{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PUY4YAMAF3G4RNO4M74IZZDSCM","short_pith_number":"pith:PUY4YAMA","canonical_record":{"source":{"id":"2506.02160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-02T18:43:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b9ed3663d38bc1afdfd654fb7563448e016005ad90c5ae186a069df9ca78ce6d","abstract_canon_sha256":"1f7713203c5edbd41f1ea0688b01df2a7051c46a7c18e9a4239eb2e3ececa09e"},"schema_version":"1.0"},"canonical_sha256":"7d31cc01802ecdc8b5dc67f88ce47213312618c9658edb803b5268f0bac60aa2","source":{"kind":"arxiv","id":"2506.02160","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02160","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02160v1","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02160","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"PUY4YAMAF3G4","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"PUY4YAMAF3G4RNO4","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"PUY4YAMA","created_at":"2026-07-05T11:14:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PUY4YAMAF3G4RNO4M74IZZDSCM","target":"record","payload":{"canonical_record":{"source":{"id":"2506.02160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-02T18:43:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"b9ed3663d38bc1afdfd654fb7563448e016005ad90c5ae186a069df9ca78ce6d","abstract_canon_sha256":"1f7713203c5edbd41f1ea0688b01df2a7051c46a7c18e9a4239eb2e3ececa09e"},"schema_version":"1.0"},"canonical_sha256":"7d31cc01802ecdc8b5dc67f88ce47213312618c9658edb803b5268f0bac60aa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:33.545815Z","signature_b64":"Nf4kXdDI4tlkADwprgS4u3hmo70pTgGAjO+i4PO+Pp2MrmIISBSSq2/N8a9A5ocdPa7OKsmpAulTBDHBJ1s5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d31cc01802ecdc8b5dc67f88ce47213312618c9658edb803b5268f0bac60aa2","last_reissued_at":"2026-07-05T11:14:33.545340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:33.545340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.02160","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":"2026-07-05T11:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u85l9esUwgZJXmGGbd1mxXRlvoK2bIGWR0h448XBM1NI1ePHy0BmqgpPxhPVFeYGJWYH/owPpFPMll7g+f57CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T05:14:46.491921Z"},"content_sha256":"91d7703ed8180276a92d437b9004552aabdb4ba7453b901618c397922c5fab63","schema_version":"1.0","event_id":"sha256:91d7703ed8180276a92d437b9004552aabdb4ba7453b901618c397922c5fab63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PUY4YAMAF3G4RNO4M74IZZDSCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Dynamic Framework for Semantic Grouping of Common Data Elements (CDE) Using Embeddings and Clustering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"Anne E Thessen, Christopher J Mungall, Daniel Korn, Madan Krishnamurthy, Melissa A Haendel","submitted_at":"2025-06-02T18:43:37Z","abstract_excerpt":"This research aims to develop a dynamic and scalable framework to facilitate harmonization of Common Data Elements (CDEs) across heterogeneous biomedical datasets by addressing challenges such as semantic heterogeneity, structural variability, and context dependence to streamline integration, enhance interoperability, and accelerate scientific discovery. Our methodology leverages Large Language Models (LLMs) for context-aware text embeddings that convert CDEs into dense vectors capturing semantic relationships and patterns. These embeddings are clustered using Hierarchical Density-Based Spatia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02160","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/2506.02160/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":"2026-07-05T11:14:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bj2BoeOVzssWSku0aZDxnfMAliJad4KHVIkcZewmmbqaZ0yMVU/5Ow6e8xIx3TrTE2V/Cr168wo+gW5Lhpj9CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T05:14:46.492291Z"},"content_sha256":"ba9ec5e7628ea3b621959c911fb718df08d70cbd581b84219c7d4a30bd6cbfff","schema_version":"1.0","event_id":"sha256:ba9ec5e7628ea3b621959c911fb718df08d70cbd581b84219c7d4a30bd6cbfff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PUY4YAMAF3G4RNO4M74IZZDSCM/bundle.json","state_url":"https://pith.science/pith/PUY4YAMAF3G4RNO