{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:A6ILFAC3MNIXHJF5QT6H4Y27EF","short_pith_number":"pith:A6ILFAC3","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"},"canonical_sha256":"0790b2805b635173a4bd84fc7e635f21567d4b6d65a7722595dd23fd6073f9f8","source":{"kind":"arxiv","id":"1810.09597","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09597","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09597v1","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09597","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"A6ILFAC3MNIX","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A6ILFAC3MNIXHJF5","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A6ILFAC3","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:A6ILFAC3MNIXHJF5QT6H4Y27EF","target":"record","payload":{"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"},"canonical_sha256":"0790b2805b635173a4bd84fc7e635f21567d4b6d65a7722595dd23fd6073f9f8","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"},"source_kind":"arxiv","source_id":"1810.09597","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":"2026-05-18T00:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RC/ZgNKBcLA8i25dMrBhoKMD8GGUM3Z8Z3clPz5Y07f36Pk5DI+unHaCsZugg0PC+1M7B/GZ/tbldfXK+lbPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T08:28:01.593599Z"},"content_sha256":"81c0d1830aa711c458031c2af14914c3ab4066dac0cb0c288d9282a2e48c734a","schema_version":"1.0","event_id":"sha256:81c0d1830aa711c458031c2af14914c3ab4066dac0cb0c288d9282a2e48c734a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:A6ILFAC3MNIXHJF5QT6H4Y27EF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YpNxpP03iIBnlQHda9zR45PdiiszAbna8+mmi/35YrREf14nCF/vvDFrc3fp6InR5wJL4OqwZrKnHAQcpm5hAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T08:28:01.594230Z"},"content_sha256":"49c65dca6c24cb5a7d8f6dc6066198f3cf77bb45f8345cc319da9feb8ca5cfec","schema_version":"1.0","event_id":"sha256:49c65dca6c24cb5a7d8f6dc6066198f3cf77bb45f8345cc319da9feb8ca5cfec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/bundle.json","state_url":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/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":"2026-06-11T08:28:01Z","links":{"resolver":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF","bundle":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/bundle.json","state":"https://pith.science/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6ILFAC3MNIXHJF5QT6H4Y27EF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A6ILFAC3MNIXHJF5QT6H4Y27EF","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":"9a3ba631a6b87372fe6f39356fb385a150ac90afce22d2b161cd49fbeffc25ec","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-22T23:37:31Z","title_canon_sha256":"dbb6a2625aee5a5f8b4fcea15905e1d0d45df9fa29c3276792e819079bfcad2f"},"schema_version":"1.0","source":{"id":"1810.09597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.09597","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"1810.09597v1","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09597","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"A6ILFAC3MNIX","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A6ILFAC3MNIXHJF5","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A6ILFAC3","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:49c65dca6c24cb5a7d8f6dc6066198f3cf77bb45f8345cc319da9feb8ca5cfec","target":"graph","created_at":"2026-05-18T00:02:39Z","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"},"paper":{"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 ","authors_text":"Setu Shah, Xiao Luo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-22T23:37:31Z","title":"Biomedical Document Clustering and Visualization based on the Concepts of Diseases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09597","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":"sha256:81c0d1830aa711c458031c2af14914c3ab4066dac0cb0c288d9282a2e48c734a","target":"record","created_at":"2026-05-18T00:02:39Z","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":"9a3ba631a6b87372fe6f39356fb385a150ac90afce22d2b161cd49fbeffc25ec","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-22T23:37:31Z","title_canon_sha256":"dbb6a2625aee5a5f8b4fcea15905e1d0d45df9fa29c3276792e819079bfcad2f"},"schema_version":"1.0","source":{"id":"1810.09597","kind":"arxiv","version":1}},"canonical_sha256":"0790b2805b635173a4bd84fc7e635f21567d4b6d65a7722595dd23fd6073f9f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0790b2805b635173a4bd84fc7e635f21567d4b6d65a7722595dd23fd6073f9f8","first_computed_at":"2026-05-18T00:02:39.092053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:39.092053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ML9TtPzYMr9UbP4vJYFrTSZhGfmEPtJYUcWslfir3CsHhw8V+XIkWcTjxjWm+zQ73ReGdQUCvCQiV2X6naFkCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:39.092694Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.09597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81c0d1830aa711c458031c2af14914c3ab4066dac0cb0c288d9282a2e48c734a","sha256:49c65dca6c24cb5a7d8f6dc6066198f3cf77bb45f8345cc319da9feb8ca5cfec"],"state_sha256":"f769d930eb30c4be8101f415738dc8f97dbd18450c88c8323a668d2525371874"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aTXF0OoNtWdYVFeLbSwn93wSHNtTeW1qET4o0a3FEGn4mGd7cc0PHM9oUAVRjXMus+4iiE85Set8TwqKpougCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T08:28:01.597875Z","bundle_sha256":"96de50ffe28a89b97827870c41cbf583438986e18998b1d64ec6679960811eae"}}