{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A6ILFAC3MNIXHJF5QT6H4Y27EF","short_pith_number":"pith:A6ILFAC3","schema_version":"1.0","canonical_sha256":"0790b2805b635173a4bd84fc7e635f21567d4b6d65a7722595dd23fd6073f9f8","source":{"kind":"arxiv","id":"1810.09597","version":1},"attestation_state":"computed","paper":{"title":"Biomedical Document Clustering and Visualization based on the Concepts of Diseases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Setu Shah, Xiao Luo","submitted_at":"2018-10-22T23:37:31Z","abstract_excerpt":"Document clustering is a text mining technique used to provide better document search and browsing in digital libraries or online corpora. A lot of research has been done on biomedical document clustering that is based on using existing ontology. But, associations and co-occurrences of the medical concepts are not well represented by using ontology. In this research, a vector representation of concepts of diseases and similarity measurement between concepts are proposed. They identify the closest concepts of diseases in the context of a corpus. Each document is represented by using the vector "},"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":"1810.09597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-22T23:37:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dbb6a2625aee5a5f8b4fcea15905e1d0d45df9fa29c3276792e819079bfcad2f","abstract_canon_sha256":"9a3ba631a6b87372fe6f39356fb385a150ac90afce22d2b161cd49fbeffc25ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:39.092694Z","signature_b64":"ML9TtPzYMr9UbP4vJYFrTSZhGfmEPtJYUcWslfir3CsHhw8V+XIkWcTjxjWm+zQ73ReGdQUCvCQiV2X6naFkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0790b2805b635173a4bd84fc7e635f21567d4b6d65a7722595dd23fd6073f9f8","last_reissued_at":"2026-05-18T00:02:39.092053Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:39.092053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Biomedical Document Clustering and Visualization based on the Concepts of Diseases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Setu Shah, Xiao Luo","submitted_at":"2018-10-22T23:37:31Z","abstract_excerpt":"Document clustering is a text mining technique used to provide better document search and browsing in digital libraries or online corpora. A lot of research has been done on biomedical document clustering that is based on using existing ontology. But, associations and co-occurrences of the medical concepts are not well represented by using ontology. In this research, a vector representation of concepts of diseases and similarity measurement between concepts are proposed. They identify the closest concepts of diseases in the context of a corpus. Each document is represented by using the vector "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09597","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":""},"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":"1810.09597","created_at":"2026-05-18T00:02:39.092157+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09597v1","created_at":"2026-05-18T00:02:39.092157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09597","created_at":"2026-05-18T00:02:39.092157+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6ILFAC3MNIX","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6ILFAC3MNIXHJF5","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6ILFAC3","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF","json":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF.json","graph_json":"https://pith.science/api/pith-number/A6ILFAC3MNIXHJF5QT6H4Y27EF/graph.json","events_json":"https://pith.science/api/pith-number/A6ILFAC3MNIXHJF5QT6H4Y27EF/events.json","paper":"https://pith.science/paper/A6ILFAC3"},"agent_actions":{"view_html":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF","download_json":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF.json","view_paper":"https://pith.science/paper/A6ILFAC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09597&json=true","fetch_graph":"https://pith.science/api/pith-number/A6ILFAC3MNIXHJF5QT6H4Y27EF/graph.json","fetch_events":"https://pith.science/api/pith-number/A6ILFAC3MNIXHJF5QT6H4Y27EF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/action/storage_attestation","attest_author":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/action/author_attestation","sign_citation":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/action/citation_signature","submit_replication":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/action/replication_record"}},"created_at":"2026-05-18T00:02:39.092157+00:00","updated_at":"2026-05-18T00:02:39.092157+00:00"}