4M74IZZDSCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PUY4YAMAF3G4RNO4M74IZZDSCM/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":"2026-07-16T05:14:46Z","links":{"resolver":"https://pith.science/pith/PUY4YAMAF3G4RNO4M74IZZDSCM","bundle":"https://pith.science/pith/PUY4YAMAF3G4RNO4M74IZZDSCM/bundle.json","state":"https://pith.science/pith/PUY4YAMAF3G4RNO4M74IZZDSCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PUY4YAMAF3G4RNO4M74IZZDSCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PUY4YAMAF3G4RNO4M74IZZDSCM","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":"1f7713203c5edbd41f1ea0688b01df2a7051c46a7c18e9a4239eb2e3ececa09e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-02T18:43:37Z","title_canon_sha256":"b9ed3663d38bc1afdfd654fb7563448e016005ad90c5ae186a069df9ca78ce6d"},"schema_version":"1.0","source":{"id":"2506.02160","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02160","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02160v1","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02160","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_12","alias_value":"PUY4YAMAF3G4","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_16","alias_value":"PUY4YAMAF3G4RNO4","created_at":"2026-07-05T11:14:33Z"},{"alias_kind":"pith_short_8","alias_value":"PUY4YAMA","created_at":"2026-07-05T11:14:33Z"}],"graph_snapshots":[{"event_id":"sha256:ba9ec5e7628ea3b621959c911fb718df08d70cbd581b84219c7d4a30bd6cbfff","target":"graph","created_at":"2026-07-05T11:14:33Z","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/2506.02160/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This research aims to develop a dynamic and scalable framework to facilitate harmonization of Common Data Elements (CDEs) across heterogeneous biomedical datasets by addressing challenges such as semantic heterogeneity, structural variability, and context dependence to streamline integration, enhance interoperability, and accelerate scientific discovery. Our methodology leverages Large Language Models (LLMs) for context-aware text embeddings that convert CDEs into dense vectors capturing semantic relationships and patterns. These embeddings are clustered using Hierarchical Density-Based Spatia","authors_text":"Anne E Thessen, Christopher J Mungall, Daniel Korn, Madan Krishnamurthy, Melissa A Haendel","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-02T18:43:37Z","title":"A Dynamic Framework for Semantic Grouping of Common Data Elements (CDE) Using Embeddings and Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02160","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":"sha256:91d7703ed8180276a92d437b9004552aabdb4ba7453b901618c397922c5fab63","target":"record","created_at":"2026-07-05T11:14:33Z","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":"1f7713203c5edbd41f1ea0688b01df2a7051c46a7c18e9a4239eb2e3ececa09e","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-02T18:43:37Z","title_canon_sha256":"b9ed3663d38bc1afdfd654fb7563448e016005ad90c5ae186a069df9ca78ce6d"},"schema_version":"1.0","source":{"id":"2506.02160","kind":"arxiv","version":1}},"canonical_sha256":"7d31cc01802ecdc8b5dc67f88ce47213312618c9658edb803b5268f0bac60aa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d31cc01802ecdc8b5dc67f88ce47213312618c9658edb803b5268f0bac60aa2","first_computed_at":"2026-07-05T11:14:33.545340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:33.545340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nf4kXdDI4tlkADwprgS4u3hmo70pTgGAjO+i4PO+Pp2MrmIISBSSq2/N8a9A5ocdPa7OKsmpAulTBDHBJ1s5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:33.545815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02160","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91d7703ed8180276a92d437b9004552aabdb4ba7453b901618c397922c5fab63","sha256:ba9ec5e7628ea3b621959c911fb718df08d70cbd581b84219c7d4a30bd6cbfff"],"state_sha256":"3f1346f5628e48541c127272e2e232530bf0f3c406884545ce6651b0c1749e70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ZhBuYGt/nCKoYagYUthQTFpc1WhzCn7k8lcms4vmRHPvhTU0YaQu9iTnZulVyC3tq52Ota22Lavh1Zq2ZKTDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T05:14:46.495236Z","bundle_sha256":"40a0d3360fc6c3159b8f1714ce5303b10fda94db192fe6b8a1e98d04c5eef1cd"}}