{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QR4QINRLGHHF523TGW2YHDZPTQ","short_pith_number":"pith:QR4QINRL","schema_version":"1.0","canonical_sha256":"847904362b31ce5eeb7335b5838f2f9c27bbe140d62879fb80fdb923f8842445","source":{"kind":"arxiv","id":"2310.08365","version":2},"attestation_state":"computed","paper":{"title":"From Large Language Models to Knowledge Graphs for Biomarker Discovery in Cancer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dietrich Rebholz-Schuhmann, Lina Molinas Comet, Md. Rezaul Karim, Md Shajalal, Oya Deniz Beyan, Stefan Decker","submitted_at":"2023-10-12T14:36:13Z","abstract_excerpt":"Domain experts often rely on most recent knowledge for apprehending and disseminating specific biological processes that help them design strategies for developing prevention and therapeutic decision-making in various disease scenarios. A challenging scenarios for artificial intelligence (AI) is using biomedical data (e.g., texts, imaging, omics, and clinical) to provide diagnosis and treatment recommendations for cancerous conditions.~Data and knowledge about biomedical entities like cancer, drugs, genes, proteins, and their mechanism is spread across structured (knowledge bases (KBs)) and un"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.08365","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T14:36:13Z","cross_cats_sorted":[],"title_canon_sha256":"2b17bd30534d00bc636307daed98a0b78ae3b6f97e2c03f24bbcf269fc81fb3d","abstract_canon_sha256":"5454590a10fe0089912ef1892061923605cf64aace6942f707d9c972cf8fd03a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:18.759546Z","signature_b64":"agKcC5J9OBxq5YPm9wDT7UBkaZlwCGNdyRBSZDttlN9hMwyLpKNgDO7m0BZoEnDJC+LROyMP8rnMTJt8BsaADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"847904362b31ce5eeb7335b5838f2f9c27bbe140d62879fb80fdb923f8842445","last_reissued_at":"2026-07-05T07:14:18.759083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:18.759083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Large Language Models to Knowledge Graphs for Biomarker Discovery in Cancer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dietrich Rebholz-Schuhmann, Lina Molinas Comet, Md. Rezaul Karim, Md Shajalal, Oya Deniz Beyan, Stefan Decker","submitted_at":"2023-10-12T14:36:13Z","abstract_excerpt":"Domain experts often rely on most recent knowledge for apprehending and disseminating specific biological processes that help them design strategies for developing prevention and therapeutic decision-making in various disease scenarios. A challenging scenarios for artificial intelligence (AI) is using biomedical data (e.g., texts, imaging, omics, and clinical) to provide diagnosis and treatment recommendations for cancerous conditions.~Data and knowledge about biomedical entities like cancer, drugs, genes, proteins, and their mechanism is spread across structured (knowledge bases (KBs)) and un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08365","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/2310.08365/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.08365","created_at":"2026-07-05T07:14:18.759153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08365v2","created_at":"2026-07-05T07:14:18.759153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08365","created_at":"2026-07-05T07:14:18.759153+00:00"},{"alias_kind":"pith_short_12","alias_value":"QR4QINRLGHHF","created_at":"2026-07-05T07:14:18.759153+00:00"},{"alias_kind":"pith_short_16","alias_value":"QR4QINRLGHHF523T","created_at":"2026-07-05T07:14:18.759153+00:00"},{"alias_kind":"pith_short_8","alias_value":"QR4QINRL","created_at":"2026-07-05T07:14:18.759153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.10697","citing_title":"A Survey on Retrieval And Structuring Augmented Generation with Large Language Models","ref_index":119,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ","json":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ.json","graph_json":"https://pith.science/api/pith-number/QR4QINRLGHHF523TGW2YHDZPTQ/graph.json","events_json":"https://pith.science/api/pith-number/QR4QINRLGHHF523TGW2YHDZPTQ/events.json","paper":"https://pith.science/paper/QR4QINRL"},"agent_actions":{"view_html":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ","download_json":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ.json","view_paper":"https://pith.science/paper/QR4QINRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08365&json=true","fetch_graph":"https://pith.science/api/pith-number/QR4QINRLGHHF523TGW2YHDZPTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QR4QINRLGHHF523TGW2YHDZPTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ/action/storage_attestation","attest_author":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ/action/author_attestation","sign_citation":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ/action/citation_signature","submit_replication":"https://pith.science/pith/QR4QINRLGHHF523TGW2YHDZPTQ/action/replication_record"}},"created_at":"2026-07-05T07:14:18.759153+00:00","updated_at":"2026-07-05T07:14:18.759153+00:00"}