{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:37YCCWWN7NBLDTEZM4LPZZPSB5","short_pith_number":"pith:37YCCWWN","canonical_record":{"source":{"id":"2405.16115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T08:00:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f2aeb6345a7e1fb32dfa025b47b1982641123b29a012ab4b6925058fdb10b39","abstract_canon_sha256":"6b22e7ced0ccb42e61e616afde2350ccef84434d0888e268314d5ae9f476bfa1"},"schema_version":"1.0"},"canonical_sha256":"dff0215acdfb42b1cc996716fce5f20f5a16ec91322e9aa2f12a38bea0216bcb","source":{"kind":"arxiv","id":"2405.16115","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16115","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16115v1","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16115","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"pith_short_12","alias_value":"37YCCWWN7NBL","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"pith_short_16","alias_value":"37YCCWWN7NBLDTEZ","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"pith_short_8","alias_value":"37YCCWWN","created_at":"2026-07-05T08:23:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:37YCCWWN7NBLDTEZM4LPZZPSB5","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16115","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T08:00:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f2aeb6345a7e1fb32dfa025b47b1982641123b29a012ab4b6925058fdb10b39","abstract_canon_sha256":"6b22e7ced0ccb42e61e616afde2350ccef84434d0888e268314d5ae9f476bfa1"},"schema_version":"1.0"},"canonical_sha256":"dff0215acdfb42b1cc996716fce5f20f5a16ec91322e9aa2f12a38bea0216bcb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:26.140972Z","signature_b64":"G4ZjfizUDWWRBCtvbIgpV9X1LVjiO+vw+lzhIjAkCIIlw5qZpHLKbHMOyJK6QNn+VPQ0hd0mB2hSopFce1qjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dff0215acdfb42b1cc996716fce5f20f5a16ec91322e9aa2f12a38bea0216bcb","last_reissued_at":"2026-07-05T08:23:26.140511Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:26.140511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16115","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":"2026-07-05T08:23:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AsQ7U400ZiqPnda3TBt6DoFdGfW54nKr27FyaffajqdSkaKzHP9O2tiAVtScowBHJGYQbF3FXnhPThGoy4wXBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:43:45.023342Z"},"content_sha256":"a27f53e874b292574e40471319298910e135d9c0a0ce0f7ba1d1d91ba0737725","schema_version":"1.0","event_id":"sha256:a27f53e874b292574e40471319298910e135d9c0a0ce0f7ba1d1d91ba0737725"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:37YCCWWN7NBLDTEZM4LPZZPSB5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SNOBERT: A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandr Galaida, Andreas Maier, Gleb Sokolov, Mikhail Kulyabin, Tomas Arias-Vergara","submitted_at":"2024-05-25T08:00:44Z","abstract_excerpt":"The extraction and analysis of insights from medical data, primarily stored in free-text formats by healthcare workers, presents significant challenges due to its unstructured nature. Medical coding, a crucial process in healthcare, remains minimally automated due to the complexity of medical ontologies and restricted access to medical texts for training Natural Language Processing models. In this paper, we proposed a method, \"SNOBERT,\" of linking text spans in clinical notes to specific concepts in the SNOMED CT using BERT-based models. The method consists of two stages: candidate selection a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16115","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/2405.16115/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":"2026-07-05T08:23:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GMFAFEvjsG45RB58yFMg3kA3x1eLv//14nHzlfPtrqMhRHfjrzm+Y2asG9ab2QQNLKtUwMk25kNnNEjBFX2qDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:43:45.024009Z"},"content_sha256":"83be6928d406a52851a6a453e60cee582b11e0bacc244463c6607dfae027ad18","schema_version":"1.0","event_id":"sha256:83be6928d406a52851a6a453e60cee582b11e0bacc244463c6607dfae027ad18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37YCCWWN7NBLDTEZM4LPZZPSB5/bundle.json","state_url":"https://pith.science/pith/37YCCWWN7NBLDTEZM4LPZZPSB5