{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LNHECW35L26ECODLAZKINRXMTO","short_pith_number":"pith:LNHECW35","canonical_record":{"source":{"id":"1812.01885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T10:02:59Z","cross_cats_sorted":[],"title_canon_sha256":"4e3b0c3997704169ff12fb0f4fcee8cc85acbad2aa0c9e9b45493bcaab3acb86","abstract_canon_sha256":"b8b4d21a6b7b0e5144fb894b9c9aaaa409b4985f3cbc1e993c993b01c2710d29"},"schema_version":"1.0"},"canonical_sha256":"5b4e415b7d5ebc41386b065486c6ec9b954b6a7ae38a98a37dc57907820cc0aa","source":{"kind":"arxiv","id":"1812.01885","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01885","created_at":"2026-05-17T23:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01885v1","created_at":"2026-05-17T23:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01885","created_at":"2026-05-17T23:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"LNHECW35L26E","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LNHECW35L26ECODL","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LNHECW35","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LNHECW35L26ECODLAZKINRXMTO","target":"record","payload":{"canonical_record":{"source":{"id":"1812.01885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T10:02:59Z","cross_cats_sorted":[],"title_canon_sha256":"4e3b0c3997704169ff12fb0f4fcee8cc85acbad2aa0c9e9b45493bcaab3acb86","abstract_canon_sha256":"b8b4d21a6b7b0e5144fb894b9c9aaaa409b4985f3cbc1e993c993b01c2710d29"},"schema_version":"1.0"},"canonical_sha256":"5b4e415b7d5ebc41386b065486c6ec9b954b6a7ae38a98a37dc57907820cc0aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:00.335991Z","signature_b64":"cOEiRPlX6iqfpNImr43dO1Sles14LtFTpZ10WAVsG7j+DFJJnwHk72PvR2dLDwRZtEMhcjlBU2DkWy4YJhDBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b4e415b7d5ebc41386b065486c6ec9b954b6a7ae38a98a37dc57907820cc0aa","last_reissued_at":"2026-05-17T23:59:00.335502Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:00.335502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.01885","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":"2026-05-17T23:59:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wPwjjvC6ShFlilb6qMhBXjAhxTOvouPBCVxu7XLGviEswNkqSBk4pmSArXj8ZADNcjJYsUO1THY3X1Y8iGlcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:46:54.310249Z"},"content_sha256":"f80d423523bbb8443739fea468534858cd6527f3c5a8fdde62551b95cd8236e9","schema_version":"1.0","event_id":"sha256:f80d423523bbb8443739fea468534858cd6527f3c5a8fdde62551b95cd8236e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LNHECW35L26ECODLAZKINRXMTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jin Zhang, Jiyue Huang, Kai Lei, Qiang Zhang, Ying Shen, Yuming Lu","submitted_at":"2018-12-05T10:02:59Z","abstract_excerpt":"Automatic text classification (TC) research can be used for real-world problems such as the classification of in-patient discharge summaries and medical text reports, which is beneficial to make medical documents more understandable to doctors. However, in electronic medical records (EMR), the texts containing sentences are shorter than that in general domain, which leads to the lack of semantic features and the ambiguity of semantic. To tackle this challenge, we propose to add word-cluster embedding to deep neural network for improving short text classification. Concretely, we first use hiera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01885","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":"2026-05-17T23:59:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qI80v1ZziMBWKV/ZGAn1tlymuzBnZu6d9cMEVSr7p5625QPfdr6t8ofwGG7DrWG4NVVQRIyKQKH6v6G4JEmpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T08:46:54.310945Z"},"content_sha256":"22f67cfd363f9b7e0f1624205f2ff2749c93e3e1c8623869c1fa308cb24d9526","schema_version":"1.0","event_id":"sha256:22f67cfd363f9b7e0f1624205f2ff2749c93e3e1c8623869c1fa308cb24d9526"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LNHECW35L26ECODLAZKINRXMTO/bundle.json","state_url":"https://pith.science/pith/LNHECW35L26ECODLAZKINRXMTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