499fd64cd9e6002303e52a5717c016898cd75dce709756f7b64","abstract_canon_sha256":"e861df0feb384199b01d1eb821cbea234da36d18e91b7a6d650e58a6bf6b1fa8"},"schema_version":"1.0"},"canonical_sha256":"b398ef29141feae4586f2618b197b5a7c09832eabceae13db8cc8779e72f5718","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T15:04:06.679176Z","signature_b64":"uY42Aij9lP6E9g7OsCzeXkohCrHH5I9VXBpo+49vjS9G5IfAu1JmKk00c6ykgsOU5FTfbaYjOU1VzlIgMF6kAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b398ef29141feae4586f2618b197b5a7c09832eabceae13db8cc8779e72f5718","last_reissued_at":"2026-05-18T15:04:06.678133Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T15:04:06.678133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.09505","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":"2026-05-18T15:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sV351CaWFrUM5jl9rcMGprV/Oucvm3QVk05G3jkbqoZ+H3YtVJCpKvSNcH0dbMnfLTBy5miB5nz4BxjCj5rBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:22:09.510056Z"},"content_sha256":"cad8a67c373d4fa83e4b7ba54a51892b928ddcdf6e96ef7c2557aae25592bc67","schema_version":"1.0","event_id":"sha256:cad8a67c373d4fa83e4b7ba54a51892b928ddcdf6e96ef7c2557aae25592bc67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WOMO6KIUD7VOIWDPEYMLDF5VU7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"A new epilepsy knowledge graph boosts LLM performance on clinical reasoning tasks by up to 41 percent.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jathurshan Pradeepkumar, Jimeng Sun, Yasuko Matsubara, Yasushi Sakurai, Yushun Dong, Yuyang Dai, Zheng Chen","submitted_at":"2026-05-10T12:27:32Z","abstract_excerpt":"Epilepsy diagnosis and treatment require evidence-intensive reasoning across heterogeneous clinical knowledge, including biosignal patterns, genetic mechanisms, pharmacogenomics, treatment strategies, and patient outcomes. In this work, we present \\textsc{EpiGraph}, a large-scale epilepsy knowledge graph and benchmark for evaluating knowledge-augmented clinical reasoning. \\textsc{EpiGraph} integrates 48,166 peer-reviewed papers and seven clinical resources into a heterogeneous graph containing 24,324 entities and 32,009 evidence-grounded triplets across five clinical layers. Built upon this gr"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"integrating EpiGraph consistently improves performance across all tasks, with the largest gains observed in pharmacogenomic reasoning (+30--41%).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the automatically extracted triplets and five-layer structure accurately capture clinically reliable knowledge without introducing systematic errors or omissions from the source papers.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EpiGraph creates a heterogeneous epilepsy knowledge graph that boosts LLM performance on clinical reasoning tasks by 30-41% in pharmacogenomics when used with Graph-RAG.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new epilepsy knowledge graph boosts LLM performance on clinical reasoning tasks by up to 41 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"be3f10b2b69c977f714a91517ed6abd523ca5987135d50a7ebbda265c9bf4bc9"},"source":{"id":"2605.09505","kind":"arxiv","version":2},"verdict":{"id":"86230406-e2b5-4ad3-8a42-63dd5ee671b1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:20:48.007939Z","strongest_claim":"integrating EpiGraph consistently improves performance across all tasks, with the largest gains observed in pharmacogenomic reasoning (+30--41%).","one_line_summary":"EpiGraph creates a heterogeneous epilepsy knowledge graph that boosts LLM performance on clinical reasoning tasks by 30-41% in pharmacogenomics when used with Graph-RAG.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the automatically extracted triplets and five-layer structure accurately capture clinically reliable knowledge without introducing systematic errors or omissions from the source papers.","pith_extraction_headline":"A new epilepsy knowledge graph boosts LLM performance on clinical reasoning tasks by up to 41 percent."