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37YCCWWN7NBLDTEZM4LPZZPSB5/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":"2026-08-20T20:43:45Z","links":{"resolver":"https://pith.science/pith/37YCCWWN7NBLDTEZM4LPZZPSB5","bundle":"https://pith.science/pith/37YCCWWN7NBLDTEZM4LPZZPSB5/bundle.json","state":"https://pith.science/pith/37YCCWWN7NBLDTEZM4LPZZPSB5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37YCCWWN7NBLDTEZM4LPZZPSB5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:37YCCWWN7NBLDTEZM4LPZZPSB5","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":"6b22e7ced0ccb42e61e616afde2350ccef84434d0888e268314d5ae9f476bfa1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T08:00:44Z","title_canon_sha256":"3f2aeb6345a7e1fb32dfa025b47b1982641123b29a012ab4b6925058fdb10b39"},"schema_version":"1.0","source":{"id":"2405.16115","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16115","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16115v1","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16115","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"pith_short_12","alias_value":"37YCCWWN7NBL","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"pith_short_16","alias_value":"37YCCWWN7NBLDTEZ","created_at":"2026-07-05T08:23:26Z"},{"alias_kind":"pith_short_8","alias_value":"37YCCWWN","created_at":"2026-07-05T08:23:26Z"}],"graph_snapshots":[{"event_id":"sha256:83be6928d406a52851a6a453e60cee582b11e0bacc244463c6607dfae027ad18","target":"graph","created_at":"2026-07-05T08:23:26Z","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/2405.16115/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The extraction and analysis of insights from medical data, primarily stored in free-text formats by healthcare workers, presents significant challenges due to its unstructured nature. Medical coding, a crucial process in healthcare, remains minimally automated due to the complexity of medical ontologies and restricted access to medical texts for training Natural Language Processing models. In this paper, we proposed a method, \"SNOBERT,\" of linking text spans in clinical notes to specific concepts in the SNOMED CT using BERT-based models. The method consists of two stages: candidate selection a","authors_text":"Aleksandr Galaida, Andreas Maier, Gleb Sokolov, Mikhail Kulyabin, Tomas Arias-Vergara","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T08:00:44Z","title":"SNOBERT: A Benchmark for clinical notes entity linking in the SNOMED CT clinical terminology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16115","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:a27f53e874b292574e40471319298910e135d9c0a0ce0f7ba1d1d91ba0737725","target":"record","created_at":"2026-07-05T08:23:26Z","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":"6b22e7ced0ccb42e61e616afde2350ccef84434d0888e268314d5ae9f476bfa1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T08:00:44Z","title_canon_sha256":"3f2aeb6345a7e1fb32dfa025b47b1982641123b29a012ab4b6925058fdb10b39"},"schema_version":"1.0","source":{"id":"2405.16115","kind":"arxiv","version":1}},"canonical_sha256":"dff0215acdfb42b1cc996716fce5f20f5a16ec91322e9aa2f12a38bea0216bcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dff0215acdfb42b1cc996716fce5f20f5a16ec91322e9aa2f12a38bea0216bcb","first_computed_at":"2026-07-05T08:23:26.140511Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:26.140511Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G4ZjfizUDWWRBCtvbIgpV9X1LVjiO+vw+lzhIjAkCIIlw5qZpHLKbHMOyJK6QNn+VPQ0hd0mB2hSopFce1qjCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:26.140972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16115","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a27f53e874b292574e40471319298910e135d9c0a0ce0f7ba1d1d91ba0737725","sha256:83be6928d406a52851a6a453e60cee582b11e0bacc244463c6607dfae027ad18"],"state_sha256":"cabfe91198662a923a138692027755aa1cb35c35e02bcf934c66873b910fc257"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"22PsY8v//Hcwleacar+9pAKzQY0sGgSUb3Se1diNdg8W4BsKxZpApB4ssCa0oeB4Kx1wuNpffC97tjxjdDbsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:43:45.029286Z","bundle_sha256":"fb4537eb965b308272387f1d32e83475c8029fd66356f482af6ad2d76a231048"}}