LNHECW35L26ECODLAZKINRXMTO/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":"2026-05-25T08:46:54Z","links":{"resolver":"https://pith.science/pith/LNHECW35L26ECODLAZKINRXMTO","bundle":"https://pith.science/pith/LNHECW35L26ECODLAZKINRXMTO/bundle.json","state":"https://pith.science/pith/LNHECW35L26ECODLAZKINRXMTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LNHECW35L26ECODLAZKINRXMTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LNHECW35L26ECODLAZKINRXMTO","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":"b8b4d21a6b7b0e5144fb894b9c9aaaa409b4985f3cbc1e993c993b01c2710d29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T10:02:59Z","title_canon_sha256":"4e3b0c3997704169ff12fb0f4fcee8cc85acbad2aa0c9e9b45493bcaab3acb86"},"schema_version":"1.0","source":{"id":"1812.01885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.01885","created_at":"2026-05-17T23:59:00Z"},{"alias_kind":"arxiv_version","alias_value":"1812.01885v1","created_at":"2026-05-17T23:59:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01885","created_at":"2026-05-17T23:59:00Z"},{"alias_kind":"pith_short_12","alias_value":"LNHECW35L26E","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LNHECW35L26ECODL","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LNHECW35","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:22f67cfd363f9b7e0f1624205f2ff2749c93e3e1c8623869c1fa308cb24d9526","target":"graph","created_at":"2026-05-17T23:59:00Z","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":"Automatic text classification (TC) research can be used for real-world problems such as the classification of in-patient discharge summaries and medical text reports, which is beneficial to make medical documents more understandable to doctors. However, in electronic medical records (EMR), the texts containing sentences are shorter than that in general domain, which leads to the lack of semantic features and the ambiguity of semantic. To tackle this challenge, we propose to add word-cluster embedding to deep neural network for improving short text classification. Concretely, we first use hiera","authors_text":"Jin Zhang, Jiyue Huang, Kai Lei, Qiang Zhang, Ying Shen, Yuming Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T10:02:59Z","title":"Improving Medical Short Text Classification with Semantic Expansion Using Word-Cluster Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01885","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:f80d423523bbb8443739fea468534858cd6527f3c5a8fdde62551b95cd8236e9","target":"record","created_at":"2026-05-17T23:59:00Z","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":"b8b4d21a6b7b0e5144fb894b9c9aaaa409b4985f3cbc1e993c993b01c2710d29","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-05T10:02:59Z","title_canon_sha256":"4e3b0c3997704169ff12fb0f4fcee8cc85acbad2aa0c9e9b45493bcaab3acb86"},"schema_version":"1.0","source":{"id":"1812.01885","kind":"arxiv","version":1}},"canonical_sha256":"5b4e415b7d5ebc41386b065486c6ec9b954b6a7ae38a98a37dc57907820cc0aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b4e415b7d5ebc41386b065486c6ec9b954b6a7ae38a98a37dc57907820cc0aa","first_computed_at":"2026-05-17T23:59:00.335502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:00.335502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cOEiRPlX6iqfpNImr43dO1Sles14LtFTpZ10WAVsG7j+DFJJnwHk72PvR2dLDwRZtEMhcjlBU2DkWy4YJhDBBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:00.335991Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.01885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f80d423523bbb8443739fea468534858cd6527f3c5a8fdde62551b95cd8236e9","sha256:22f67cfd363f9b7e0f1624205f2ff2749c93e3e1c8623869c1fa308cb24d9526"],"state_sha256":"7d271de22e9f5d7bea7caca68837bfbc7b8a79164885ddc26fd888f9c63dd560"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sK/qaJHm0++A9kYta33XgmBIEhzfa8zpKY0MLzfaQAWuJjVAyDJCtEZ9OPL88cZ3dbDhEoj6rt+OoMGxWsheDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T08:46:54.314975Z","bundle_sha256":"63f5f88417e02d8e484ec6ed37739b9df05c8fc129a6f7571f9a56f4c55075ea"}}