},"references":{"count":66,"sample":[{"doi":"","year":2025,"title":"Evobrain: Dynamic multi-channel EEG graph modeling for time-evolving brain networks","work_id":"2f700eec-3c27-447e-8c6f-2418e4663365","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Drug-resistant epilepsy","work_id":"63bdc733-4fd3-4ba2-96a1-15da50de0a7b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Long-term eeg partitioning for seizure onset detection","work_id":"46c6f1d6-6b32-4f73-bdcd-26f31e32866d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Review of pharmacogenetics of antiseizure medications: focusing on genetic variants of mecha- nistic targets","work_id":"ff1d9200-7592-4e35-b3f7-be57b8a77717","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"A review on knowledge graphs for healthcare: Resources, applications, and promises","work_id":"41e00ad7-c530-4d1c-bf16-d097ae5e7432","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":66,"snapshot_sha256":"75c22219f158aff05da13eaa5abe8250b00b7fec7a9c6035eb38b30a034879fc","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8e08aed194b6709bbcaf4b7ce3740103c10862055a2c0f6cec3ca82d73ae5adb"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"86230406-e2b5-4ad3-8a42-63dd5ee671b1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T15:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00bjs/vticXR9kM0wfoB6NYpm222Sz2KsrYHaZuAbOqY0CGy4gaDhLSt+Ii4GiQX52wHLtpCXUgJPVMytxLJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:22:09.511135Z"},"content_sha256":"5a41313437a00aa2686b43926e2876fdb28849d14b7c8bd992202df6c211e3be","schema_version":"1.0","event_id":"sha256:5a41313437a00aa2686b43926e2876fdb28849d14b7c8bd992202df6c211e3be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WOMO6KIUD7VOIWDPEYMLDF5VU7/bundle.json","state_url":"https://pith.science/pith/WOMO6KIUD7VOIWDPEYMLDF5VU7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WOMO6KIUD7VOIWDPEYMLDF5VU7/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":"2026-05-30T02:22:09Z","links":{"resolver":"https://pith.science/pith/WOMO6KIUD7VOIWDPEYMLDF5VU7","bundle":"https://pith.science/pith/WOMO6KIUD7VOIWDPEYMLDF5VU7/bundle.json","state":"https://pith.science/pith/WOMO6KIUD7VOIWDPEYMLDF5VU7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WOMO6KIUD7VOIWDPEYMLDF5VU7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WOMO6KIUD7VOIWDPEYMLDF5VU7","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":"e861df0feb384199b01d1eb821cbea234da36d18e91b7a6d650e58a6bf6b1fa8","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-10T12:27:32Z","title_canon_sha256":"40cc4f0d515f2499fd64cd9e6002303e52a5717c016898cd75dce709756f7b64"},"schema_version":"1.0","source":{"id":"2605.09505","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.09505","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.09505v2","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.09505","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"WOMO6KIUD7VO","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"WOMO6KIUD7VOIWDP","created_at":"2026-05-18T15:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"WOMO6KIU","created_at":"2026-05-18T15:04:06Z"}],"graph_snapshots":[{"event_id":"sha256:5a41313437a00aa2686b43926e2876fdb28849d14b7c8bd992202df6c211e3be","target":"graph","created_at":"2026-05-18T15:04:06Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"integrating EpiGraph consistently improves performance across all tasks, with the largest gains observed in pharmacogenomic reasoning (+30--41%)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the automatically extracted triplets and five-layer structure accurately capture clinically reliable knowledge without introducing systematic errors or omissions from the source papers."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EpiGraph creates a heterogeneous epilepsy knowledge graph that boosts LLM performance on clinical reasoning tasks by 30-41% in pharmacogenomics when used with Graph-RAG."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new epilepsy knowledge graph boosts LLM performance on clinical reasoning tasks by up to 41 percent."}],"snapshot_sha256":"be3f10b2b69c977f714a91517ed6abd523ca5987135d50a7ebbda265c9bf4bc9"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"8e08aed194b6709bbcaf4b7ce3740103c10862055a2c0f6cec3ca82d73ae5adb"},"paper":{"abstract_excerpt":"Epilepsy diagnosis and treatment require evidence-intensive reasoning across heterogeneous clinical knowledge, including biosignal patterns, genetic mechanisms, pharmacogenomics, treatment strategies, and patient outcomes. In this work, we present \\textsc{EpiGraph}, a large-scale epilepsy knowledge graph and benchmark for evaluating knowledge-augmented clinical reasoning. \\textsc{EpiGraph} integrates 48,166 peer-reviewed papers and seven clinical resources into a heterogeneous graph containing 24,324 entities and 32,009 evidence-grounded triplets across five clinical layers. Built upon this gr","authors_text":"Jathurshan Pradeepkumar, Jimeng Sun, Yasuko Matsubara, Yasushi Sakurai, Yushun Dong, Yuyang Dai, Zheng Chen","cross_cats":[],"headline":"A new epilepsy knowledge graph boosts LLM performance on clinical reasoning tasks by up to 41 percent.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-10T12:27:32Z","title":"EpiGraph: Building Generalists for Evidence-Intensive Epilepsy Reasoning in the Wild"},"references":{"count":66,"internal_anchors":12,"resolved_work":66,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Evobrain: Dynamic multi-channel EEG graph modeling for time-evolving brain networks","work_id":"2f700eec-3c27-447e-8c6f-2418e4663365","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Drug-resistant epilepsy","work_id":"63bdc733-4fd3-4ba2-96a1-15da50de0a7b","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Long-term eeg partitioning for seizure onset detection","work_id":"46c6f1d6-6b32-4f73-bdcd-26f31e32866d","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Review of pharmacogenetics of antiseizure medications: focusing on genetic variants of mecha- nistic targets","work_id":"ff1d9200-7592-4e35-b3f7-be57b8a77717","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"A review on knowledge graphs for healthcare: Resources, applications, and promises","work_id":"41e00ad7-c530-4d1c-bf16-d097ae5e7432","year":2025}],"snapshot_sha256":"75c22219f158aff05da13eaa5abe8250b00b7fec7a9c6035eb38b30a034879fc"},"source":{"id":"2605.09505","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-14T21:20:48.007939Z","id":"86230406-e2b5-4ad3-8a42-63dd5ee671b1","model_set":{"reader":"grok-4.3"},"one_line_summary":"EpiGraph creates a heterogeneous epilepsy knowledge graph that boosts LLM performance on clinical reasoning tasks by 30-41% in pharmacogenomics when used with Graph-RAG.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A new epilepsy knowledge graph boosts LLM performance on clinical reasoning tasks by up to 41 percent.","strongest_claim":"integrating EpiGraph consistently improves performance across all tasks, with the largest gains observed in pharmacogenomic reasoning (+30--41%).","weakest_assumption":"That the automatically extracted triplets and five-layer structure accurately capture clinically reliable knowledge without introducing systematic errors or omissions from the source papers."}},"verdict_id":"86230406-e2b5-4ad3-8a42-63dd5ee671b1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cad8a67c373d4fa83e4b7ba54a51892b928ddcdf6e96ef7c2557aae25592bc67","target":"record","created_at":"2026-05-18T15:04:06Z","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":"e861df0feb384199b01d1eb821cbea234da36d18e91b7a6d650e58a6bf6b1fa8","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-10T12:27:32Z","title_canon_sha256":"40cc4f0d515f2499fd64cd9e6002303e52a5717c016898cd75dce709756f7b64"},"schema_version":"1.0","source":{"id":"2605.09505","kind":"arxiv","version":2}},"canonical_sha256":"b398ef29141feae4586f2618b197b5a7c09832eabceae13db8cc8779e72f5718","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b398ef29141feae4586f2618b197b5a7c09832eabceae13db8cc8779e72f5718","first_computed_at":"2026-05-18T15:04:06.678133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T15:04:06.678133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uY42Aij9lP6E9g7OsCzeXkohCrHH5I9VXBpo+49vjS9G5IfAu1JmKk00c6ykgsOU5FTfbaYjOU1VzlIgMF6kAw==","signature_status":"signed_v1","signed_at":"2026-05-18T15:04:06.679176Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.09505","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cad8a67c373d4fa83e4b7ba54a51892b928ddcdf6e96ef7c2557aae25592bc67","sha256:5a41313437a00aa2686b43926e2876fdb28849d14b7c8bd992202df6c211e3be"],"state_sha256":"4d98618359a4baf11ad28121b86b0906796ac0ce352ba71c89a00eb3090cdc87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDwh3Z5WQmWLCXP8V4lR99YD9FiFHF8TgvxtSPdOsuaCIAD6PIrwLbj3c3EBbpthkMNygKTWS/mFIEi1GtdEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T02:22:09.515590Z","bundle_sha256":"0cc25894f1dd0dbf538471c0a4cd218bc1564c3bf6b7367902db131480a197e7"}}